From 109fcb41cbdb19f332c2e014c877ec804bb1fef2 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 17 Oct 2024 16:48:25 +0200 Subject: [PATCH 01/26] Support remap rules in the segmenter (#949) --- .../ucd/dev/auxiliary/GraphemeBreakTest.html | 4 +- .../data/ucd/dev/auxiliary/LineBreakTest.html | 17 +- .../data/ucd/dev/auxiliary/LineBreakTest.txt | 274 +++++++++--------- .../ucd/dev/auxiliary/SentenceBreakTest.html | 4 +- .../data/ucd/dev/auxiliary/WordBreakTest.html | 4 +- .../unicode/text/UCD/GenerateBreakTest.java | 16 +- .../java/org/unicode/tools/Segmenter.java | 261 ++++++++++++++--- .../java/org/unicode/tools/TestSegments.java | 5 +- .../org/unicode/tools/SegmenterDefault.txt | 91 +----- .../java/org/unicode/test/TestSegment.java | 6 +- 10 files changed, 395 insertions(+), 287 deletions(-) diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html index 405d0078c..5b6026ef5 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html @@ -7,7 +7,7 @@

Grapheme_Cluster_Break Chart

Unicode Version: 17.0.0

-

Date: 2024-09-12, 14:11:44 GMT

+

Date: 2024-10-14, 12:06:04 GMT

This page illustrates the application of the Grapheme_Cluster_Break specification. The material here is informative, not normative.

The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

After the heavy blue line in the table are additional rows, either with different sample characters or for sequences. Some column headers may be composed, reflecting “treat as” or “ignore” rules.

If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of LVT and T shows ×, with the rule 8.0. Checking below the table, rule 8.0 is “( LVT | T) × T”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

@@ -39,7 +39,7 @@

Table

Other÷÷÷÷×÷÷×÷÷÷÷÷×÷÷÷÷××××

Rules

-

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule GB9a is given the number 9.1.
  4. Any “treat as” or “ignore” rules are handled as discussed in UAX #29, and thus reflected in a transformation of the rules usually not visible here. In addition, final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  5. In some cases, the numbering and form of a rule is changed due to “treat as” rules.

For the original rules, see UAX #29.

+

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule GB9a is given the number 9.1.
  4. Final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.

For the original rules, see UAX #29.

diff --git a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html index 4cfb8f6d9..3b2899e64 100644 --- a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html @@ -7,7 +7,7 @@

Line_Break Chart

Unicode Version: 17.0.0

-

Date: 2024-09-12, 14:11:46 GMT

+

Date: 2024-10-14, 12:25:22 GMT

This page illustrates the application of the Line_Break specification. The material here is informative, not normative.

The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

Some column headers may be composed, reflecting “treat as” or “ignore” rules.

If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of H3 and JT shows ×, with the rule 26.03. Checking below the table, rule 26.03 is “JT | H3 × JT”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

@@ -67,9 +67,9 @@

Table

- + - + @@ -79,7 +79,7 @@

Table

0.2sot ÷
0.3÷ eot
BA_NotEastAsian_NonEastAsianBA_Hyphen××××÷÷÷÷×÷×÷÷÷÷÷××××××÷÷×××÷××÷×÷×÷÷÷÷÷÷÷÷×÷××÷÷÷÷×××÷××××××××××
CP_NotEastAsian_CP30×××××÷÷÷×÷×÷÷÷÷÷××××××÷÷××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷×××÷××××××××××
OP_NotEastAsian_OP30××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××
CM1_NotEastAsian_CM×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
CM1_NotEastAsian_CM×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
ZWJ_O_ZWJ_NotEastAsian_CM××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××××
CM1_CM×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
CM1_CM×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
AL_NotEastAsian_AL×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
AI_NotEastAsian_AL×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
XX_NotEastAsian_AL×××××÷÷÷×÷×÷××÷÷××××××××××××××××÷××÷÷÷÷÷÷÷×÷××÷÷÷÷××××××××××××××
CJ_NS÷××××÷÷÷×÷×÷÷÷÷÷××××××÷÷×××÷××××÷×÷÷÷÷÷÷÷÷×÷××÷÷÷÷×××÷×××÷÷÷÷÷××

Rules

-

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ×”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule LB21a is given the number 21.1.
  4. Any “treat as” or “ignore” rules are handled as discussed in UAX #14, and thus reflected in a transformation of the rules usually not visible here. Where it does show up, an extra variable like CM+ may appear, and the rule may be recast. In addition, final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  5. Where a rule has multiple parts (lines), each one is numbered using hundredths, such as 21.01) × BA, 21.02) × HY, ... In some cases, the numbering and form of a rule is changed due to “treat as” rules.

For the original rules, see UAX #14.

+

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ×”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule LB21a is given the number 21.1.
  4. Final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  5. Where a rule has multiple parts (lines), each one is numbered using hundredths, such as 21.01) × BA, 21.02) × HY, ...

For the original rules, see UAX #14.

@@ -93,13 +93,12 @@

Rules

- + + - - - + @@ -229,7 +228,7 @@

Sample Strings

diff --git a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt index 472c419c5..cc03bb2fb 100644 --- a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt +++ b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.txt @@ -1,5 +1,5 @@ -# LineBreakTest-16.0.0.txt -# Date: 2024-07-05, 00:45:20 GMT +# LineBreakTest-17.0.0.txt +# Date: 2024-10-11, 18:57:27 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -40,7 +40,7 @@ × 23E9 × 0308 × 0020 × FE15 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 23E9 × 16FE4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 23E9 × 0020 ÷ 16FE4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 23E9 × 0308 × 16FE4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 23E9 × 0308 × 16FE4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 23E9 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 23E9 ÷ AC00 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 23E9 × 0020 ÷ AC00 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -144,11 +144,11 @@ × 23E9 × 0308 × 0020 × 0085 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 23E9 × 00A0 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 23E9 × 0020 ÷ 00A0 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 23E9 × 0308 × 00A0 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 23E9 × 0308 × 00A0 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 23E9 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 23E9 × 00AB ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 23E9 × 0020 ÷ 00AB ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 23E9 × 0308 × 00AB ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 23E9 × 0308 × 00AB ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 23E9 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 23E9 ÷ 00B4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 23E9 × 0020 ÷ 00B4 ÷ # × [0.3] BLACK RIGHT-POINTING DOUBLE TRIANGLE (AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -404,7 +404,7 @@ × 3000 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3000 × 00AB ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3000 × 0020 ÷ 00AB ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 3000 × 0308 × 00AB ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 3000 × 0308 × 00AB ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3000 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3000 ÷ 00B4 ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 3000 × 0020 ÷ 00B4 ÷ # × [0.3] IDEOGRAPHIC SPACE (BA) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -552,7 +552,7 @@ × 232A × 0308 × 0020 × FE15 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 232A × 16FE4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 232A × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 232A × 0308 × 16FE4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 232A × 0308 × 16FE4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 232A × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 232A ÷ AC00 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 232A × 0020 ÷ AC00 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -656,11 +656,11 @@ × 232A × 0308 × 0020 × 0085 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 232A × 00A0 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 232A × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 232A × 0308 × 00A0 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 232A × 0308 × 00A0 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 232A × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 232A × 00AB ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 232A × 0020 ÷ 00AB ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 232A × 0308 × 00AB ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 232A × 0308 × 00AB ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 232A × 0308 × 0020 ÷ 00AB ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 232A ÷ 00B4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 232A × 0020 ÷ 00B4 ÷ # × [0.3] RIGHT-POINTING ANGLE BRACKET (CL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -808,7 +808,7 @@ × FE15 × 0308 × 0020 × FE15 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × FE15 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE15 × 0020 ÷ 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× FE15 × 0308 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× FE15 × 0308 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE15 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE15 ÷ AC00 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × FE15 × 0020 ÷ AC00 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -912,11 +912,11 @@ × FE15 × 0308 × 0020 × 0085 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × FE15 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE15 × 0020 ÷ 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× FE15 × 0308 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× FE15 × 0308 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE15 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE15 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE15 × 0020 ÷ 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× FE15 × 0308 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× FE15 × 0308 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE15 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE15 ÷ 00B4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × FE15 × 0020 ÷ 00B4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -1320,7 +1320,7 @@ × AC00 × 0308 × 0020 × FE15 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × AC00 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC00 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× AC00 × 0308 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× AC00 × 0308 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC00 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC00 ÷ AC00 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × AC00 × 0020 ÷ AC00 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -1424,11 +1424,11 @@ × AC00 × 0308 × 0020 × 0085 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × AC00 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC00 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× AC00 × 0308 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× AC00 × 0308 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC00 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC00 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC00 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× AC00 × 0308 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× AC00 × 0308 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC00 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC00 ÷ 00B4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × AC00 × 0020 ÷ 00B4 ÷ # × [0.3] HANGUL SYLLABLE GA (H2) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -1576,7 +1576,7 @@ × AC01 × 0308 × 0020 × FE15 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × AC01 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC01 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× AC01 × 0308 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× AC01 × 0308 × 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC01 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × AC01 ÷ AC00 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × AC01 × 0020 ÷ AC00 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -1680,11 +1680,11 @@ × AC01 × 0308 × 0020 × 0085 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × AC01 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC01 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× AC01 × 0308 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× AC01 × 0308 × 00A0 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC01 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × AC01 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC01 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× AC01 × 0308 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× AC01 × 0308 × 00AB ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC01 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × AC01 ÷ 00B4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × AC01 × 0020 ÷ 00B4 ÷ # × [0.3] HANGUL SYLLABLE GAG (H3) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -1832,7 +1832,7 @@ × 231A × 0308 × 0020 × FE15 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 231A × 16FE4 ÷ # × [0.3] WATCH (ID) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 231A × 0020 ÷ 16FE4 ÷ # × [0.3] WATCH (ID) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 231A × 0308 × 16FE4 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 231A × 0308 × 16FE4 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 231A × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 231A ÷ AC00 ÷ # × [0.3] WATCH (ID) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 231A × 0020 ÷ AC00 ÷ # × [0.3] WATCH (ID) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -1936,11 +1936,11 @@ × 231A × 0308 × 0020 × 0085 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 231A × 00A0 ÷ # × [0.3] WATCH (ID) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 231A × 0020 ÷ 00A0 ÷ # × [0.3] WATCH (ID) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 231A × 0308 × 00A0 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 231A × 0308 × 00A0 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 231A × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 231A × 00AB ÷ # × [0.3] WATCH (ID) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 231A × 0020 ÷ 00AB ÷ # × [0.3] WATCH (ID) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 231A × 0308 × 00AB ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 231A × 0308 × 00AB ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 231A × 0308 × 0020 ÷ 00AB ÷ # × [0.3] WATCH (ID) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 231A ÷ 00B4 ÷ # × [0.3] WATCH (ID) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 231A × 0020 ÷ 00B4 ÷ # × [0.3] WATCH (ID) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -2088,7 +2088,7 @@ × FE19 × 0308 × 0020 × FE15 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × FE19 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE19 × 0020 ÷ 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× FE19 × 0308 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× FE19 × 0308 × 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE19 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE19 ÷ AC00 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × FE19 × 0020 ÷ AC00 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -2192,11 +2192,11 @@ × FE19 × 0308 × 0020 × 0085 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × FE19 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE19 × 0020 ÷ 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× FE19 × 0308 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× FE19 × 0308 × 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE19 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE19 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE19 × 0020 ÷ 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× FE19 × 0308 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× FE19 × 0308 × 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE19 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE19 ÷ 00B4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × FE19 × 0020 ÷ 00B4 ÷ # × [0.3] PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS (IN) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -2344,7 +2344,7 @@ × 1100 × 0308 × 0020 × FE15 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1100 × 16FE4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1100 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1100 × 0308 × 16FE4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1100 × 0308 × 16FE4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1100 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1100 × AC00 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [26.01] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1100 × 0020 ÷ AC00 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -2448,11 +2448,11 @@ × 1100 × 0308 × 0020 × 0085 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1100 × 00A0 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1100 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1100 × 0308 × 00A0 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1100 × 0308 × 00A0 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1100 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1100 × 00AB ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1100 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 1100 × 0308 × 00AB ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 1100 × 0308 × 00AB ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1100 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1100 ÷ 00B4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 1100 × 0020 ÷ 00B4 ÷ # × [0.3] HANGUL CHOSEONG KIYEOK (JL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -2600,7 +2600,7 @@ × 3005 × 0308 × 0020 × FE15 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 3005 × 16FE4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3005 × 0020 ÷ 16FE4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 3005 × 0308 × 16FE4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 3005 × 0308 × 16FE4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3005 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3005 ÷ AC00 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 3005 × 0020 ÷ AC00 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -2704,11 +2704,11 @@ × 3005 × 0308 × 0020 × 0085 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 3005 × 00A0 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3005 × 0020 ÷ 00A0 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 3005 × 0308 × 00A0 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 3005 × 0308 × 00A0 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3005 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3005 × 00AB ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3005 × 0020 ÷ 00AB ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 3005 × 0308 × 00AB ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 3005 × 0308 × 00AB ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3005 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3005 ÷ 00B4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 3005 × 0020 ÷ 00B4 ÷ # × [0.3] IDEOGRAPHIC ITERATION MARK (NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -2856,7 +2856,7 @@ × 2329 × 0308 × 0020 × FE15 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 2329 × 16FE4 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2329 × 0020 × 16FE4 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [7.01] SPACE (SP_NotEastAsian) × [14.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 2329 × 0308 × 16FE4 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 2329 × 0308 × 16FE4 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2329 × 0308 × 0020 × 16FE4 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [14.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2329 × AC00 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [14.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 2329 × 0020 × AC00 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [7.01] SPACE (SP_NotEastAsian) × [14.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -2960,7 +2960,7 @@ × 2329 × 0308 × 0020 × 0085 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 2329 × 00A0 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2329 × 0020 × 00A0 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [7.01] SPACE (SP_NotEastAsian) × [14.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 2329 × 0308 × 00A0 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 2329 × 0308 × 00A0 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2329 × 0308 × 0020 × 00A0 ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [14.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2329 × 00AB ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [14.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2329 × 0020 × 00AB ÷ # × [0.3] LEFT-POINTING ANGLE BRACKET (OP) × [7.01] SPACE (SP_NotEastAsian) × [14.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -3112,7 +3112,7 @@ × FE6A × 0308 × 0020 × FE15 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × FE6A × 16FE4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE6A × 0020 ÷ 16FE4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× FE6A × 0308 × 16FE4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× FE6A × 0308 × 16FE4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE6A × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FE6A ÷ AC00 ÷ # × [0.3] SMALL PERCENT SIGN (PO) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × FE6A × 0020 ÷ AC00 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -3216,11 +3216,11 @@ × FE6A × 0308 × 0020 × 0085 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × FE6A × 00A0 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE6A × 0020 ÷ 00A0 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× FE6A × 0308 × 00A0 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× FE6A × 0308 × 00A0 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE6A × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FE6A × 00AB ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE6A × 0020 ÷ 00AB ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× FE6A × 0308 × 00AB ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× FE6A × 0308 × 00AB ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE6A × 0308 × 0020 ÷ 00AB ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FE6A ÷ 00B4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × FE6A × 0020 ÷ 00B4 ÷ # × [0.3] SMALL PERCENT SIGN (PO) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -3368,7 +3368,7 @@ × 20A9 × 0308 × 0020 × FE15 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 20A9 × 16FE4 ÷ # × [0.3] WON SIGN (PR) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 20A9 × 0020 ÷ 16FE4 ÷ # × [0.3] WON SIGN (PR) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 20A9 × 0308 × 16FE4 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 20A9 × 0308 × 16FE4 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 20A9 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 20A9 × AC00 ÷ # × [0.3] WON SIGN (PR) × [27.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 20A9 × 0020 ÷ AC00 ÷ # × [0.3] WON SIGN (PR) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -3472,11 +3472,11 @@ × 20A9 × 0308 × 0020 × 0085 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 20A9 × 00A0 ÷ # × [0.3] WON SIGN (PR) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 20A9 × 0020 ÷ 00A0 ÷ # × [0.3] WON SIGN (PR) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 20A9 × 0308 × 00A0 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 20A9 × 0308 × 00A0 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 20A9 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 20A9 × 00AB ÷ # × [0.3] WON SIGN (PR) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 20A9 × 0020 ÷ 00AB ÷ # × [0.3] WON SIGN (PR) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 20A9 × 0308 × 00AB ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 20A9 × 0308 × 00AB ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 20A9 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] WON SIGN (PR) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 20A9 ÷ 00B4 ÷ # × [0.3] WON SIGN (PR) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 20A9 × 0020 ÷ 00B4 ÷ # × [0.3] WON SIGN (PR) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -3624,7 +3624,7 @@ × 270A × 0308 × 0020 × FE15 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 270A × 16FE4 ÷ # × [0.3] RAISED FIST (EB) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 270A × 0020 ÷ 16FE4 ÷ # × [0.3] RAISED FIST (EB) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 270A × 0308 × 16FE4 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 270A × 0308 × 16FE4 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 270A × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 270A ÷ AC00 ÷ # × [0.3] RAISED FIST (EB) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 270A × 0020 ÷ AC00 ÷ # × [0.3] RAISED FIST (EB) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -3728,11 +3728,11 @@ × 270A × 0308 × 0020 × 0085 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 270A × 00A0 ÷ # × [0.3] RAISED FIST (EB) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 270A × 0020 ÷ 00A0 ÷ # × [0.3] RAISED FIST (EB) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 270A × 0308 × 00A0 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 270A × 0308 × 00A0 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 270A × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 270A × 00AB ÷ # × [0.3] RAISED FIST (EB) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 270A × 0020 ÷ 00AB ÷ # × [0.3] RAISED FIST (EB) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 270A × 0308 × 00AB ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 270A × 0308 × 00AB ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 270A × 0308 × 0020 ÷ 00AB ÷ # × [0.3] RAISED FIST (EB) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 270A ÷ 00B4 ÷ # × [0.3] RAISED FIST (EB) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 270A × 0020 ÷ 00B4 ÷ # × [0.3] RAISED FIST (EB) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -3880,7 +3880,7 @@ × 1F3FB × 0308 × 0020 × FE15 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1F3FB × 16FE4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F3FB × 0020 ÷ 16FE4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1F3FB × 0308 × 16FE4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1F3FB × 0308 × 16FE4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F3FB × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F3FB ÷ AC00 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1F3FB × 0020 ÷ AC00 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -3984,11 +3984,11 @@ × 1F3FB × 0308 × 0020 × 0085 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1F3FB × 00A0 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F3FB × 0020 ÷ 00A0 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1F3FB × 0308 × 00A0 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1F3FB × 0308 × 00A0 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F3FB × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F3FB × 00AB ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1F3FB × 0020 ÷ 00AB ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 1F3FB × 0308 × 00AB ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 1F3FB × 0308 × 00AB ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1F3FB × 0308 × 0020 ÷ 00AB ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1F3FB ÷ 00B4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 1F3FB × 0020 ÷ 00B4 ÷ # × [0.3] EMOJI MODIFIER FITZPATRICK TYPE-1-2 (EM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -4136,7 +4136,7 @@ × 000A ÷ 0308 × 0020 × FE15 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 000A ÷ 16FE4 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000A ÷ 0020 ÷ 16FE4 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 000A ÷ 0308 × 16FE4 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 000A ÷ 0308 × 16FE4 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000A ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000A ÷ AC00 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 000A ÷ 0020 ÷ AC00 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -4240,7 +4240,7 @@ × 000A ÷ 0308 × 0020 × 0085 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 000A ÷ 00A0 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000A ÷ 0020 ÷ 00A0 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 000A ÷ 0308 × 00A0 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 000A ÷ 0308 × 00A0 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000A ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000A ÷ 00AB ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 000A ÷ 0020 ÷ 00AB ÷ # × [0.3] (LF_NotEastAsian) ÷ [5.03] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -4392,7 +4392,7 @@ × 000B ÷ 0308 × 0020 × FE15 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 000B ÷ 16FE4 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000B ÷ 0020 ÷ 16FE4 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 000B ÷ 0308 × 16FE4 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 000B ÷ 0308 × 16FE4 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000B ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000B ÷ AC00 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 000B ÷ 0020 ÷ AC00 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -4496,7 +4496,7 @@ × 000B ÷ 0308 × 0020 × 0085 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 000B ÷ 00A0 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000B ÷ 0020 ÷ 00A0 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 000B ÷ 0308 × 00A0 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 000B ÷ 0308 × 00A0 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000B ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000B ÷ 00AB ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 000B ÷ 0020 ÷ 00AB ÷ # × [0.3] (BK_NotEastAsian) ÷ [4.0] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -4648,7 +4648,7 @@ × 000D ÷ 0308 × 0020 × FE15 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 000D ÷ 16FE4 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000D ÷ 0020 ÷ 16FE4 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 000D ÷ 0308 × 16FE4 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 000D ÷ 0308 × 16FE4 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000D ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 000D ÷ AC00 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 000D ÷ 0020 ÷ AC00 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -4752,7 +4752,7 @@ × 000D ÷ 0308 × 0020 × 0085 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 000D ÷ 00A0 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000D ÷ 0020 ÷ 00A0 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 000D ÷ 0308 × 00A0 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 000D ÷ 0308 × 00A0 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000D ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 000D ÷ 00AB ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 000D ÷ 0020 ÷ 00AB ÷ # × [0.3] (CR_NotEastAsian) ÷ [5.02] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -4904,7 +4904,7 @@ × 0020 ÷ 0308 × 0020 × FE15 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0020 ÷ 16FE4 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0020 × 0020 ÷ 16FE4 ÷ # × [0.3] SPACE (SP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0020 ÷ 0308 × 16FE4 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0020 ÷ 0308 × 16FE4 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0020 ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0020 ÷ AC00 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0020 × 0020 ÷ AC00 ÷ # × [0.3] SPACE (SP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -5008,7 +5008,7 @@ × 0020 ÷ 0308 × 0020 × 0085 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0020 ÷ 00A0 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0020 × 0020 ÷ 00A0 ÷ # × [0.3] SPACE (SP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0020 ÷ 0308 × 00A0 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0020 ÷ 0308 × 00A0 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0020 ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0020 ÷ 00AB ÷ # × [0.3] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0020 × 0020 ÷ 00AB ÷ # × [0.3] SPACE (SP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -5160,7 +5160,7 @@ × 0021 × 0308 × 0020 × FE15 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0021 × 16FE4 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0021 × 0020 ÷ 16FE4 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0021 × 0308 × 16FE4 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0021 × 0308 × 16FE4 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0021 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0021 ÷ AC00 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0021 × 0020 ÷ AC00 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -5264,7 +5264,7 @@ × 0021 × 0308 × 0020 × 0085 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0021 × 00A0 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0021 × 0020 ÷ 00A0 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0021 × 0308 × 00A0 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0021 × 0308 × 00A0 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0021 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0021 × 00AB ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0021 × 0020 ÷ 00AB ÷ # × [0.3] EXCLAMATION MARK (EX_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -5416,7 +5416,7 @@ × 0022 × 0308 × 0020 × FE15 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0022 × 16FE4 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0022 × 0020 ÷ 16FE4 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0022 × 0308 × 16FE4 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0022 × 0308 × 16FE4 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0022 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0022 × AC00 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [19.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0022 × 0020 ÷ AC00 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -5520,7 +5520,7 @@ × 0022 × 0308 × 0020 × 0085 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0022 × 00A0 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0022 × 0020 ÷ 00A0 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0022 × 0308 × 00A0 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0022 × 0308 × 00A0 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0022 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0022 × 00AB ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [19.02] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0022 × 0020 ÷ 00AB ÷ # × [0.3] QUOTATION MARK (QU_QUmPi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -5672,7 +5672,7 @@ × 0024 × 0308 × 0020 × FE15 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0024 × 16FE4 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0024 × 0020 ÷ 16FE4 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0024 × 0308 × 16FE4 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0024 × 0308 × 16FE4 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0024 × AC00 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [27.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0024 × 0020 ÷ AC00 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -5776,7 +5776,7 @@ × 0024 × 0308 × 0020 × 0085 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0024 × 00A0 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0024 × 0020 ÷ 00A0 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0024 × 0308 × 00A0 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0024 × 0308 × 00A0 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0024 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0024 × 00AB ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0024 × 0020 ÷ 00AB ÷ # × [0.3] DOLLAR SIGN (PR_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -5928,7 +5928,7 @@ × 0025 × 0308 × 0020 × FE15 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0025 × 16FE4 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0025 × 0020 ÷ 16FE4 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0025 × 0308 × 16FE4 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0025 × 0308 × 16FE4 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0025 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0025 ÷ AC00 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0025 × 0020 ÷ AC00 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -6032,7 +6032,7 @@ × 0025 × 0308 × 0020 × 0085 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0025 × 00A0 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0025 × 0020 ÷ 00A0 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0025 × 0308 × 00A0 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0025 × 0308 × 00A0 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0025 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0025 × 00AB ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0025 × 0020 ÷ 00AB ÷ # × [0.3] PERCENT SIGN (PO_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -6184,7 +6184,7 @@ × 002C × 0308 × 0020 × FE15 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 002C × 16FE4 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002C × 0020 ÷ 16FE4 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 002C × 0308 × 16FE4 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 002C × 0308 × 16FE4 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002C × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002C ÷ AC00 ÷ # × [0.3] COMMA (IS_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 002C × 0020 ÷ AC00 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -6288,7 +6288,7 @@ × 002C × 0308 × 0020 × 0085 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 002C × 00A0 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002C × 0020 ÷ 00A0 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 002C × 0308 × 00A0 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 002C × 0308 × 00A0 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002C × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] COMMA (IS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002C × 00AB ÷ # × [0.3] COMMA (IS_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 002C × 0020 ÷ 00AB ÷ # × [0.3] COMMA (IS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -6696,7 +6696,7 @@ × 002F × 0308 × 0020 × FE15 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 002F × 16FE4 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002F × 0020 ÷ 16FE4 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 002F × 0308 × 16FE4 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 002F × 0308 × 16FE4 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002F × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 002F ÷ AC00 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 002F × 0020 ÷ AC00 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -6800,7 +6800,7 @@ × 002F × 0308 × 0020 × 0085 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 002F × 00A0 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002F × 0020 ÷ 00A0 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 002F × 0308 × 00A0 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 002F × 0308 × 00A0 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002F × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 002F × 00AB ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 002F × 0020 ÷ 00AB ÷ # × [0.3] SOLIDUS (SY_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -6952,7 +6952,7 @@ × 0030 × 0308 × 0020 × FE15 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0030 × 16FE4 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0030 × 0020 ÷ 16FE4 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0030 × 0308 × 16FE4 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0030 × 0308 × 16FE4 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0030 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0030 ÷ AC00 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0030 × 0020 ÷ AC00 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -7056,7 +7056,7 @@ × 0030 × 0308 × 0020 × 0085 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0030 × 00A0 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0030 × 0020 ÷ 00A0 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0030 × 0308 × 00A0 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0030 × 0308 × 00A0 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0030 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0030 × 00AB ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0030 × 0020 ÷ 00AB ÷ # × [0.3] DIGIT ZERO (NU_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -7208,7 +7208,7 @@ × 007D × 0308 × 0020 × FE15 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 007D × 16FE4 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 007D × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 007D × 0308 × 16FE4 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 007D × 0308 × 16FE4 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 007D × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 007D ÷ AC00 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 007D × 0020 ÷ AC00 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -7312,7 +7312,7 @@ × 007D × 0308 × 0020 × 0085 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 007D × 00A0 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 007D × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 007D × 0308 × 00A0 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 007D × 0308 × 00A0 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 007D × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 007D × 00AB ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 007D × 0020 ÷ 00AB ÷ # × [0.3] RIGHT CURLY BRACKET (CL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -7464,7 +7464,7 @@ × 0085 ÷ 0308 × 0020 × FE15 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0085 ÷ 16FE4 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0085 ÷ 0020 ÷ 16FE4 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0085 ÷ 0308 × 16FE4 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0085 ÷ 0308 × 16FE4 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0085 ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0085 ÷ AC00 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0085 ÷ 0020 ÷ AC00 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -7568,7 +7568,7 @@ × 0085 ÷ 0308 × 0020 × 0085 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0085 ÷ 00A0 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0085 ÷ 0020 ÷ 00A0 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0085 ÷ 0308 × 00A0 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0085 ÷ 0308 × 00A0 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0085 ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0085 ÷ 00AB ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0085 ÷ 0020 ÷ 00AB ÷ # × [0.3] (NL_NotEastAsian) ÷ [5.04] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -7976,7 +7976,7 @@ × 00AB × 0308 × 0020 × FE15 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 00AB × 16FE4 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00AB × 0020 × 16FE4 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) × [15.11] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 00AB × 0308 × 16FE4 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 00AB × 0308 × 16FE4 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00AB × 0308 × 0020 × 16FE4 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [15.11] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00AB × AC00 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [15.11] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 00AB × 0020 × AC00 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) × [15.11] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -8080,7 +8080,7 @@ × 00AB × 0308 × 0020 × 0085 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 00AB × 00A0 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00AB × 0020 × 00A0 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) × [15.11] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 00AB × 0308 × 00A0 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 00AB × 0308 × 00A0 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00AB × 0308 × 0020 × 00A0 ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [15.11] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00AB × 00AB ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [15.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 00AB × 0020 × 00AB ÷ # × [0.3] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) × [15.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -8232,7 +8232,7 @@ × 00B4 × 0308 × 0020 × FE15 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 00B4 × 16FE4 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00B4 × 0020 ÷ 16FE4 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 00B4 × 0308 × 16FE4 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 00B4 × 0308 × 16FE4 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00B4 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00B4 × AC00 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [21.04] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 00B4 × 0020 ÷ AC00 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -8336,7 +8336,7 @@ × 00B4 × 0308 × 0020 × 0085 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 00B4 × 00A0 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00B4 × 0020 ÷ 00A0 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 00B4 × 0308 × 00A0 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 00B4 × 0308 × 00A0 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00B4 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00B4 × 00AB ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 00B4 × 0020 ÷ 00AB ÷ # × [0.3] ACUTE ACCENT (BB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -8488,7 +8488,7 @@ × 00BB × 0308 × 0020 × FE15 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 00BB × 16FE4 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00BB × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 00BB × 0308 × 16FE4 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 00BB × 0308 × 16FE4 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00BB × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00BB × AC00 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [19.13] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 00BB × 0020 ÷ AC00 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -8592,7 +8592,7 @@ × 00BB × 0308 × 0020 × 0085 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 00BB × 00A0 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00BB × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 00BB × 0308 × 00A0 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 00BB × 0308 × 00A0 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00BB × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00BB × 00AB ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 00BB × 0020 ÷ 00AB ÷ # × [0.3] RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pf_QUmPi_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -8744,7 +8744,7 @@ × 05D0 × 0308 × 0020 × FE15 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 05D0 × 16FE4 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 05D0 × 0020 ÷ 16FE4 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 05D0 × 0308 × 16FE4 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 05D0 × 0308 × 16FE4 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 05D0 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 05D0 ÷ AC00 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 05D0 × 0020 ÷ AC00 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -8848,7 +8848,7 @@ × 05D0 × 0308 × 0020 × 0085 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 05D0 × 00A0 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 05D0 × 0020 ÷ 00A0 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 05D0 × 0308 × 00A0 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 05D0 × 0308 × 00A0 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 05D0 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 05D0 × 00AB ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 05D0 × 0020 ÷ 00AB ÷ # × [0.3] HEBREW LETTER ALEF (HL_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -9000,7 +9000,7 @@ × 1160 × 0308 × 0020 × FE15 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1160 × 16FE4 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1160 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1160 × 0308 × 16FE4 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1160 × 0308 × 16FE4 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1160 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1160 ÷ AC00 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1160 × 0020 ÷ AC00 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -9104,7 +9104,7 @@ × 1160 × 0308 × 0020 × 0085 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1160 × 00A0 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1160 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1160 × 0308 × 00A0 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1160 × 0308 × 00A0 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1160 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1160 × 00AB ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1160 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL JUNGSEONG FILLER (JV_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -9256,7 +9256,7 @@ × 11A8 × 0308 × 0020 × FE15 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 11A8 × 16FE4 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11A8 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 11A8 × 0308 × 16FE4 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 11A8 × 0308 × 16FE4 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11A8 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11A8 ÷ AC00 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 11A8 × 0020 ÷ AC00 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -9360,7 +9360,7 @@ × 11A8 × 0308 × 0020 × 0085 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 11A8 × 00A0 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11A8 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 11A8 × 0308 × 00A0 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 11A8 × 0308 × 00A0 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11A8 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11A8 × 00AB ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 11A8 × 0020 ÷ 00AB ÷ # × [0.3] HANGUL JONGSEONG KIYEOK (JT_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -9512,7 +9512,7 @@ × 1B05 × 0308 × 0020 × FE15 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1B05 × 16FE4 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B05 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1B05 × 0308 × 16FE4 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1B05 × 0308 × 16FE4 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B05 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B05 ÷ AC00 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1B05 × 0020 ÷ AC00 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -9616,7 +9616,7 @@ × 1B05 × 0308 × 0020 × 0085 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1B05 × 00A0 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B05 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1B05 × 0308 × 00A0 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1B05 × 0308 × 00A0 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B05 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B05 × 00AB ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1B05 × 0020 ÷ 00AB ÷ # × [0.3] BALINESE LETTER AKARA (AK_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -9768,7 +9768,7 @@ × 1B44 × 0308 × 0020 × FE15 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1B44 × 16FE4 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B44 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1B44 × 0308 × 16FE4 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1B44 × 0308 × 16FE4 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B44 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B44 ÷ AC00 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1B44 × 0020 ÷ AC00 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -9872,7 +9872,7 @@ × 1B44 × 0308 × 0020 × 0085 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1B44 × 00A0 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B44 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1B44 × 0308 × 00A0 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1B44 × 0308 × 00A0 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B44 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B44 × 00AB ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1B44 × 0020 ÷ 00AB ÷ # × [0.3] BALINESE ADEG ADEG (VI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -10024,7 +10024,7 @@ × 1B50 × 0308 × 0020 × FE15 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1B50 × 16FE4 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B50 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1B50 × 0308 × 16FE4 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1B50 × 0308 × 16FE4 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B50 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B50 ÷ AC00 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1B50 × 0020 ÷ AC00 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -10128,7 +10128,7 @@ × 1B50 × 0308 × 0020 × 0085 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1B50 × 00A0 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B50 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1B50 × 0308 × 00A0 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1B50 × 0308 × 00A0 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B50 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B50 × 00AB ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1B50 × 0020 ÷ 00AB ÷ # × [0.3] BALINESE DIGIT ZERO (AS_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -10280,7 +10280,7 @@ × 1B5C × 0308 × 0020 × FE15 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1B5C × 16FE4 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B5C × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1B5C × 0308 × 16FE4 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1B5C × 0308 × 16FE4 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B5C × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1B5C ÷ AC00 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1B5C × 0020 ÷ AC00 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -10384,7 +10384,7 @@ × 1B5C × 0308 × 0020 × 0085 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1B5C × 00A0 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B5C × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1B5C × 0308 × 00A0 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1B5C × 0308 × 00A0 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B5C × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1B5C × 00AB ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1B5C × 0020 ÷ 00AB ÷ # × [0.3] BALINESE WINDU (ID_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -10536,7 +10536,7 @@ × 1BF2 × 0308 × 0020 × FE15 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1BF2 × 16FE4 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1BF2 × 0020 ÷ 16FE4 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1BF2 × 0308 × 16FE4 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1BF2 × 0308 × 16FE4 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1BF2 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1BF2 ÷ AC00 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1BF2 × 0020 ÷ AC00 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -10640,7 +10640,7 @@ × 1BF2 × 0308 × 0020 × 0085 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1BF2 × 00A0 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1BF2 × 0020 ÷ 00A0 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1BF2 × 0308 × 00A0 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1BF2 × 0308 × 00A0 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1BF2 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1BF2 × 00AB ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1BF2 × 0020 ÷ 00AB ÷ # × [0.3] BATAK PANGOLAT (VF_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -10792,7 +10792,7 @@ × 200B ÷ 0308 × 0020 × FE15 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 200B ÷ 16FE4 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200B × 0020 ÷ 16FE4 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [8.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 200B ÷ 0308 × 16FE4 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 200B ÷ 0308 × 16FE4 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200B ÷ 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200B ÷ AC00 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 200B × 0020 ÷ AC00 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [8.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -10896,7 +10896,7 @@ × 200B ÷ 0308 × 0020 × 0085 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 200B ÷ 00A0 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200B × 0020 ÷ 00A0 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [8.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 200B ÷ 0308 × 00A0 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 200B ÷ 0308 × 00A0 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200B ÷ 0308 × 0020 ÷ 00A0 ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200B ÷ 00AB ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) ÷ [8.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 200B × 0020 ÷ 00AB ÷ # × [0.3] ZERO WIDTH SPACE (ZW_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [8.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -11048,7 +11048,7 @@ × 2014 × 0308 × 0020 × FE15 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 2014 × 16FE4 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2014 × 0020 ÷ 16FE4 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 2014 × 0308 × 16FE4 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 2014 × 0308 × 16FE4 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2014 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2014 ÷ AC00 ÷ # × [0.3] EM DASH (B2_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 2014 × 0020 ÷ AC00 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -11152,7 +11152,7 @@ × 2014 × 0308 × 0020 × 0085 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 2014 × 00A0 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2014 × 0020 ÷ 00A0 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 2014 × 0308 × 00A0 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 2014 × 0308 × 00A0 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2014 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2014 × 00AB ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2014 × 0020 ÷ 00AB ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -11304,7 +11304,7 @@ × 2024 × 0308 × 0020 × FE15 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 2024 × 16FE4 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2024 × 0020 ÷ 16FE4 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 2024 × 0308 × 16FE4 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 2024 × 0308 × 16FE4 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2024 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2024 ÷ AC00 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 2024 × 0020 ÷ AC00 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -11408,7 +11408,7 @@ × 2024 × 0308 × 0020 × 0085 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 2024 × 00A0 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2024 × 0020 ÷ 00A0 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 2024 × 0308 × 00A0 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 2024 × 0308 × 00A0 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2024 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2024 × 00AB ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2024 × 0020 ÷ 00AB ÷ # × [0.3] ONE DOT LEADER (IN_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -11816,7 +11816,7 @@ × 261D × 0308 × 0020 × FE15 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 261D × 16FE4 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 261D × 0020 ÷ 16FE4 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 261D × 0308 × 16FE4 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 261D × 0308 × 16FE4 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 261D × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 261D ÷ AC00 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 261D × 0020 ÷ AC00 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -11920,7 +11920,7 @@ × 261D × 0308 × 0020 × 0085 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 261D × 00A0 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 261D × 0020 ÷ 00A0 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 261D × 0308 × 00A0 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 261D × 0308 × 00A0 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 261D × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 261D × 00AB ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 261D × 0020 ÷ 00AB ÷ # × [0.3] WHITE UP POINTING INDEX (EB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -12072,7 +12072,7 @@ × FFFC × 0308 × 0020 × FE15 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × FFFC × 16FE4 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FFFC × 0020 ÷ 16FE4 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× FFFC × 0308 × 16FE4 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× FFFC × 0308 × 16FE4 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FFFC × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × FFFC ÷ AC00 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) ÷ [20.02] HANGUL SYLLABLE GA (H2) ÷ [0.3] × FFFC × 0020 ÷ AC00 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -12176,7 +12176,7 @@ × FFFC × 0308 × 0020 × 0085 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × FFFC × 00A0 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FFFC × 0020 ÷ 00A0 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× FFFC × 0308 × 00A0 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× FFFC × 0308 × 00A0 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FFFC × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × FFFC × 00AB ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × FFFC × 0020 ÷ 00AB ÷ # × [0.3] OBJECT REPLACEMENT CHARACTER (CB_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -12328,7 +12328,7 @@ × 11003 × 0308 × 0020 × FE15 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 11003 × 16FE4 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11003 × 0020 ÷ 16FE4 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 11003 × 0308 × 16FE4 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 11003 × 0308 × 16FE4 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11003 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 11003 ÷ AC00 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 11003 × 0020 ÷ AC00 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -12432,7 +12432,7 @@ × 11003 × 0308 × 0020 × 0085 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 11003 × 00A0 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11003 × 0020 ÷ 00A0 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 11003 × 0308 × 00A0 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 11003 × 0308 × 00A0 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11003 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 11003 × 00AB ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 11003 × 0020 ÷ 00AB ÷ # × [0.3] BRAHMI SIGN JIHVAMULIYA (AP_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -12584,7 +12584,7 @@ × 1F1E6 × 0308 × 0020 × FE15 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 1F1E6 × 16FE4 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F1E6 × 0020 ÷ 16FE4 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 1F1E6 × 0308 × 16FE4 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 1F1E6 × 0308 × 16FE4 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F1E6 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 1F1E6 ÷ AC00 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 1F1E6 × 0020 ÷ AC00 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -12688,7 +12688,7 @@ × 1F1E6 × 0308 × 0020 × 0085 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 1F1E6 × 00A0 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F1E6 × 0020 ÷ 00A0 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 1F1E6 × 0308 × 00A0 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 1F1E6 × 0308 × 00A0 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F1E6 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 1F1E6 × 00AB ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 1F1E6 × 0020 ÷ 00AB ÷ # × [0.3] REGIONAL INDICATOR SYMBOL LETTER A (RI_NotEastAsian) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -13352,7 +13352,7 @@ × 0029 × 0308 × 0020 × FE15 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0029 × 16FE4 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0029 × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0029 × 0308 × 16FE4 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0029 × 0308 × 16FE4 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0029 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0029 ÷ AC00 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0029 × 0020 ÷ AC00 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -13456,7 +13456,7 @@ × 0029 × 0308 × 0020 × 0085 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0029 × 00A0 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0029 × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0029 × 0308 × 00A0 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0029 × 0308 × 00A0 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0029 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0029 × 00AB ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0029 × 0020 ÷ 00AB ÷ # × [0.3] RIGHT PARENTHESIS (CP_NotEastAsian_CP30) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -13608,7 +13608,7 @@ × 0028 × 0308 × 0020 × FE15 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0028 × 16FE4 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0028 × 0020 × 16FE4 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [7.01] SPACE (SP_NotEastAsian) × [14.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0028 × 0308 × 16FE4 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0028 × 0308 × 16FE4 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0028 × 0308 × 0020 × 16FE4 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [14.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0028 × AC00 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [14.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0028 × 0020 × AC00 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [7.01] SPACE (SP_NotEastAsian) × [14.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -13712,7 +13712,7 @@ × 0028 × 0308 × 0020 × 0085 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0028 × 00A0 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0028 × 0020 × 00A0 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [7.01] SPACE (SP_NotEastAsian) × [14.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0028 × 0308 × 00A0 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0028 × 0308 × 00A0 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0028 × 0308 × 0020 × 00A0 ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [14.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0028 × 00AB ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [14.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0028 × 0020 × 00AB ÷ # × [0.3] LEFT PARENTHESIS (OP_NotEastAsian_OP30) × [7.01] SPACE (SP_NotEastAsian) × [14.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -13862,9 +13862,9 @@ × 0001 × 0020 × FE15 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0001 × 0308 × FE15 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0001 × 0308 × 0020 × FE15 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] -× 0001 × 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [12.3] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0001 × 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0001 × 0020 ÷ 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0001 × 0308 × 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0001 × 0308 × 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0001 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0001 ÷ AC00 ÷ # × [0.3] (CM1_NotEastAsian_CM) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0001 × 0020 ÷ AC00 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -13966,9 +13966,9 @@ × 0001 × 0020 × 0085 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0001 × 0308 × 0085 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0001 × 0308 × 0020 × 0085 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] -× 0001 × 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [12.3] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0001 × 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0001 × 0020 ÷ 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0001 × 0308 × 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0001 × 0308 × 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0001 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (CM1_NotEastAsian_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0001 × 00AB ÷ # × [0.3] (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0001 × 0020 ÷ 00AB ÷ # × [0.3] (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -14120,7 +14120,7 @@ × 200D × 0308 × 0020 × FE15 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 200D × 16FE4 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200D × 0020 ÷ 16FE4 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 200D × 0308 × 16FE4 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 200D × 0308 × 16FE4 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200D × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 200D × AC00 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 200D × 0020 ÷ AC00 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -14224,7 +14224,7 @@ × 200D × 0308 × 0020 × 0085 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 200D × 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200D × 0020 ÷ 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 200D × 0308 × 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 200D × 0308 × 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200D × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200D × 00AB ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 200D × 0020 ÷ 00AB ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -14374,9 +14374,9 @@ × 302A × 0020 × FE15 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 302A × 0308 × FE15 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 302A × 0308 × 0020 × FE15 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] -× 302A × 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [12.3] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 302A × 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 302A × 0020 ÷ 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 302A × 0308 × 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 302A × 0308 × 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 302A × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 302A ÷ AC00 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 302A × 0020 ÷ AC00 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -14478,9 +14478,9 @@ × 302A × 0020 × 0085 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 302A × 0308 × 0085 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 302A × 0308 × 0020 × 0085 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] -× 302A × 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [12.3] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 302A × 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 302A × 0020 ÷ 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 302A × 0308 × 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.3] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 302A × 0308 × 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 302A × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 302A × 00AB ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 302A × 0020 ÷ 00AB ÷ # × [0.3] IDEOGRAPHIC LEVEL TONE MARK (CM1_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -14632,7 +14632,7 @@ × 0023 × 0308 × 0020 × FE15 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0023 × 16FE4 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0023 × 0020 ÷ 16FE4 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0023 × 0308 × 16FE4 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0023 × 0308 × 16FE4 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0023 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0023 ÷ AC00 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0023 × 0020 ÷ AC00 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -14736,7 +14736,7 @@ × 0023 × 0308 × 0020 × 0085 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0023 × 00A0 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0023 × 0020 ÷ 00A0 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0023 × 0308 × 00A0 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0023 × 0308 × 00A0 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0023 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0023 × 00AB ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0023 × 0020 ÷ 00AB ÷ # × [0.3] NUMBER SIGN (AL_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -14888,7 +14888,7 @@ × 00A7 × 0308 × 0020 × FE15 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 00A7 × 16FE4 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00A7 × 0020 ÷ 16FE4 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 00A7 × 0308 × 16FE4 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 00A7 × 0308 × 16FE4 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00A7 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 00A7 ÷ AC00 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 00A7 × 0020 ÷ AC00 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -14992,7 +14992,7 @@ × 00A7 × 0308 × 0020 × 0085 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 00A7 × 00A0 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00A7 × 0020 ÷ 00A0 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 00A7 × 0308 × 00A0 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 00A7 × 0308 × 00A0 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00A7 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 00A7 × 00AB ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 00A7 × 0020 ÷ 00AB ÷ # × [0.3] SECTION SIGN (AI_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -15144,7 +15144,7 @@ × 50005 × 0308 × 0020 × FE15 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 50005 × 16FE4 ÷ # × [0.3] (XX_NotEastAsian_AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 50005 × 0020 ÷ 16FE4 ÷ # × [0.3] (XX_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 50005 × 0308 × 16FE4 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 50005 × 0308 × 16FE4 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 50005 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 50005 ÷ AC00 ÷ # × [0.3] (XX_NotEastAsian_AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 50005 × 0020 ÷ AC00 ÷ # × [0.3] (XX_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -15248,7 +15248,7 @@ × 50005 × 0308 × 0020 × 0085 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 50005 × 00A0 ÷ # × [0.3] (XX_NotEastAsian_AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 50005 × 0020 ÷ 00A0 ÷ # × [0.3] (XX_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 50005 × 0308 × 00A0 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 50005 × 0308 × 00A0 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 50005 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] (XX_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 50005 × 00AB ÷ # × [0.3] (XX_NotEastAsian_AL) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 50005 × 0020 ÷ 00AB ÷ # × [0.3] (XX_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -15400,7 +15400,7 @@ × 0E01 × 0308 × 0020 × FE15 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 0E01 × 16FE4 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0E01 × 0020 ÷ 16FE4 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 0E01 × 0308 × 16FE4 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 0E01 × 0308 × 16FE4 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0E01 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 0E01 ÷ AC00 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 0E01 × 0020 ÷ AC00 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -15504,7 +15504,7 @@ × 0E01 × 0308 × 0020 × 0085 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 0E01 × 00A0 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0E01 × 0020 ÷ 00A0 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 0E01 × 0308 × 00A0 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 0E01 × 0308 × 00A0 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0E01 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 0E01 × 00AB ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 0E01 × 0020 ÷ 00AB ÷ # × [0.3] THAI CHARACTER KO KAI (SA_NotEastAsian_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -15656,7 +15656,7 @@ × 2757 × 0308 × 0020 × FE15 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 2757 × 16FE4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2757 × 0020 ÷ 16FE4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 2757 × 0308 × 16FE4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 2757 × 0308 × 16FE4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2757 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 2757 ÷ AC00 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 2757 × 0020 ÷ AC00 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -15760,11 +15760,11 @@ × 2757 × 0308 × 0020 × 0085 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 2757 × 00A0 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2757 × 0020 ÷ 00A0 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 2757 × 0308 × 00A0 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 2757 × 0308 × 00A0 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2757 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 2757 × 00AB ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2757 × 0020 ÷ 00AB ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 2757 × 0308 × 00AB ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 2757 × 0308 × 00AB ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2757 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 2757 ÷ 00B4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 2757 × 0020 ÷ 00B4 ÷ # × [0.3] HEAVY EXCLAMATION MARK SYMBOL (AI_AL) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -15912,7 +15912,7 @@ × 17D6 × 0308 × 0020 × FE15 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 17D6 × 16FE4 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 17D6 × 0020 ÷ 16FE4 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 17D6 × 0308 × 16FE4 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 17D6 × 0308 × 16FE4 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 17D6 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 17D6 ÷ AC00 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 17D6 × 0020 ÷ AC00 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -16016,7 +16016,7 @@ × 17D6 × 0308 × 0020 × 0085 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 17D6 × 00A0 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 17D6 × 0020 ÷ 00A0 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 17D6 × 0308 × 00A0 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 17D6 × 0308 × 00A0 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 17D6 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 17D6 × 00AB ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 17D6 × 0020 ÷ 00AB ÷ # × [0.3] KHMER SIGN CAMNUC PII KUUH (NS_NotEastAsian_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] @@ -16168,7 +16168,7 @@ × 3041 × 0308 × 0020 × FE15 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [13.01] PRESENTATION FORM FOR VERTICAL EXCLAMATION MARK (EX) ÷ [0.3] × 3041 × 16FE4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3041 × 0020 ÷ 16FE4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] -× 3041 × 0308 × 16FE4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] +× 3041 × 0308 × 16FE4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3041 × 0308 × 0020 ÷ 16FE4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] KHITAN SMALL SCRIPT FILLER (GL) ÷ [0.3] × 3041 ÷ AC00 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) ÷ [999.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] × 3041 × 0020 ÷ AC00 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] HANGUL SYLLABLE GA (H2) ÷ [0.3] @@ -16272,11 +16272,11 @@ × 3041 × 0308 × 0020 × 0085 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) × [6.0] (NL_NotEastAsian) ÷ [0.3] × 3041 × 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3041 × 0020 ÷ 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] -× 3041 × 0308 × 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 3041 × 0308 × 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3041 × 0308 × 0020 ÷ 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 3041 × 00AB ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3041 × 0020 ÷ 00AB ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] -× 3041 × 0308 × 00AB ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.1] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] +× 3041 × 0308 × 00AB ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [19.11] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3041 × 0308 × 0020 ÷ 00AB ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] LEFT-POINTING DOUBLE ANGLE QUOTATION MARK (QU_QU_Pi_QUmPf_NotEastAsian) ÷ [0.3] × 3041 ÷ 00B4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) ÷ [999.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] × 3041 × 0020 ÷ 00B4 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [7.01] SPACE (SP_NotEastAsian) ÷ [18.0] ACUTE ACCENT (BB_NotEastAsian) ÷ [0.3] @@ -16416,7 +16416,7 @@ × 200D × 261D ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] WHITE UP POINTING INDEX (EB_NotEastAsian) ÷ [0.3] × 3041 × 2060 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [11.01] WORD JOINER (WJ_NotEastAsian) ÷ [0.3] × 2060 × 3041 ÷ # × [0.3] WORD JOINER (WJ_NotEastAsian) × [11.02] HIRAGANA LETTER SMALL A (CJ_NS) ÷ [0.3] -× 3041 × 0308 × 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.2] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] +× 3041 × 0308 × 00A0 ÷ # × [0.3] HIRAGANA LETTER SMALL A (CJ_NS) × [9.0] COMBINING DIAERESIS (CM1_NotEastAsian_CM) × [12.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200D × 00A0 ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] NO-BREAK SPACE (GL_NotEastAsian) ÷ [0.3] × 200D × 002F ÷ # × [0.3] ZERO WIDTH JOINER (ZWJ_O_ZWJ_NotEastAsian_CM) × [8.1] SOLIDUS (SY_NotEastAsian) ÷ [0.3] × 2014 × 2014 ÷ # × [0.3] EM DASH (B2_NotEastAsian) × [17.0] EM DASH (B2_NotEastAsian) ÷ [0.3] diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakTest.html index a698e956c..a851a3035 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakTest.html @@ -7,7 +7,7 @@

Sentence_Break Chart

Unicode Version: 17.0.0

-

Date: 2024-09-12, 14:12:16 GMT

+

Date: 2024-10-14, 12:07:04 GMT

This page illustrates the application of the Sentence_Break specification. The material here is informative, not normative.

The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

Some column headers may be composed, reflecting “treat as” or “ignore” rules.

If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of ATerm and Close shows ×, with the rule 9.0. Checking below the table, rule 9.0 is “SATerm Close* × ( Close | Sp | ParaSep )”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

@@ -30,7 +30,7 @@

Table

0.2sot ×
0.3÷ eot
7.02× ZW
8.0ZW SP* ÷
8.1ZWJ_O ×
9.0[^ SP BK CR LF NL ZW] × CM
9.0(?<X>[^SP BK CR LF NL ZW]) ( CM | ZWJ )* → {X}
10.0( CM | ZWJ ) → A
11.01× WJ
11.02WJ ×
12.0GL ×
12.1[^ SP BA HY CM] × GL
12.2[^ BA HY CM] CM+ × GL
12.3^ CM+ × GL
12.1[^ SP BA HY] × GL
13.01× EX
13.02× CL
13.03× CP
11   ぁ   -◌̈   +◌̈      
Extend_FE×××××××××××××××

Rules

-

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule SB8a is given the number 8.1.
  4. Any “treat as” or “ignore” rules are handled as discussed in UAX #29, and thus reflected in a transformation of the rules usually not visible here. In addition, final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  5. In some cases, the numbering and form of a rule is changed due to “treat as” rules.

For the original rules and the macro values they use, see UAX #29.

+

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule SB8a is given the number 8.1.
  4. Final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.

For the original rules and the macro values they use, see UAX #29.

diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/WordBreakTest.html index 52a647c4a..6c25af5cf 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakTest.html @@ -7,7 +7,7 @@

Word_Break Chart

Unicode Version: 17.0.0

-

Date: 2024-09-12, 14:12:18 GMT

+

Date: 2024-10-14, 12:07:11 GMT

This page illustrates the application of the Word_Break specification. The material here is informative, not normative.

The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

After the heavy blue line in the table are additional rows, either with different sample characters or for sequences, such as “ALetter MidLetter”. Some column headers may be composed, reflecting “treat as” or “ignore” rules.

If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of ExtendNumLet and ALetter shows ×, with the rule 13.2. Checking below the table, rule 13.2 is “ExtendNumLet × (AHLetter | Numeric | Katakana)”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

@@ -45,7 +45,7 @@

Table

0.2sot ÷
0.3÷ eot
Numeric MidNumLet Format_FE÷÷÷÷÷÷÷÷÷×÷÷÷÷÷÷÷×××

Rules

-

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule WB13a is given the number 13.1.
  4. Any “treat as” or “ignore” rules are handled as discussed in UAX #29, and thus reflected in a transformation of the rules usually not visible here. In addition, final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  5. In some cases, the numbering and form of a rule is changed due to “treat as” rules.

For the original rules and the macro values they use, see UAX #29.

+

This section shows the rules. They are mechanically modified for programmatic generation of the tables and test code, and thus do not match the UAX rules precisely. In particular:

  1. The rules are cast into a form that is more like regular expressions.
  2. The rules “sot ÷”, “÷ eot”, and “÷ Any” are added mechanically, and have artificial numbers.
  3. The rules are given decimal numbers using tenths, and are written without prefix. For example, rule WB13a is given the number 13.1.
  4. Final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.

For the original rules and the macro values they use, see UAX #29.

diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java b/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java index ff506b4ee..2340d71f8 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java @@ -855,23 +855,14 @@ public void generateTable(PrintWriter out) { } out.print( "." - + "
  • Any “treat as” or “ignore” rules are handled as discussed in UAX #" - + (fileName.equals("Line") ? "14" : "29") - + ", and thus reflected in a transformation of the rules usually not visible here. "); - if (fileName.equals("Line")) { - out.print( - "Where it does show up, an extra variable like CM+ may appear, and the rule may be recast. "); - } - out.print( - "In addition, final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  • "); + + "
  • Final rules like “Any ÷ Any” may be recast as the equivalent expression “÷ Any”.
  • "); if (fileName.equals("Line")) { out.print( "Where a rule has multiple parts (lines), each one is numbered using hundredths, " + "such as 21.01) × BA, 21.02) × HY, ... "); } out.println( - "In some cases, the numbering and form of a rule is changed due to “treat as” rules.
    • " - + "" + "" + "

    For the original rules" + (fileName.equals("Word") || fileName.equals("Sentence") ? " and the macro values they use" @@ -926,6 +917,9 @@ public void generateTable(PrintWriter out) { if (breakPoint < 0) { breakPoint = ruleBody.indexOf('÷'); } + if (breakPoint < 0) { + breakPoint = ruleBody.indexOf('→'); + } out.println( "

    +
    0.2sot ÷
    0.3÷ eot
    " + linkAndAnchor("r" + ruleNumber, ruleNumber) diff --git a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java index f630b199e..80873d43c 100644 --- a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java +++ b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java @@ -32,6 +32,7 @@ import java.util.Map; import java.util.TreeMap; import java.util.concurrent.ConcurrentHashMap; +import java.util.function.Consumer; import java.util.regex.Matcher; import java.util.regex.Pattern; import java.util.regex.PatternSyntaxException; @@ -42,7 +43,7 @@ import org.unicode.text.UCD.Default; import org.unicode.text.UCD.ToolUnicodePropertySource; import org.unicode.text.utility.Settings; -import org.unicode.tools.Segmenter.Rule.Breaks; +import org.unicode.tools.Segmenter.SegmentationRule.Breaks; /** Ordered list of rules, with variables resolved before building. Use Builder to make. */ public class Segmenter { @@ -170,16 +171,26 @@ public boolean breaksAt(CharSequence text, int position) { breakRule = NOBREAK_SUPPLEMENTARY; return false; } + StringBuilder remapped = new StringBuilder(text.toString()); + Consumer remap = + (s) -> { + remapped.setLength(0); + remapped.append(s); + }; + Integer[] indexInRemapped = new Integer[text.length() + 1]; + for (int i = 0; i < indexInRemapped.length; ++i) { + indexInRemapped[i] = i; + } for (int i = 0; i < rules.size(); ++i) { - Rule rule = rules.get(i); + SegmentationRule rule = rules.get(i); if (DEBUG_AT_RULE_CONTAINING != null && rule.toString().contains(DEBUG_AT_RULE_CONTAINING)) { System.out.println(" !#$@543 Debug"); } - Breaks result = rule.matches(text, position); - if (result != Rule.Breaks.UNKNOWN_BREAK) { + Breaks result = rule.applyAt(position, remapped, indexInRemapped, remap); + if (result != SegmentationRule.Breaks.UNKNOWN_BREAK) { breakRule = orders.get(i).doubleValue(); - return result == Rule.Breaks.BREAK; + return result == SegmentationRule.Breaks.BREAK; } } breakRule = BREAK_ANY; @@ -197,12 +208,12 @@ public int getRuleStatusVec(int[] ruleStatus) { * @param order * @param rule */ - public void add(double order, Rule rule) { + public void add(double order, SegmentationRule rule) { orders.add(new Double(order)); rules.add(rule); } - public Rule get(double order) { + public SegmentationRule get(double order) { int loc = orders.indexOf(new Double(order)); if (loc < 0) return null; return rules.get(loc); @@ -231,8 +242,7 @@ public String toString(boolean showResolved) { return result; } - /** A rule that determines the status of an offset. */ - public static class Rule { + public abstract static class SegmentationRule { /** Status of a breaking rule */ public enum Breaks { UNKNOWN_BREAK, @@ -240,13 +250,145 @@ public enum Breaks { NO_BREAK }; + /** + * Applies this rule throughout the text. + * + * @param remappedString The text, with any preceding remappings applied. + * @param indexInRemapped An array whose size is one greater than the original string. + * Associates indices in the original string to indices in remappedString. + * indexInRemapped[0] == 0, and indexInRemapped[indexInRemapped.size() - 1] == + * remappedString.size(). Whenever indexInRemapped[i] == null, resolvedBreaks[i] == + * NO_BREAK: this corresponds to positions inside a string which has been replaced by a + * remap rule. Remap rules may update this mapping. + * @param resolvedBreaks An array whose size is one greater than the original string, + * indicating resolved breaks in the string. Values that are UNKNOWN_BREAK are updated + * if the rule applies to their position. + * @param remap Called by remap rules with the value of remappedString to be passed to + * subsequent rules. The indices in indexInRemapped are updated consistently. + */ + public abstract void apply( + CharSequence remappedString, + Integer[] indexInRemapped, + Breaks[] resolvedBreaks, + Consumer remap); + + protected abstract String toString(boolean showResolved); + + /** Same as above, but only returns the resolution at the current position. */ + public abstract Breaks applyAt( + int position, + CharSequence remappedString, + Integer[] indexInRemapped, + Consumer remap); + + public String toString() { + return toString(false); + } + } + + /** A « treat as » rule. */ + public static class RemapRule extends SegmentationRule { + + public RemapRule(String leftHandSide, String replacement, String line) { + pattern = Pattern.compile(leftHandSide, REGEX_FLAGS); + this.replacement = replacement; + name = line; + } + + @Override + public void apply( + CharSequence remappedString, + Integer[] indexInRemapped, + Breaks[] resolvedBreaks, + Consumer remap) { + final var result = new StringBuilder(); + int i = 0; + int offset = 0; + final var matcher = pattern.matcher(remappedString); + while (matcher.find()) { + for (; ; ++i) { + if (indexInRemapped[i] == null) { + continue; + } + if (indexInRemapped[i] > matcher.start()) { + break; + } + indexInRemapped[i] += offset; + } + for (; ; ++i) { + if (indexInRemapped[i] == null) { + continue; + } + if (indexInRemapped[i] == matcher.end()) { + break; + } + if (resolvedBreaks[i] == Breaks.BREAK) { + throw new IllegalArgumentException( + "Replacement rule at remapped indices " + + matcher.start() + + " sqq. spans a break: " + + remappedString); + } + resolvedBreaks[i] = Breaks.NO_BREAK; + indexInRemapped[i] = null; + } + matcher.appendReplacement(result, replacement); + offset = result.length() - indexInRemapped[i]; + } + for (; i < indexInRemapped.length; ++i) { + if (indexInRemapped[i] == null) { + continue; + } + indexInRemapped[i] += offset; + } + matcher.appendTail(result); + if (indexInRemapped[indexInRemapped.length - 1] != result.length()) { + StringBuilder indices = new StringBuilder(); + for (var j : indexInRemapped) { + indices.append(j == null ? "null" : j.toString()); + indices.append(","); + } + throw new IllegalArgumentException( + "Inconsistent indexInRemapped " + + indices + + " for new remapped string " + + result); + } + remap.accept(result); + } + + private Pattern pattern; + private String replacement; + private String name; + + @Override + public Breaks applyAt( + int position, + CharSequence remappedString, + Integer[] indexInRemapped, + Consumer remap) { + var resolvedBreaks = new Breaks[indexInRemapped.length]; + apply(remappedString, indexInRemapped, resolvedBreaks, remap); + return resolvedBreaks[position] == null + ? Breaks.UNKNOWN_BREAK + : resolvedBreaks[position]; + } + + @Override + protected String toString(boolean showResolved) { + return name; + } + } + + /** A rule that determines the status of an offset. */ + public static class RegexRule extends SegmentationRule { /** * @param before pattern for the text after the offset. All variables must be resolved. * @param result the break status to return when the rule is invoked * @param after pattern for the text before the offset. All variables must be resolved. * @param line */ - public Rule(String before, Breaks result, String after, String line) { + public RegexRule(String before, Breaks result, String after, String line) { breaks = result; before = ".*(" + before + ")"; String parsing = null; @@ -279,26 +421,33 @@ public Rule(String before, Breaks result, String after, String line) { // COMMENTS allows whitespace } - // Matcher numberMatcher = PatternCache.get("[0-9]+").matcher(""); - - /** - * Match the rule against text, at a position - * - * @param text - * @param position - * @return break status - */ - public Breaks matches(CharSequence text, int position) { - if (!matchAfter(matchSucceeding, text, position)) return Breaks.UNKNOWN_BREAK; - if (!matchBefore(matchPrevious, text, position)) return Breaks.UNKNOWN_BREAK; - return breaks; + @Override + public void apply( + CharSequence remappedString, + Integer[] indexInRemapped, + Breaks[] resolvedBreaks, + Consumer remap) { + for (int i = 0; i < indexInRemapped.length; ++i) { + if (resolvedBreaks[i] == Breaks.UNKNOWN_BREAK) { + resolvedBreaks[i] = applyAt(i, remappedString, indexInRemapped, remap); + } + } } - /** Debugging aid */ - public String toString() { - return toString(false); + @Override + public Breaks applyAt( + int position, + CharSequence remappedString, + Integer[] indexInRemapped, + Consumer remap) { + if (matchAfter(matchSucceeding, remappedString, indexInRemapped[position]) + && matchBefore(matchPrevious, remappedString, indexInRemapped[position])) { + return breaks; + } + return Breaks.UNKNOWN_BREAK; } + @Override public String toString(boolean showResolved) { String result = name; if (showResolved) result += ": " + resolved; @@ -474,17 +623,26 @@ public boolean addLine(String line) { throw new IllegalArgumentException("Rule must be of form '1)...': <" + line + ">"); } line = line.substring(relationPosition + 1).trim(); + relationPosition = line.indexOf('→'); + if (relationPosition >= 0) { + addRemapRule( + order, + line.substring(0, relationPosition).trim(), + line.substring(relationPosition + 1).trim(), + line); + return true; + } relationPosition = line.indexOf('\u00F7'); - Breaks breaks = Segmenter.Rule.Breaks.BREAK; + Breaks breaks = Segmenter.RegexRule.Breaks.BREAK; if (relationPosition < 0) { relationPosition = line.indexOf('\u00D7'); if (relationPosition < 0) { throw new IllegalArgumentException( "Couldn't find =, \u00F7, or \u00D7 on line: " + line); } - breaks = Segmenter.Rule.Breaks.NO_BREAK; + breaks = Segmenter.RegexRule.Breaks.NO_BREAK; } - addRule( + addRegexRule( order, line.substring(0, relationPosition).trim(), breaks, @@ -591,6 +749,40 @@ public static UnicodeMap composeWith( return target; } + Builder addRemapRule(Double order, String before, String after, String line) { + line = whiteSpace.reset(line).replaceAll(" "); + if (lastComments.size() != 0) { + double increment = 0.0001; + double temp = order.doubleValue() - increment * lastComments.size(); + for (int i = 0; i < lastComments.size(); ++i) { + Double position = new Double(temp); + if (xmlRules.containsKey(position)) { + System.out.println("WARNING: Overriding rule " + position); + } + xmlRules.put(position, lastComments.get(i)); + temp += increment; + } + lastComments.clear(); + } + if (htmlRules.containsKey(order) + || xmlRules.containsKey(order) + || rules.containsKey(order)) { + throw new IllegalArgumentException("Duplicate numbers for rules: " + order); + } + htmlRules.put(order, TransliteratorUtilities.toHTML.transliterate(line)); + xmlRules.put( + order, + " " + + TransliteratorUtilities.toXML.transliterate(line) + + " "); + rules.put(order, new Segmenter.RemapRule(replaceVariables(before), after, line)); + return this; + } + /** * Add a numbered rule, already broken into the parts before and after. * @@ -601,7 +793,8 @@ public static UnicodeMap composeWith( * @param line * @return */ - Builder addRule(Double order, String before, Breaks breaks, String after, String line) { + Builder addRegexRule( + Double order, String before, Breaks breaks, String after, String line) { // if (brokenIdentifierMatcher.reset(line).find()) { // int start = brokenIdentifierMatcher.start(); // int end = brokenIdentifierMatcher.end(); @@ -646,7 +839,7 @@ Builder addRule(Double order, String before, Breaks breaks, String after, String } rules.put( order, - new Segmenter.Rule( + new Segmenter.RegexRule( replaceVariables(before), breaks, replaceVariables(after), line)); return this; } @@ -671,9 +864,9 @@ public Segmenter make() { // longest first, to // make substitution // easy - private Map rules = new TreeMap(); + private Map rules = new TreeMap(); - public Map getProcessedRules() { + public Map getProcessedRules() { return rules; } @@ -813,7 +1006,7 @@ public Map getOriginalVariables() { // ============== Internals ================ - private List rules = new ArrayList(1); + private List rules = new ArrayList(1); private List orders = new ArrayList(1); private double breakRule; diff --git a/unicodetools/src/main/java/org/unicode/tools/TestSegments.java b/unicodetools/src/main/java/org/unicode/tools/TestSegments.java index e748ff9c6..ead5331b7 100644 --- a/unicodetools/src/main/java/org/unicode/tools/TestSegments.java +++ b/unicodetools/src/main/java/org/unicode/tools/TestSegments.java @@ -22,7 +22,6 @@ import org.unicode.jsp.ICUPropertyFactory; import org.unicode.props.RandomStringGenerator; import org.unicode.props.UnicodeProperty; -import org.unicode.tools.Segmenter.Rule.Breaks; /** * Quick class for testing proposed syntax for Segments. TODO doesn't yet handle supplementaries. It @@ -133,7 +132,7 @@ public static void main(String[] args) throws IOException { } private static void debugRule(Segmenter.Builder rb) { - Segmenter.Rule rule = rb.make().get(16.01); + Segmenter.SegmentationRule rule = rb.make().get(16.01); String oldAL = (String) rb.getVariables().get("$oldAL"); UnicodeSet oldALSet = new UnicodeSet(oldAL); String testStr = "\uA80D/\u0745\u2026"; @@ -142,7 +141,7 @@ private static void debugRule(Segmenter.Builder rb) { System.out.println( k + ": " + inside + com.ibm.icu.impl.Utility.escape("" + testStr.charAt(k))); } - Breaks m = rule.matches(testStr, 3); + rule.applyAt(3, testStr, new Integer[] {0, 1, 2, 3}, null); } private static void doCompare(UnicodeProperty.Factory factory, Segmenter rl, String line) { diff --git a/unicodetools/src/main/resources/org/unicode/tools/SegmenterDefault.txt b/unicodetools/src/main/resources/org/unicode/tools/SegmenterDefault.txt index e7e6193bd..eb9b2b132 100644 --- a/unicodetools/src/main/resources/org/unicode/tools/SegmenterDefault.txt +++ b/unicodetools/src/main/resources/org/unicode/tools/SegmenterDefault.txt @@ -142,86 +142,10 @@ $CM=[$CM1 $ZWJ] ## show $AL $AL=[$AI $AL $SG $XX $SA] $NS=[$NS $CJ] -## show $AL -## $oldAL=$AL // for debugging -# WARNING: Fixes for Rule 9 -# Treat X (CM|ZWJ* as if it were X. -# Where X is any line break class except SP, BK, CR, LF, NL or ZW. -$X=$CM* # MACROS -$Spec1_=[$SP $BK $CR $LF $NL $ZW] -$Spec2_=[^ $SP $BK $CR $LF $NL $ZW] -$Spec3a_=[^ $SP $BA $HY $CM] -$Spec3b_=[^ $BA $HY $CM] -$Spec4_=[^ $NU $CM] - -# SPECIAL EXTENSIONS - -$AI=($AI $X) -$AK=($AK $X) -$AL=($AL $X) -$AP=($AP $X) -$AS=($AS $X) -$B2=($B2 $X) -$BA=($BA $X) -$BB=($BB $X) -$CB=($CB $X) -$CL=($CL $X) -$CP=($CP $X) -$CM=($CM $X) -## $CM=($CM $X) -$EX=($EX $X) -$GL=($GL $X) -$H2=($H2 $X) -$H3=($H3 $X) -$HL=($HL $X) -$HY=($HY $X) -$ID=($ID $X) -$IN=($IN $X) -$IS=($IS $X) -$JL=($JL $X) -$JT=($JT $X) -$JV=($JV $X) -$NS=($NS $X) -$NU=($NU $X) -$OP=($OP $X) -$PO=($PO $X) -$PR=($PR $X) -$QU=($QU $X) -$SA=($SA $X) -$SG=($SG $X) -$SY=($SY $X) -$VF=($VF $X) -$VI=($VI $X) -$WJ=($WJ $X) -$XX=($XX $X) -$RI=($RI $X) -$EB=($EB $X) -$EM=($EM $X) -$ZWJ=($ZWJ $X) - -$QU_Pi=($QU_Pi $X) -$QU_Pf=($QU_Pf $X) - -$QUmPi=($QUmPi $X) -$QUmPf=($QUmPf $X) - -$NotEastAsian=( $NotEastAsian | [$NotEastAsian - $Spec1_] $X) -$NonEastAsianBA=(NonEastAsianBA $X) - -$DottedCircle=($DottedCircle $X) -$Hyphen=($Hyphen $X) - -$CP30=($CP30 $X) -$OP30=($OP30 $X) - -# OUT OF ORDER ON PURPOSE - -# LB 10 Treat any remaining combining mark as AL and non-$EastAsian. -$AL=($AL | ^ $CM | (?<=$Spec1_) $CM) -$NotEastAsian=( $NotEastAsian | ^ $CM | (?<=$Spec1_) $CM ) +$Spec3a_=[^ $SP $BA $HY] # RULES @@ -241,19 +165,18 @@ $NotEastAsian=( $NotEastAsian | ^ $CM | (?<=$Spec1_) $CM ) 8) $ZW $SP* ÷ # LB 8a Don't break between ZWJ and IDs (for use in Emoji ZWJ sequences) 8.1) $ZWJ_O × -# LB 9 Do not break a combining character sequence; treat it as if it has the LB class of the base character -# in all of the following rules. (Where X is any line break class except SP, BK, CR, LF, NL or ZW.) -9) $Spec2_ × $CM -##WARNING: this is done by modifying the variable values for all but SP.... That is, $AL is really ($AI $CM*)! +# LB 9 Do not break a combining character sequence; treat it as if it has the line breaking class +# of the base character in all of the following rules. Treat ZWJ as if it were CM. +9) (?[^$BK $CR $LF $NL $SP $ZW]) ( $CM | $ZWJ )* → ${X} +# LB10 Treat any remaining combining mark or ZWJ as AL. +10) ( $CM | $ZWJ ) → A ## LB 11 Do not break before or after WORD JOINER and related characters. 11.01) × $WJ 11.02) $WJ × # LB 12 Do not break after NBSP and related characters. -## 12.01) [^$SP] × $GL 12) $GL × +# LB 12a Do not break before NBSP and related characters, except after spaces and hyphens. 12.1) $Spec3a_ × $GL -12.2) $Spec3b_ $CM+ × $GL -12.3) ^ $CM+ × $GL # LB 13 Do not break before \u2018]\u2019 or \u2018!\u2019 or \u2018;\u2019 or \u2018/\u2019, even after spaces. 13.01) × $EX 13.02) × $CL diff --git a/unicodetools/src/test/java/org/unicode/test/TestSegment.java b/unicodetools/src/test/java/org/unicode/test/TestSegment.java index baf52f539..719f3cf14 100644 --- a/unicodetools/src/test/java/org/unicode/test/TestSegment.java +++ b/unicodetools/src/test/java/org/unicode/test/TestSegment.java @@ -31,7 +31,7 @@ import org.unicode.text.utility.Utility; import org.unicode.tools.Segmenter; import org.unicode.tools.Segmenter.Builder; -import org.unicode.tools.Segmenter.Rule; +import org.unicode.tools.Segmenter.SegmentationRule; public class TestSegment { @@ -398,8 +398,8 @@ private static void checkExemplars() { } private static void getExemplarStrings(UnicodeMap exemplars, Builder segmenter) { - Map srules = segmenter.getProcessedRules(); - for (Entry entry : srules.entrySet()) { + Map srules = segmenter.getProcessedRules(); + for (Entry entry : srules.entrySet()) { System.out.println(entry.getKey() + "\t\t" + entry.getValue()); } } From bf10f7d64da3db53861a03ccc13f673dc7605d7f Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 17 Oct 2024 19:30:51 +0200 Subject: [PATCH 02/26] We are not using Java 1.4 anymore. (#950) --- .../java/org/unicode/tools/Segmenter.java | 33 +++++++------------ 1 file changed, 12 insertions(+), 21 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java index 80873d43c..994a79e7d 100644 --- a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java +++ b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java @@ -393,8 +393,8 @@ public RegexRule(String before, Breaks result, String after, String line) { before = ".*(" + before + ")"; String parsing = null; try { - matchPrevious = Pattern.compile(parsing = before, REGEX_FLAGS).matcher(""); - matchSucceeding = Pattern.compile(parsing = after, REGEX_FLAGS).matcher(""); + this.before = Pattern.compile(parsing = before, REGEX_FLAGS); + this.after = Pattern.compile(parsing = after, REGEX_FLAGS); } catch (PatternSyntaxException e) { // Format: Unclosed character class near index 927 int index = e.getIndex(); @@ -440,8 +440,12 @@ public Breaks applyAt( CharSequence remappedString, Integer[] indexInRemapped, Consumer remap) { - if (matchAfter(matchSucceeding, remappedString, indexInRemapped[position]) - && matchBefore(matchPrevious, remappedString, indexInRemapped[position])) { + if (after.matcher(remappedString) + .region(indexInRemapped[position], remappedString.length()) + .lookingAt() + && before.matcher(remappedString) + .region(0, indexInRemapped[position]) + .matches()) { return breaks; } return Breaks.UNKNOWN_BREAK; @@ -455,29 +459,16 @@ public String toString(boolean showResolved) { } // ============== Internals ================ - // in Java 5, this can be more efficient, and use a single regex - // of the form "(?<= before) after". MUST then have transparent bounds - private Matcher matchPrevious; - private Matcher matchSucceeding; + // We cannot use a single regex of the form "(?<= before) after" because + // (RI RI)* RI × RI would require unbounded lookbehind. + private Pattern before; + private Pattern after; private String name; private String resolved; private Breaks breaks; } - /** utility, since we are using Java 1.4 */ - static boolean matchAfter(Matcher matcher, CharSequence text, int position) { - return matcher.reset(text.subSequence(position, text.length())).lookingAt(); - } - - /** - * utility, since we are using Java 1.4 depends on the pattern having been built with .* not - * very efficient, works for testing and the best we can do. - */ - static boolean matchBefore(Matcher matcher, CharSequence text, int position) { - return matcher.reset(text.subSequence(0, position)).matches(); - } - /** Separate the builder for clarity */ /** Sort the longest strings first. Used for variable lists. */ From 250884c8357ad9b67bb7d6f46f89b743a1f4652d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 31 Oct 2024 15:36:29 +0100 Subject: [PATCH 03/26] Test InCB=Extend for Gujarati Shadda (#957) * Shadda on a half-form * Regenerate UCD --- .../data/ucd/dev/auxiliary/GraphemeBreakTest.html | 10 +++++++++- .../data/ucd/dev/auxiliary/GraphemeBreakTest.txt | 7 ++++--- unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html | 4 ++-- .../java/org/unicode/text/UCD/GenerateBreakTest.java | 5 ++++- 4 files changed, 19 insertions(+), 7 deletions(-) diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html index 5b6026ef5..619182f0b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.html @@ -7,7 +7,7 @@

    Grapheme_Cluster_Break Chart

    Unicode Version: 17.0.0

    -

    Date: 2024-10-14, 12:06:04 GMT

    +

    Date: 2024-10-30, 21:25:11 GMT

    This page illustrates the application of the Grapheme_Cluster_Break specification. The material here is informative, not normative.

    The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

    Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

    After the heavy blue line in the table are additional rows, either with different sample characters or for sequences. Some column headers may be composed, reflecting “treat as” or “ignore” rules.

    If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of LVT and T shows ×, with the rule 8.0. Checking below the table, rule 8.0 is “( LVT | T) × T”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

    @@ -294,6 +294,14 @@

    Sample Strings

    ◌्   त   +
    36 +  સ   +◌ૻ   +◌્   +સ   +◌ૻ   +
    diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.txt index d10c174b6..4e55634d7 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakTest.txt @@ -1,5 +1,5 @@ -# GraphemeBreakTest-16.0.0.txt -# Date: 2024-05-02, 15:02:48 GMT +# GraphemeBreakTest-17.0.0.txt +# Date: 2024-10-30, 21:25:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1115,7 +1115,8 @@ ÷ 0061 × 094D ÷ 0924 ÷ # ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] DEVANAGARI SIGN VIRAMA (Extend_ConjunctLinkingScripts_ConjunctLinker_ExtCccZwj) ÷ [999.0] DEVANAGARI LETTER TA (ConjunctLinkingScripts_LinkingConsonant) ÷ [0.3] ÷ 003F × 094D ÷ 0924 ÷ # ÷ [0.2] QUESTION MARK (Other) × [9.0] DEVANAGARI SIGN VIRAMA (Extend_ConjunctLinkingScripts_ConjunctLinker_ExtCccZwj) ÷ [999.0] DEVANAGARI LETTER TA (ConjunctLinkingScripts_LinkingConsonant) ÷ [0.3] ÷ 0915 × 094D × 094D × 0924 ÷ # ÷ [0.2] DEVANAGARI LETTER KA (ConjunctLinkingScripts_LinkingConsonant) × [9.0] DEVANAGARI SIGN VIRAMA (Extend_ConjunctLinkingScripts_ConjunctLinker_ExtCccZwj) × [9.0] DEVANAGARI SIGN VIRAMA (Extend_ConjunctLinkingScripts_ConjunctLinker_ExtCccZwj) × [9.3] DEVANAGARI LETTER TA (ConjunctLinkingScripts_LinkingConsonant) ÷ [0.3] +÷ 0AB8 × 0AFB × 0ACD × 0AB8 × 0AFB ÷ # ÷ [0.2] GUJARATI LETTER SA (ConjunctLinkingScripts_LinkingConsonant) × [9.0] GUJARATI SIGN SHADDA (Extend_ConjunctLinkingScripts_ExtCccZwj) × [9.0] GUJARATI SIGN VIRAMA (Extend_ConjunctLinkingScripts_ConjunctLinker_ExtCccZwj) × [9.3] GUJARATI LETTER SA (ConjunctLinkingScripts_LinkingConsonant) × [9.0] GUJARATI SIGN SHADDA (Extend_ConjunctLinkingScripts_ExtCccZwj) ÷ [0.3] # -# Lines: 1093 +# Lines: 1094 # # EOF diff --git a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html index 3b2899e64..745622907 100644 --- a/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html +++ b/unicodetools/data/ucd/dev/auxiliary/LineBreakTest.html @@ -7,7 +7,7 @@

    Line_Break Chart

    Unicode Version: 17.0.0

    -

    Date: 2024-10-14, 12:25:22 GMT

    +

    Date: 2024-10-30, 21:25:12 GMT

    This page illustrates the application of the Line_Break specification. The material here is informative, not normative.

    The first chart shows where breaks would appear between different sample characters or strings. The sample characters are chosen mechanically to represent the different properties used by the specification.

    Each cell shows the break-status for the position between the character(s) in its row header and the character(s) in its column header. The × symbol indicates no break, while the ÷ symbol indicated a break. The cells with × are also shaded to make it easier to scan the table. For example, in the cell at the intersection of the row headed by “CR” and the column headed by “LF”, there is a × symbol, indicating that there is no break between CR and LF.

    Some column headers may be composed, reflecting “treat as” or “ignore” rules.

    If your browser handles titles (tooltips), then hovering the mouse over the row header will show a sample character of that type. Hovering over a column header will show the sample character, plus its abbreviated general category and script. Hovering over the intersected cells shows the rule number that produces the break-status. For example, hovering over the cell at the intersection of H3 and JT shows ×, with the rule 26.03. Checking below the table, rule 26.03 is “JT | H3 × JT”, which is the one that applies to that case. Note that a rule is invoked only when no lower-numbered rules have applied.

    @@ -93,7 +93,7 @@

    Rules

    7.02× ZW 8.0ZW SP* ÷ 8.1ZWJ_O × -9.0(?<X>[^SP BK CR LF NL ZW]) ( CM | ZWJ )* → {X} +9.0(?<X>[^BK CR LF NL SP ZW]) ( CM | ZWJ )* → {X} 10.0( CM | ZWJ ) → A 11.01× WJ 11.02WJ × diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java b/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java index 2340d71f8..597862b41 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/GenerateBreakTest.java @@ -1393,7 +1393,10 @@ public GenerateGraphemeBreakTest(UCD ucd, Segmenter.Target target) { "क" + "\u094D" + "a", "a" + "\u094D" + "त", "?" + "\u094D" + "त", - "क" + "\u094D\u094D" + "त")); + "क" + "\u094D\u094D" + "त", + // From L2/14-131, §3.2; made into a single EGC by 179-C31. + // This test would have caught ICU-22956. + "સૻ્સૻ")); } } From fc59f0d5506704d38ede683bf2efd9ad390d00f6 Mon Sep 17 00:00:00 2001 From: Elango Cheran Date: Tue, 5 Nov 2024 14:32:28 -0800 Subject: [PATCH 04/26] Only run Maven cache workflow on the upstream repo (#959) --- .github/workflows/cache_retain.yml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/.github/workflows/cache_retain.yml b/.github/workflows/cache_retain.yml index 471d25a21..e0df6fbe9 100644 --- a/.github/workflows/cache_retain.yml +++ b/.github/workflows/cache_retain.yml @@ -30,6 +30,10 @@ jobs: retain-maven-cache: name: Run all tests with Maven runs-on: ubuntu-latest + # Only run this on the upstream repo. Otherwise, running in a person fork will cause + # Github to disable the personal fork copy of the workflow + # (Github complains about running a scheduled workflow on a repo with > 60 days of inactivity) + if: github.ref == 'refs/heads/main' && github.repository == 'unicode-org/unicodetools' steps: - name: Checkout and setup uses: actions/checkout@v2 From c5ad6353e4a994e9477d67f036d50da9e13d9ebd Mon Sep 17 00:00:00 2001 From: Elango Cheran Date: Tue, 5 Nov 2024 15:13:09 -0800 Subject: [PATCH 05/26] fix typo (#960) --- .github/workflows/cache_retain.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/cache_retain.yml b/.github/workflows/cache_retain.yml index e0df6fbe9..8cfc236d1 100644 --- a/.github/workflows/cache_retain.yml +++ b/.github/workflows/cache_retain.yml @@ -30,7 +30,7 @@ jobs: retain-maven-cache: name: Run all tests with Maven runs-on: ubuntu-latest - # Only run this on the upstream repo. Otherwise, running in a person fork will cause + # Only run this on the upstream repo. Otherwise, running in a personal fork will cause # Github to disable the personal fork copy of the workflow # (Github complains about running a scheduled workflow on a repo with > 60 days of inactivity) if: github.ref == 'refs/heads/main' && github.repository == 'unicode-org/unicodetools' From f32aee21ab831455175908d3d36e6c3bb93930d4 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 12 Nov 2024 10:47:04 +0100 Subject: [PATCH 06/26] Allow redundant lines in data files to facilitate merging (#962) --- .../src/main/java/org/unicode/props/PropertyUtilities.java | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/props/PropertyUtilities.java b/unicodetools/src/main/java/org/unicode/props/PropertyUtilities.java index e2e9c1708..9b8019062 100644 --- a/unicodetools/src/main/java/org/unicode/props/PropertyUtilities.java +++ b/unicodetools/src/main/java/org/unicode/props/PropertyUtilities.java @@ -31,6 +31,9 @@ public String merge(String first, String second) { static final > M putNew(M map, K key, V value) { final V oldValue = map.get(key); if (oldValue != null) { + if (oldValue.equals(value)) { + return map; + } throw new UnicodePropertyException( "Key already present in Map: " + key @@ -48,6 +51,9 @@ static final UnicodeMap putNew( final V oldValue = map.get(key); if (oldValue != null && (missingSet == null || !missingSet.contains(key))) { if (merger == null) { + if (oldValue.equals(value)) { + return map; + } throw new UnicodePropertyException( "Key already present in UnicodeMap: " + Utility.hex(key) From a3e374000ae31f2139a96a22584b6f6dad9b9238 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 17:02:26 +0100 Subject: [PATCH 07/26] ARABIC LETTER NOON WITH RING ABOVE (#703) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * UnicodeData.txt from the proposal * lb=AL like nearby noons * Script=Arabic * ArabicShaping.txt * Regenerate UCD * Comparison with other نs * New syntax * Ignore Unicode_1_Name * Ignore Block too * Expect what the comment says we expect. --- unicodetools/data/ucd/dev/ArabicShaping.txt | 1 + unicodetools/data/ucd/dev/DerivedAge.txt | 14 +++++++-- .../data/ucd/dev/DerivedCoreProperties.txt | 28 ++++++++--------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 +-- unicodetools/data/ucd/dev/LineBreak.txt | 6 ++-- unicodetools/data/ucd/dev/Scripts.txt | 6 ++-- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 4 +-- .../dev/auxiliary/SentenceBreakProperty.txt | 8 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 8 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 8 ++--- .../dev/extracted/DerivedCombiningClass.txt | 8 ++--- .../dev/extracted/DerivedEastAsianWidth.txt | 8 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 11 ++++--- .../ucd/dev/extracted/DerivedJoiningGroup.txt | 7 +++-- .../ucd/dev/extracted/DerivedJoiningType.txt | 7 +++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 12 ++++---- .../data/ucd/dev/extracted/DerivedName.txt | 7 +++-- .../text/UCD/AdditionComparisons/118.txt | 30 +++++++++++++++++++ 19 files changed, 111 insertions(+), 67 deletions(-) create mode 100644 unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/118.txt diff --git a/unicodetools/data/ucd/dev/ArabicShaping.txt b/unicodetools/data/ucd/dev/ArabicShaping.txt index 3c9e0ca80..20d103cd5 100644 --- a/unicodetools/data/ucd/dev/ArabicShaping.txt +++ b/unicodetools/data/ucd/dev/ArabicShaping.txt @@ -482,6 +482,7 @@ 088C; TAH WITH 3 DOTS BELOW; D; TAH 088D; KEHEH WITH VERTICAL 2 DOTS BELOW; D; GAF 088E; VERTICAL TAIL; R; VERTICAL TAIL +088F; DOTLESS NOON WITH SEPARATE RING ABOVE; D; NOON 0890; ARABIC POUND MARK ABOVE; U; No_Joining_Group 0891; ARABIC PIASTRE MARK ABOVE; U; No_Joining_Group diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index b4dcd2e48..a94174a98 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ -# DerivedAge-16.0.0.txt -# Date: 2024-04-30, 21:48:12 GMT +# DerivedAge-17.0.0.txt +# Date: 2024-10-15, 12:06:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2059,4 +2059,14 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L # Total code points: 5185 +# ================================================ + +# Age=V17_0 + +# Newly assigned in Unicode 17.0.0 (September, 2025) + +088F ; 17.0 # ARABIC LETTER NOON WITH RING ABOVE + +# Total code points: 1 + # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1075638f1..952f65edf 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ -# DerivedCoreProperties-16.0.0.txt -# Date: 2024-05-31, 18:09:32 GMT +# DerivedCoreProperties-17.0.0.txt +# Date: 2024-10-15, 12:06:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -344,7 +344,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0840..0858 ; Alphabetic # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Alphabetic # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; Alphabetic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; Alphabetic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; Alphabetic # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897 ; Alphabetic # Mn ARABIC PEPET 08A0..08C8 ; Alphabetic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; Alphabetic # Lm ARABIC SMALL FARSI YEH @@ -1441,7 +1441,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142759 +# Total code points: 142760 # ================================================ @@ -6259,7 +6259,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0840..0858 ; ID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; ID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; ID_Start # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; ID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -6962,7 +6962,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141269 +# Total code points: 141270 # ================================================ @@ -7068,7 +7068,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0859..085B ; ID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; ID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; ID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; ID_Continue # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897..089F ; ID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; ID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ID_Continue # Lm ARABIC SMALL FARSI YEH @@ -8370,7 +8370,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144541 +# Total code points: 144542 # ================================================ @@ -8441,7 +8441,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0840..0858 ; XID_Start # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; XID_Start # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; XID_Start # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; XID_Start # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; XID_Start # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; XID_Start # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; XID_Start # Lm ARABIC SMALL FARSI YEH 0904..0939 ; XID_Start # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -9148,7 +9148,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141246 +# Total code points: 141247 # ================================================ @@ -9250,7 +9250,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0859..085B ; XID_Continue # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 0860..086A ; XID_Continue # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; XID_Continue # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; XID_Continue # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; XID_Continue # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0897..089F ; XID_Continue # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; XID_Continue # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; XID_Continue # Lm ARABIC SMALL FARSI YEH @@ -10557,7 +10557,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144522 +# Total code points: 144523 # ================================================ @@ -11190,7 +11190,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0860..086A ; Grapheme_Base # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; Grapheme_Base # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; Grapheme_Base # Sk ARABIC RAISED ROUND DOT -0889..088E ; Grapheme_Base # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; Grapheme_Base # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; Grapheme_Base # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; Grapheme_Base # Lm ARABIC SMALL FARSI YEH 0903 ; Grapheme_Base # Mc DEVANAGARI SIGN VISARGA @@ -12812,7 +12812,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152730 +# Total code points: 152731 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 99f7a31ea..a86664d64 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2024-04-30, 21:48:20 GMT +# Date: 2024-05-31, 18:59:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -332,7 +332,7 @@ 0860..086A ; N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; N # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; N # Sk ARABIC RAISED ROUND DOT -0889..088E ; N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; N # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; N # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 3ce258217..174be204c 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ -# LineBreak-16.0.0.txt -# Date: 2024-07-29, 16:26:55 GMT +# LineBreak-17.0.0.txt +# Date: 2024-10-15, 12:06:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -278,7 +278,7 @@ 0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; AL # Sk ARABIC RAISED ROUND DOT -0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; AL # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; NU # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; CM # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 443a6d2dd..fd898bef9 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2024-04-30, 21:48:40 GMT +# Date: 2024-05-31, 19:00:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -869,7 +869,7 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 0750..077F ; Arabic # Lo [48] ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS ABOVE 0870..0887 ; Arabic # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; Arabic # Sk ARABIC RAISED ROUND DOT -0889..088E ; Arabic # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; Arabic # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; Arabic # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; Arabic # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; Arabic # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF @@ -926,7 +926,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1373 +# Total code points: 1374 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 64258a373..f323b4ad6 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -2121,6 +2121,7 @@ 088C;ARABIC LETTER TAH WITH THREE DOTS BELOW;Lo;0;AL;;;;;N;;;;; 088D;ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 088E;ARABIC VERTICAL TAIL;Lo;0;AL;;;;;N;;;;; +088F;ARABIC LETTER NOON WITH RING ABOVE;Lo;0;AL;;;;;N;;;;; 0890;ARABIC POUND MARK ABOVE;Cf;0;AN;;;;;N;;;;; 0891;ARABIC PIASTRE MARK ABOVE;Cf;0;AN;;;;;N;;;;; 0897;ARABIC PEPET;Mn;230;NSM;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 1ebcd7228..82f24ccc7 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2024-04-30, 21:48:42 GMT +# Date: 2024-05-31, 19:00:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -266,7 +266,7 @@ 0860..086A ; R # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; R # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; R # Sk ARABIC RAISED ROUND DOT -0889..088E ; R # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; R # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; R # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; R # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; R # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index ca3689e6b..3de833156 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ -# SentenceBreakProperty-16.0.0.txt -# Date: 2024-07-29, 16:27:32 GMT +# SentenceBreakProperty-17.0.0.txt +# Date: 2024-10-15, 12:07:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2022,7 +2022,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0840..0858 ; OLetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; OLetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; OLetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; OLetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; OLetter # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; OLetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; OLetter # Lm ARABIC SMALL FARSI YEH 0904..0939 ; OLetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -2585,7 +2585,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136908 +# Total code points: 136909 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index e557c3d0d..c99a5cc9b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ -# WordBreakProperty-16.0.0.txt -# Date: 2024-07-29, 16:27:36 GMT +# WordBreakProperty-17.0.0.txt +# Date: 2024-10-15, 12:07:36 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -745,7 +745,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0840..0858 ; ALetter # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; ALetter # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; ALetter # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; ALetter # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; ALetter # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; ALetter # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; ALetter # Lm ARABIC SMALL FARSI YEH 0904..0939 ; ALetter # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -1355,7 +1355,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33791 +# Total code points: 33792 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 2aceac0aa..fe077592f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ -# DerivedBidiClass-16.0.0.txt -# Date: 2024-04-30, 21:48:13 GMT +# DerivedBidiClass-17.0.0.txt +# Date: 2024-10-15, 12:06:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2442,7 +2442,7 @@ E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; AL # Sk ARABIC RAISED ROUND DOT -0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; AL # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; AL # Lm ARABIC SMALL FARSI YEH FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM @@ -2501,7 +2501,7 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 293 code points not listed here. +# The above property value applies to 292 code points not listed here. # Total code points: 1767 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index a5d57af96..a8f2afcb0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ -# DerivedCombiningClass-16.0.0.txt -# Date: 2024-04-30, 21:48:15 GMT +# DerivedCombiningClass-17.0.0.txt +# Date: 2024-10-15, 12:06:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -182,7 +182,7 @@ 0860..086A ; 0 # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; 0 # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; 0 # Sk ARABIC RAISED ROUND DOT -0889..088E ; 0 # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; 0 # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; 0 # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 08A0..08C8 ; 0 # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; 0 # Lm ARABIC SMALL FARSI YEH @@ -2060,7 +2060,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821581 code points not listed here. +# The above property value applies to 821580 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index cc1d91aaa..357665e7f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ -# DerivedEastAsianWidth-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedEastAsianWidth-17.0.0.txt +# Date: 2024-10-15, 12:06:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -223,7 +223,7 @@ 0860..086A ; N # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; N # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; N # Sk ARABIC RAISED ROUND DOT -0889..088E ; N # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; N # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 0890..0891 ; N # Cf [2] ARABIC POUND MARK ABOVE..ARABIC PIASTRE MARK ABOVE 0897..089F ; N # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA 08A0..08C8 ; N # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF @@ -2103,7 +2103,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761099 code points not listed here. +# The above property value applies to 761098 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 07bf7bca9..aa74b7e2e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ -# DerivedGeneralCategory-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedGeneralCategory-17.0.0.txt +# Date: 2024-10-15, 12:06:50 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -36,7 +36,6 @@ 085C..085D ; Cn # [2] .. 085F ; Cn # 086B..086F ; Cn # [5] .. -088F ; Cn # 0892..0896 ; Cn # [5] .. 0984 ; Cn # 098D..098E ; Cn # [2] .. @@ -747,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819533 +# Total code points: 819532 # ================================================ @@ -2203,7 +2202,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0840..0858 ; Lo # [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 0860..086A ; Lo # [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; Lo # [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT -0889..088E ; Lo # [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; Lo # [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; Lo # [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 0904..0939 ; Lo # [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA 093D ; Lo # DEVANAGARI SIGN AVAGRAHA @@ -2708,7 +2707,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136477 +# Total code points: 136478 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt index 17778a8a0..d2c5547ed 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt @@ -1,5 +1,5 @@ -# DerivedJoiningGroup-16.0.0.txt -# Date: 2024-07-30, 21:15:55 GMT +# DerivedJoiningGroup-17.0.0.txt +# Date: 2024-10-15, 12:06:51 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -231,8 +231,9 @@ 06B9..06BC ; Noon # Lo [4] ARABIC LETTER NOON WITH DOT BELOW..ARABIC LETTER NOON WITH RING 0767..0769 ; Noon # Lo [3] ARABIC LETTER NOON WITH TWO DOTS BELOW..ARABIC LETTER NOON WITH SMALL V 0889 ; Noon # Lo ARABIC LETTER NOON WITH INVERTED SMALL V +088F ; Noon # Lo ARABIC LETTER NOON WITH RING ABOVE -# Total code points: 9 +# Total code points: 10 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 3841a92cc..d08bfdd7e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ -# DerivedJoiningType-16.0.0.txt -# Date: 2024-04-30, 21:48:18 GMT +# DerivedJoiningType-17.0.0.txt +# Date: 2024-10-15, 12:06:51 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -70,6 +70,7 @@ 0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA 0886 ; D # Lo ARABIC LETTER THIN YEH 0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +088F ; D # Lo ARABIC LETTER NOON WITH RING ABOVE 08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE 08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE 08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE @@ -111,7 +112,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FCA ; D # No CHORASMIAN NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 612 +# Total code points: 613 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 31d143e92..d368bd0ba 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ -# DerivedLineBreak-16.0.0.txt -# Date: 2024-07-29, 16:26:50 GMT +# DerivedLineBreak-17.0.0.txt +# Date: 2024-10-15, 12:06:52 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757653 code points not listed here. -# Total code points: 895121 +# The above property value applies to 757652 code points not listed here. +# Total code points: 895120 # ================================================ @@ -665,7 +665,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0860..086A ; AL # Lo [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA 0870..0887 ; AL # Lo [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT 0888 ; AL # Sk ARABIC RAISED ROUND DOT -0889..088E ; AL # Lo [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL +0889..088F ; AL # Lo [7] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER NOON WITH RING ABOVE 08A0..08C8 ; AL # Lo [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF 08C9 ; AL # Lm ARABIC SMALL FARSI YEH 0904..0939 ; AL # Lo [54] DEVANAGARI LETTER SHORT A..DEVANAGARI LETTER HA @@ -1613,7 +1613,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26679 +# Total code points: 26680 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 07b0176b5..17697332e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ -# DerivedName-16.0.0.txt -# Date: 2024-04-30, 21:48:18 GMT +# DerivedName-17.0.0.txt +# Date: 2024-10-15, 12:06:52 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2096,6 +2096,7 @@ 088C ; ARABIC LETTER TAH WITH THREE DOTS BELOW 088D ; ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW 088E ; ARABIC VERTICAL TAIL +088F ; ARABIC LETTER NOON WITH RING ABOVE 0890 ; ARABIC POUND MARK ABOVE 0891 ; ARABIC PIASTRE MARK ABOVE 0897 ; ARABIC PEPET @@ -45367,6 +45368,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 154998 +# Total code points: 154999 # EOF diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/118.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/118.txt new file mode 100644 index 000000000..58662bbb8 --- /dev/null +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/AdditionComparisons/118.txt @@ -0,0 +1,30 @@ +# ARABIC LETTER NOON WITH RING ABOVE (088F) +# https://github.com/unicode-org/utc-release-management/issues/118 + +Let $OldNoons := [ ن ڹ ں ڻ ڼ ڽ ݧ ݨ ݩ ࢉ ] + +# Names always differ. +# Age always differs since these tests are comparing additions to pre-existing characters. +Ignoring Name Age: + +# Ignore the security and IDNA properties, as these are not yet included for provisionally assigned characters. +Ignoring Confusable_MA Identifier_Status Identifier_Type Idn_Status Idn_Mapping Idn_2008: + +Ignoring Block Unicode_1_Name: + +# « Another ن, propertywise like the others. ». + +# Differs from ڽ (with three dots above) in Joining_Group, +# ڽ being jg=Nya vs. jg=Noon for the others; see +# https://www.unicode.org/versions/latest/ch09.pdf#G39824. +Ignoring Joining_Group: +Propertywise [ $OldNoons \N{ARABIC LETTER NOON WITH RING ABOVE} ] AreAlike +end Ignoring; + +Propertywise [ $OldNoons - [ڽ] \N{ARABIC LETTER NOON WITH RING ABOVE} ] AreAlike + +end Ignoring; + +end Ignoring; + +end Ignoring; From 7da5a74ba89954c233aa47a24e975d4914de556c Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 17:17:50 +0100 Subject: [PATCH 08/26] Bengali Sanskrit BA (#758) * UnicodeData.txt line from L2/22-268R * lb=AL * script * InSC from proposal * Regenerate UCD * UTC-178-C38 Approve the name change for provisionally assigned character U+09FF from BENGALI LETTER ALTERNATE BA to BENGALI LETTER SANSKRIT BA. * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 ++-- .../data/ucd/dev/DerivedCoreProperties.txt | 23 ++++++++++++------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 ++-- .../data/ucd/dev/IndicSyllabicCategory.txt | 3 ++- unicodetools/data/ucd/dev/LineBreak.txt | 3 ++- unicodetools/data/ucd/dev/Scripts.txt | 7 +++--- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 5 ++-- .../dev/auxiliary/SentenceBreakProperty.txt | 5 ++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 5 ++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 5 ++-- .../dev/extracted/DerivedCombiningClass.txt | 5 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 5 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 9 ++++---- .../ucd/dev/extracted/DerivedLineBreak.txt | 9 ++++---- .../data/ucd/dev/extracted/DerivedName.txt | 5 ++-- 16 files changed, 61 insertions(+), 39 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index a94174a98..2bfaba38d 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-10-15, 12:06:14 GMT +# Date: 2024-11-13, 16:03:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2066,7 +2066,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L # Newly assigned in Unicode 17.0.0 (September, 2025) 088F ; 17.0 # ARABIC LETTER NOON WITH RING ABOVE +09FF ; 17.0 # BENGALI LETTER SANSKRIT BA -# Total code points: 1 +# Total code points: 2 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 952f65edf..25aac7794 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-10-15, 12:06:47 GMT +# Date: 2024-11-13, 16:03:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -386,6 +386,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 09E2..09E3 ; Alphabetic # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL 09F0..09F1 ; Alphabetic # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; Alphabetic # Lo BENGALI LETTER VEDIC ANUSVARA +09FF ; Alphabetic # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; Alphabetic # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; Alphabetic # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Alphabetic # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -1441,7 +1442,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142760 +# Total code points: 142761 # ================================================ @@ -6280,6 +6281,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 09DF..09E1 ; ID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; ID_Start # Lo BENGALI LETTER VEDIC ANUSVARA +09FF ; ID_Start # Lo BENGALI LETTER SANSKRIT BA 0A05..0A0A ; ID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -6962,7 +6964,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141270 +# Total code points: 141271 # ================================================ @@ -7116,6 +7118,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 09F0..09F1 ; ID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; ID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 09FE ; ID_Continue # Mn BENGALI SANDHI MARK +09FF ; ID_Continue # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; ID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; ID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; ID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -8370,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144542 +# Total code points: 144543 # ================================================ @@ -8462,6 +8465,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 09DF..09E1 ; XID_Start # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; XID_Start # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; XID_Start # Lo BENGALI LETTER VEDIC ANUSVARA +09FF ; XID_Start # Lo BENGALI LETTER SANSKRIT BA 0A05..0A0A ; XID_Start # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; XID_Start # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; XID_Start # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -9148,7 +9152,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141247 +# Total code points: 141248 # ================================================ @@ -9298,6 +9302,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 09F0..09F1 ; XID_Continue # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; XID_Continue # Lo BENGALI LETTER VEDIC ANUSVARA 09FE ; XID_Continue # Mn BENGALI SANDHI MARK +09FF ; XID_Continue # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; XID_Continue # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; XID_Continue # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; XID_Continue # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -10557,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144523 +# Total code points: 144524 # ================================================ @@ -11229,6 +11234,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 09FB ; Grapheme_Base # Sc BENGALI GANDA MARK 09FC ; Grapheme_Base # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; Grapheme_Base # Po BENGALI ABBREVIATION SIGN +09FF ; Grapheme_Base # Lo BENGALI LETTER SANSKRIT BA 0A03 ; Grapheme_Base # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; Grapheme_Base # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Grapheme_Base # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -12812,7 +12818,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152731 +# Total code points: 152732 # ================================================ @@ -12926,6 +12932,7 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 09DC..09DD ; InCB; Consonant # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF ; InCB; Consonant # Lo BENGALI LETTER YYA 09F0..09F1 ; InCB; Consonant # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FF ; InCB; Consonant # Lo BENGALI LETTER SANSKRIT BA 0A95..0AA8 ; InCB; Consonant # Lo [20] GUJARATI LETTER KA..GUJARATI LETTER NA 0AAA..0AB0 ; InCB; Consonant # Lo [7] GUJARATI LETTER PA..GUJARATI LETTER RA 0AB2..0AB3 ; InCB; Consonant # Lo [2] GUJARATI LETTER LA..GUJARATI LETTER LLA @@ -12943,7 +12950,7 @@ ABED ; Grapheme_Link # Mn MEETEI MAYEK APUN IYEK 0C58..0C5A ; InCB; Consonant # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA 0D15..0D3A ; InCB; Consonant # Lo [38] MALAYALAM LETTER KA..MALAYALAM LETTER TTTA -# Total code points: 240 +# Total code points: 241 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index a86664d64..a6456503f 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ -# EastAsianWidth-16.0.0.txt -# Date: 2024-05-31, 18:59:23 GMT +# EastAsianWidth-17.0.0.txt +# Date: 2024-11-13, 16:04:00 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -391,6 +391,7 @@ 09FC ; N # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; N # Po BENGALI ABBREVIATION SIGN 09FE ; N # Mn BENGALI SANDHI MARK +09FF ; N # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU diff --git a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt index dc0760462..b5ac9d2a7 100644 --- a/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt +++ b/unicodetools/data/ucd/dev/IndicSyllabicCategory.txt @@ -1,5 +1,5 @@ # IndicSyllabicCategory-16.0.0.txt -# Date: 2024-04-30, 21:48:21 GMT +# Date: 2024-06-06, 09:53:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -814,6 +814,7 @@ AA74..AA76 ; Consonant_Placeholder # Lo [3] MYANMAR LOGOGRAM KHAMTI OAY..MY 09DC..09DD ; Consonant # Lo [2] BENGALI LETTER RRA..BENGALI LETTER RHA 09DF ; Consonant # Lo BENGALI LETTER YYA 09F0..09F1 ; Consonant # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL +09FF ; Consonant # Lo BENGALI LETTER SANSKRIT BA 0A15..0A28 ; Consonant # Lo [20] GURMUKHI LETTER KA..GURMUKHI LETTER NA 0A2A..0A30 ; Consonant # Lo [7] GURMUKHI LETTER PA..GURMUKHI LETTER RA 0A32..0A33 ; Consonant # Lo [2] GURMUKHI LETTER LA..GURMUKHI LETTER LLA diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 174be204c..1fb5157e3 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-10-15, 12:06:57 GMT +# Date: 2024-11-13, 16:04:00 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -338,6 +338,7 @@ 09FC ; AL # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; AL # Po BENGALI ABBREVIATION SIGN 09FE ; CM # Mn BENGALI SANDHI MARK +09FF ; AL # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; CM # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; CM # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index fd898bef9..31fa7a356 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ -# Scripts-16.0.0.txt -# Date: 2024-05-31, 19:00:14 GMT +# Scripts-17.0.0.txt +# Date: 2024-11-13, 16:04:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1014,8 +1014,9 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 09FC ; Bengali # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; Bengali # Po BENGALI ABBREVIATION SIGN 09FE ; Bengali # Mn BENGALI SANDHI MARK +09FF ; Bengali # Lo BENGALI LETTER SANSKRIT BA -# Total code points: 96 +# Total code points: 97 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index f323b4ad6..6644d363f 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -2453,6 +2453,7 @@ 09FC;BENGALI LETTER VEDIC ANUSVARA;Lo;0;L;;;;;N;;;;; 09FD;BENGALI ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 09FE;BENGALI SANDHI MARK;Mn;230;NSM;;;;;N;;;;; +09FF;BENGALI LETTER SANSKRIT BA;Lo;0;L;;;;;N;;;;; 0A01;GURMUKHI SIGN ADAK BINDI;Mn;0;NSM;;;;;N;;;;; 0A02;GURMUKHI SIGN BINDI;Mn;0;NSM;;;;;N;;;;; 0A03;GURMUKHI SIGN VISARGA;Mc;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 82f24ccc7..b7b77d6b4 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ -# VerticalOrientation-16.0.0.txt -# Date: 2024-05-31, 19:00:21 GMT +# VerticalOrientation-17.0.0.txt +# Date: 2024-11-13, 16:04:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -325,6 +325,7 @@ 09FC ; R # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; R # Po BENGALI ABBREVIATION SIGN 09FE ; R # Mn BENGALI SANDHI MARK +09FF ; R # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; R # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; R # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; R # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 3de833156..74787a3b9 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-10-15, 12:07:32 GMT +# Date: 2024-11-13, 16:04:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2043,6 +2043,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 09DF..09E1 ; OLetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; OLetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; OLetter # Lo BENGALI LETTER VEDIC ANUSVARA +09FF ; OLetter # Lo BENGALI LETTER SANSKRIT BA 0A05..0A0A ; OLetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; OLetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; OLetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -2585,7 +2586,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136909 +# Total code points: 136910 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index c99a5cc9b..7418faa9a 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-10-15, 12:07:36 GMT +# Date: 2024-11-13, 16:04:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -766,6 +766,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 09DF..09E1 ; ALetter # Lo [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; ALetter # Lo [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; ALetter # Lo BENGALI LETTER VEDIC ANUSVARA +09FF ; ALetter # Lo BENGALI LETTER SANSKRIT BA 0A05..0A0A ; ALetter # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; ALetter # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; ALetter # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -1355,7 +1356,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33792 +# Total code points: 33793 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index fe077592f..286c768bc 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-10-15, 12:06:44 GMT +# Date: 2024-11-13, 16:03:53 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -198,6 +198,7 @@ 09FA ; L # So BENGALI ISSHAR 09FC ; L # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; L # Po BENGALI ABBREVIATION SIGN +09FF ; L # Lo BENGALI LETTER SANSKRIT BA 0A03 ; L # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; L # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; L # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI @@ -1214,7 +1215,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815351 code points not listed here. +# The above property value applies to 815350 code points not listed here. # Total code points: 1095513 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index a8f2afcb0..b0cf0ca6c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-10-15, 12:06:46 GMT +# Date: 2024-11-13, 16:03:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -232,6 +232,7 @@ 09FB ; 0 # Sc BENGALI GANDA MARK 09FC ; 0 # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; 0 # Po BENGALI ABBREVIATION SIGN +09FF ; 0 # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; 0 # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; 0 # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; 0 # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -2060,7 +2061,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821580 code points not listed here. +# The above property value applies to 821579 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 357665e7f..2eb9bc962 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-10-15, 12:06:49 GMT +# Date: 2024-11-13, 16:03:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -280,6 +280,7 @@ 09FC ; N # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; N # Po BENGALI ABBREVIATION SIGN 09FE ; N # Mn BENGALI SANDHI MARK +09FF ; N # Lo BENGALI LETTER SANSKRIT BA 0A01..0A02 ; N # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI 0A03 ; N # Mc GURMUKHI SIGN VISARGA 0A05..0A0A ; N # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU @@ -2103,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761098 code points not listed here. +# The above property value applies to 761097 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index aa74b7e2e..037c06b31 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-10-15, 12:06:50 GMT +# Date: 2024-11-13, 16:03:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -50,7 +50,7 @@ 09D8..09DB ; Cn # [4] .. 09DE ; Cn # 09E4..09E5 ; Cn # [2] .. -09FF..0A00 ; Cn # [2] .. +0A00 ; Cn # 0A04 ; Cn # 0A0B..0A0E ; Cn # [4] .. 0A11..0A12 ; Cn # [2] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819532 +# Total code points: 819531 # ================================================ @@ -2221,6 +2221,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 09DF..09E1 ; Lo # [3] BENGALI LETTER YYA..BENGALI LETTER VOCALIC LL 09F0..09F1 ; Lo # [2] BENGALI LETTER RA WITH MIDDLE DIAGONAL..BENGALI LETTER RA WITH LOWER DIAGONAL 09FC ; Lo # BENGALI LETTER VEDIC ANUSVARA +09FF ; Lo # BENGALI LETTER SANSKRIT BA 0A05..0A0A ; Lo # [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; Lo # [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; Lo # [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -2707,7 +2708,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136478 +# Total code points: 136479 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index d368bd0ba..931ee1f27 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-10-15, 12:06:52 GMT +# Date: 2024-11-13, 16:03:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757652 code points not listed here. -# Total code points: 895120 +# The above property value applies to 757651 code points not listed here. +# Total code points: 895119 # ================================================ @@ -690,6 +690,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 09FA ; AL # So BENGALI ISSHAR 09FC ; AL # Lo BENGALI LETTER VEDIC ANUSVARA 09FD ; AL # Po BENGALI ABBREVIATION SIGN +09FF ; AL # Lo BENGALI LETTER SANSKRIT BA 0A05..0A0A ; AL # Lo [6] GURMUKHI LETTER A..GURMUKHI LETTER UU 0A0F..0A10 ; AL # Lo [2] GURMUKHI LETTER EE..GURMUKHI LETTER AI 0A13..0A28 ; AL # Lo [22] GURMUKHI LETTER OO..GURMUKHI LETTER NA @@ -1613,7 +1614,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26680 +# Total code points: 26681 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 17697332e..3b46c52f1 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-10-15, 12:06:52 GMT +# Date: 2024-11-13, 16:03:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2428,6 +2428,7 @@ 09FC ; BENGALI LETTER VEDIC ANUSVARA 09FD ; BENGALI ABBREVIATION SIGN 09FE ; BENGALI SANDHI MARK +09FF ; BENGALI LETTER SANSKRIT BA 0A01 ; GURMUKHI SIGN ADAK BINDI 0A02 ; GURMUKHI SIGN BINDI 0A03 ; GURMUKHI SIGN VISARGA @@ -45368,6 +45369,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 154999 +# Total code points: 155000 # EOF From 97d58bf3aee06fc64f2aff9c8e7b4372d1611112 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 17:38:02 +0100 Subject: [PATCH 09/26] Oriya dots above (#781) * UnicodeData.txt lines from L2/24-106 * lb=CM * Oriya * IndicMeowCategory from L2/24-106 * Both diacritics and the double dot an extender * Regenerate UCD * more invariant exceptions * oops * Typo in ORIYA --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +++-- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- .../data/ucd/dev/IndicPositionalCategory.txt | 4 ++-- .../data/ucd/dev/IndicSyllabicCategory.txt | 6 ++--- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- unicodetools/data/ucd/dev/PropList.txt | 12 +++++----- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 2 ++ .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 8 +++---- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++----- .../dev/extracted/DerivedCombiningClass.txt | 6 ++--- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++++----- .../data/ucd/dev/extracted/DerivedName.txt | 6 +++-- .../unicode/text/UCD/UnicodeInvariantTest.txt | 3 ++- 21 files changed, 76 insertions(+), 70 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 2bfaba38d..ef061a1d3 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 16:03:37 GMT +# Date: 2024-11-13, 16:21:36 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2067,7 +2067,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 088F ; 17.0 # ARABIC LETTER NOON WITH RING ABOVE 09FF ; 17.0 # BENGALI LETTER SANSKRIT BA +0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE -# Total code points: 2 +# Total code points: 4 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 25aac7794..915d290db 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 16:03:55 GMT +# Date: 2024-11-13, 16:21:56 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3104,7 +3104,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 0B3F ; Case_Ignorable # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; Case_Ignorable # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Case_Ignorable # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Case_Ignorable # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Case_Ignorable # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; Case_Ignorable # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Case_Ignorable # Mn TAMIL SIGN ANUSVARA 0BC0 ; Case_Ignorable # Mn TAMIL VOWEL SIGN II @@ -3506,7 +3506,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2749 +# Total code points: 2751 # ================================================ @@ -7179,7 +7179,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0B47..0B48 ; ID_Continue # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; ID_Continue # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; ID_Continue # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; ID_Continue # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; ID_Continue # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; ID_Continue # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; ID_Continue # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; ID_Continue # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144543 +# Total code points: 144545 # ================================================ @@ -9363,7 +9363,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0B47..0B48 ; XID_Continue # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; XID_Continue # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; XID_Continue # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; XID_Continue # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; XID_Continue # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; XID_Continue # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; XID_Continue # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; XID_Continue # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144524 +# Total code points: 144526 # ================================================ @@ -10685,7 +10685,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 0B3F ; Extend # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; Extend # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -495,7 +495,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2198 +# Total code points: 2200 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 74787a3b9..010e2eaea 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:04:21 GMT +# Date: 2024-11-13, 16:22:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -111,7 +111,7 @@ 0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2601 +# Total code points: 2603 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 7418faa9a..2d3d10c79 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:04:23 GMT +# Date: 2024-11-13, 16:22:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -147,7 +147,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 0B47..0B48 ; Extend # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; Extend # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; Extend # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; Extend # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Extend # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; Extend # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; Extend # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Extend # Mn TAMIL SIGN ANUSVARA @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2605 +# Total code points: 2607 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 286c768bc..de30f8204 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 16:03:53 GMT +# Date: 2024-11-13, 16:21:54 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815350 code points not listed here. -# Total code points: 1095513 +# The above property value applies to 815348 code points not listed here. +# Total code points: 1095511 # ================================================ @@ -2108,7 +2108,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 0B3F ; NSM # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; NSM # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; NSM # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; NSM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; NSM # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; NSM # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; NSM # Mn TAMIL SIGN ANUSVARA 0BC0 ; NSM # Mn TAMIL VOWEL SIGN II @@ -2409,7 +2409,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2028 +# Total code points: 2030 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index b0cf0ca6c..a67aa3100 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 16:03:55 GMT +# Date: 2024-11-13, 16:21:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -291,7 +291,7 @@ 0B41..0B44 ; 0 # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B47..0B48 ; 0 # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; 0 # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU -0B55..0B56 ; 0 # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; 0 # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; 0 # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; 0 # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; 0 # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -2061,7 +2061,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821579 code points not listed here. +# The above property value applies to 821577 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 2eb9bc962..d3efc8f0b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 16:03:57 GMT +# Date: 2024-11-13, 16:21:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -344,7 +344,7 @@ 0B47..0B48 ; N # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; N # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; N # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; N # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; N # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; N # Mc ORIYA AU LENGTH MARK 0B5C..0B5D ; N # Lo [2] ORIYA LETTER RRA..ORIYA LETTER RHA 0B5F..0B61 ; N # Lo [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761097 code points not listed here. +# The above property value applies to 761095 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 037c06b31..4e2501104 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 16:03:57 GMT +# Date: 2024-11-13, 16:21:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -90,7 +90,7 @@ 0B3A..0B3B ; Cn # [2] .. 0B45..0B46 ; Cn # [2] .. 0B49..0B4A ; Cn # [2] .. -0B4E..0B54 ; Cn # [7] .. +0B4E..0B52 ; Cn # [5] .. 0B58..0B5B ; Cn # [4] .. 0B5E ; Cn # 0B64..0B65 ; Cn # [2] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819531 +# Total code points: 819529 # ================================================ @@ -2773,7 +2773,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 0B3F ; Mn # ORIYA VOWEL SIGN I 0B41..0B44 ; Mn # [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; Mn # ORIYA SIGN VIRAMA -0B55..0B56 ; Mn # [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; Mn # [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; Mn # [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; Mn # TAMIL SIGN ANUSVARA 0BC0 ; Mn # TAMIL VOWEL SIGN II @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2020 +# Total code points: 2022 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index d08bfdd7e..443125089 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-10-15, 12:06:51 GMT +# Date: 2024-11-13, 16:21:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -266,7 +266,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 0B3F ; T # Mn ORIYA VOWEL SIGN I 0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR 0B4D ; T # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; T # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; T # Mn TAMIL SIGN ANUSVARA 0BC0 ; T # Mn TAMIL VOWEL SIGN II @@ -582,6 +582,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2185 +# Total code points: 2187 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 931ee1f27..3c482e58d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 16:03:58 GMT +# Date: 2024-11-13, 16:21:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757651 code points not listed here. -# Total code points: 895119 +# The above property value applies to 757649 code points not listed here. +# Total code points: 895117 # ================================================ @@ -1967,7 +1967,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 0B47..0B48 ; CM # Mc [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI 0B4B..0B4C ; CM # Mc [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU 0B4D ; CM # Mn ORIYA SIGN VIRAMA -0B55..0B56 ; CM # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B53..0B56 ; CM # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK 0B57 ; CM # Mc ORIYA AU LENGTH MARK 0B62..0B63 ; CM # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL 0B82 ; CM # Mn TAMIL SIGN ANUSVARA @@ -2388,7 +2388,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2470 +# Total code points: 2472 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 3b46c52f1..253d43288 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 16:03:58 GMT +# Date: 2024-11-13, 16:21:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2663,6 +2663,8 @@ 0B4B ; ORIYA VOWEL SIGN O 0B4C ; ORIYA VOWEL SIGN AU 0B4D ; ORIYA SIGN VIRAMA +0B53 ; ORIYA SIGN DOT ABOVE +0B54 ; ORIYA SIGN DOUBLE DOT ABOVE 0B55 ; ORIYA SIGN OVERLINE 0B56 ; ORIYA AI LENGTH MARK 0B57 ; ORIYA AU LENGTH MARK @@ -45369,6 +45371,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155000 +# Total code points: 155002 # EOF diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt index 570de2e90..4e4685029 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/UnicodeInvariantTest.txt @@ -700,6 +700,7 @@ Let $nonAlphabeticBindus := [] Let $nonAlphabeticDependentVowels := [ \N{ORIYA SIGN OVERLINE} + \p{Name=/^ORIYA SIGN (DOUBLE )?DOT ABOVE$/} # L2/24-106R, related to the overline. \N{THAI CHARACTER MAITAIKHU} \N{LIMBU SIGN KEMPHRENG} \N{SHARADA VOWEL MODIFIER MARK} @@ -1379,4 +1380,4 @@ Ignoring Unicode_1_Name Confusable_MA: end Ignoring; -end Ignoring; \ No newline at end of file +end Ignoring; From 5e40d67f7a45c1496ed4c345d0cbf90649734cc8 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 18:21:21 +0100 Subject: [PATCH 10/26] Kannada and Telugu: Archaic Ligature SHRII (#862) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Revert "No archaic shriis in 16 (#786)" This reverts commit aeefbb8fda1e74a0e959e0cf5d69ff8316121d25. * Don’t try to bring back the IDNA mapping table --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 38 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 6 +-- unicodetools/data/ucd/dev/LineBreak.txt | 6 +-- unicodetools/data/ucd/dev/Scripts.txt | 10 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 2 + .../data/ucd/dev/VerticalOrientation.txt | 6 +-- .../dev/auxiliary/SentenceBreakProperty.txt | 8 ++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 8 ++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 8 ++-- .../dev/extracted/DerivedCombiningClass.txt | 8 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 8 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 14 +++---- .../ucd/dev/extracted/DerivedLineBreak.txt | 12 +++--- .../data/ucd/dev/extracted/DerivedName.txt | 6 ++- 15 files changed, 76 insertions(+), 70 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index ef061a1d3..361ae7087 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 16:21:36 GMT +# Date: 2024-11-13, 16:38:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2068,7 +2068,9 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 088F ; 17.0 # ARABIC LETTER NOON WITH RING ABOVE 09FF ; 17.0 # BENGALI LETTER SANSKRIT BA 0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE +0C5C ; 17.0 # TELUGU ARCHAIC SHRII +0CDC ; 17.0 # KANNADA ARCHAIC SHRII -# Total code points: 4 +# Total code points: 6 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 915d290db..28640c632 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 16:21:56 GMT +# Date: 2024-11-13, 16:38:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -478,7 +478,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0C4A..0C4C ; Alphabetic # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C55..0C56 ; Alphabetic # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Alphabetic # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; Alphabetic # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; Alphabetic # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Alphabetic # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Alphabetic # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C80 ; Alphabetic # Lo KANNADA SIGN SPACING CANDRABINDU @@ -498,7 +498,7 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 0CCA..0CCB ; Alphabetic # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; Alphabetic # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; Alphabetic # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; Alphabetic # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Alphabetic # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; Alphabetic # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Alphabetic # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CF1..0CF2 ; Alphabetic # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -1442,7 +1442,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142761 +# Total code points: 142763 # ================================================ @@ -6329,7 +6329,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0C2A..0C39 ; ID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; ID_Start # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; ID_Start # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -6338,7 +6338,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 0CAA..0CB3 ; ID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ID_Start # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; ID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; ID_Start # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; ID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -6964,7 +6964,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141271 +# Total code points: 141273 # ================================================ @@ -7221,7 +7221,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0C4A..0C4D ; ID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; ID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; ID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; ID_Continue # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; ID_Continue # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; ID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; ID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -7243,7 +7243,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 0CCA..0CCB ; ID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; ID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; ID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; ID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; ID_Continue # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; ID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; ID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; ID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144545 +# Total code points: 144547 # ================================================ @@ -8513,7 +8513,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0C2A..0C39 ; XID_Start # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; XID_Start # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; XID_Start # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; XID_Start # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; XID_Start # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Start # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; XID_Start # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; XID_Start # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -8522,7 +8522,7 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 0CAA..0CB3 ; XID_Start # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; XID_Start # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; XID_Start # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; XID_Start # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; XID_Start # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; XID_Start # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; XID_Start # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; XID_Start # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -9152,7 +9152,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141248 +# Total code points: 141250 # ================================================ @@ -9405,7 +9405,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0C4A..0C4D ; XID_Continue # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; XID_Continue # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; XID_Continue # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; XID_Continue # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; XID_Continue # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; XID_Continue # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; XID_Continue # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; XID_Continue # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -9427,7 +9427,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 0CCA..0CCB ; XID_Continue # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; XID_Continue # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; XID_Continue # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; XID_Continue # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; XID_Continue # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; XID_Continue # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; XID_Continue # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; XID_Continue # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144526 +# Total code points: 144528 # ================================================ @@ -11311,7 +11311,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0C3D ; Grapheme_Base # Lo TELUGU SIGN AVAGRAHA 0C41..0C44 ; Grapheme_Base # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C58..0C5A ; Grapheme_Base # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; Grapheme_Base # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; Grapheme_Base # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Grapheme_Base # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; Grapheme_Base # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C77 ; Grapheme_Base # Po TELUGU SIGN SIDDHAM @@ -11329,7 +11329,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 0CBE ; Grapheme_Base # Mc KANNADA VOWEL SIGN AA 0CC1 ; Grapheme_Base # Mc KANNADA VOWEL SIGN U 0CC3..0CC4 ; Grapheme_Base # Mc [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR -0CDD..0CDE ; Grapheme_Base # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Grapheme_Base # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; Grapheme_Base # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE6..0CEF ; Grapheme_Base # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Grapheme_Base # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -12818,7 +12818,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152732 +# Total code points: 152734 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index e5f391ab3..9cf4406bf 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 16:22:01 GMT +# Date: 2024-11-13, 16:38:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -503,7 +503,7 @@ 0C4A..0C4D ; N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; N # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; N # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -529,7 +529,7 @@ 0CCA..0CCB ; N # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; N # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; N # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; N # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; N # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; N # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index bd7bb5294..0adaea260 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 16:22:02 GMT +# Date: 2024-11-13, 16:38:48 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -450,7 +450,7 @@ 0C4A..0C4D ; CM # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; CM # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; AL # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; AL # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; AL # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; CM # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; NU # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -476,7 +476,7 @@ 0CCA..0CCB ; CM # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; CM # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; CM # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; AL # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; AL # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; AL # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; CM # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; NU # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 7aaea2a1a..05817b648 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 16:22:25 GMT +# Date: 2024-11-13, 16:39:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1156,7 +1156,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0C4A..0C4D ; Telugu # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; Telugu # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; Telugu # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; Telugu # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; Telugu # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Telugu # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; Telugu # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; Telugu # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -1164,7 +1164,7 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0C78..0C7E ; Telugu # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; Telugu # So TELUGU SIGN TUUMU -# Total code points: 100 +# Total code points: 101 # ================================================ @@ -1187,14 +1187,14 @@ A8FF ; Devanagari # Mn DEVANAGARI VOWEL SIGN AY 0CCA..0CCB ; Kannada # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; Kannada # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; Kannada # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; Kannada # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Kannada # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; Kannada # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; Kannada # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; Kannada # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; Kannada # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0CF3 ; Kannada # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT -# Total code points: 91 +# Total code points: 92 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 053dba6c8..1a933a3b1 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -2866,6 +2866,7 @@ 0C58;TELUGU LETTER TSA;Lo;0;L;;;;;N;;;;; 0C59;TELUGU LETTER DZA;Lo;0;L;;;;;N;;;;; 0C5A;TELUGU LETTER RRRA;Lo;0;L;;;;;N;;;;; +0C5C;TELUGU ARCHAIC SHRII;Lo;0;L;;;;;N;;;;; 0C5D;TELUGU LETTER NAKAARA POLLU;Lo;0;L;;;;;N;;;;; 0C60;TELUGU LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; 0C61;TELUGU LETTER VOCALIC LL;Lo;0;L;;;;;N;;;;; @@ -2962,6 +2963,7 @@ 0CCD;KANNADA SIGN VIRAMA;Mn;9;NSM;;;;;N;;;;; 0CD5;KANNADA LENGTH MARK;Mc;0;L;;;;;N;;;;; 0CD6;KANNADA AI LENGTH MARK;Mc;0;L;;;;;N;;;;; +0CDC;KANNADA ARCHAIC SHRII;Lo;0;L;;;;;N;;;;; 0CDD;KANNADA LETTER NAKAARA POLLU;Lo;0;L;;;;;N;;;;; 0CDE;KANNADA LETTER FA;Lo;0;L;;;;;N;;;;; 0CE0;KANNADA LETTER VOCALIC RR;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index e2b88a7cc..2a8fcb64d 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 16:22:28 GMT +# Date: 2024-11-13, 16:39:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -437,7 +437,7 @@ 0C4A..0C4D ; R # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; R # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; R # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; R # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; R # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; R # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; R # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; R # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -463,7 +463,7 @@ 0CCA..0CCB ; R # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; R # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; R # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; R # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; R # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; R # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; R # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; R # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 010e2eaea..1185503c0 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:22:26 GMT +# Date: 2024-11-13, 16:39:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2091,7 +2091,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0C2A..0C39 ; OLetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; OLetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; OLetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; OLetter # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; OLetter # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; OLetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; OLetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; OLetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -2100,7 +2100,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 0CAA..0CB3 ; OLetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; OLetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; OLetter # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; OLetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; OLetter # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; OLetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; OLetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; OLetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -2586,7 +2586,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136910 +# Total code points: 136912 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 2d3d10c79..f99235a6b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:22:28 GMT +# Date: 2024-11-13, 16:39:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -814,7 +814,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0C2A..0C39 ; ALetter # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; ALetter # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; ALetter # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; ALetter # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; ALetter # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; ALetter # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; ALetter # Lo KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; ALetter # Lo [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -823,7 +823,7 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 0CAA..0CB3 ; ALetter # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; ALetter # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; ALetter # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; ALetter # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; ALetter # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; ALetter # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; ALetter # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; ALetter # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -1356,7 +1356,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33793 +# Total code points: 33795 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index de30f8204..aecb29e0e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 16:21:54 GMT +# Date: 2024-11-13, 16:38:41 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -274,7 +274,7 @@ 0C3D ; L # Lo TELUGU SIGN AVAGRAHA 0C41..0C44 ; L # Mc [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR 0C58..0C5A ; L # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; L # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; L # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; L # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C66..0C6F ; L # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE 0C77 ; L # Po TELUGU SIGN SIDDHAM @@ -295,7 +295,7 @@ 0CC7..0CC8 ; L # Mc [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI 0CCA..0CCB ; L # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CD5..0CD6 ; L # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; L # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; L # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; L # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE6..0CEF ; L # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE 0CF1..0CF2 ; L # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA @@ -1215,7 +1215,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815348 code points not listed here. +# The above property value applies to 815346 code points not listed here. # Total code points: 1095511 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index a67aa3100..3469c47c7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 16:21:55 GMT +# Date: 2024-11-13, 16:38:42 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -336,7 +336,7 @@ 0C46..0C48 ; 0 # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI 0C4A..0C4C ; 0 # Mn [3] TELUGU VOWEL SIGN O..TELUGU VOWEL SIGN AU 0C58..0C5A ; 0 # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; 0 # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; 0 # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; 0 # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; 0 # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; 0 # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -361,7 +361,7 @@ 0CCA..0CCB ; 0 # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC ; 0 # Mn KANNADA VOWEL SIGN AU 0CD5..0CD6 ; 0 # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; 0 # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; 0 # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; 0 # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; 0 # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; 0 # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -2061,7 +2061,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821577 code points not listed here. +# The above property value applies to 821575 code points not listed here. # Total code points: 1113178 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index d3efc8f0b..e24073197 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 16:21:57 GMT +# Date: 2024-11-13, 16:38:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -392,7 +392,7 @@ 0C4A..0C4D ; N # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA 0C55..0C56 ; N # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK 0C58..0C5A ; N # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; N # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; N # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; N # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C62..0C63 ; N # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL 0C66..0C6F ; N # Nd [10] TELUGU DIGIT ZERO..TELUGU DIGIT NINE @@ -418,7 +418,7 @@ 0CCA..0CCB ; N # Mc [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO 0CCC..0CCD ; N # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA 0CD5..0CD6 ; N # Mc [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK -0CDD..0CDE ; N # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; N # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; N # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CE2..0CE3 ; N # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL 0CE6..0CEF ; N # Nd [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761095 code points not listed here. +# The above property value applies to 761093 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 4e2501104..f14ea8635 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 16:21:57 GMT +# Date: 2024-11-13, 16:38:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -119,7 +119,7 @@ 0C49 ; Cn # 0C4E..0C54 ; Cn # [7] .. 0C57 ; Cn # -0C5B..0C5C ; Cn # [2] .. +0C5B ; Cn # 0C5E..0C5F ; Cn # [2] .. 0C64..0C65 ; Cn # [2] .. 0C70..0C76 ; Cn # [7] .. @@ -131,7 +131,7 @@ 0CC5 ; Cn # 0CC9 ; Cn # 0CCE..0CD4 ; Cn # [7] .. -0CD7..0CDC ; Cn # [6] .. +0CD7..0CDB ; Cn # [5] .. 0CDF ; Cn # 0CE4..0CE5 ; Cn # [2] .. 0CF0 ; Cn # @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819529 +# Total code points: 819527 # ================================================ @@ -2269,7 +2269,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0C2A..0C39 ; Lo # [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; Lo # TELUGU SIGN AVAGRAHA 0C58..0C5A ; Lo # [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; Lo # TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; Lo # [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; Lo # [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C80 ; Lo # KANNADA SIGN SPACING CANDRABINDU 0C85..0C8C ; Lo # [8] KANNADA LETTER A..KANNADA LETTER VOCALIC L @@ -2278,7 +2278,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 0CAA..0CB3 ; Lo # [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; Lo # [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; Lo # KANNADA SIGN AVAGRAHA -0CDD..0CDE ; Lo # [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; Lo # [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; Lo # [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; Lo # [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; Lo # [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -2708,7 +2708,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136479 +# Total code points: 136481 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 3c482e58d..2967c392c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 16:21:59 GMT +# Date: 2024-11-13, 16:38:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757649 code points not listed here. -# Total code points: 895117 +# The above property value applies to 757647 code points not listed here. +# Total code points: 895115 # ================================================ @@ -745,7 +745,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0C2A..0C39 ; AL # Lo [16] TELUGU LETTER PA..TELUGU LETTER HA 0C3D ; AL # Lo TELUGU SIGN AVAGRAHA 0C58..0C5A ; AL # Lo [3] TELUGU LETTER TSA..TELUGU LETTER RRRA -0C5D ; AL # Lo TELUGU LETTER NAKAARA POLLU +0C5C..0C5D ; AL # Lo [2] TELUGU ARCHAIC SHRII..TELUGU LETTER NAKAARA POLLU 0C60..0C61 ; AL # Lo [2] TELUGU LETTER VOCALIC RR..TELUGU LETTER VOCALIC LL 0C78..0C7E ; AL # No [7] TELUGU FRACTION DIGIT ZERO FOR ODD POWERS OF FOUR..TELUGU FRACTION DIGIT THREE FOR EVEN POWERS OF FOUR 0C7F ; AL # So TELUGU SIGN TUUMU @@ -756,7 +756,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 0CAA..0CB3 ; AL # Lo [10] KANNADA LETTER PA..KANNADA LETTER LLA 0CB5..0CB9 ; AL # Lo [5] KANNADA LETTER VA..KANNADA LETTER HA 0CBD ; AL # Lo KANNADA SIGN AVAGRAHA -0CDD..0CDE ; AL # Lo [2] KANNADA LETTER NAKAARA POLLU..KANNADA LETTER FA +0CDC..0CDE ; AL # Lo [3] KANNADA ARCHAIC SHRII..KANNADA LETTER FA 0CE0..0CE1 ; AL # Lo [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL 0CF1..0CF2 ; AL # Lo [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA 0D04..0D0C ; AL # Lo [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L @@ -1614,7 +1614,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26681 +# Total code points: 26683 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 253d43288..20d056f93 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 16:21:59 GMT +# Date: 2024-11-13, 16:38:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2841,6 +2841,7 @@ 0C58 ; TELUGU LETTER TSA 0C59 ; TELUGU LETTER DZA 0C5A ; TELUGU LETTER RRRA +0C5C ; TELUGU ARCHAIC SHRII 0C5D ; TELUGU LETTER NAKAARA POLLU 0C60 ; TELUGU LETTER VOCALIC RR 0C61 ; TELUGU LETTER VOCALIC LL @@ -2937,6 +2938,7 @@ 0CCD ; KANNADA SIGN VIRAMA 0CD5 ; KANNADA LENGTH MARK 0CD6 ; KANNADA AI LENGTH MARK +0CDC ; KANNADA ARCHAIC SHRII 0CDD ; KANNADA LETTER NAKAARA POLLU 0CDE ; KANNADA LETTER FA 0CE0 ; KANNADA LETTER VOCALIC RR @@ -45371,6 +45373,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155002 +# Total code points: 155004 # EOF From 617b9d193ffc5c6814b39b87b3cbd5ac70750620 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 18:49:44 +0100 Subject: [PATCH 11/26] Combining double caron (#779) * UnicodeData.txt line from L2/24-105 * lb=CM * Inherited * Diacritic * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +++-- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- .../data/ucd/dev/NormalizationTest.txt | 4 +++- unicodetools/data/ucd/dev/PropList.txt | 5 +++-- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 ++--- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++----- .../dev/extracted/DerivedCombiningClass.txt | 10 ++++----- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++++----- .../data/ucd/dev/extracted/DerivedName.txt | 5 +++-- 19 files changed, 68 insertions(+), 62 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 361ae7087..fdc63ca6f 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 16:38:26 GMT +# Date: 2024-11-13, 17:23:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2070,7 +2070,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0C5C ; 17.0 # TELUGU ARCHAIC SHRII 0CDC ; 17.0 # KANNADA ARCHAIC SHRII +1ACF ; 17.0 # COMBINING DOUBLE CARON -# Total code points: 6 +# Total code points: 7 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 28640c632..3a330db8e 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 16:38:43 GMT +# Date: 2024-11-13, 17:23:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3195,7 +3195,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; Case_Ignorable # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; Case_Ignorable # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3506,7 +3506,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2751 +# Total code points: 2752 # ================================================ @@ -7460,7 +7460,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACE ; ID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; ID_Continue # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144547 +# Total code points: 144548 # ================================================ @@ -9644,7 +9644,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACE ; XID_Continue # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; XID_Continue # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144528 +# Total code points: 144529 # ================================================ @@ -10783,7 +10783,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -495,7 +495,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2200 +# Total code points: 2201 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 1185503c0..6abb2f7d2 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:39:08 GMT +# Date: 2024-11-13, 17:23:48 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -247,7 +247,7 @@ 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2603 +# Total code points: 2604 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index f99235a6b..96a1fe880 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 16:39:10 GMT +# Date: 2024-11-13, 17:23:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -283,7 +283,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; Extend # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2607 +# Total code points: 2608 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index aecb29e0e..a0f66966d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 16:38:41 GMT +# Date: 2024-11-13, 17:23:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815346 code points not listed here. -# Total code points: 1095511 +# The above property value applies to 815345 code points not listed here. +# Total code points: 1095510 # ================================================ @@ -2190,7 +2190,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 1A7F ; NSM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; NSM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; NSM # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2409,7 +2409,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2030 +# Total code points: 2031 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 3469c47c7..55d320c71 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 16:38:42 GMT +# Date: 2024-11-13, 17:23:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2061,8 +2061,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821575 code points not listed here. -# Total code points: 1113178 +# The above property value applies to 821574 code points not listed here. +# Total code points: 1113177 # ================================================ @@ -2737,7 +2737,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1ABB..1ABC ; 230 # Mn [2] COMBINING PARENTHESES ABOVE..COMBINING DOUBLE PARENTHESES ABOVE 1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT 1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE -1ACB..1ACE ; 230 # Mn [4] COMBINING TRIPLE ACUTE ACCENT..COMBINING LATIN SMALL LETTER INSULAR T +1ACB..1ACF ; 230 # Mn [5] COMBINING TRIPLE ACUTE ACCENT..COMBINING DOUBLE CARON 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2804,7 +2804,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 517 +# Total code points: 518 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index e24073197..84155dc38 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 16:38:44 GMT +# Date: 2024-11-13, 17:23:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -692,7 +692,7 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; N # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; N # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761093 code points not listed here. +# The above property value applies to 761092 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index f14ea8635..29de338a3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 16:38:44 GMT +# Date: 2024-11-13, 17:23:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -227,7 +227,7 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1ACF..1AFF ; Cn # [49] .. +1AD0..1AFF ; Cn # [48] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819527 +# Total code points: 819526 # ================================================ @@ -2856,7 +2856,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACE ; Mn # [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; Mn # [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2022 +# Total code points: 2023 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 443125089..6986f8e7f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 16:21:58 GMT +# Date: 2024-11-13, 17:23:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -350,7 +350,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; T # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -582,6 +582,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2187 +# Total code points: 2188 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 2967c392c..15cacb25b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 16:38:45 GMT +# Date: 2024-11-13, 17:23:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757647 code points not listed here. -# Total code points: 895115 +# The above property value applies to 757646 code points not listed here. +# Total code points: 895114 # ================================================ @@ -2055,7 +2055,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACE ; CM # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1ABF..1ACF ; CM # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2388,7 +2388,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2472 +# Total code points: 2473 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 20d056f93..29f7e5ae5 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 16:38:46 GMT +# Date: 2024-11-13, 17:23:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -6118,6 +6118,7 @@ 1ACC ; COMBINING LATIN SMALL LETTER INSULAR G 1ACD ; COMBINING LATIN SMALL LETTER INSULAR R 1ACE ; COMBINING LATIN SMALL LETTER INSULAR T +1ACF ; COMBINING DOUBLE CARON 1B00 ; BALINESE SIGN ULU RICEM 1B01 ; BALINESE SIGN ULU CANDRA 1B02 ; BALINESE SIGN CECEK @@ -45373,6 +45374,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155004 +# Total code points: 155005 # EOF From 7a3737c56cd9d9698cf5986e3b9d5b5261122e13 Mon Sep 17 00:00:00 2001 From: Mark Davis Date: Wed, 13 Nov 2024 11:27:48 -0800 Subject: [PATCH 12/26] UTC-176-C35 Six compound tone diacritics (#637) * UTC-176-C35 Six compound tone diacritics * Missed one file * Diacritics are, in fact, diacritics. * Regenerate UCD --------- Co-authored-by: Robin Leroy --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- .../data/ucd/dev/NormalizationTest.txt | 16 ++++++++++++-- unicodetools/data/ucd/dev/PropList.txt | 6 ++--- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 6 +++++ .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 ++--- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++----- .../dev/extracted/DerivedCombiningClass.txt | 10 ++++----- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++++----- .../data/ucd/dev/extracted/DerivedName.txt | 10 +++++++-- 19 files changed, 89 insertions(+), 65 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index fdc63ca6f..9c57f526b 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 17:23:03 GMT +# Date: 2024-11-13, 17:50:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2070,8 +2070,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0C5C ; 17.0 # TELUGU ARCHAIC SHRII 0CDC ; 17.0 # KANNADA ARCHAIC SHRII -1ACF ; 17.0 # COMBINING DOUBLE CARON +1ACF..1AD5 ; 17.0 # [7] COMBINING DOUBLE CARON..COMBINING MACRON-VERTICAL-LINE -# Total code points: 7 +# Total code points: 13 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 3a330db8e..531cc7816 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 17:23:21 GMT +# Date: 2024-11-13, 17:50:34 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3195,7 +3195,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; Case_Ignorable # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; Case_Ignorable # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3506,7 +3506,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2752 +# Total code points: 2758 # ================================================ @@ -7460,7 +7460,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACF ; ID_Continue # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; ID_Continue # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144548 +# Total code points: 144554 # ================================================ @@ -9644,7 +9644,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACF ; XID_Continue # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; XID_Continue # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144529 +# Total code points: 144535 # ================================================ @@ -10783,7 +10783,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -495,7 +495,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2201 +# Total code points: 2207 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 6abb2f7d2..1a242c881 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 17:23:48 GMT +# Date: 2024-11-13, 17:50:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -247,7 +247,7 @@ 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2604 +# Total code points: 2610 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 96a1fe880..1120cd60a 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 17:23:49 GMT +# Date: 2024-11-13, 17:51:01 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -283,7 +283,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; Extend # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2608 +# Total code points: 2614 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index a0f66966d..dc9976e2c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 17:23:19 GMT +# Date: 2024-11-13, 17:50:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815345 code points not listed here. -# Total code points: 1095510 +# The above property value applies to 815339 code points not listed here. +# Total code points: 1095504 # ================================================ @@ -2190,7 +2190,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 1A7F ; NSM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; NSM # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; NSM # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2409,7 +2409,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2031 +# Total code points: 2037 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 55d320c71..f544c79e5 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 17:23:20 GMT +# Date: 2024-11-13, 17:50:34 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2061,8 +2061,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821574 code points not listed here. -# Total code points: 1113177 +# The above property value applies to 821568 code points not listed here. +# Total code points: 1113171 # ================================================ @@ -2737,7 +2737,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1ABB..1ABC ; 230 # Mn [2] COMBINING PARENTHESES ABOVE..COMBINING DOUBLE PARENTHESES ABOVE 1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT 1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE -1ACB..1ACF ; 230 # Mn [5] COMBINING TRIPLE ACUTE ACCENT..COMBINING DOUBLE CARON +1ACB..1AD5 ; 230 # Mn [11] COMBINING TRIPLE ACUTE ACCENT..COMBINING MACRON-VERTICAL-LINE 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2804,7 +2804,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 518 +# Total code points: 524 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 84155dc38..535c77663 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 17:23:22 GMT +# Date: 2024-11-13, 17:50:35 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -692,7 +692,7 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; N # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; N # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761092 code points not listed here. +# The above property value applies to 761086 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 29de338a3..6fbbecc6f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 17:23:23 GMT +# Date: 2024-11-13, 17:50:36 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -227,7 +227,7 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1AD0..1AFF ; Cn # [48] .. +1AD6..1AFF ; Cn # [42] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819526 +# Total code points: 819520 # ================================================ @@ -2856,7 +2856,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1ACF ; Mn # [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; Mn # [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2023 +# Total code points: 2029 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 6986f8e7f..1963202c1 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 17:23:24 GMT +# Date: 2024-11-13, 17:50:36 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -350,7 +350,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; T # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; T # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -582,6 +582,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2188 +# Total code points: 2194 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 15cacb25b..c51ee0406 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 17:23:24 GMT +# Date: 2024-11-13, 17:50:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757646 code points not listed here. -# Total code points: 895114 +# The above property value applies to 757640 code points not listed here. +# Total code points: 895108 # ================================================ @@ -2055,7 +2055,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1ACF ; CM # Mn [17] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE CARON +1ABF..1AD5 ; CM # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2388,7 +2388,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2473 +# Total code points: 2479 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 29f7e5ae5..f7a36b3fb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 17:23:24 GMT +# Date: 2024-11-13, 17:50:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -6119,6 +6119,12 @@ 1ACD ; COMBINING LATIN SMALL LETTER INSULAR R 1ACE ; COMBINING LATIN SMALL LETTER INSULAR T 1ACF ; COMBINING DOUBLE CARON +1AD0 ; COMBINING VERTICAL-LINE-ACUTE +1AD1 ; COMBINING GRAVE-VERTICAL-LINE +1AD2 ; COMBINING VERTICAL-LINE-GRAVE +1AD3 ; COMBINING ACUTE-VERTICAL-LINE +1AD4 ; COMBINING VERTICAL-LINE-MACRON +1AD5 ; COMBINING MACRON-VERTICAL-LINE 1B00 ; BALINESE SIGN ULU RICEM 1B01 ; BALINESE SIGN ULU CANDRA 1B02 ; BALINESE SIGN CECEK @@ -45374,6 +45380,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155005 +# Total code points: 155011 # EOF From 6a6f6a5f76044a0ea8ab4b6bf2667cb44d98611a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 20:42:47 +0100 Subject: [PATCH 13/26] Remove expired canned rules (#964) * Remove expired canned rules * spots --- .../java/org/unicode/tools/Segmenter.java | 526 ------------------ 1 file changed, 526 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java index 994a79e7d..2b3644b85 100644 --- a/unicodetools/src/main/java/org/unicode/tools/Segmenter.java +++ b/unicodetools/src/main/java/org/unicode/tools/Segmenter.java @@ -20,8 +20,6 @@ import com.ibm.icu.text.UnicodeSet.XSymbolTable; import com.ibm.icu.text.UnicodeSetIterator; import com.ibm.icu.util.ULocale; -import java.io.IOException; -import java.io.PrintWriter; import java.text.ParsePosition; import java.util.ArrayList; import java.util.Collection; @@ -40,9 +38,6 @@ import org.unicode.cldr.util.RegexUtilities; import org.unicode.cldr.util.TransliteratorUtilities; import org.unicode.props.UnicodeProperty; -import org.unicode.text.UCD.Default; -import org.unicode.text.UCD.ToolUnicodePropertySource; -import org.unicode.text.utility.Settings; import org.unicode.tools.Segmenter.SegmentationRule.Breaks; /** Ordered list of rules, with variables resolved before building. Use Builder to make. */ @@ -1004,525 +999,4 @@ public Map getOriginalVariables() { public UnicodeMap getSamples() { return samples; } - - // TODO: delete? move elsewhere? - // Only used in main() to write to some files. Out of sync with SegmenterDefault.txt. - private static final String[][] cannedRules = { - { - "GraphemeClusterBreak", - "$CR=\\p{Grapheme_Cluster_Break=CR}", - "$LF=\\p{Grapheme_Cluster_Break=LF}", - "$Control=\\p{Grapheme_Cluster_Break=Control}", - "$Extend=\\p{Grapheme_Cluster_Break=Extend}", - "$ZWJ=\\p{Grapheme_Cluster_Break=ZWJ}", - "$RI=\\p{Grapheme_Cluster_Break=Regional_Indicator}", - "$Prepend=\\p{Grapheme_Cluster_Break=Prepend}", - "$SpacingMark=\\p{Grapheme_Cluster_Break=SpacingMark}", - "$L=\\p{Grapheme_Cluster_Break=L}", - "$V=\\p{Grapheme_Cluster_Break=V}", - "$T=\\p{Grapheme_Cluster_Break=T}", - "$LV=\\p{Grapheme_Cluster_Break=LV}", - "$LVT=\\p{Grapheme_Cluster_Break=LVT}", - "$Virama=[\\p{Gujr}\\p{sc=Telu}\\p{sc=Mlym}\\p{sc=Orya}\\p{sc=Beng}\\p{sc=Deva}&\\p{Indic_Syllabic_Category=Virama}]", - "$LinkingConsonant=[\\p{Gujr}\\p{sc=Telu}\\p{sc=Mlym}\\p{sc=Orya}\\p{sc=Beng}\\p{sc=Deva}&\\p{Indic_Syllabic_Category=Consonant}]", - - // "$E_Base=\\p{Grapheme_Cluster_Break=E_Base}", - // "$E_Modifier=\\p{Grapheme_Cluster_Break=E_Modifier}", - - "$ExtPict=\\p{Extended_Pictographic}", - "$ExtCccZwj=[[$Extend-\\p{ccc=0}] $ZWJ]", - // "$EBG=\\p{Grapheme_Cluster_Break=E_Base_GAZ}", - // "$Glue_After_Zwj=\\p{Grapheme_Cluster_Break=Glue_After_Zwj}", - - "# Rules", - "# Break at the start and end of text, unless the text is empty.", - "# Do not break between a CR and LF. Otherwise, break before and after controls.", - "3) $CR \u00D7 $LF", - "4) ( $Control | $CR | $LF ) \u00F7", - "5) \u00F7 ( $Control | $CR | $LF )", - "# Do not break Hangul syllable sequences.", - "6) $L \u00D7 ( $L | $V | $LV | $LVT )", - "7) ( $LV | $V ) \u00D7 ( $V | $T )", - "8) ( $LVT | $T) \u00D7 $T", - "# Do not break before extending characters or ZWJ.", - // "9) \u00D7 ($Extend | $ZWJ | $Virama)", - "9) \u00D7 ($Extend | $ZWJ)", - "# Only for extended grapheme clusters: Do not break before SpacingMarks, or after Prepend characters.", - "9.1) \u00D7 $SpacingMark", - "9.2) $Prepend \u00D7", - "9.3) $LinkingConsonant $ExtCccZwj* $Virama $ExtCccZwj* \u00D7 $LinkingConsonant", - "# Do not break within emoji modifier sequences or emoji zwj sequences.", - // "10) $E_Base $Extend* × $E_Modifier", - "11) $ExtPict $Extend* $ZWJ × $ExtPict", - "# Do not break within emoji flag sequences. That is, do not break between regional indicator (RI) symbols if there is an odd number of RI characters before the break point.", - "12) ^ ($RI $RI)* $RI × $RI", - "13) [^$RI] ($RI $RI)* $RI × $RI", - "# Otherwise, break everywhere.", - }, - { - "LineBreak", - "# Variables", - "$AI=\\p{Line_Break=Ambiguous}", - "$AL=\\p{Line_Break=Alphabetic}", - "$B2=\\p{Line_Break=Break_Both}", - "$BA=\\p{Line_Break=Break_After}", - "$BB=\\p{Line_Break=Break_Before}", - "$BK=\\p{Line_Break=Mandatory_Break}", - "$CB=\\p{Line_Break=Contingent_Break}", - "$CL=\\p{Line_Break=Close_Punctuation}", - "$CP=\\p{Line_Break=CP}", - "$CM1=\\p{Line_Break=Combining_Mark}", - "$CR=\\p{Line_Break=Carriage_Return}", - "$EX=\\p{Line_Break=Exclamation}", - "$GL=\\p{Line_Break=Glue}", - "$H2=\\p{Line_Break=H2}", - "$H3=\\p{Line_Break=H3}", - "$HL=\\p{Line_Break=HL}", - "$HY=\\p{Line_Break=Hyphen}", - "$ID=\\p{Line_Break=Ideographic}", - "$IN=\\p{Line_Break=Inseparable}", - "$IS=\\p{Line_Break=Infix_Numeric}", - "$JL=\\p{Line_Break=JL}", - "$JT=\\p{Line_Break=JT}", - "$JV=\\p{Line_Break=JV}", - "$LF=\\p{Line_Break=Line_Feed}", - "$NL=\\p{Line_Break=Next_Line}", - "$NS=\\p{Line_Break=Nonstarter}", - "$NU=\\p{Line_Break=Numeric}", - "$OP=\\p{Line_Break=Open_Punctuation}", - "$PO=\\p{Line_Break=Postfix_Numeric}", - "$PR=\\p{Line_Break=Prefix_Numeric}", - "$QU=\\p{Line_Break=Quotation}", - "$SA=\\p{Line_Break=Complex_Context}", - "$SG=\\p{Line_Break=Surrogate}", - "$SP=\\p{Line_Break=Space}", - "$SY=\\p{Line_Break=Break_Symbols}", - "$WJ=\\p{Line_Break=Word_Joiner}", - "$XX=\\p{Line_Break=Unknown}", - "$ZW=\\p{Line_Break=ZWSpace}", - "$CJ=\\p{Line_Break=Conditional_Japanese_Starter}", - "$RI=\\p{Line_Break=Regional_Indicator}", - "$EB=\\p{Line_Break=E_Base}", - "$EM=\\p{Line_Break=E_Modifier}", - "$ZWJ_O=\\p{Line_Break=ZWJ}", - "$ZWJ=\\p{Line_Break=ZWJ}", - "# Macros", - "$CM=[$CM1 $ZWJ]", - "# LB 1 Assign a line breaking class to each code point of the input. ", - "# Resolve AI, CB, SA, SG, and XX into other line breaking classes depending on criteria outside the scope of this algorithm.", - "# NOTE: CB is ok to fall through, but must handle others here.", - // "show $AL", - "$AL=[$AI $AL $SG $XX $SA]", - "$NS=[$NS $CJ]", - // "show $AL", - // "$oldAL=$AL", // for debugging - "# WARNING: Fixes for Rule 9", - "# Treat X (CM|ZWJ* as if it were X.", - "# Where X is any line break class except SP, BK, CR, LF, NL or ZW.", - "$X=$CM*", - "# Macros", - "$Spec1_=[$SP $BK $CR $LF $NL $ZW]", - "$Spec2_=[^ $SP $BK $CR $LF $NL $ZW]", - "$Spec3a_=[^ $SP $BA $HY $CM]", - "$Spec3b_=[^ $BA $HY $CM]", - "$Spec4_=[^ $NU $CM]", - "$AI=($AI $X)", - "$AL=($AL $X)", - "$B2=($B2 $X)", - "$BA=($BA $X)", - "$BB=($BB $X)", - "$CB=($CB $X)", - "$CL=($CL $X)", - "$CP=($CP $X)", - "$CM=($CM $X)", - // "$CM=($CM $X)", - "$EX=($EX $X)", - "$GL=($GL $X)", - "$H2=($H2 $X)", - "$H3=($H3 $X)", - "$HL=($HL $X)", - "$HY=($HY $X)", - "$ID=($ID $X)", - "$IN=($IN $X)", - "$IS=($IS $X)", - "$JL=($JL $X)", - "$JT=($JT $X)", - "$JV=($JV $X)", - "$NS=($NS $X)", - "$NU=($NU $X)", - "$OP=($OP $X)", - "$PO=($PO $X)", - "$PR=($PR $X)", - "$QU=($QU $X)", - "$SA=($SA $X)", - "$SG=($SG $X)", - "$SY=($SY $X)", - "$WJ=($WJ $X)", - "$XX=($XX $X)", - "$RI=($RI $X)", - "$EB=($EB $X)", - "$EM=($EM $X)", - "$ZWJ=($ZWJ $X)", - "# OUT OF ORDER ON PURPOSE", - "# LB 10 Treat any remaining combining mark as AL.", - "$AL=($AL | ^ $CM | (?<=$Spec1_) $CM)", - "# Rules", - "# LB 4 Always break after hard line breaks (but never between CR and LF).", - "4) $BK \u00F7", - "# LB 5 Treat CR followed by LF, as well as CR, LF and NL as hard line breaks.", - "5.01) $CR \u00D7 $LF", - "5.02) $CR \u00F7", - "5.03) $LF \u00F7", - "5.04) $NL \u00F7", - "# LB 6 Do not break before hard line breaks.", - "6) \u00D7 ( $BK | $CR | $LF | $NL )", - "# LB 7 Do not break before spaces or zero-width space.", - "7.01) \u00D7 $SP", - "7.02) \u00D7 $ZW", - "# LB 8 Break before any character following a zero-width space, even if one or more spaces intervene.", - "8) $ZW $SP* \u00F7", - "# LB 8a Don't break between ZWJ and IDs (for use in Emoji ZWJ sequences)", - "8.1) $ZWJ_O \u00D7", - "# LB 9 Do not break a combining character sequence; treat it as if it has the LB class of the base character", - "# in all of the following rules. (Where X is any line break class except SP, BK, CR, LF, NL or ZW.)", - "9) $Spec2_ \u00D7 $CM", - "#WARNING: this is done by modifying the variable values for all but SP.... That is, $AL is really ($AI $CM*)!", - "# LB 11 Do not break before or after WORD JOINER and related characters.", - "11.01) \u00D7 $WJ", - "11.02) $WJ \u00D7", - "# LB 12 Do not break after NBSP and related characters.", - // "12.01) [^$SP] \u00D7 $GL", - "12) $GL \u00D7", - "12.1) $Spec3a_ \u00D7 $GL", - "12.2) $Spec3b_ $CM+ \u00D7 $GL", - "12.3) ^ $CM+ \u00D7 $GL", - "# LB 13 Do not break before \u2018]\u2019 or \u2018!\u2019 or \u2018;\u2019 or \u2018/\u2019, even after spaces.", - "# Using customization 7.", - "13.01) \u00D7 $EX", - "13.02) $Spec4_ \u00D7 ($CL | $CP | $IS | $SY)", - "13.03) $Spec4_ $CM+ \u00D7 ($CL | $CP | $IS | $SY)", - "13.04) ^ $CM+ \u00D7 ($CL | $CP | $IS | $SY)", - // "13.03) $Spec4_ \u00D7 $IS", - // "13.04) $Spec4_ \u00D7 $SY", - "#LB 14 Do not break after \u2018[\u2019, even after spaces.", - "14) $OP $SP* \u00D7", - "# LB 15 Do not break within \u2018\"[\u2019, even with intervening spaces.", - "15) $QU $SP* \u00D7 $OP", - "# LB 16 Do not break between closing punctuation and a nonstarter (lb=NS), even with intervening spaces.", - "16) ($CL | $CP) $SP* \u00D7 $NS", - "# LB 17 Do not break within \u2018\u2014\u2014\u2019, even with intervening spaces.", - "17) $B2 $SP* \u00D7 $B2", - "# LB 18 Break after spaces.", - "18) $SP \u00F7", - "# LB 19 Do not break before or after \u2018\"\u2019.", - "19.01) \u00D7 $QU", - "19.02) $QU \u00D7", - "# LB 20 Break before and after unresolved CB.", - "20.01) \u00F7 $CB", - "20.02) $CB \u00F7", - "# LB 21 Do not break before hyphen-minus, other hyphens, fixed-width spaces, small kana and other non-starters, or after acute accents.", - "21.01) \u00D7 $BA", - "21.02) \u00D7 $HY", - "21.03) \u00D7 $NS", - "21.04) $BB \u00D7", - "# LB 21a Don't break after Hebrew + Hyphen.", - "21.1) $HL ($HY | $BA) \u00D7", - "# LB 21b Don’t break between Solidus and Hebrew letters.", - "21.2) $SY × $HL", - "# LB 22 Do not break between two ellipses, or between letters, numbers or exclamations and ellipsis.", - // "show $AL", - "22.01) ($AL | $HL) \u00D7 $IN", - "22.02) $EX \u00D7 $IN", - "22.03) ($ID | $EB | $EM) \u00D7 $IN", - "22.04) $IN \u00D7 $IN", - "22.05) $NU \u00D7 $IN", - "# LB 23 Do not break between digits and letters.", - // "23.01) ($ID | $EB | $EM) \u00D7 $PO", - "23.02) ($AL | $HL) \u00D7 $NU", - "23.03) $NU \u00D7 ($AL | $HL)", - "# LB 24 Do not break between prefix and letters or ideographs.", - "23.12) $PR \u00D7 ($ID | $EB | $EM)", - "23.13) ($ID | $EB | $EM) \u00D7 $PO", - "# LB24 Do not break between numeric prefix/postfix and letters, or between letters and prefix/postfix.", - "24.02) ($PR | $PO) \u00D7 ($AL | $HL)", - "24.03) ($AL | $HL) \u00D7 ($PR | $PO)", - "# Using customization 7", - "# LB Alternative: ( PR | PO) ? ( OP | HY ) ? NU (NU | SY | IS) * (CL | CP) ? ( PR | PO) ?", - "# Insert \u00D7 every place it could go. However, make sure that at least one thing is concrete, otherwise would cause $NU to not break before or after ", - "25.01) ($PR | $PO) \u00D7 ( $OP | $HY )? $NU", - "25.02) ( $OP | $HY ) \u00D7 $NU", - "25.03) $NU \u00D7 ($NU | $SY | $IS)", - "25.04) $NU ($NU | $SY | $IS)* \u00D7 ($NU | $SY | $IS | $CL | $CP)", - "25.05) $NU ($NU | $SY | $IS)* ($CL | $CP)? \u00D7 ($PO | $PR)", - "#LB 26 Do not break a Korean syllable.", - "26.01) $JL \u00D7 $JL | $JV | $H2 | $H3", - "26.02) $JV | $H2 \u00D7 $JV | $JT", - "26.03) $JT | $H3 \u00D7 $JT", - "# LB 27 Treat a Korean Syllable Block the same as ID.", - "27.01) $JL | $JV | $JT | $H2 | $H3 \u00D7 $PO", - "27.02) $PR \u00D7 $JL | $JV | $JT | $H2 | $H3", - "# LB 28 Do not break between alphabetics (\"at\").", - "28) ($AL | $HL) \u00D7 ($AL | $HL)", - "# LB 29 Do not break between numeric punctuation and alphabetics (\"e.g.\").", - "29) $IS \u00D7 ($AL | $HL)", - "# LB 30 Do not break between letters, numbers or ordinary symbols and opening or closing punctuation.", - "30.01) ($AL | $HL | $NU) \u00D7 $OP", - "30.02) $CP \u00D7 ($AL | $HL | $NU)", - "# LB 30a Break between two Regional Indicators if and only if there is an even number of them before the point being considered.", - "30.11) ^ ($RI $RI)* $RI × $RI", - "30.12) [^$RI] ($RI $RI)* $RI × $RI", - "30.13) $RI ÷ $RI", - "30.2) $EB × $EM", - }, - { - "SentenceBreak", - "$CR=\\p{Sentence_Break=CR}", - "$LF=\\p{Sentence_Break=LF}", - "$Extend=\\p{Sentence_Break=Extend}", - "$Format=\\p{Sentence_Break=Format}", - "$Sep=\\p{Sentence_Break=Sep}", - "$Sp=\\p{Sentence_Break=Sp}", - "$Lower=\\p{Sentence_Break=Lower}", - "$Upper=\\p{Sentence_Break=Upper}", - "$OLetter=\\p{Sentence_Break=OLetter}", - "$Numeric=\\p{Sentence_Break=Numeric}", - "$ATerm=\\p{Sentence_Break=ATerm}", - "$STerm=\\p{Sentence_Break=STerm}", - "$Close=\\p{Sentence_Break=Close}", - "$SContinue=\\p{Sentence_Break=SContinue}", - "$Any=.", - // "# subtract Format from Control, since we don't want to break before/after", - // "$Control=[$Control-$Format]", - "# Expresses the negation in rule 8; can't do this with normal regex, but works with UnicodeSet, which is all we need.", - // "$NotStuff=[^$OLetter $Upper $Lower $Sep]", - // "# $ATerm and $Sterm are temporary, to match ICU until UTC decides.", - - "# WARNING: For Rule 5, now add format and extend to everything but Sep, Format, and Extend", - "$FE=[$Format $Extend]", - "# Special rules", - "$NotPreLower_=[^ $OLetter $Upper $Lower $Sep $CR $LF $STerm $ATerm]", - // "$NotSep_=[^ $Sep $CR $LF]", - - // "$FE=$Extend* $Format*", - "$Sp=($Sp $FE*)", - "$Lower=($Lower $FE*)", - "$Upper=($Upper $FE*)", - "$OLetter=($OLetter $FE*)", - "$Numeric=($Numeric $FE*)", - "$ATerm=($ATerm $FE*)", - "$STerm=($STerm $FE*)", - "$Close=($Close $FE*)", - "$SContinue=($SContinue $FE*)", - "# Macros", - "$ParaSep = ($Sep | $CR | $LF)", - "$SATerm = ($STerm | $ATerm)", - "# Rules", - "# Break at the start and end of text, unless the text is empty.", - "# Do not break within CRLF.", - "3) $CR \u00D7 $LF", - "# Break after paragraph separators.", - "4) $ParaSep \u00F7", - // "3.4) ( $Control | $CR | $LF ) \u00F7", - // "3.5) \u00F7 ( $Control | $CR | $LF )", - "# Ignore Format and Extend characters, except after sot, ParaSep, and within CRLF. (See Section 6.2, Replacing Ignore Rules.) This also has the effect of: Any × (Format | Extend)", - "# WARNING: Implemented as don't break before format (except after linebreaks),", - "# AND add format and extend in all variables definitions that appear after this point!", - // "3.91) [^$Control | $CR | $LF] \u00D7 $Extend", - "5) \u00D7 [$Format $Extend]", - "# Do not break after full stop in certain contexts. [See note below.]", - "# Do not break after ambiguous terminators like period, if immediately followed by a number or lowercase letter,", - "# is between uppercase letters, or if the first following letter (optionally after certain punctuation) is lowercase.", - "# For example, a period may be an abbreviation or numeric period, and not mark the end of a sentence.", - "6) $ATerm \u00D7 $Numeric", - "7) ($Upper | $Lower) $ATerm \u00D7 $Upper", - "8) $ATerm $Close* $Sp* \u00D7 $NotPreLower_* $Lower", - "8.1) $SATerm $Close* $Sp* \u00D7 ($SContinue | $SATerm)", - "# Break after sentence terminators, but include closing punctuation, trailing spaces, and any paragraph separator. [See note below.] Include closing punctuation, trailing spaces, and (optionally) a paragraph separator.", - "9) $SATerm $Close* \u00D7 ( $Close | $Sp | $ParaSep )", - "# Note the fix to $Sp*, $Sep?", - "10) $SATerm $Close* $Sp* \u00D7 ( $Sp | $ParaSep )", - "11) $SATerm $Close* $Sp* $ParaSep? \u00F7", - "#Otherwise, do not break", - "998) \u00D7 $Any", - }, - { - "WordBreak", - "$CR=\\p{Word_Break=CR}", - "$LF=\\p{Word_Break=LF}", - "$Newline=\\p{Word_Break=Newline}", - // "$Control=\\p{Word_Break=Control}", - "$Extend=\\p{Word_Break=Extend}", - // "$NEWLINE=[$CR $LF \\u0085 \\u000B \\u000C \\u2028 \\u2029]", - // "$Sep=\\p{Sentence_Break=Sep}", - "# Now normal variables", - "$Format=\\p{Word_Break=Format}", - "$Katakana=\\p{Word_Break=Katakana}", - "$ALetter=\\p{Word_Break=ALetter}", - "$MidLetter=\\p{Word_Break=MidLetter}", - "$MidNum=\\p{Word_Break=MidNum}", - "$MidNumLet=\\p{Word_Break=MidNumLet}", - "$Numeric=\\p{Word_Break=Numeric}", - "$ExtendNumLet=\\p{Word_Break=ExtendNumLet}", - "$RI=\\p{Word_Break=Regional_Indicator}", - "$Hebrew_Letter=\\p{Word_Break=Hebrew_Letter}", - "$Double_Quote=\\p{Word_Break=Double_Quote}", - "$Single_Quote=\\p{Word_Break=Single_Quote}", - - // "$E_Base=\\p{Word_Break=E_Base}", - // "$E_Modifier=\\p{Word_Break=E_Modifier}", - "$ZWJ=\\p{Word_Break=ZWJ}", - "$ExtPict=\\p{Extended_Pictographic}", - - // "$EBG=\\p{Word_Break=E_Base_GAZ}", - // "$Glue_After_Zwj=\\p{Word_Break=Glue_After_Zwj}", - - "$WSegSpace=\\p{Word_Break=WSegSpace}", - "# Macros", - "$AHLetter=($ALetter | $Hebrew_Letter)", - "$MidNumLetQ=($MidNumLet | $Single_Quote)", - "# WARNING: For Rule 4: Fixes for GC, Format", - // "# Subtract Format from Control, since we don't want to break before/after", - // "$Control=[$Control-$Format]", - "# Add format and extend to everything", - "$FE=[$Format $Extend $ZWJ]", - "# Special rules", - "$NotBreak_=[^ $Newline $CR $LF ]", - // "$FE= ($Extend | $Format)*", - "$Katakana=($Katakana $FE*)", - "$ALetter=($ALetter $FE*)", - "$MidLetter=($MidLetter $FE*)", - "$MidNum=($MidNum $FE*)", - "$MidNumLet=($MidNumLet $FE*)", - "$Numeric=($Numeric $FE*)", - "$ExtendNumLet=($ExtendNumLet $FE*)", - "$RI=($RI $FE*)", - "$Hebrew_Letter=($Hebrew_Letter $FE*)", - "$Double_Quote=($Double_Quote $FE*)", - "$Single_Quote=($Single_Quote $FE*)", - - // "$E_Base=($E_Base $FE*)", - // "$E_Modifier=($E_Modifier $FE*)", - // "$ZWJ=($ZWJ $FE*)", don't do this one! - // "$Glue_After_Zwj=($Glue_After_Zwj $FE*)", - // "$EBG=($EBG $FE*)", - - "$AHLetter=($AHLetter $FE*)", - "$MidNumLetQ=($MidNumLetQ $FE*)", - "# Rules", - "# Break at the start and end of text, unless the text is empty.", - "# Do not break within CRLF.", - "3) $CR \u00D7 $LF", - "# Otherwise break before and after Newlines (including CR and LF)", - "3.1) ($Newline | $CR | $LF) \u00F7", - "3.2) \u00F7 ($Newline | $CR | $LF)", - "# Do not break within emoji zwj sequences.", - "3.3) $ZWJ × $ExtPict", - "3.4) $WSegSpace × $WSegSpace", - - // "3.4) ( $Control | $CR | $LF ) \u00F7", - // "3.5) \u00F7 ( $Control | $CR | $LF )", - // "3.9) \u00D7 $Extend", - // "3.91) [^$Control | $CR | $LF] \u00D7 $Extend", - "# Ignore Format and Extend characters, except after sot, CR, LF, and Newline. (See Section 6.2, Replacing Ignore Rules.) This also has the effect of: Any × (Format | Extend)", - "# WARNING: Implemented as don't break before format (except after linebreaks),", - "# AND add format and extend in all variables definitions that appear after this point!", - // "4) \u00D7 [$Format $Extend]", - "4) $NotBreak_ \u00D7 [$Format $Extend $ZWJ]", - "# Vanilla rules", - "# Do not break between most letters.", - "5) $AHLetter \u00D7 $AHLetter", - "# Do not break letters across certain punctuation.", - "6) $AHLetter \u00D7 ($MidLetter | $MidNumLetQ) $AHLetter", - "7) $AHLetter ($MidLetter | $MidNumLetQ) \u00D7 $AHLetter", - "7.1) $Hebrew_Letter × $Single_Quote", - "7.2) $Hebrew_Letter × $Double_Quote $Hebrew_Letter", - "7.3) $Hebrew_Letter $Double_Quote × $Hebrew_Letter", - "# Do not break within sequences of digits, or digits adjacent to letters (“3a”, or “A3”).", - "8) $Numeric \u00D7 $Numeric", - "9) $AHLetter \u00D7 $Numeric", - "10) $Numeric \u00D7 $AHLetter", - "# Do not break within sequences, such as “3.2” or “3,456.789”.", - "11) $Numeric ($MidNum | $MidNumLetQ) \u00D7 $Numeric", - "12) $Numeric \u00D7 ($MidNum | $MidNumLetQ) $Numeric", - "# Do not break between Katakana.", - "13) $Katakana \u00D7 $Katakana", - "# Do not break from extenders.", - "13.1) ($AHLetter | $Numeric | $Katakana | $ExtendNumLet) \u00D7 $ExtendNumLet", - "13.2) $ExtendNumLet \u00D7 ($AHLetter | $Numeric | $Katakana)", - - // "# Do not break within emoji modifier sequences.", - // "14) $E_Base × $E_Modifier", - - "# Do not break within emoji flag sequences. That is, do not break between regional indicator (RI) symbols if there is an odd number of RI characters before the break point.", - "15) ^ ($RI $RI)* $RI × $RI", - "16) [^$RI] ($RI $RI)* $RI × $RI", - "# Otherwise, break everywhere (including around ideographs).", - } - }; - - public static void main(String[] args) throws IOException { - for (int i = 0; i < cannedRules.length; ++i) { - String type = cannedRules[i][0]; - boolean hadHash = false; - try (PrintWriter out = - FileUtilities.openUTF8Writer( - Settings.Output.GEN_DIR + "segmentation/", type + "Rules.txt")) { - out.println("# Segmentation rules for " + type); - out.println("#"); - out.println("# Character Classes"); - out.println("#"); - for (int j = 1; j < cannedRules[i].length; ++j) { - String cannedRule = cannedRules[i][j].trim(); - if (cannedRule.equals("#")) { - continue; - } - boolean hasHash = cannedRule.startsWith("#"); - if (hasHash && !hadHash) { - out.println("#"); - } - out.println(cannedRule); - if (hasHash) { - out.println("#"); - } - hadHash = hasHash; - } - } - } - - try (PrintWriter out = - FileUtilities.openUTF8Writer( - Settings.Output.GEN_DIR + "cldr/segmentation/", "rootAddon.xml")) { - out.println( - "\n" - + "\n" - + "\n" - + "\n" - + "\t\n" - + "\t\t\n" - + "\t\t\n" - + "\t\n" - + "\t"); - for (final String type : - new String[] { - "GraphemeClusterBreak", "LineBreak", "SentenceBreak", "WordBreak" - }) { - final Builder segBuilder = - Segmenter.make(ToolUnicodePropertySource.make(Default.ucdVersion()), type); - out.print(segBuilder.toString(type, "\t\t")); - if (type.equals("")) { - out.print( - "\t\t\t\n" - + "\t\t\t\t\n" - + "\t\t\t\n"); - } - } - out.println("\t\n" + ""); - } - } } From 47d165a233ced67aeb3a3896724ff00d73ad9129 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 22:00:19 +0100 Subject: [PATCH 14/26] 3 compound tone diacritics 1AD6..1AD8 (#588) * UnicodeData.txt from L2/23-208 * LB=CM * Scripts.txt * Diacritics are diacritics. * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- .../data/ucd/dev/NormalizationTest.txt | 8 ++++++- unicodetools/data/ucd/dev/PropList.txt | 6 ++--- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 3 +++ .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 ++--- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++----- .../dev/extracted/DerivedCombiningClass.txt | 10 ++++----- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++++----- .../data/ucd/dev/extracted/DerivedName.txt | 7 ++++-- 19 files changed, 76 insertions(+), 64 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 9c57f526b..a24865de5 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 17:50:18 GMT +# Date: 2024-11-13, 19:41:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2070,8 +2070,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0C5C ; 17.0 # TELUGU ARCHAIC SHRII 0CDC ; 17.0 # KANNADA ARCHAIC SHRII -1ACF..1AD5 ; 17.0 # [7] COMBINING DOUBLE CARON..COMBINING MACRON-VERTICAL-LINE +1ACF..1AD8 ; 17.0 # [10] COMBINING DOUBLE CARON..COMBINING MACRON-ACUTE-GRAVE -# Total code points: 13 +# Total code points: 16 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 531cc7816..8dad8df1d 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 17:50:34 GMT +# Date: 2024-11-13, 19:41:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3195,7 +3195,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; Case_Ignorable # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; Case_Ignorable # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3506,7 +3506,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2758 +# Total code points: 2761 # ================================================ @@ -7460,7 +7460,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD5 ; ID_Continue # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; ID_Continue # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144554 +# Total code points: 144557 # ================================================ @@ -9644,7 +9644,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD5 ; XID_Continue # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; XID_Continue # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144535 +# Total code points: 144538 # ================================================ @@ -10783,7 +10783,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -495,7 +495,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2207 +# Total code points: 2210 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 1a242c881..158e1014d 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 17:50:59 GMT +# Date: 2024-11-13, 19:42:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -247,7 +247,7 @@ 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2610 +# Total code points: 2613 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 1120cd60a..e85bddb54 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 17:51:01 GMT +# Date: 2024-11-13, 19:42:05 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -283,7 +283,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; Extend # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2614 +# Total code points: 2617 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index dc9976e2c..2bd2e39ba 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 17:50:32 GMT +# Date: 2024-11-13, 19:41:35 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815339 code points not listed here. -# Total code points: 1095504 +# The above property value applies to 815336 code points not listed here. +# Total code points: 1095501 # ================================================ @@ -2190,7 +2190,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 1A7F ; NSM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; NSM # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; NSM # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2409,7 +2409,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2037 +# Total code points: 2040 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index f544c79e5..000a34270 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 17:50:34 GMT +# Date: 2024-11-13, 19:41:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2061,8 +2061,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821568 code points not listed here. -# Total code points: 1113171 +# The above property value applies to 821565 code points not listed here. +# Total code points: 1113168 # ================================================ @@ -2737,7 +2737,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1ABB..1ABC ; 230 # Mn [2] COMBINING PARENTHESES ABOVE..COMBINING DOUBLE PARENTHESES ABOVE 1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT 1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE -1ACB..1AD5 ; 230 # Mn [11] COMBINING TRIPLE ACUTE ACCENT..COMBINING MACRON-VERTICAL-LINE +1ACB..1AD8 ; 230 # Mn [14] COMBINING TRIPLE ACUTE ACCENT..COMBINING MACRON-ACUTE-GRAVE 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2804,7 +2804,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 524 +# Total code points: 527 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 535c77663..23037fe00 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 17:50:35 GMT +# Date: 2024-11-13, 19:41:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -692,7 +692,7 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; N # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; N # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761086 code points not listed here. +# The above property value applies to 761083 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 6fbbecc6f..e940037f3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 17:50:36 GMT +# Date: 2024-11-13, 19:41:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -227,7 +227,7 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1AD6..1AFF ; Cn # [42] .. +1AD9..1AFF ; Cn # [39] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819520 +# Total code points: 819517 # ================================================ @@ -2856,7 +2856,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD5 ; Mn # [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; Mn # [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2029 +# Total code points: 2032 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 1963202c1..2a1034c07 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 17:50:36 GMT +# Date: 2024-11-13, 19:41:40 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -350,7 +350,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; T # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; T # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -582,6 +582,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2194 +# Total code points: 2197 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index c51ee0406..a91c7453c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 17:50:37 GMT +# Date: 2024-11-13, 19:41:40 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757640 code points not listed here. -# Total code points: 895108 +# The above property value applies to 757637 code points not listed here. +# Total code points: 895105 # ================================================ @@ -2055,7 +2055,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD5 ; CM # Mn [23] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-VERTICAL-LINE +1ABF..1AD8 ; CM # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2388,7 +2388,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2479 +# Total code points: 2482 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index f7a36b3fb..7dc96c32d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 17:50:37 GMT +# Date: 2024-11-13, 19:41:40 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -6125,6 +6125,9 @@ 1AD3 ; COMBINING ACUTE-VERTICAL-LINE 1AD4 ; COMBINING VERTICAL-LINE-MACRON 1AD5 ; COMBINING MACRON-VERTICAL-LINE +1AD6 ; COMBINING VERTICAL-LINE-ACUTE-GRAVE +1AD7 ; COMBINING VERTICAL-LINE-GRAVE-ACUTE +1AD8 ; COMBINING MACRON-ACUTE-GRAVE 1B00 ; BALINESE SIGN ULU RICEM 1B01 ; BALINESE SIGN ULU CANDRA 1B02 ; BALINESE SIGN CECEK @@ -45380,6 +45383,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155011 +# Total code points: 155014 # EOF From 8f518642376777a4eff7e458c136925fc896bc3b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 22:20:09 +0100 Subject: [PATCH 15/26] 5 Harrington diacritics (#587) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * UnicodeData.txt from L2/23-206 * LB=CM * Scripts.txt * Regenerate UCD * Let’s say that the diacritics are diacritics * Regenerate UCD * UnicodeData.txt from L2/23-206R * Regenerate UCD * Approve the name change for provisionally assigned character U+1ADC COMBINING FALLING DIAGONAL DIAERESIS to COMBINING DIAERESIS WITH RAISED LEFT DOT. * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 22 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- .../data/ucd/dev/NormalizationTest.txt | 12 +++++++++- unicodetools/data/ucd/dev/PropList.txt | 6 ++--- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 5 +++++ .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 ++--- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 10 ++++----- .../dev/extracted/DerivedCombiningClass.txt | 13 ++++++----- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++----- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++++----- .../data/ucd/dev/extracted/DerivedName.txt | 9 ++++++-- 19 files changed, 86 insertions(+), 65 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index a24865de5..dd8846909 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 19:41:18 GMT +# Date: 2024-11-13, 21:07:25 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2070,8 +2070,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0B53..0B54 ; 17.0 # [2] ORIYA SIGN DOT ABOVE..ORIYA SIGN DOUBLE DOT ABOVE 0C5C ; 17.0 # TELUGU ARCHAIC SHRII 0CDC ; 17.0 # KANNADA ARCHAIC SHRII -1ACF..1AD8 ; 17.0 # [10] COMBINING DOUBLE CARON..COMBINING MACRON-ACUTE-GRAVE +1ACF..1ADD ; 17.0 # [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW -# Total code points: 16 +# Total code points: 21 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 8dad8df1d..14aacf7bf 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 19:41:37 GMT +# Date: 2024-11-13, 21:07:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3195,7 +3195,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AA7 ; Case_Ignorable # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; Case_Ignorable # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; Case_Ignorable # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3506,7 +3506,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2761 +# Total code points: 2766 # ================================================ @@ -7460,7 +7460,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1A90..1A99 ; ID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD8 ; ID_Continue # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; ID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -8373,7 +8373,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144557 +# Total code points: 144562 # ================================================ @@ -9644,7 +9644,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1A90..1A99 ; XID_Continue # Nd [10] TAI THAM THAM DIGIT ZERO..TAI THAM THAM DIGIT NINE 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD8 ; XID_Continue # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; XID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -10562,7 +10562,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144538 +# Total code points: 144543 # ================================================ @@ -10783,7 +10783,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -495,7 +495,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2210 +# Total code points: 2215 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 158e1014d..015ce1c42 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 19:42:03 GMT +# Date: 2024-11-13, 21:08:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -247,7 +247,7 @@ 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -586,7 +586,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2613 +# Total code points: 2618 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index e85bddb54..ee543e71d 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 19:42:05 GMT +# Date: 2024-11-13, 21:08:13 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -283,7 +283,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1A7F ; Extend # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; Extend # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -623,7 +623,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2617 +# Total code points: 2622 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 2bd2e39ba..4d67d80ab 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 19:41:35 GMT +# Date: 2024-11-13, 21:07:41 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815336 code points not listed here. -# Total code points: 1095501 +# The above property value applies to 815331 code points not listed here. +# Total code points: 1095496 # ================================================ @@ -2190,7 +2190,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 1A7F ; NSM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; NSM # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; NSM # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2409,7 +2409,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2040 +# Total code points: 2045 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 000a34270..3f16e7c62 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 19:41:37 GMT +# Date: 2024-11-13, 21:07:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2061,8 +2061,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821565 code points not listed here. -# Total code points: 1113168 +# The above property value applies to 821560 code points not listed here. +# Total code points: 1113163 # ================================================ @@ -2596,6 +2596,7 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1ABF..1AC0 ; 220 # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW 1AC3..1AC4 ; 220 # Mn [2] COMBINING LEFT PARENTHESIS BELOW LEFT..COMBINING RIGHT PARENTHESIS BELOW RIGHT 1ACA ; 220 # Mn COMBINING DOUBLE PLUS SIGN BELOW +1ADD ; 220 # Mn COMBINING DOT-AND-RING BELOW 1B6C ; 220 # Mn BALINESE MUSICAL SYMBOL COMBINING ENDEP 1CD5..1CD9 ; 220 # Mn [5] VEDIC TONE YAJURVEDIC AGGRAVATED INDEPENDENT SVARITA..VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER 1CDC..1CDF ; 220 # Mn [4] VEDIC TONE KATHAKA ANUDATTA..VEDIC TONE THREE DOTS BELOW @@ -2628,7 +2629,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 182 +# Total code points: 183 # ================================================ @@ -2737,7 +2738,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1ABB..1ABC ; 230 # Mn [2] COMBINING PARENTHESES ABOVE..COMBINING DOUBLE PARENTHESES ABOVE 1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT 1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE -1ACB..1AD8 ; 230 # Mn [14] COMBINING TRIPLE ACUTE ACCENT..COMBINING MACRON-ACUTE-GRAVE +1ACB..1ADC ; 230 # Mn [18] COMBINING TRIPLE ACUTE ACCENT..COMBINING DIAERESIS WITH RAISED LEFT DOT 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2804,7 +2805,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 527 +# Total code points: 531 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 23037fe00..c72d382d0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 19:41:39 GMT +# Date: 2024-11-13, 21:07:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -692,7 +692,7 @@ 1AA8..1AAD ; N # Po [6] TAI THAM SIGN KAAN..TAI THAM SIGN CAANG 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; N # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; N # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761083 code points not listed here. +# The above property value applies to 761078 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index e940037f3..27331217a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 19:41:39 GMT +# Date: 2024-11-13, 21:07:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -227,7 +227,7 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1AD9..1AFF ; Cn # [39] .. +1ADE..1AFF ; Cn # [34] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -746,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819517 +# Total code points: 819512 # ================================================ @@ -2856,7 +2856,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A73..1A7C ; Mn # [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW -1ABF..1AD8 ; Mn # [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; Mn # [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3072,7 +3072,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2032 +# Total code points: 2037 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 2a1034c07..c2d9a40ef 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 19:41:40 GMT +# Date: 2024-11-13, 21:07:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -350,7 +350,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; T # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; T # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -582,6 +582,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2197 +# Total code points: 2202 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index a91c7453c..f04298e3c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 19:41:40 GMT +# Date: 2024-11-13, 21:07:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757637 code points not listed here. -# Total code points: 895105 +# The above property value applies to 757632 code points not listed here. +# Total code points: 895100 # ================================================ @@ -2055,7 +2055,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1A7F ; CM # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY -1ABF..1AD8 ; CM # Mn [26] COMBINING LATIN SMALL LETTER W BELOW..COMBINING MACRON-ACUTE-GRAVE +1ABF..1ADD ; CM # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2388,7 +2388,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2482 +# Total code points: 2487 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 7dc96c32d..447bb6104 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 19:41:40 GMT +# Date: 2024-11-13, 21:07:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -6128,6 +6128,11 @@ 1AD6 ; COMBINING VERTICAL-LINE-ACUTE-GRAVE 1AD7 ; COMBINING VERTICAL-LINE-GRAVE-ACUTE 1AD8 ; COMBINING MACRON-ACUTE-GRAVE +1AD9 ; COMBINING SHARP SIGN +1ADA ; COMBINING FLAT SIGN +1ADB ; COMBINING DOWN TACK ABOVE +1ADC ; COMBINING DIAERESIS WITH RAISED LEFT DOT +1ADD ; COMBINING DOT-AND-RING BELOW 1B00 ; BALINESE SIGN ULU RICEM 1B01 ; BALINESE SIGN ULU CANDRA 1B02 ; BALINESE SIGN CECEK @@ -45383,6 +45388,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155014 +# Total code points: 155019 # EOF From 2fb2e8b3015a5a12969edfc52996217d0df96b4e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 22:33:21 +0100 Subject: [PATCH 16/26] 12 IPA diacritics, 11 above and 1 below (#742) * UnicodeData.txt lines from proposal * LineBreak.txt as described in the proposal * Inherited * diacritics are diacritics. * Regenerate UCD * en-GB-oxendict * Regenerate UCD * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 ++-- .../data/ucd/dev/DerivedCoreProperties.txt | 17 +++++++----- unicodetools/data/ucd/dev/EastAsianWidth.txt | 3 ++- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++- .../data/ucd/dev/NormalizationTest.txt | 26 ++++++++++++++++++- unicodetools/data/ucd/dev/PropList.txt | 5 ++-- unicodetools/data/ucd/dev/Scripts.txt | 5 ++-- unicodetools/data/ucd/dev/UnicodeData.txt | 12 +++++++++ .../data/ucd/dev/VerticalOrientation.txt | 3 ++- .../dev/auxiliary/GraphemeBreakProperty.txt | 5 ++-- .../dev/auxiliary/SentenceBreakProperty.txt | 5 ++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 5 ++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 9 ++++--- .../dev/extracted/DerivedCombiningClass.txt | 16 +++++++----- .../dev/extracted/DerivedEastAsianWidth.txt | 5 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++++--- .../ucd/dev/extracted/DerivedJoiningType.txt | 5 ++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 12 +++++---- .../data/ucd/dev/extracted/DerivedName.txt | 16 ++++++++++-- 19 files changed, 121 insertions(+), 47 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index dd8846909..7444c951e 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 21:07:25 GMT +# Date: 2024-11-13, 21:22:30 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2071,7 +2071,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0C5C ; 17.0 # TELUGU ARCHAIC SHRII 0CDC ; 17.0 # KANNADA ARCHAIC SHRII 1ACF..1ADD ; 17.0 # [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; 17.0 # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE -# Total code points: 21 +# Total code points: 33 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 14aacf7bf..437bcdc7a 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 21:07:43 GMT +# Date: 2024-11-13, 21:22:48 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3196,6 +3196,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1AB0..1ABD ; Case_Ignorable # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Case_Ignorable # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; Case_Ignorable # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Case_Ignorable # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Case_Ignorable # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Case_Ignorable # Mn BALINESE SIGN REREKAN 1B36..1B3A ; Case_Ignorable # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3506,7 +3507,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2766 +# Total code points: 2778 # ================================================ @@ -7461,6 +7462,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1AA7 ; ID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; ID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABF..1ADD ; ID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; ID_Continue # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; ID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; ID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; ID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -8373,7 +8375,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144562 +# Total code points: 144574 # ================================================ @@ -9645,6 +9647,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1AA7 ; XID_Continue # Lm TAI THAM SIGN MAI YAMOK 1AB0..1ABD ; XID_Continue # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABF..1ADD ; XID_Continue # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; XID_Continue # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; XID_Continue # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; XID_Continue # Mc BALINESE SIGN BISAH 1B05..1B33 ; XID_Continue # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -10562,7 +10565,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144543 +# Total code points: 144555 # ================================================ @@ -10784,6 +10787,7 @@ E01F0..E0FFF ; Default_Ignorable_Code_Point # Cn [3600] .... 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Extend # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Extend # Mn BALINESE SIGN REREKAN 1B35 ; Extend # Mc BALINESE VOWEL SIGN TEDUNG @@ -495,7 +496,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2215 +# Total code points: 2227 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 015ce1c42..6fbcfa5e8 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:08:10 GMT +# Date: 2024-11-13, 21:23:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -248,6 +248,7 @@ 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Extend # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -586,7 +587,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2618 +# Total code points: 2630 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index ee543e71d..935c90d01 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:08:13 GMT +# Date: 2024-11-13, 21:23:15 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -284,6 +284,7 @@ FB46..FB4F ; Hebrew_Letter # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW 1AB0..1ABD ; Extend # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; Extend # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; Extend # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Extend # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Extend # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; Extend # Mc BALINESE SIGN BISAH 1B34 ; Extend # Mn BALINESE SIGN REREKAN @@ -623,7 +624,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2622 +# Total code points: 2634 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 4d67d80ab..92d70ffa7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 21:07:41 GMT +# Date: 2024-11-13, 21:22:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815331 code points not listed here. -# Total code points: 1095496 +# The above property value applies to 815319 code points not listed here. +# Total code points: 1095484 # ================================================ @@ -2191,6 +2191,7 @@ FFFFE..FFFFF ; BN # Cn [2] .. 1AB0..1ABD ; NSM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; NSM # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; NSM # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; NSM # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; NSM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; NSM # Mn BALINESE SIGN REREKAN 1B36..1B3A ; NSM # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -2409,7 +2410,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2045 +# Total code points: 2057 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 3f16e7c62..b29cba1f7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 21:07:43 GMT +# Date: 2024-11-13, 21:22:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2061,8 +2061,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821560 code points not listed here. -# Total code points: 1113163 +# The above property value applies to 821548 code points not listed here. +# Total code points: 1113151 # ================================================ @@ -2597,6 +2597,7 @@ FB1E ; 26 # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1AC3..1AC4 ; 220 # Mn [2] COMBINING LEFT PARENTHESIS BELOW LEFT..COMBINING RIGHT PARENTHESIS BELOW RIGHT 1ACA ; 220 # Mn COMBINING DOUBLE PLUS SIGN BELOW 1ADD ; 220 # Mn COMBINING DOT-AND-RING BELOW +1AE6 ; 220 # Mn COMBINING DOUBLE ARCH BELOW 1B6C ; 220 # Mn BALINESE MUSICAL SYMBOL COMBINING ENDEP 1CD5..1CD9 ; 220 # Mn [5] VEDIC TONE YAJURVEDIC AGGRAVATED INDEPENDENT SVARITA..VEDIC TONE YAJURVEDIC KATHAKA INDEPENDENT SVARITA SCHROEDER 1CDC..1CDF ; 220 # Mn [4] VEDIC TONE KATHAKA ANUDATTA..VEDIC TONE THREE DOTS BELOW @@ -2629,7 +2630,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 183 +# Total code points: 184 # ================================================ @@ -2739,6 +2740,8 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1AC1..1AC2 ; 230 # Mn [2] COMBINING LEFT PARENTHESIS ABOVE LEFT..COMBINING RIGHT PARENTHESIS ABOVE RIGHT 1AC5..1AC9 ; 230 # Mn [5] COMBINING SQUARE BRACKETS ABOVE..COMBINING DOUBLE PLUS SIGN ABOVE 1ACB..1ADC ; 230 # Mn [18] COMBINING TRIPLE ACUTE ACCENT..COMBINING DIAERESIS WITH RAISED LEFT DOT +1AE0..1AE5 ; 230 # Mn [6] COMBINING LEFT TACK ABOVE..COMBINING SEAGULL ABOVE +1AE7..1AEA ; 230 # Mn [4] COMBINING DOUBLE ARCH ABOVE..COMBINING UPWARDS ARROW ABOVE 1B6B ; 230 # Mn BALINESE MUSICAL SYMBOL COMBINING TEGEH 1B6D..1B73 ; 230 # Mn [7] BALINESE MUSICAL SYMBOL COMBINING KEMPUL..BALINESE MUSICAL SYMBOL COMBINING GONG 1CD0..1CD2 ; 230 # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA @@ -2805,7 +2808,7 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 531 +# Total code points: 541 # ================================================ @@ -2837,9 +2840,10 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 035D..035E ; 234 # Mn [2] COMBINING DOUBLE BREVE..COMBINING DOUBLE MACRON 0360..0361 ; 234 # Mn [2] COMBINING DOUBLE TILDE..COMBINING DOUBLE INVERTED BREVE +1AEB ; 234 # Mn COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1DCD ; 234 # Mn COMBINING DOUBLE CIRCUMFLEX ABOVE -# Total code points: 5 +# Total code points: 6 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index c72d382d0..720171224 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:07:45 GMT +# Date: 2024-11-13, 21:22:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -693,6 +693,7 @@ 1AB0..1ABD ; N # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; N # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; N # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; N # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; N # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; N # Mc BALINESE SIGN BISAH 1B05..1B33 ; N # Lo [47] BALINESE LETTER AKARA..BALINESE LETTER HA @@ -2104,7 +2105,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761078 code points not listed here. +# The above property value applies to 761066 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 27331217a..5ec607ad7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 21:07:45 GMT +# Date: 2024-11-13, 21:22:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -227,7 +227,8 @@ 1A8A..1A8F ; Cn # [6] .. 1A9A..1A9F ; Cn # [6] .. 1AAE..1AAF ; Cn # [2] .. -1ADE..1AFF ; Cn # [34] .. +1ADE..1ADF ; Cn # [2] .. +1AEC..1AFF ; Cn # [20] .. 1B4D ; Cn # 1BF4..1BFB ; Cn # [8] .. 1C38..1C3A ; Cn # [3] .. @@ -746,7 +747,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819512 +# Total code points: 819500 # ================================================ @@ -2857,6 +2858,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1A7F ; Mn # TAI THAM COMBINING CRYPTOGRAMMIC DOT 1AB0..1ABD ; Mn # [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABF..1ADD ; Mn # [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; Mn # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; Mn # [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; Mn # BALINESE SIGN REREKAN 1B36..1B3A ; Mn # [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -3072,7 +3074,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2037 +# Total code points: 2049 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index c2d9a40ef..d57fd1f6f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 21:07:46 GMT +# Date: 2024-11-13, 21:22:50 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -351,6 +351,7 @@ A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA 1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; T # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; T # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; T # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B34 ; T # Mn BALINESE SIGN REREKAN 1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA @@ -582,6 +583,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2202 +# Total code points: 2214 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index f04298e3c..e42e13f6b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 21:07:46 GMT +# Date: 2024-11-13, 21:22:51 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757632 code points not listed here. -# Total code points: 895100 +# The above property value applies to 757620 code points not listed here. +# Total code points: 895088 # ================================================ @@ -312,6 +312,7 @@ FF64 ; CL # Po HALFWIDTH IDEOGRAPHIC COMMA 0F12 ; GL # Po TIBETAN MARK RGYA GRAM SHAD 0FD9..0FDA ; GL # Po [2] TIBETAN MARK LEADING MCHAN RTAGS..TIBETAN MARK TRAILING MCHAN RTAGS 180E ; GL # Cf MONGOLIAN VOWEL SEPARATOR +1AEB ; GL # Mn COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1DCD ; GL # Mn COMBINING DOUBLE CIRCUMFLEX ABOVE 1DFC ; GL # Mn COMBINING DOUBLE INVERTED BREVE BELOW 2007 ; GL # Zs FIGURE SPACE @@ -329,7 +330,7 @@ FE2D..FE2E ; GL # Mn [2] COMBINING CONJOINING MACRON BELOW..COMBINING CYRIL 13439..1343B ; GL # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM 16FE4 ; GL # Mn KHITAN SMALL SCRIPT FILLER -# Total code points: 41 +# Total code points: 42 # ================================================ @@ -2056,6 +2057,7 @@ FE19 ; IN # Po PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS 1AB0..1ABD ; CM # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW 1ABE ; CM # Me COMBINING PARENTHESES OVERLAY 1ABF..1ADD ; CM # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEA ; CM # Mn [11] COMBINING LEFT TACK ABOVE..COMBINING UPWARDS ARROW ABOVE 1B00..1B03 ; CM # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG 1B04 ; CM # Mc BALINESE SIGN BISAH 1B34 ; CM # Mn BALINESE SIGN REREKAN @@ -2388,7 +2390,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2487 +# Total code points: 2498 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 447bb6104..31baaea9b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 21:07:46 GMT +# Date: 2024-11-13, 21:22:51 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -6133,6 +6133,18 @@ 1ADB ; COMBINING DOWN TACK ABOVE 1ADC ; COMBINING DIAERESIS WITH RAISED LEFT DOT 1ADD ; COMBINING DOT-AND-RING BELOW +1AE0 ; COMBINING LEFT TACK ABOVE +1AE1 ; COMBINING RIGHT TACK ABOVE +1AE2 ; COMBINING MINUS SIGN ABOVE +1AE3 ; COMBINING INVERTED BRIDGE ABOVE +1AE4 ; COMBINING SQUARE ABOVE +1AE5 ; COMBINING SEAGULL ABOVE +1AE6 ; COMBINING DOUBLE ARCH BELOW +1AE7 ; COMBINING DOUBLE ARCH ABOVE +1AE8 ; COMBINING EQUALS SIGN ABOVE +1AE9 ; COMBINING LEFT ANGLE CENTRED ABOVE +1AEA ; COMBINING UPWARDS ARROW ABOVE +1AEB ; COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 1B00 ; BALINESE SIGN ULU RICEM 1B01 ; BALINESE SIGN ULU CANDRA 1B02 ; BALINESE SIGN CECEK @@ -45388,6 +45400,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155019 +# Total code points: 155031 # EOF From 422bf479b05a3ff2bde561d2bbf6914ce99c0963 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 22:47:00 +0100 Subject: [PATCH 17/26] One Chess Symbol (#664) * UnicodeData.txt line from L2/24-018 * lb=AL like U+2BF9. * Common like U+2BF9. * Regenerate UCD * move it * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +++-- unicodetools/data/ucd/dev/DerivedCoreProperties.txt | 7 +++---- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 ++--- unicodetools/data/ucd/dev/LineBreak.txt | 5 ++--- unicodetools/data/ucd/dev/PropList.txt | 6 ++---- unicodetools/data/ucd/dev/Scripts.txt | 7 +++---- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + unicodetools/data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../data/ucd/dev/extracted/DerivedBidiClass.txt | 11 +++++------ .../data/ucd/dev/extracted/DerivedCombiningClass.txt | 7 +++---- .../data/ucd/dev/extracted/DerivedEastAsianWidth.txt | 7 +++---- .../data/ucd/dev/extracted/DerivedGeneralCategory.txt | 10 ++++------ .../data/ucd/dev/extracted/DerivedLineBreak.txt | 11 +++++------ unicodetools/data/ucd/dev/extracted/DerivedName.txt | 5 +++-- 14 files changed, 41 insertions(+), 50 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 7444c951e..13742ee49 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 21:22:30 GMT +# Date: 2024-11-13, 21:34:52 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2072,7 +2072,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 0CDC ; 17.0 # KANNADA ARCHAIC SHRII 1ACF..1ADD ; 17.0 # [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW 1AE0..1AEB ; 17.0 # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE +2B96 ; 17.0 # EQUALS SIGN WITH INFINITY ABOVE -# Total code points: 33 +# Total code points: 34 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 437bcdc7a..7b44bcca3 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 21:22:48 GMT +# Date: 2024-11-13, 21:35:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -11806,8 +11806,7 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 2B45..2B46 ; Grapheme_Base # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C ; Grapheme_Base # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; Grapheme_Base # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; Grapheme_Base # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; Grapheme_Base # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; Grapheme_Base # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C7B ; Grapheme_Base # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; Grapheme_Base # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; Grapheme_Base # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI @@ -12822,7 +12821,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152734 +# Total code points: 152735 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 2bd32a68b..e7019bcf1 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:22:52 GMT +# Date: 2024-11-13, 21:35:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1353,8 +1353,7 @@ 2B55 ; W # So HEAVY LARGE CIRCLE 2B56..2B59 ; A # So [4] HEAVY OVAL WITH OVAL INSIDE..HEAVY CIRCLED SALTIRE 2B5A..2B73 ; N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; N # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; N # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C5F ; N # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B ; N # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; N # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index bec9be145..071dcb538 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 21:22:53 GMT +# Date: 2024-11-13, 21:35:15 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1320,8 +1320,7 @@ 2B4D..2B54 ; AL # So [8] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..WHITE RIGHT-POINTING PENTAGON 2B55..2B59 ; AI # So [5] HEAVY LARGE CIRCLE..HEAVY CIRCLED SALTIRE 2B5A..2B73 ; AL # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; AL # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; AL # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C5F ; AL # L& [96] GLAGOLITIC CAPITAL LETTER AZU..GLAGOLITIC SMALL LETTER CAUDATE CHRIVI 2C60..2C7B ; AL # L& [28] LATIN CAPITAL LETTER L WITH DOUBLE BAR..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; AL # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index cced0526c..1cbd57d2a 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-17.0.0.txt -# Date: 2024-11-13, 21:23:00 GMT +# Date: 2024-11-13, 21:35:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1811,9 +1811,7 @@ E0100..E01EF ; Variation_Selector # Mn [240] VARIATION SELECTOR-17..VARIATION S 2B47..2B4C ; Pattern_Syntax # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; Pattern_Syntax # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR 2B74..2B75 ; Pattern_Syntax # Cn [2] .. -2B76..2B95 ; Pattern_Syntax # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B96 ; Pattern_Syntax # Cn -2B97..2BFF ; Pattern_Syntax # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; Pattern_Syntax # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2E00..2E01 ; Pattern_Syntax # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER 2E02 ; Pattern_Syntax # Pi LEFT SUBSTITUTION BRACKET 2E03 ; Pattern_Syntax # Pf RIGHT SUBSTITUTION BRACKET diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 6282eb580..47a23f20b 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 21:23:13 GMT +# Date: 2024-11-13, 21:35:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -306,8 +306,7 @@ 2B45..2B46 ; Common # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C ; Common # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; Common # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; Common # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; Common # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; Common # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2E00..2E01 ; Common # Po [2] RIGHT ANGLE SUBSTITUTION MARKER..RIGHT ANGLE DOTTED SUBSTITUTION MARKER 2E02 ; Common # Pi LEFT SUBSTITUTION BRACKET 2E03 ; Common # Pf RIGHT SUBSTITUTION BRACKET @@ -633,7 +632,7 @@ FFFC..FFFD ; Common # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHAR E0001 ; Common # Cf LANGUAGE TAG E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG -# Total code points: 9053 +# Total code points: 9054 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 5f7a66113..631fca167 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -10272,6 +10272,7 @@ 2B93;NEWLINE RIGHT;So;0;ON;;;;;N;;;;; 2B94;FOUR CORNER ARROWS CIRCLING ANTICLOCKWISE;So;0;ON;;;;;N;;;;; 2B95;RIGHTWARDS BLACK ARROW;So;0;ON;;;;;N;;;;; +2B96;EQUALS SIGN WITH INFINITY ABOVE;So;0;ON;;;;;N;;;;; 2B97;SYMBOL FOR TYPE A ELECTRONICS;So;0;ON;;;;;N;;;;; 2B98;THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD;So;0;ON;;;;;N;;;;; 2B99;THREE-D RIGHT-LIGHTED UPWARDS EQUILATERAL ARROWHEAD;So;0;ON;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index d720bb978..afadbe23c 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 21:23:15 GMT +# Date: 2024-11-13, 21:35:41 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1094,7 +1094,7 @@ 2B4D..2B4F ; R # So [3] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..SHORT BACKSLANTED SOUTH ARROW 2B50..2B59 ; U # So [10] WHITE MEDIUM STAR..HEAVY CIRCLED SALTIRE 2B5A..2B73 ; R # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; R # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW +2B76..2B96 ; R # So [33] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..EQUALS SIGN WITH INFINITY ABOVE 2B97 ; U # So SYMBOL FOR TYPE A ELECTRONICS 2B98..2BB7 ; R # So [32] THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD..RIBBON ARROW RIGHT DOWN 2BB8..2BD1 ; U # So [26] UPWARDS WHITE ARROW FROM BAR WITH HORIZONTAL BAR..UNCERTAINTY SIGN diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 92d70ffa7..6386021e6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 21:22:46 GMT +# Date: 2024-11-13, 21:35:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1215,8 +1215,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815319 code points not listed here. -# Total code points: 1095484 +# The above property value applies to 815318 code points not listed here. +# Total code points: 1095483 # ================================================ @@ -1732,8 +1732,7 @@ FF1A ; CS # Po FULLWIDTH COLON 2B45..2B46 ; ON # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C ; ON # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; ON # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; ON # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; ON # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; ON # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2CE5..2CEA ; ON # So [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2CF9..2CFC ; ON # Po [4] COPTIC OLD NUBIAN FULL STOP..COPTIC OLD NUBIAN VERSE DIVIDER 2CFD ; ON # No COPTIC FRACTION ONE HALF @@ -1998,7 +1997,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; ON # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 6751 +# Total code points: 6752 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index b29cba1f7..84fbc414d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 21:22:47 GMT +# Date: 2024-11-13, 21:35:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -912,8 +912,7 @@ 2B45..2B46 ; 0 # So [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B47..2B4C ; 0 # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B73 ; 0 # So [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; 0 # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; 0 # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; 0 # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C7B ; 0 # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; 0 # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; 0 # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI @@ -2061,7 +2060,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821548 code points not listed here. +# The above property value applies to 821547 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 720171224..408410f88 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:22:49 GMT +# Date: 2024-11-13, 21:35:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1071,8 +1071,7 @@ 2B4D..2B4F ; N # So [3] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..SHORT BACKSLANTED SOUTH ARROW 2B51..2B54 ; N # So [4] BLACK SMALL STAR..WHITE RIGHT-POINTING PENTAGON 2B5A..2B73 ; N # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; N # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; N # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; N # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C7B ; N # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; N # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; N # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI @@ -2105,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761066 code points not listed here. +# The above property value applies to 761065 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 5ec607ad7..9c9216414 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 21:22:49 GMT +# Date: 2024-11-13, 21:35:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -263,7 +263,6 @@ 242A..243F ; Cn # [22] .. 244B..245F ; Cn # [21] .. 2B74..2B75 ; Cn # [2] .. -2B96 ; Cn # 2CF4..2CF8 ; Cn # [5] .. 2D26 ; Cn # 2D28..2D2C ; Cn # [5] .. @@ -747,7 +746,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819500 +# Total code points: 819499 # ================================================ @@ -4176,8 +4175,7 @@ FFE3 ; Sk # FULLWIDTH MACRON 2B00..2B2F ; So # [48] NORTH EAST WHITE ARROW..WHITE VERTICAL ELLIPSE 2B45..2B46 ; So # [2] LEFTWARDS QUADRUPLE ARROW..RIGHTWARDS QUADRUPLE ARROW 2B4D..2B73 ; So # [39] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; So # [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; So # [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; So # [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2CE5..2CEA ; So # [6] COPTIC SYMBOL MI RO..COPTIC SYMBOL SHIMA SIMA 2E50..2E51 ; So # [2] CROSS PATTY WITH RIGHT CROSSBAR..CROSS PATTY WITH LEFT CROSSBAR 2E80..2E99 ; So # [26] CJK RADICAL REPEAT..CJK RADICAL RAP @@ -4285,7 +4283,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; So # [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 7376 +# Total code points: 7377 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index e42e13f6b..49803bb27 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 21:22:51 GMT +# Date: 2024-11-13, 21:35:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757620 code points not listed here. -# Total code points: 895088 +# The above property value applies to 757619 code points not listed here. +# Total code points: 895087 # ================================================ @@ -1080,8 +1080,7 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 2B47..2B4C ; AL # Sm [6] REVERSE TILDE OPERATOR ABOVE RIGHTWARDS ARROW..RIGHTWARDS ARROW ABOVE REVERSE TILDE OPERATOR 2B4D..2B54 ; AL # So [8] DOWNWARDS TRIANGLE-HEADED ZIGZAG ARROW..WHITE RIGHT-POINTING PENTAGON 2B5A..2B73 ; AL # So [26] SLANTED NORTH ARROW WITH HOOKED HEAD..DOWNWARDS TRIANGLE-HEADED ARROW TO BAR -2B76..2B95 ; AL # So [32] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..RIGHTWARDS BLACK ARROW -2B97..2BFF ; AL # So [105] SYMBOL FOR TYPE A ELECTRONICS..HELLSCHREIBER PAUSE SYMBOL +2B76..2BFF ; AL # So [138] NORTH WEST TRIANGLE-HEADED ARROW TO BAR..HELLSCHREIBER PAUSE SYMBOL 2C00..2C7B ; AL # L& [124] GLAGOLITIC CAPITAL LETTER AZU..LATIN LETTER SMALL CAPITAL TURNED E 2C7C..2C7D ; AL # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V 2C7E..2CE4 ; AL # L& [103] LATIN CAPITAL LETTER S WITH SWASH TAIL..COPTIC SYMBOL KAI @@ -1615,7 +1614,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26683 +# Total code points: 26684 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 31baaea9b..20b8bd47d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 21:22:51 GMT +# Date: 2024-11-13, 21:35:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -10247,6 +10247,7 @@ 2B93 ; NEWLINE RIGHT 2B94 ; FOUR CORNER ARROWS CIRCLING ANTICLOCKWISE 2B95 ; RIGHTWARDS BLACK ARROW +2B96 ; EQUALS SIGN WITH INFINITY ABOVE 2B97 ; SYMBOL FOR TYPE A ELECTRONICS 2B98 ; THREE-D TOP-LIGHTED LEFTWARDS EQUILATERAL ARROWHEAD 2B99 ; THREE-D RIGHT-LIGHTED UPWARDS EQUILATERAL ARROWHEAD @@ -45400,6 +45401,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155031 +# Total code points: 155032 # EOF From 7b4359d60c2f01b9733ed7e6c4138ab1e45bffe0 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 23:01:53 +0100 Subject: [PATCH 18/26] Latin small and capital pharyngeal voiced fricative (#589) * UnicodeData.txt from L2/23-219 * LB=AL * Scripts.txt * Regenerate UCD --- unicodetools/data/ucd/dev/CaseFolding.txt | 3 +- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +- .../data/ucd/dev/DerivedCoreProperties.txt | 86 +++++++++---------- .../ucd/dev/DerivedNormalizationProps.txt | 13 +-- unicodetools/data/ucd/dev/EastAsianWidth.txt | 9 +- unicodetools/data/ucd/dev/LineBreak.txt | 9 +- unicodetools/data/ucd/dev/Scripts.txt | 11 ++- unicodetools/data/ucd/dev/UnicodeData.txt | 4 +- .../data/ucd/dev/VerticalOrientation.txt | 9 +- .../dev/auxiliary/SentenceBreakProperty.txt | 12 +-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 11 ++- .../ucd/dev/extracted/DerivedBidiClass.txt | 11 ++- .../dev/extracted/DerivedCombiningClass.txt | 11 ++- .../dev/extracted/DerivedEastAsianWidth.txt | 11 ++- .../dev/extracted/DerivedGeneralCategory.txt | 15 ++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 15 ++-- .../data/ucd/dev/extracted/DerivedName.txt | 6 +- 17 files changed, 121 insertions(+), 120 deletions(-) diff --git a/unicodetools/data/ucd/dev/CaseFolding.txt b/unicodetools/data/ucd/dev/CaseFolding.txt index 1b7a9c156..e52ba9146 100644 --- a/unicodetools/data/ucd/dev/CaseFolding.txt +++ b/unicodetools/data/ucd/dev/CaseFolding.txt @@ -1,5 +1,5 @@ # CaseFolding-16.0.0.txt -# Date: 2024-04-30, 21:48:11 GMT +# Date: 2024-06-07, 20:34:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1243,6 +1243,7 @@ A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE; C; A7CF; # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 13742ee49..d13de90a8 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 21:34:52 GMT +# Date: 2024-11-13, 21:48:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2073,7 +2073,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1ACF..1ADD ; 17.0 # [15] COMBINING DOUBLE CARON..COMBINING DOT-AND-RING BELOW 1AE0..1AEB ; 17.0 # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 2B96 ; 17.0 # EQUALS SIGN WITH INFINITY ABOVE +A7CE..A7CF ; 17.0 # [2] LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE -# Total code points: 34 +# Total code points: 36 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 7b44bcca3..448553ba3 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 21:35:10 GMT +# Date: 2024-11-13, 21:48:56 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -273,8 +273,8 @@ FFE9..FFEC ; Math # Sm [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A 01BC..01BF ; Alphabetic # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; Alphabetic # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; Alphabetic # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; Alphabetic # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; Alphabetic # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; Alphabetic # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; Alphabetic # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; Alphabetic # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; Alphabetic # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; Alphabetic # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -834,8 +834,7 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; Alphabetic # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Alphabetic # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; Alphabetic # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; Alphabetic # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -1442,7 +1441,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142763 +# Total code points: 142765 # ================================================ @@ -1596,7 +1595,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 024B ; Lowercase # L& LATIN SMALL LETTER Q WITH HOOK TAIL 024D ; Lowercase # L& LATIN SMALL LETTER R WITH STROKE 024F..0293 ; Lowercase # L& [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Lowercase # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Lowercase # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Lowercase # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02C0..02C1 ; Lowercase # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP 02E0..02E4 ; Lowercase # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -2074,6 +2073,7 @@ A7C3 ; Lowercase # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lowercase # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lowercase # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Lowercase # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Lowercase # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Lowercase # L& LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Lowercase # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN @@ -2751,6 +2751,7 @@ A7C2 ; Uppercase # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Uppercase # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Uppercase # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Uppercase # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S @@ -2804,7 +2805,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1978 +# Total code points: 1979 # ================================================ @@ -2822,7 +2823,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 00F8..01BA ; Cased # L& [195] LATIN SMALL LETTER O WITH STROKE..LATIN SMALL LETTER EZH WITH TAIL 01BC..01BF ; Cased # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C4..0293 ; Cased # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Cased # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Cased # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Cased # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02C0..02C1 ; Cased # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP 02E0..02E4 ; Cased # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -2912,8 +2913,7 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7CD ; Cased # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Cased # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; Cased # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; Cased # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -2989,7 +2989,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4578 +# Total code points: 4579 # ================================================ @@ -4112,6 +4112,7 @@ A7C2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER ANGLICAN A7C4..A7C7 ; Changes_When_Lowercased # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Changes_When_Lowercased # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S @@ -4131,7 +4132,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1460 +# Total code points: 1461 # ================================================ @@ -4749,6 +4750,7 @@ A7C3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER ANGLICANA A7C8 ; Changes_When_Uppercased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Changes_When_Uppercased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S @@ -4771,7 +4773,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1552 +# Total code points: 1553 # ================================================ @@ -5388,6 +5390,7 @@ A7C3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER ANGLICANA A7C8 ; Changes_When_Titlecased # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Changes_When_Titlecased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S @@ -5410,7 +5413,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1479 +# Total code points: 1480 # ================================================ @@ -6024,6 +6027,7 @@ A7C2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER ANGLICAN A7C4..A7C7 ; Changes_When_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Changes_When_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S @@ -6046,7 +6050,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1533 +# Total code points: 1534 # ================================================ @@ -6158,8 +6162,7 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7CD ; Changes_When_Casemapped # L& [30] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A7B0..A7D1 ; Changes_When_Casemapped # L& [34] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER CLOSED INSULAR G A7D6..A7DC ; Changes_When_Casemapped # L& [7] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI @@ -6187,7 +6190,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2981 +# Total code points: 2983 # ================================================ @@ -6212,8 +6215,8 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 01BC..01BF ; ID_Start # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; ID_Start # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; ID_Start # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; ID_Start # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; ID_Start # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; ID_Start # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; ID_Start # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ID_Start # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; ID_Start # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; ID_Start # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -6564,8 +6567,7 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; ID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; ID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; ID_Start # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; ID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -6965,7 +6967,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141273 +# Total code points: 141275 # ================================================ @@ -6994,8 +6996,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 01BC..01BF ; ID_Continue # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; ID_Continue # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; ID_Continue # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; ID_Continue # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; ID_Continue # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; ID_Continue # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; ID_Continue # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ID_Continue # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; ID_Continue # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; ID_Continue # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -7651,8 +7653,7 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; ID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; ID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; ID_Continue # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; ID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -8375,7 +8376,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144574 +# Total code points: 144576 # ================================================ @@ -8398,8 +8399,8 @@ E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR 01BC..01BF ; XID_Start # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; XID_Start # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; XID_Start # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; XID_Start # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; XID_Start # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; XID_Start # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; XID_Start # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; XID_Start # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; XID_Start # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; XID_Start # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -8748,8 +8749,7 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; XID_Start # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; XID_Start # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; XID_Start # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; XID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -9154,7 +9154,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141250 +# Total code points: 141252 # ================================================ @@ -9180,8 +9180,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 01BC..01BF ; XID_Continue # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; XID_Continue # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; XID_Continue # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; XID_Continue # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; XID_Continue # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; XID_Continue # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; XID_Continue # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; XID_Continue # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C6..02D1 ; XID_Continue # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02E0..02E4 ; XID_Continue # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -9835,8 +9835,7 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; XID_Continue # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; XID_Continue # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; XID_Continue # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; XID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -10565,7 +10564,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144555 +# Total code points: 144557 # ================================================ @@ -11107,8 +11106,8 @@ E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELE 01BC..01BF ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; Grapheme_Base # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; Grapheme_Base # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; Grapheme_Base # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; Grapheme_Base # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; Grapheme_Base # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; Grapheme_Base # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; Grapheme_Base # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; Grapheme_Base # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; Grapheme_Base # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON @@ -11986,8 +11985,7 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; Grapheme_Base # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; Grapheme_Base # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Grapheme_Base # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; Grapheme_Base # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -12821,7 +12819,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152735 +# Total code points: 152737 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index ce636abb5..4a4b36243 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ -# DerivedNormalizationProps-16.0.0.txt -# Date: 2024-04-30, 21:48:18 GMT +# DerivedNormalizationProps-17.0.0.txt +# Date: 2024-11-13, 21:48:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -5448,6 +5448,7 @@ A7C7 ; NFKC_CF; A7C8 # L& LATIN CAPITAL LETTER D WITH S A7C9 ; NFKC_CF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB ; NFKC_CF; 0264 # L& LATIN CAPITAL LETTER RAMS HORN A7CC ; NFKC_CF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; NFKC_CF; A7CF # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; NFKC_CF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S @@ -9148,7 +9149,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] .... -# Total code points: 10554 +# Total code points: 10555 # ================================================ @@ -11582,6 +11583,7 @@ A7C7 ; NFKC_SCF; A7C8 # L& LATIN CAPITAL LETTER D WITH A7C9 ; NFKC_SCF; A7CA # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB ; NFKC_SCF; 0264 # L& LATIN CAPITAL LETTER RAMS HORN A7CC ; NFKC_SCF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; NFKC_SCF; A7CF # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; NFKC_SCF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S @@ -15282,7 +15284,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] .... -# Total code points: 10516 +# Total code points: 10517 # ================================================ @@ -16052,6 +16054,7 @@ A7C2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER ANG A7C4..A7C7 ; Changes_When_NFKC_Casefolded # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Changes_When_NFKC_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S @@ -16300,6 +16303,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] .... -# Total code points: 10554 +# Total code points: 10555 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index e7019bcf1..525f3ed34 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:35:14 GMT +# Date: 2024-11-13, 21:49:00 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -180,8 +180,8 @@ 0252..0260 ; N # Ll [15] LATIN SMALL LETTER TURNED ALPHA..LATIN SMALL LETTER G WITH HOOK 0261 ; A # Ll LATIN SMALL LETTER SCRIPT G 0262..0293 ; N # Ll [50] LATIN LETTER SMALL CAPITAL G..LATIN SMALL LETTER EZH WITH CURL -0294 ; N # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; N # Ll [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; N # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; N # Ll [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; N # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C3 ; N # Sk [2] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER RIGHT ARROWHEAD 02C4 ; A # Sk MODIFIER LETTER UP ARROWHEAD @@ -1549,8 +1549,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; N # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; N # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; N # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 071dcb538..237a89163 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 21:35:15 GMT +# Date: 2024-11-13, 21:49:01 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -132,8 +132,8 @@ 01C0..01C3 ; AL # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..024F ; AL # L& [140] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER Y WITH STROKE 0250..0293 ; AL # Ll [68] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER EZH WITH CURL -0294 ; AL # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; AL # Ll [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; AL # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; AL # Ll [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; AL # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; AL # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6 ; AL # Lm MODIFIER LETTER CIRCUMFLEX ACCENT @@ -1576,8 +1576,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; AL # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; AL # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; AL # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 47a23f20b..e98eca2e3 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 21:35:38 GMT +# Date: 2024-11-13, 21:49:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -647,8 +647,8 @@ E0020..E007F ; Common # Cf [96] TAG SPACE..CANCEL TAG 01BC..01BF ; Latin # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; Latin # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; Latin # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; Latin # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; Latin # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; Latin # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; Latin # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Latin # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02E0..02E4 ; Latin # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP 1D00..1D25 ; Latin # L& [38] LATIN LETTER SMALL CAPITAL A..LATIN LETTER AIN @@ -675,8 +675,7 @@ A770 ; Latin # Lm MODIFIER LETTER US A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; Latin # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; Latin # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; Latin # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Latin # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; Latin # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Latin # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -701,7 +700,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK -# Total code points: 1487 +# Total code points: 1489 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 631fca167..aae6db78a 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -659,7 +659,7 @@ 0292;LATIN SMALL LETTER EZH;Ll;0;L;;;;;N;LATIN SMALL LETTER YOGH;;01B7;;01B7 0293;LATIN SMALL LETTER EZH WITH CURL;Ll;0;L;;;;;N;LATIN SMALL LETTER YOGH CURL;;;; 0294;LATIN LETTER GLOTTAL STOP;Lo;0;L;;;;;N;;;;; -0295;LATIN LETTER PHARYNGEAL VOICED FRICATIVE;Ll;0;L;;;;;N;LATIN LETTER REVERSED GLOTTAL STOP;;;; +0295;LATIN LETTER PHARYNGEAL VOICED FRICATIVE;Lo;0;L;;;;;N;LATIN LETTER REVERSED GLOTTAL STOP;;;; 0296;LATIN LETTER INVERTED GLOTTAL STOP;Ll;0;L;;;;;N;;;;; 0297;LATIN LETTER STRETCHED C;Ll;0;L;;;;;N;;;;; 0298;LATIN LETTER BILABIAL CLICK;Ll;0;L;;;;;N;LATIN LETTER BULLSEYE;;;; @@ -14308,6 +14308,8 @@ A7CA;LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY;Ll;0;L;;;;;N;;;A7C9;;A7C9 A7CB;LATIN CAPITAL LETTER RAMS HORN;Lu;0;L;;;;;N;;;;0264; A7CC;LATIN CAPITAL LETTER S WITH DIAGONAL STROKE;Lu;0;L;;;;;N;;;;A7CD; A7CD;LATIN SMALL LETTER S WITH DIAGONAL STROKE;Ll;0;L;;;;;N;;;A7CC;;A7CC +A7CE;LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE;Lu;0;L;;;;;N;;;;A7CF; +A7CF;LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE;Ll;0;L;;;;;N;;;A7CE;;A7CE A7D0;LATIN CAPITAL LETTER CLOSED INSULAR G;Lu;0;L;;;;;N;;;;A7D1; A7D1;LATIN SMALL LETTER CLOSED INSULAR G;Ll;0;L;;;;;N;;;A7D0;;A7D0 A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index afadbe23c..3ee1e2b95 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 21:35:41 GMT +# Date: 2024-11-13, 21:49:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -140,8 +140,8 @@ 01C0..01C3 ; R # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..024F ; R # L& [140] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER Y WITH STROKE 0250..0293 ; R # Ll [68] LATIN SMALL LETTER TURNED A..LATIN SMALL LETTER EZH WITH CURL -0294 ; R # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; R # Ll [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; R # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; R # Ll [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; R # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; R # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; R # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON @@ -1358,8 +1358,7 @@ A788 ; R # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; R # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; R # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; R # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; R # Ll LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; R # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; R # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 6fbcfa5e8..34646f2ae 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:23:14 GMT +# Date: 2024-11-13, 21:49:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -780,7 +780,7 @@ E0001 ; Format # Cf LANGUAGE TAG 024B ; Lower # L& LATIN SMALL LETTER Q WITH HOOK TAIL 024D ; Lower # L& LATIN SMALL LETTER R WITH STROKE 024F..0293 ; Lower # L& [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Lower # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Lower # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; Lower # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02C0..02C1 ; Lower # Lm [2] MODIFIER LETTER GLOTTAL STOP..MODIFIER LETTER REVERSED GLOTTAL STOP 02E0..02E4 ; Lower # Lm [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP @@ -1255,6 +1255,7 @@ A7C3 ; Lower # L& LATIN SMALL LETTER ANGLICANA W A7C8 ; Lower # L& LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Lower # L& LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Lower # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Lower # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Lower # L& LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Lower # L& LATIN SMALL LETTER DOUBLE THORN A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN @@ -1930,6 +1931,7 @@ A7C2 ; Upper # L& LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Upper # L& [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Upper # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Upper # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Upper # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Upper # L& LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S @@ -1983,13 +1985,13 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1963 +# Total code points: 1964 # ================================================ 01BB ; OLetter # Lo LATIN LETTER TWO WITH STROKE 01C0..01C3 ; OLetter # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK -0294 ; OLetter # Lo LATIN LETTER GLOTTAL STOP +0294..0295 ; OLetter # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE 02B9..02BF ; OLetter # Lm [7] MODIFIER LETTER PRIME..MODIFIER LETTER LEFT HALF RING 02C6..02D1 ; OLetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON 02EC ; OLetter # Lm MODIFIER LETTER VOICING @@ -2587,7 +2589,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136912 +# Total code points: 136913 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 935c90d01..bb5a423f0 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:23:15 GMT +# Date: 2024-11-13, 21:49:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -688,8 +688,8 @@ FF71..FF9D ; Katakana # Lo [45] HALFWIDTH KATAKANA LETTER A..HALFWIDTH KATAK 01BC..01BF ; ALetter # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; ALetter # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; ALetter # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; ALetter # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; ALetter # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; ALetter # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; ALetter # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; ALetter # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; ALetter # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; ALetter # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON @@ -1004,8 +1004,7 @@ A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; ALetter # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; ALetter # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; ALetter # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; ALetter # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; ALetter # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -1357,7 +1356,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33795 +# Total code points: 33797 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 6386021e6..4244cc093 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 21:35:08 GMT +# Date: 2024-11-13, 21:48:54 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -138,8 +138,8 @@ 01BC..01BF ; L # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; L # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; L # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; L # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; L # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; L # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; L # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02B8 ; L # Lm [9] MODIFIER LETTER SMALL H..MODIFIER LETTER SMALL Y 02BB..02C1 ; L # Lm [7] MODIFIER LETTER TURNED COMMA..MODIFIER LETTER REVERSED GLOTTAL STOP 02D0..02D1 ; L # Lm [2] MODIFIER LETTER TRIANGULAR COLON..MODIFIER LETTER HALF TRIANGULAR COLON @@ -663,8 +663,7 @@ A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; L # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; L # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; L # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; L # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; L # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; L # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -1215,7 +1214,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815318 code points not listed here. +# The above property value applies to 815316 code points not listed here. # Total code points: 1095483 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 84fbc414d..f18e1c9e2 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 21:35:09 GMT +# Date: 2024-11-13, 21:48:55 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -83,8 +83,8 @@ 01BC..01BF ; 0 # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; 0 # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; 0 # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; 0 # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; 0 # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; 0 # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; 0 # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; 0 # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; 0 # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6..02D1 ; 0 # Lm [12] MODIFIER LETTER CIRCUMFLEX ACCENT..MODIFIER LETTER HALF TRIANGULAR COLON @@ -1093,8 +1093,7 @@ A788 ; 0 # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; 0 # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; 0 # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; 0 # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; 0 # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; 0 # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; 0 # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -2060,7 +2059,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821547 code points not listed here. +# The above property value applies to 821545 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 408410f88..12a6af6ef 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:35:11 GMT +# Date: 2024-11-13, 21:48:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -91,8 +91,8 @@ 01DD..0250 ; N # L& [116] LATIN SMALL LETTER TURNED E..LATIN SMALL LETTER TURNED A 0252..0260 ; N # L& [15] LATIN SMALL LETTER TURNED ALPHA..LATIN SMALL LETTER G WITH HOOK 0262..0293 ; N # L& [50] LATIN LETTER SMALL CAPITAL G..LATIN SMALL LETTER EZH WITH CURL -0294 ; N # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; N # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; N # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; N # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; N # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C3 ; N # Sk [2] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER RIGHT ARROWHEAD 02C5 ; N # Sk MODIFIER LETTER DOWN ARROWHEAD @@ -1183,8 +1183,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; N # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; N # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; N # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; N # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -2104,7 +2103,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761065 code points not listed here. +# The above property value applies to 761063 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 9c9216414..78edfffc3 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 21:35:11 GMT +# Date: 2024-11-13, 21:48:58 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -293,7 +293,6 @@ A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7CE..A7CF ; Cn # [2] .. A7D2 ; Cn # A7D4 ; Cn # A7DD..A7F1 ; Cn # [21] .. @@ -746,7 +745,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819499 +# Total code points: 819497 # ================================================ @@ -1354,6 +1353,7 @@ A7C2 ; Lu # LATIN CAPITAL LETTER ANGLICANA W A7C4..A7C7 ; Lu # [4] LATIN CAPITAL LETTER C WITH PALATAL HOOK..LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY A7C9 ; Lu # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Lu # [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE +A7CE ; Lu # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S @@ -1404,7 +1404,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA 1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1858 +# Total code points: 1859 # ================================================ @@ -1555,7 +1555,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 024B ; Ll # LATIN SMALL LETTER Q WITH HOOK TAIL 024D ; Ll # LATIN SMALL LETTER R WITH STROKE 024F..0293 ; Ll # [69] LATIN SMALL LETTER Y WITH STROKE..LATIN SMALL LETTER EZH WITH CURL -0295..02AF ; Ll # [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0296..02AF ; Ll # [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 0371 ; Ll # GREEK SMALL LETTER HETA 0373 ; Ll # GREEK SMALL LETTER ARCHAIC SAMPI 0377 ; Ll # GREEK SMALL LETTER PAMPHYLIAN DIGAMMA @@ -2016,6 +2016,7 @@ A7C3 ; Ll # LATIN SMALL LETTER ANGLICANA W A7C8 ; Ll # LATIN SMALL LETTER D WITH SHORT STROKE OVERLAY A7CA ; Ll # LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CD ; Ll # LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CF ; Ll # LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Ll # LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; Ll # LATIN SMALL LETTER DOUBLE THORN A7D5 ; Ll # LATIN SMALL LETTER DOUBLE WYNN @@ -2182,7 +2183,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 00BA ; Lo # MASCULINE ORDINAL INDICATOR 01BB ; Lo # LATIN LETTER TWO WITH STROKE 01C0..01C3 ; Lo # [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK -0294 ; Lo # LATIN LETTER GLOTTAL STOP +0294..0295 ; Lo # [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE 05D0..05EA ; Lo # [27] HEBREW LETTER ALEF..HEBREW LETTER TAV 05EF..05F2 ; Lo # [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD 0620..063F ; Lo # [32] ARABIC LETTER KASHMIRI YEH..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE @@ -2708,7 +2709,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136481 +# Total code points: 136482 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 49803bb27..683cf66b0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 21:35:12 GMT +# Date: 2024-11-13, 21:48:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757619 code points not listed here. -# Total code points: 895087 +# The above property value applies to 757617 code points not listed here. +# Total code points: 895085 # ================================================ @@ -587,8 +587,8 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 01BC..01BF ; AL # L& [4] LATIN CAPITAL LETTER TONE FIVE..LATIN LETTER WYNN 01C0..01C3 ; AL # Lo [4] LATIN LETTER DENTAL CLICK..LATIN LETTER RETROFLEX CLICK 01C4..0293 ; AL # L& [208] LATIN CAPITAL LETTER DZ WITH CARON..LATIN SMALL LETTER EZH WITH CURL -0294 ; AL # Lo LATIN LETTER GLOTTAL STOP -0295..02AF ; AL # L& [27] LATIN LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL +0294..0295 ; AL # Lo [2] LATIN LETTER GLOTTAL STOP..LATIN LETTER PHARYNGEAL VOICED FRICATIVE +0296..02AF ; AL # L& [26] LATIN LETTER INVERTED GLOTTAL STOP..LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL 02B0..02C1 ; AL # Lm [18] MODIFIER LETTER SMALL H..MODIFIER LETTER REVERSED GLOTTAL STOP 02C2..02C5 ; AL # Sk [4] MODIFIER LETTER LEFT ARROWHEAD..MODIFIER LETTER DOWN ARROWHEAD 02C6 ; AL # Lm MODIFIER LETTER CIRCUMFLEX ACCENT @@ -1141,8 +1141,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7CD ; AL # L& [62] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER S WITH DIAGONAL STROKE -A7D0..A7D1 ; AL # L& [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G +A790..A7D1 ; AL # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; AL # L& LATIN SMALL LETTER DOUBLE THORN A7D5..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q @@ -1614,7 +1613,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26684 +# Total code points: 26686 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 20b8bd47d..8e4a91993 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 21:35:12 GMT +# Date: 2024-11-13, 21:48:59 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -14281,6 +14281,8 @@ A7CA ; LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY A7CB ; LATIN CAPITAL LETTER RAMS HORN A7CC ; LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CD ; LATIN SMALL LETTER S WITH DIAGONAL STROKE +A7CE ; LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE +A7CF ; LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; LATIN CAPITAL LETTER CLOSED INSULAR G A7D1 ; LATIN SMALL LETTER CLOSED INSULAR G A7D3 ; LATIN SMALL LETTER DOUBLE THORN @@ -45401,6 +45403,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155032 +# Total code points: 155034 # EOF From 2fa8b481733863ddac54724a4e64188d7a6e6443 Mon Sep 17 00:00:00 2001 From: Mark Davis Date: Wed, 13 Nov 2024 14:16:22 -0800 Subject: [PATCH 19/26] UTC-176-C32 Adding capital double thorn/wynn (#635) * UTC-176-C32 first cut * Fix linebreak * Now Scripts --------- Co-authored-by: Robin Leroy --- unicodetools/data/ucd/dev/CaseFolding.txt | 6 +- unicodetools/data/ucd/dev/DerivedAge.txt | 6 +- .../data/ucd/dev/DerivedCoreProperties.txt | 69 +++++++++---------- .../ucd/dev/DerivedNormalizationProps.txt | 14 ++-- unicodetools/data/ucd/dev/EastAsianWidth.txt | 6 +- unicodetools/data/ucd/dev/LineBreak.txt | 6 +- unicodetools/data/ucd/dev/Scripts.txt | 8 +-- unicodetools/data/ucd/dev/UnicodeData.txt | 6 +- .../data/ucd/dev/VerticalOrientation.txt | 6 +- .../dev/auxiliary/SentenceBreakProperty.txt | 6 +- .../ucd/dev/auxiliary/WordBreakProperty.txt | 8 +-- .../ucd/dev/extracted/DerivedBidiClass.txt | 8 +-- .../dev/extracted/DerivedCombiningClass.txt | 8 +-- .../dev/extracted/DerivedEastAsianWidth.txt | 8 +-- .../dev/extracted/DerivedGeneralCategory.txt | 10 +-- .../ucd/dev/extracted/DerivedLineBreak.txt | 12 ++-- .../data/ucd/dev/extracted/DerivedName.txt | 6 +- 17 files changed, 93 insertions(+), 100 deletions(-) diff --git a/unicodetools/data/ucd/dev/CaseFolding.txt b/unicodetools/data/ucd/dev/CaseFolding.txt index e52ba9146..533abab63 100644 --- a/unicodetools/data/ucd/dev/CaseFolding.txt +++ b/unicodetools/data/ucd/dev/CaseFolding.txt @@ -1,5 +1,5 @@ -# CaseFolding-16.0.0.txt -# Date: 2024-06-07, 20:34:09 GMT +# CaseFolding-17.0.0.txt +# Date: 2024-11-13, 22:03:16 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1245,6 +1245,8 @@ A7CB; C; 0264; # LATIN CAPITAL LETTER RAMS HORN A7CC; C; A7CD; # LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE; C; A7CF; # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2; C; A7D3; # LATIN CAPITAL LETTER DOUBLE THORN +A7D4; C; A7D5; # LATIN CAPITAL LETTER DOUBLE WYNN A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S A7DA; C; A7DB; # LATIN CAPITAL LETTER LAMBDA diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index d13de90a8..9d9cd0412 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 21:48:39 GMT +# Date: 2024-11-13, 22:03:17 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2074,7 +2074,9 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L 1AE0..1AEB ; 17.0 # [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE 2B96 ; 17.0 # EQUALS SIGN WITH INFINITY ABOVE A7CE..A7CF ; 17.0 # [2] LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE +A7D2 ; 17.0 # LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; 17.0 # LATIN CAPITAL LETTER DOUBLE WYNN -# Total code points: 36 +# Total code points: 38 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 448553ba3..1f5ee8261 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 21:48:56 GMT +# Date: 2024-11-13, 22:03:35 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -834,9 +834,7 @@ A771..A787 ; Alphabetic # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; Alphabetic # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Alphabetic # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Alphabetic # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; Alphabetic # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1441,7 +1439,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142765 +# Total code points: 142767 # ================================================ @@ -2753,6 +2751,8 @@ A7C9 ; Uppercase # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OV A7CB..A7CC ; Uppercase # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Uppercase # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Uppercase # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Uppercase # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Uppercase # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Uppercase # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Uppercase # L& LATIN CAPITAL LETTER LAMBDA @@ -2805,7 +2805,7 @@ FF21..FF3A ; Uppercase # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH 1F150..1F169 ; Uppercase # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Uppercase # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1979 +# Total code points: 1981 # ================================================ @@ -2913,9 +2913,7 @@ A722..A76F ; Cased # L& [78] LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF..LATIN A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT -A790..A7D1 ; Cased # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Cased # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Cased # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; Cased # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -2989,7 +2987,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4579 +# Total code points: 4581 # ================================================ @@ -4114,6 +4112,8 @@ A7C9 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER S WITH S A7CB..A7CC ; Changes_When_Lowercased # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Lowercased # L& LATIN CAPITAL LETTER LAMBDA @@ -4132,7 +4132,7 @@ FF21..FF3A ; Changes_When_Lowercased # L& [26] FULLWIDTH LATIN CAPITAL LETTE 16E40..16E5F ; Changes_When_Lowercased # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Lowercased # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1461 +# Total code points: 1463 # ================================================ @@ -4752,6 +4752,8 @@ A7CA ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH SHO A7CD ; Changes_When_Uppercased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7CF ; Changes_When_Uppercased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Uppercased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Uppercased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Uppercased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Uppercased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Uppercased # L& LATIN SMALL LETTER LAMBDA @@ -4773,7 +4775,7 @@ FF41..FF5A ; Changes_When_Uppercased # L& [26] FULLWIDTH LATIN SMALL LETTER 16E60..16E7F ; Changes_When_Uppercased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Uppercased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1553 +# Total code points: 1555 # ================================================ @@ -5392,6 +5394,8 @@ A7CA ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH SHO A7CD ; Changes_When_Titlecased # L& LATIN SMALL LETTER S WITH DIAGONAL STROKE A7CF ; Changes_When_Titlecased # L& LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D1 ; Changes_When_Titlecased # L& LATIN SMALL LETTER CLOSED INSULAR G +A7D3 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE THORN +A7D5 ; Changes_When_Titlecased # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Changes_When_Titlecased # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Changes_When_Titlecased # L& LATIN SMALL LETTER SIGMOID S A7DB ; Changes_When_Titlecased # L& LATIN SMALL LETTER LAMBDA @@ -5413,7 +5417,7 @@ FF41..FF5A ; Changes_When_Titlecased # L& [26] FULLWIDTH LATIN SMALL LETTER 16E60..16E7F ; Changes_When_Titlecased # L& [32] MEDEFAIDRIN SMALL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E922..1E943 ; Changes_When_Titlecased # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 1480 +# Total code points: 1482 # ================================================ @@ -6029,6 +6033,8 @@ A7C9 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER S WITH S A7CB..A7CC ; Changes_When_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_Casefolded # L& LATIN CAPITAL LETTER LAMBDA @@ -6050,7 +6056,7 @@ FF21..FF3A ; Changes_When_Casefolded # L& [26] FULLWIDTH LATIN CAPITAL LETTE 16E40..16E5F ; Changes_When_Casefolded # L& [32] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN CAPITAL LETTER Y 1E900..1E921 ; Changes_When_Casefolded # L& [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1534 +# Total code points: 1536 # ================================================ @@ -6162,8 +6168,7 @@ A779..A787 ; Changes_When_Casemapped # L& [15] LATIN CAPITAL LETTER INSULAR A78B..A78D ; Changes_When_Casemapped # L& [3] LATIN CAPITAL LETTER SALTILLO..LATIN CAPITAL LETTER TURNED H A790..A794 ; Changes_When_Casemapped # L& [5] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER C WITH PALATAL HOOK A796..A7AE ; Changes_When_Casemapped # L& [25] LATIN CAPITAL LETTER B WITH FLOURISH..LATIN CAPITAL LETTER SMALL CAPITAL I -A7B0..A7D1 ; Changes_When_Casemapped # L& [34] LATIN CAPITAL LETTER TURNED K..LATIN SMALL LETTER CLOSED INSULAR G -A7D6..A7DC ; Changes_When_Casemapped # L& [7] LATIN CAPITAL LETTER MIDDLE SCOTS S..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7B0..A7DC ; Changes_When_Casemapped # L& [45] LATIN CAPITAL LETTER TURNED K..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F5..A7F6 ; Changes_When_Casemapped # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H AB53 ; Changes_When_Casemapped # L& LATIN SMALL LETTER CHI AB70..ABBF ; Changes_When_Casemapped # L& [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA @@ -6190,7 +6195,7 @@ FF41..FF5A ; Changes_When_Casemapped # L& [26] FULLWIDTH LATIN SMALL LETTER 16E40..16E7F ; Changes_When_Casemapped # L& [64] MEDEFAIDRIN CAPITAL LETTER M..MEDEFAIDRIN SMALL LETTER Y 1E900..1E943 ; Changes_When_Casemapped # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2983 +# Total code points: 2987 # ================================================ @@ -6567,9 +6572,7 @@ A771..A787 ; ID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER I A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; ID_Start # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; ID_Start # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; ID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; ID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -6967,7 +6970,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141275 +# Total code points: 141277 # ================================================ @@ -7653,9 +7656,7 @@ A771..A787 ; ID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTE A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; ID_Continue # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; ID_Continue # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; ID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; ID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -8376,7 +8377,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144576 +# Total code points: 144578 # ================================================ @@ -8749,9 +8750,7 @@ A771..A787 ; XID_Start # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; XID_Start # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; XID_Start # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; XID_Start # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; XID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -9154,7 +9153,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141252 +# Total code points: 141254 # ================================================ @@ -9835,9 +9834,7 @@ A771..A787 ; XID_Continue # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETT A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; XID_Continue # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; XID_Continue # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; XID_Continue # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; XID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -10564,7 +10561,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144557 +# Total code points: 144559 # ================================================ @@ -11985,9 +11982,7 @@ A788 ; Grapheme_Base # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; Grapheme_Base # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Grapheme_Base # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Grapheme_Base # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; Grapheme_Base # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -12819,7 +12814,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152737 +# Total code points: 152739 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 4a4b36243..7ee1f72a2 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-17.0.0.txt -# Date: 2024-11-13, 21:48:59 GMT +# Date: 2024-11-13, 22:03:39 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -5450,6 +5450,8 @@ A7CB ; NFKC_CF; 0264 # L& LATIN CAPITAL LETTER RAMS HOR A7CC ; NFKC_CF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; NFKC_CF; A7CF # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; NFKC_CF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; NFKC_CF; A7D3 # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; NFKC_CF; A7D5 # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_CF; A7DB # L& LATIN CAPITAL LETTER LAMBDA @@ -9149,7 +9151,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] .... -# Total code points: 10555 +# Total code points: 10557 # ================================================ @@ -11585,6 +11587,8 @@ A7CB ; NFKC_SCF; 0264 # L& LATIN CAPITAL LETTER RAMS HO A7CC ; NFKC_SCF; A7CD # L& LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; NFKC_SCF; A7CF # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; NFKC_SCF; A7D1 # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; NFKC_SCF; A7D3 # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; NFKC_SCF; A7D5 # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_SCF; A7DB # L& LATIN CAPITAL LETTER LAMBDA @@ -15284,7 +15288,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] .... -# Total code points: 10517 +# Total code points: 10519 # ================================================ @@ -16056,6 +16060,8 @@ A7C9 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER S W A7CB..A7CC ; Changes_When_NFKC_Casefolded # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA @@ -16303,6 +16309,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] .... -# Total code points: 10555 +# Total code points: 10557 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 525f3ed34..4a39b0c77 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:49:00 GMT +# Date: 2024-11-13, 22:03:40 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1549,9 +1549,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; N # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; N # Ll LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 237a89163..dd2c46881 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 21:49:01 GMT +# Date: 2024-11-13, 22:03:41 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1576,9 +1576,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; AL # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; AL # Ll LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index e98eca2e3..e199ef2b4 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 21:49:20 GMT +# Date: 2024-11-13, 22:04:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -675,9 +675,7 @@ A770 ; Latin # Lm MODIFIER LETTER US A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; Latin # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; Latin # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; Latin # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; Latin # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; Latin # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Latin # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -700,7 +698,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK -# Total code points: 1489 +# Total code points: 1491 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index aae6db78a..66dc3c27d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -14312,8 +14312,10 @@ A7CE;LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE;Lu;0;L;;;;;N;;;;A7CF; A7CF;LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE;Ll;0;L;;;;;N;;;A7CE;;A7CE A7D0;LATIN CAPITAL LETTER CLOSED INSULAR G;Lu;0;L;;;;;N;;;;A7D1; A7D1;LATIN SMALL LETTER CLOSED INSULAR G;Ll;0;L;;;;;N;;;A7D0;;A7D0 -A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;;; -A7D5;LATIN SMALL LETTER DOUBLE WYNN;Ll;0;L;;;;;N;;;;; +A7D2;LATIN CAPITAL LETTER DOUBLE THORN;Lu;0;L;;;;;N;;;;A7D3; +A7D3;LATIN SMALL LETTER DOUBLE THORN;Ll;0;L;;;;;N;;;A7D2;;A7D2 +A7D4;LATIN CAPITAL LETTER DOUBLE WYNN;Lu;0;L;;;;;N;;;;A7D5; +A7D5;LATIN SMALL LETTER DOUBLE WYNN;Ll;0;L;;;;;N;;;A7D4;;A7D4 A7D6;LATIN CAPITAL LETTER MIDDLE SCOTS S;Lu;0;L;;;;;N;;;;A7D7; A7D7;LATIN SMALL LETTER MIDDLE SCOTS S;Ll;0;L;;;;;N;;;A7D6;;A7D6 A7D8;LATIN CAPITAL LETTER SIGMOID S;Lu;0;L;;;;;N;;;;A7D9; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 3ee1e2b95..d6167b1f8 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 21:49:22 GMT +# Date: 2024-11-13, 22:04:05 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1358,9 +1358,7 @@ A788 ; R # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; R # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; R # Ll LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; R # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; R # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; R # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; R # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 34646f2ae..76b500a96 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:49:20 GMT +# Date: 2024-11-13, 22:04:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1933,6 +1933,8 @@ A7C9 ; Upper # L& LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLA A7CB..A7CC ; Upper # L& [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Upper # L& LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Upper # L& LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Upper # L& LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Upper # L& LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Upper # L& LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Upper # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Upper # L& LATIN CAPITAL LETTER LAMBDA @@ -1985,7 +1987,7 @@ FF21..FF3A ; Upper # L& [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LAT 1F150..1F169 ; Upper # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Upper # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1964 +# Total code points: 1966 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index bb5a423f0..211ba68df 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:49:22 GMT +# Date: 2024-11-13, 22:04:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1004,9 +1004,7 @@ A788 ; ALetter # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; ALetter # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; ALetter # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; ALetter # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; ALetter # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ALetter # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1356,7 +1354,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33797 +# Total code points: 33799 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 4244cc093..97d173eb6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 21:48:54 GMT +# Date: 2024-11-13, 22:03:33 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -663,9 +663,7 @@ A771..A787 ; L # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; L # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; L # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; L # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; L # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; L # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; L # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1214,7 +1212,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815316 code points not listed here. +# The above property value applies to 815314 code points not listed here. # Total code points: 1095483 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index f18e1c9e2..dc20c62a1 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 21:48:55 GMT +# Date: 2024-11-13, 22:03:35 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1093,9 +1093,7 @@ A788 ; 0 # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; 0 # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; 0 # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; 0 # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; 0 # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; 0 # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; 0 # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; 0 # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -2059,7 +2057,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821545 code points not listed here. +# The above property value applies to 821543 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 12a6af6ef..3e5013b07 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 21:48:57 GMT +# Date: 2024-11-13, 22:03:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1183,9 +1183,7 @@ A788 ; N # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; N # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; N # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; N # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -2103,7 +2101,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761063 code points not listed here. +# The above property value applies to 761061 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 78edfffc3..5c4d67c71 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 21:48:58 GMT +# Date: 2024-11-13, 22:03:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -293,8 +293,6 @@ A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7D2 ; Cn # -A7D4 ; Cn # A7DD..A7F1 ; Cn # [21] .. A82D..A82F ; Cn # [3] .. A83A..A83F ; Cn # [6] .. @@ -745,7 +743,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819497 +# Total code points: 819495 # ================================================ @@ -1355,6 +1353,8 @@ A7C9 ; Lu # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY A7CB..A7CC ; Lu # [2] LATIN CAPITAL LETTER RAMS HORN..LATIN CAPITAL LETTER S WITH DIAGONAL STROKE A7CE ; Lu # LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; Lu # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D2 ; Lu # LATIN CAPITAL LETTER DOUBLE THORN +A7D4 ; Lu # LATIN CAPITAL LETTER DOUBLE WYNN A7D6 ; Lu # LATIN CAPITAL LETTER MIDDLE SCOTS S A7D8 ; Lu # LATIN CAPITAL LETTER SIGMOID S A7DA ; Lu # LATIN CAPITAL LETTER LAMBDA @@ -1404,7 +1404,7 @@ FF21..FF3A ; Lu # [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH LATIN CAP 1D7CA ; Lu # MATHEMATICAL BOLD CAPITAL DIGAMMA 1E900..1E921 ; Lu # [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA -# Total code points: 1859 +# Total code points: 1861 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 683cf66b0..fa995911f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 21:48:59 GMT +# Date: 2024-11-13, 22:03:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757617 code points not listed here. -# Total code points: 895085 +# The above property value applies to 757615 code points not listed here. +# Total code points: 895083 # ================================================ @@ -1141,9 +1141,7 @@ A788 ; AL # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT -A790..A7D1 ; AL # L& [66] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SMALL LETTER CLOSED INSULAR G -A7D3 ; AL # L& LATIN SMALL LETTER DOUBLE THORN -A7D5..A7DC ; AL # L& [8] LATIN SMALL LETTER DOUBLE WYNN..LATIN CAPITAL LETTER LAMBDA WITH STROKE +A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I @@ -1613,7 +1611,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26686 +# Total code points: 26688 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 8e4a91993..191c963dd 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 21:48:59 GMT +# Date: 2024-11-13, 22:03:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -14285,7 +14285,9 @@ A7CE ; LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE A7CF ; LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D0 ; LATIN CAPITAL LETTER CLOSED INSULAR G A7D1 ; LATIN SMALL LETTER CLOSED INSULAR G +A7D2 ; LATIN CAPITAL LETTER DOUBLE THORN A7D3 ; LATIN SMALL LETTER DOUBLE THORN +A7D4 ; LATIN CAPITAL LETTER DOUBLE WYNN A7D5 ; LATIN SMALL LETTER DOUBLE WYNN A7D6 ; LATIN CAPITAL LETTER MIDDLE SCOTS S A7D7 ; LATIN SMALL LETTER MIDDLE SCOTS S @@ -45403,6 +45405,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155034 +# Total code points: 155036 # EOF From ce13c8b5c1ddd91036c8a95259dfdf8dbdf0892b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 13 Nov 2024 23:43:53 +0100 Subject: [PATCH 20/26] Modifier capital S (#743) * UnicodeData.txt from the proposal * lb=AL most likely * Looks Latin to me * Diacritic and Lowercase I think * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 38 +++++++++---------- .../ucd/dev/DerivedNormalizationProps.txt | 23 ++++++----- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 +- unicodetools/data/ucd/dev/LineBreak.txt | 4 +- .../data/ucd/dev/NormalizationTest.txt | 3 +- unicodetools/data/ucd/dev/PropList.txt | 9 +++-- unicodetools/data/ucd/dev/Scripts.txt | 6 +-- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 4 +- .../dev/auxiliary/SentenceBreakProperty.txt | 6 +-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 +-- .../ucd/dev/extracted/DerivedBidiClass.txt | 6 +-- .../dev/extracted/DerivedCombiningClass.txt | 6 +-- .../extracted/DerivedDecompositionType.txt | 8 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 6 +-- .../dev/extracted/DerivedGeneralCategory.txt | 10 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 ++--- .../data/ucd/dev/extracted/DerivedName.txt | 5 ++- 19 files changed, 84 insertions(+), 76 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 9d9cd0412..c4be3a7a0 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 22:03:17 GMT +# Date: 2024-11-13, 22:18:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2076,7 +2076,8 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L A7CE..A7CF ; 17.0 # [2] LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE..LATIN SMALL LETTER PHARYNGEAL VOICED FRICATIVE A7D2 ; 17.0 # LATIN CAPITAL LETTER DOUBLE THORN A7D4 ; 17.0 # LATIN CAPITAL LETTER DOUBLE WYNN +A7F1 ; 17.0 # MODIFIER LETTER CAPITAL S -# Total code points: 38 +# Total code points: 39 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 1f5ee8261..0893db2d0 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 22:03:35 GMT +# Date: 2024-11-13, 22:18:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -835,7 +835,7 @@ A788 ; Alphabetic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; Alphabetic # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Alphabetic # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; Alphabetic # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Alphabetic # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Alphabetic # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Alphabetic # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Alphabetic # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Alphabetic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1439,7 +1439,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142767 +# Total code points: 142768 # ================================================ @@ -2078,7 +2078,7 @@ A7D5 ; Lowercase # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Lowercase # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Lowercase # L& LATIN SMALL LETTER SIGMOID S A7DB ; Lowercase # L& LATIN SMALL LETTER LAMBDA -A7F2..A7F4 ; Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Lowercase # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F6 ; Lowercase # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lowercase # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2138,7 +2138,7 @@ FF41..FF5A ; Lowercase # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L 1E030..1E06D ; Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lowercase # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2569 +# Total code points: 2570 # ================================================ @@ -2914,7 +2914,7 @@ A770 ; Cased # Lm MODIFIER LETTER US A771..A787 ; Cased # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSULAR T A78B..A78E ; Cased # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A790..A7DC ; Cased # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Cased # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Cased # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Cased # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Cased # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Cased # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -2987,7 +2987,7 @@ FF41..FF5A ; Cased # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1F150..1F169 ; Cased # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Cased # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 4581 +# Total code points: 4582 # ================================================ @@ -3274,7 +3274,7 @@ A720..A721 ; Case_Ignorable # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE.. A770 ; Case_Ignorable # Lm MODIFIER LETTER US A788 ; Case_Ignorable # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Case_Ignorable # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN -A7F2..A7F4 ; Case_Ignorable # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Case_Ignorable # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Case_Ignorable # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A802 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN DVISVARA A806 ; Case_Ignorable # Mn SYLOTI NAGRI SIGN HASANTA @@ -3505,7 +3505,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2778 +# Total code points: 2779 # ================================================ @@ -6573,7 +6573,7 @@ A788 ; ID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Start # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; ID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; ID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; ID_Start # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -6970,7 +6970,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141277 +# Total code points: 141278 # ================================================ @@ -7657,7 +7657,7 @@ A788 ; ID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; ID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ID_Continue # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; ID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; ID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; ID_Continue # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -8377,7 +8377,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144578 +# Total code points: 144579 # ================================================ @@ -8751,7 +8751,7 @@ A788 ; XID_Start # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Start # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Start # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; XID_Start # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; XID_Start # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; XID_Start # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Start # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Start # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Start # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -9153,7 +9153,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141254 +# Total code points: 141255 # ================================================ @@ -9835,7 +9835,7 @@ A788 ; XID_Continue # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A78B..A78E ; XID_Continue # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; XID_Continue # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; XID_Continue # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; XID_Continue # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; XID_Continue # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; XID_Continue # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; XID_Continue # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; XID_Continue # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -10561,7 +10561,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144559 +# Total code points: 144560 # ================================================ @@ -11983,7 +11983,7 @@ A789..A78A ; Grapheme_Base # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER A78B..A78E ; Grapheme_Base # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Grapheme_Base # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; Grapheme_Base # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Grapheme_Base # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Grapheme_Base # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Grapheme_Base # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Grapheme_Base # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Grapheme_Base # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -12814,7 +12814,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152739 +# Total code points: 152740 # ================================================ diff --git a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt index 7ee1f72a2..743f1cdcb 100644 --- a/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt +++ b/unicodetools/data/ucd/dev/DerivedNormalizationProps.txt @@ -1,5 +1,5 @@ # DerivedNormalizationProps-17.0.0.txt -# Date: 2024-11-13, 22:03:39 GMT +# Date: 2024-11-13, 22:18:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -132,6 +132,7 @@ 33DD ; FC_NFKC; 0077 0062 # So SQUARE WB 33DE ; FC_NFKC; 0076 2215 006D # So SQUARE V OVER M 33DF ; FC_NFKC; 0061 2215 006D # So SQUARE A OVER M +A7F1 ; FC_NFKC; 0073 # Lm MODIFIER LETTER CAPITAL S A7F2 ; FC_NFKC; 0063 # Lm MODIFIER LETTER CAPITAL C A7F3 ; FC_NFKC; 0066 # Lm MODIFIER LETTER CAPITAL F A7F4 ; FC_NFKC; 0071 # Lm MODIFIER LETTER CAPITAL Q @@ -679,7 +680,7 @@ A7F8 ; FC_NFKC; 0127 # Lm MODIFIER LETTER CAPITAL H WITH STROKE 1F16C ; FC_NFKC; 006D 0072 # So RAISED MR SIGN 1F190 ; FC_NFKC; 0064 006A # So SQUARE DJ -# Total code points: 663 +# Total code points: 664 # ================================================ @@ -1515,7 +1516,7 @@ FB46..FB4E ; NFC_QC; N # Lo [9] HEBREW LETTER TSADI WITH DAGESH..HEBREW LET 32C0..33FF ; NFKD_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKD_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKD_QC; N # Lm MODIFIER LETTER US -A7F2..A7F4 ; NFKD_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; NFKD_QC; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKD_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKD_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKD_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -1753,7 +1754,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKD_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKD_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 17085 +# Total code points: 17086 # ================================================ @@ -1946,7 +1947,7 @@ FFED..FFEE ; NFKD_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 32C0..33FF ; NFKC_QC; N # So [320] IDEOGRAPHIC TELEGRAPH SYMBOL FOR JANUARY..SQUARE GAL A69C..A69D ; NFKC_QC; N # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; NFKC_QC; N # Lm MODIFIER LETTER US -A7F2..A7F4 ; NFKC_QC; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; NFKC_QC; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; NFKC_QC; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; NFKC_QC; N # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; NFKC_QC; N # Lm MODIFIER LETTER SMALL TURNED W @@ -2164,7 +2165,7 @@ FFED..FFEE ; NFKC_QC; N # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CI 1FBF0..1FBF9 ; NFKC_QC; N # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE 2F800..2FA1D ; NFKC_QC; N # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D -# Total code points: 4964 +# Total code points: 4965 # ================================================ @@ -5456,6 +5457,7 @@ A7D6 ; NFKC_CF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE S A7D8 ; NFKC_CF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_CF; A7DB # L& LATIN CAPITAL LETTER LAMBDA A7DC ; NFKC_CF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1 ; NFKC_CF; 0073 # Lm MODIFIER LETTER CAPITAL S A7F2 ; NFKC_CF; 0063 # Lm MODIFIER LETTER CAPITAL C A7F3 ; NFKC_CF; 0066 # Lm MODIFIER LETTER CAPITAL F A7F4 ; NFKC_CF; 0071 # Lm MODIFIER LETTER CAPITAL Q @@ -9151,7 +9153,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] .... -# Total code points: 10557 +# Total code points: 10558 # ================================================ @@ -11593,6 +11595,7 @@ A7D6 ; NFKC_SCF; A7D7 # L& LATIN CAPITAL LETTER MIDDLE A7D8 ; NFKC_SCF; A7D9 # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; NFKC_SCF; A7DB # L& LATIN CAPITAL LETTER LAMBDA A7DC ; NFKC_SCF; 019B # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1 ; NFKC_SCF; 0073 # Lm MODIFIER LETTER CAPITAL S A7F2 ; NFKC_SCF; 0063 # Lm MODIFIER LETTER CAPITAL C A7F3 ; NFKC_SCF; 0066 # Lm MODIFIER LETTER CAPITAL F A7F4 ; NFKC_SCF; 0071 # Lm MODIFIER LETTER CAPITAL Q @@ -15288,7 +15291,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] .... -# Total code points: 10519 +# Total code points: 10520 # ================================================ @@ -16066,7 +16069,7 @@ A7D6 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER MID A7D8 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER SIGMOID S A7DA ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA A7DC ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Changes_When_NFKC_Casefolded # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5 ; Changes_When_NFKC_Casefolded # L& LATIN CAPITAL LETTER REVERSED HALF H A7F8..A7F9 ; Changes_When_NFKC_Casefolded # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Changes_When_NFKC_Casefolded # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK @@ -16309,6 +16312,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] .... -# Total code points: 10557 +# Total code points: 10558 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 4a39b0c77..8fe7aeb60 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:03:40 GMT +# Date: 2024-11-13, 22:18:48 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1550,7 +1550,7 @@ A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index dd2c46881..54860f25a 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 22:03:41 GMT +# Date: 2024-11-13, 22:18:49 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1577,7 +1577,7 @@ A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; AL # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 768ef03d4..dd98635df 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-17.0.0.txt -# Date: 2024-11-13, 21:22:57 GMT +# Date: 2024-11-13, 22:18:53 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2429,6 +2429,7 @@ FEFA 0334;FEFA 0334;FEFA 0334;0644 0625 0334;0644 0627 0334 0655; # (ﻺ◌̴; A69C;A69C;A69C;044A;044A; # (ꚜ; ꚜ; ꚜ; ъ; ъ; ) MODIFIER LETTER CYRILLIC HARD SIGN A69D;A69D;A69D;044C;044C; # (ꚝ; ꚝ; ꚝ; ь; ь; ) MODIFIER LETTER CYRILLIC SOFT SIGN A770;A770;A770;A76F;A76F; # (ꝰ; ꝰ; ꝰ; ꝯ; ꝯ; ) MODIFIER LETTER US +A7F1;A7F1;A7F1;0053;0053; # (꟱; ꟱; ꟱; S; S; ) MODIFIER LETTER CAPITAL S A7F2;A7F2;A7F2;0043;0043; # (ꟲ; ꟲ; ꟲ; C; C; ) MODIFIER LETTER CAPITAL C A7F3;A7F3;A7F3;0046;0046; # (ꟳ; ꟳ; ꟳ; F; F; ) MODIFIER LETTER CAPITAL F A7F4;A7F4;A7F4;0051;0051; # (ꟴ; ꟴ; ꟴ; Q; Q; ) MODIFIER LETTER CAPITAL Q diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 1cbd57d2a..7744fcc3e 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-17.0.0.txt -# Date: 2024-11-13, 21:35:23 GMT +# Date: 2024-11-13, 22:18:57 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1036,6 +1036,7 @@ A717..A71F ; Diacritic # Lm [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER A720..A721 ; Diacritic # Sk [2] MODIFIER LETTER STRESS AND HIGH TONE..MODIFIER LETTER STRESS AND LOW TONE A788 ; Diacritic # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A789..A78A ; Diacritic # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS SIGN +A7F1 ; Diacritic # Lm MODIFIER LETTER CAPITAL S A7F8..A7F9 ; Diacritic # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A806 ; Diacritic # Mn SYLOTI NAGRI SIGN HASANTA A82C ; Diacritic # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA @@ -1152,7 +1153,7 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1207 +# Total code points: 1208 # ================================================ @@ -1222,7 +1223,7 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 2C7C..2C7D ; Other_Lowercase # Lm [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V A69C..A69D ; Other_Lowercase # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; Other_Lowercase # Lm MODIFIER LETTER US -A7F2..A7F4 ; Other_Lowercase # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Other_Lowercase # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Other_Lowercase # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Other_Lowercase # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W @@ -1232,7 +1233,7 @@ AB69 ; Other_Lowercase # Lm MODIFIER LETTER SMALL TURNED W 107B2..107BA ; Other_Lowercase # Lm [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 1E030..1E06D ; Other_Lowercase # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE -# Total code points: 311 +# Total code points: 312 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index e199ef2b4..13a5ce001 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 22:04:03 GMT +# Date: 2024-11-13, 22:19:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -676,7 +676,7 @@ A771..A787 ; Latin # L& [23] LATIN SMALL LETTER DUM..LATIN SMALL LETTER INSU A78B..A78E ; Latin # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; Latin # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; Latin # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; Latin # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Latin # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; Latin # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; Latin # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; Latin # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -698,7 +698,7 @@ FF41..FF5A ; Latin # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1DF0B..1DF1E ; Latin # L& [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL 1DF25..1DF2A ; Latin # L& [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK -# Total code points: 1491 +# Total code points: 1492 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 66dc3c27d..f366c3da2 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -14323,6 +14323,7 @@ A7D9;LATIN SMALL LETTER SIGMOID S;Ll;0;L;;;;;N;;;A7D8;;A7D8 A7DA;LATIN CAPITAL LETTER LAMBDA;Lu;0;L;;;;;N;;;;A7DB; A7DB;LATIN SMALL LETTER LAMBDA;Ll;0;L;;;;;N;;;A7DA;;A7DA A7DC;LATIN CAPITAL LETTER LAMBDA WITH STROKE;Lu;0;L;;;;;N;;;;019B; +A7F1;MODIFIER LETTER CAPITAL S;Lm;0;L; 0053;;;;N;;;;; A7F2;MODIFIER LETTER CAPITAL C;Lm;0;L; 0043;;;;N;;;;; A7F3;MODIFIER LETTER CAPITAL F;Lm;0;L; 0046;;;;N;;;;; A7F4;MODIFIER LETTER CAPITAL Q;Lm;0;L; 0051;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index d6167b1f8..9e6eec88a 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 22:04:05 GMT +# Date: 2024-11-13, 22:19:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1359,7 +1359,7 @@ A789..A78A ; R # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQ A78B..A78E ; R # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; R # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; R # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; R # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; R # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; R # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; R # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; R # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 76b500a96..44f556893 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 22:04:04 GMT +# Date: 2024-11-13, 22:19:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1262,7 +1262,7 @@ A7D5 ; Lower # L& LATIN SMALL LETTER DOUBLE WYNN A7D7 ; Lower # L& LATIN SMALL LETTER MIDDLE SCOTS S A7D9 ; Lower # L& LATIN SMALL LETTER SIGMOID S A7DB ; Lower # L& LATIN SMALL LETTER LAMBDA -A7F2..A7F4 ; Lower # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Lower # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F6 ; Lower # L& LATIN SMALL LETTER REVERSED HALF H A7F8..A7F9 ; Lower # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A7FA ; Lower # L& LATIN LETTER SMALL CAPITAL TURNED M @@ -1322,7 +1322,7 @@ FF41..FF5A ; Lower # L& [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN 1E030..1E06D ; Lower # Lm [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1E922..1E943 ; Lower # L& [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 2522 +# Total code points: 2523 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 211ba68df..6ddc428da 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 22:04:06 GMT +# Date: 2024-11-13, 22:19:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1005,7 +1005,7 @@ A789..A78A ; ALetter # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT A78B..A78E ; ALetter # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; ALetter # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; ALetter # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; ALetter # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; ALetter # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; ALetter # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; ALetter # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; ALetter # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1354,7 +1354,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33799 +# Total code points: 33800 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 97d173eb6..07e2f9666 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 22:03:33 GMT +# Date: 2024-11-13, 22:18:42 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -664,7 +664,7 @@ A789..A78A ; L # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS A78B..A78E ; L # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; L # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; L # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; L # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; L # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; L # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; L # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; L # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1212,7 +1212,7 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 815314 code points not listed here. +# The above property value applies to 815313 code points not listed here. # Total code points: 1095483 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index dc20c62a1..08ede4e2b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 22:03:35 GMT +# Date: 2024-11-13, 22:18:43 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1094,7 +1094,7 @@ A789..A78A ; 0 # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS A78B..A78E ; 0 # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; 0 # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; 0 # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; 0 # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; 0 # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; 0 # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; 0 # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; 0 # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -2057,7 +2057,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821543 code points not listed here. +# The above property value applies to 821542 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt index a825479ac..1b8d1ae99 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedDecompositionType.txt @@ -1,5 +1,5 @@ -# DerivedDecompositionType-16.0.0.txt -# Date: 2024-04-30, 21:48:17 GMT +# DerivedDecompositionType-17.0.0.txt +# Date: 2024-11-13, 22:18:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -873,7 +873,7 @@ FEFB ; Isolated # Lo ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM 3196..319F ; Super # So [10] IDEOGRAPHIC ANNOTATION TOP MARK..IDEOGRAPHIC ANNOTATION MAN MARK A69C..A69D ; Super # Lm [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN A770 ; Super # Lm MODIFIER LETTER US -A7F2..A7F4 ; Super # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Super # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Super # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE AB5C..AB5F ; Super # Lm [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK AB69 ; Super # Lm MODIFIER LETTER SMALL TURNED W @@ -884,7 +884,7 @@ AB69 ; Super # Lm MODIFIER LETTER SMALL TURNED W 1E06B..1E06D ; Super # Lm [3] MODIFIER LETTER CYRILLIC SMALL ES WITH DESCENDER..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE 1F16A..1F16C ; Super # So [3] RAISED MC SIGN..RAISED MR SIGN -# Total code points: 249 +# Total code points: 250 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 3e5013b07..0ff7edb44 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:03:37 GMT +# Date: 2024-11-13, 22:18:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1184,7 +1184,7 @@ A789..A78A ; N # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUALS A78B..A78E ; N # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; N # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; N # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; N # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; N # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; N # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; N # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; N # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -2101,7 +2101,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761061 code points not listed here. +# The above property value applies to 761060 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 5c4d67c71..3b9741ec5 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 22:03:37 GMT +# Date: 2024-11-13, 22:18:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -293,7 +293,7 @@ A48D..A48F ; Cn # [3] .. A4C7..A4CF ; Cn # [9] .. A62C..A63F ; Cn # [20] .. A6F8..A6FF ; Cn # [8] .. -A7DD..A7F1 ; Cn # [21] .. +A7DD..A7F0 ; Cn # [20] .. A82D..A82F ; Cn # [3] .. A83A..A83F ; Cn # [6] .. A878..A87F ; Cn # [8] .. @@ -743,7 +743,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819495 +# Total code points: 819494 # ================================================ @@ -2143,7 +2143,7 @@ A69C..A69D ; Lm # [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER C A717..A71F ; Lm # [9] MODIFIER LETTER DOT VERTICAL BAR..MODIFIER LETTER LOW INVERTED EXCLAMATION MARK A770 ; Lm # MODIFIER LETTER US A788 ; Lm # MODIFIER LETTER LOW CIRCUMFLEX ACCENT -A7F2..A7F4 ; Lm # [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; Lm # [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F8..A7F9 ; Lm # [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE A9CF ; Lm # JAVANESE PANGRANGKEP A9E6 ; Lm # MYANMAR MODIFIER LETTER SHAN REDUPLICATION @@ -2173,7 +2173,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 404 +# Total code points: 405 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index fa995911f..59a9dd70f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 22:03:38 GMT +# Date: 2024-11-13, 22:18:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757615 code points not listed here. -# Total code points: 895083 +# The above property value applies to 757614 code points not listed here. +# Total code points: 895082 # ================================================ @@ -1142,7 +1142,7 @@ A789..A78A ; AL # Sk [2] MODIFIER LETTER COLON..MODIFIER LETTER SHORT EQUAL A78B..A78E ; AL # L& [4] LATIN CAPITAL LETTER SALTILLO..LATIN SMALL LETTER L WITH RETROFLEX HOOK AND BELT A78F ; AL # Lo LATIN LETTER SINOLOGICAL DOT A790..A7DC ; AL # L& [77] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN CAPITAL LETTER LAMBDA WITH STROKE -A7F2..A7F4 ; AL # Lm [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q +A7F1..A7F4 ; AL # Lm [4] MODIFIER LETTER CAPITAL S..MODIFIER LETTER CAPITAL Q A7F5..A7F6 ; AL # L& [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H A7F7 ; AL # Lo LATIN EPIGRAPHIC LETTER SIDEWAYS I A7F8..A7F9 ; AL # Lm [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE @@ -1611,7 +1611,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26688 +# Total code points: 26689 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 191c963dd..c79c68ffc 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 22:03:38 GMT +# Date: 2024-11-13, 22:18:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -14296,6 +14296,7 @@ A7D9 ; LATIN SMALL LETTER SIGMOID S A7DA ; LATIN CAPITAL LETTER LAMBDA A7DB ; LATIN SMALL LETTER LAMBDA A7DC ; LATIN CAPITAL LETTER LAMBDA WITH STROKE +A7F1 ; MODIFIER LETTER CAPITAL S A7F2 ; MODIFIER LETTER CAPITAL C A7F3 ; MODIFIER LETTER CAPITAL F A7F4 ; MODIFIER LETTER CAPITAL Q @@ -45405,6 +45406,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155036 +# Total code points: 155037 # EOF From 399ba7f8e9b0900898167e26c9ee075beb666c18 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 00:04:04 +0100 Subject: [PATCH 21/26] Twenty-five more Arabic honorifics (#705) * UnicodeData.txt lines from Roozbeh * lb=AL like the other honorifics * Scripts.txt * Regenerate UCD * Fix spelling for unicode-org/sah#484 * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 7 +++-- .../data/ucd/dev/DerivedCoreProperties.txt | 7 +++-- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 +++- unicodetools/data/ucd/dev/LineBreak.txt | 5 +++- unicodetools/data/ucd/dev/Scripts.txt | 7 +++-- unicodetools/data/ucd/dev/UnicodeData.txt | 25 ++++++++++++++++ .../data/ucd/dev/VerticalOrientation.txt | 5 +++- .../ucd/dev/extracted/DerivedBidiClass.txt | 11 ++++--- .../dev/extracted/DerivedCombiningClass.txt | 7 +++-- .../dev/extracted/DerivedEastAsianWidth.txt | 7 +++-- .../dev/extracted/DerivedGeneralCategory.txt | 15 ++++++---- .../ucd/dev/extracted/DerivedLineBreak.txt | 11 ++++--- .../data/ucd/dev/extracted/DerivedName.txt | 29 +++++++++++++++++-- 13 files changed, 112 insertions(+), 29 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index c4be3a7a0..a072b4d64 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 22:18:26 GMT +# Date: 2024-11-13, 22:47:02 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2077,7 +2077,10 @@ A7CE..A7CF ; 17.0 # [2] LATIN CAPITAL LETTER PHARYNGEAL VOICED FRICATIVE..L A7D2 ; 17.0 # LATIN CAPITAL LETTER DOUBLE THORN A7D4 ; 17.0 # LATIN CAPITAL LETTER DOUBLE WYNN A7F1 ; 17.0 # MODIFIER LETTER CAPITAL S +FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH +FD91 ; 17.0 # ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -# Total code points: 39 +# Total code points: 64 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 0893db2d0..425b65947 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 22:18:44 GMT +# Date: 2024-11-13, 22:47:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -12099,11 +12099,13 @@ FB40..FB41 ; Grapheme_Base # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW L FB43..FB44 ; Grapheme_Base # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; Grapheme_Base # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; Grapheme_Base # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; Grapheme_Base # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; Grapheme_Base # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; Grapheme_Base # Pe ORNATE LEFT PARENTHESIS FD3F ; Grapheme_Base # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; Grapheme_Base # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Grapheme_Base # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; Grapheme_Base # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; Grapheme_Base # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; Grapheme_Base # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Grapheme_Base # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -12332,6 +12334,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10EAD ; Grapheme_Base # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; Grapheme_Base # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Grapheme_Base # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; Grapheme_Base # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; Grapheme_Base # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; Grapheme_Base # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; Grapheme_Base # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -12814,7 +12817,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152740 +# Total code points: 152765 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 8fe7aeb60..345bcf401 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:18:48 GMT +# Date: 2024-11-13, 22:47:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1707,11 +1707,13 @@ FB43..FB44 ; N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETT FB46..FB4F ; N # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1 ; N # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; N # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; N # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; N # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; N # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -1962,6 +1964,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC..10EFF ; N # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 54860f25a..4d5561bb5 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 22:18:49 GMT +# Date: 2024-11-13, 22:47:25 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2536,11 +2536,13 @@ FB43..FB44 ; HL # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETT FB46..FB4F ; HL # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; AL # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; AL # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; CL # Pe ORNATE LEFT PARENTHESIS FD3F ; OP # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; AL # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -2819,6 +2821,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10EAD ; BA # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 13a5ce001..e27f7901f 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 22:19:09 GMT +# Date: 2024-11-13, 22:47:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -874,9 +874,11 @@ FB46..FB4F ; Hebrew # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATU 08E3..08FF ; Arabic # Mn [29] ARABIC TURNED DAMMA BELOW..ARABIC MARK SIDEWAYS NOON GHUNNA FB50..FBB1 ; Arabic # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; Arabic # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; Arabic # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD40..FD4F ; Arabic # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Arabic # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; Arabic # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; Arabic # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; Arabic # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Arabic # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -886,6 +888,7 @@ FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM 10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10EC2..10EC4 ; Arabic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; Arabic # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC..10EFF ; Arabic # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF @@ -922,7 +925,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1374 +# Total code points: 1399 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index f366c3da2..29743503b 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -15964,6 +15964,22 @@ FBBF;ARABIC SYMBOL RING;Sk;0;AL;;;;;N;;;;; FBC0;ARABIC SYMBOL SMALL TAH ABOVE;Sk;0;AL;;;;;N;;;;; FBC1;ARABIC SYMBOL SMALL TAH BELOW;Sk;0;AL;;;;;N;;;;; FBC2;ARABIC SYMBOL WASLA ABOVE;Sk;0;AL;;;;;N;;;;; +FBC3;ARABIC LIGATURE JALLA WA-ALAA;So;0;ON;;;;;N;;;;; +FBC4;ARABIC LIGATURE DAAMAT BARAKAATUHUM;So;0;ON;;;;;N;;;;; +FBC5;ARABIC LIGATURE RAHMATU ALLAAHI TAAALAA ALAYH;So;0;ON;;;;;N;;;;; +FBC6;ARABIC LIGATURE RAHMATU ALLAAHI ALAYHIM;So;0;ON;;;;;N;;;;; +FBC7;ARABIC LIGATURE RAHMATU ALLAAHI ALAYHIMAA;So;0;ON;;;;;N;;;;; +FBC8;ARABIC LIGATURE RAHIMAHUM ALLAAHU TAAALAA;So;0;ON;;;;;N;;;;; +FBC9;ARABIC LIGATURE RAHIMAHUMAA ALLAAH;So;0;ON;;;;;N;;;;; +FBCA;ARABIC LIGATURE RAHIMAHUMAA ALLAAHU TAAALAA;So;0;ON;;;;;N;;;;; +FBCB;ARABIC LIGATURE RADI ALLAHU TAAALAA ANHUM;So;0;ON;;;;;N;;;;; +FBCC;ARABIC LIGATURE HAFIZAHU ALLAAH;So;0;ON;;;;;N;;;;; +FBCD;ARABIC LIGATURE HAFIZAHU ALLAAHU TAAALAA;So;0;ON;;;;;N;;;;; +FBCE;ARABIC LIGATURE HAFIZAHUM ALLAAHU TAAALAA;So;0;ON;;;;;N;;;;; +FBCF;ARABIC LIGATURE HAFIZAHUMAA ALLAAHU TAAALAA;So;0;ON;;;;;N;;;;; +FBD0;ARABIC LIGATURE SALLALLAAHU TAAALAA ALAYHI WA-SALLAM;So;0;ON;;;;;N;;;;; +FBD1;ARABIC LIGATURE AJJAL ALLAAHU FARAJAHU ASH-SHAREEF;So;0;ON;;;;;N;;;;; +FBD2;ARABIC LIGATURE ALAYHI AR-RAHMAH;So;0;ON;;;;;N;;;;; FBD3;ARABIC LETTER NG ISOLATED FORM;Lo;0;AL; 06AD;;;;N;;;;; FBD4;ARABIC LETTER NG FINAL FORM;Lo;0;AL; 06AD;;;;N;;;;; FBD5;ARABIC LETTER NG INITIAL FORM;Lo;0;AL; 06AD;;;;N;;;;; @@ -16409,6 +16425,7 @@ FD8C;ARABIC LIGATURE MEEM WITH JEEM WITH HAH INITIAL FORM;Lo;0;AL; 0645 FD8D;ARABIC LIGATURE MEEM WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0645 062C 0645;;;;N;;;;; FD8E;ARABIC LIGATURE MEEM WITH KHAH WITH JEEM INITIAL FORM;Lo;0;AL; 0645 062E 062C;;;;N;;;;; FD8F;ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM;Lo;0;AL; 0645 062E 0645;;;;N;;;;; +FD91;ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA;So;0;ON;;;;;N;;;;; FD92;ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM;Lo;0;AL; 0645 062C 062E;;;;N;;;;; FD93;ARABIC LIGATURE HEH WITH MEEM WITH JEEM INITIAL FORM;Lo;0;AL; 0647 0645 062C;;;;N;;;;; FD94;ARABIC LIGATURE HEH WITH MEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0647 0645 0645;;;;N;;;;; @@ -19580,6 +19597,14 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10EC2;ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC3;ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC4;ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; +10ED1;ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; +10ED2;ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; +10ED3;ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; +10ED4;ARABIC LIGATURE QADDASA ALLAAHU SIRRAH;So;0;ON;;;;;N;;;;; +10ED5;ARABIC LIGATURE QUDDISA SIRRAHUM;So;0;ON;;;;;N;;;;; +10ED6;ARABIC LIGATURE QUDDISA SIRRAHUMAA;So;0;ON;;;;;N;;;;; +10ED7;ARABIC LIGATURE QUDDISAT ASRAARUHUM;So;0;ON;;;;;N;;;;; +10ED8;ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH;So;0;ON;;;;;N;;;;; 10EFC;ARABIC COMBINING ALEF OVERLAY;Mn;0;NSM;;;;;N;;;;; 10EFD;ARABIC SMALL LOW WORD SAKTA;Mn;220;NSM;;;;;N;;;;; 10EFE;ARABIC SMALL LOW WORD QASR;Mn;220;NSM;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 9e6eec88a..adae42e8b 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 22:19:12 GMT +# Date: 2024-11-13, 22:47:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1520,11 +1520,13 @@ FB43..FB44 ; R # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETT FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED FB50..FBB1 ; R # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; R # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; R # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; R # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; R # Pe ORNATE LEFT PARENTHESIS FD3F ; R # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; R # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; R # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; R # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; R # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; R # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; R # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -1783,6 +1785,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10EAD ; R # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; R # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; R # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC..10EFF ; R # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; R # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; R # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 07e2f9666..dfd8e2821 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 22:18:42 GMT +# Date: 2024-11-13, 22:47:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1843,9 +1843,11 @@ A788 ; ON # Lm MODIFIER LETTER LOW CIRCUMFLEX ACCENT A828..A82B ; ON # So [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK-4 A874..A877 ; ON # Po [4] PHAGS-PA SINGLE HEAD MARK..PHAGS-PA MARK DOUBLE SHAD AB6A..AB6B ; ON # Sk [2] MODIFIER LETTER LEFT TACK..MODIFIER LETTER RIGHT TACK +FBC3..FBD2 ; ON # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD3E ; ON # Pe ORNATE LEFT PARENTHESIS FD3F ; ON # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; ON # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FD91 ; ON # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDCF ; ON # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDFD..FDFF ; ON # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE10..FE16 ; ON # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK @@ -1933,6 +1935,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1091F ; ON # Po PHOENICIAN WORD SEPARATOR 10B39..10B3F ; ON # Po [7] AVESTAN ABBREVIATION MARK..LARGE ONE RING OVER TWO RINGS PUNCTUATION 10D6E ; ON # Pd GARAY HYPHEN +10ED1..10ED8 ; ON # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 11052..11065 ; ON # No [20] BRAHMI NUMBER ONE..BRAHMI NUMBER ONE THOUSAND 11660..1166C ; ON # Po [13] MONGOLIAN BIRGA WITH ORNAMENT..MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT 11FD5..11FDC ; ON # So [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI @@ -1994,7 +1997,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; ON # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 6752 +# Total code points: 6777 # ================================================ @@ -2499,8 +2502,8 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 292 code points not listed here. -# Total code points: 1767 +# The above property value applies to 267 code points not listed here. +# Total code points: 1742 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 08ede4e2b..dd9824c6d 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 22:18:43 GMT +# Date: 2024-11-13, 22:47:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1231,11 +1231,13 @@ FB40..FB41 ; 0 # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH FB43..FB44 ; 0 # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; 0 # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; 0 # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; 0 # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; 0 # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; 0 # Pe ORNATE LEFT PARENTHESIS FD3F ; 0 # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; 0 # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; 0 # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; 0 # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; 0 # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; 0 # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; 0 # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -1472,6 +1474,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10EAD ; 0 # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; 0 # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; 0 # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; 0 # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC ; 0 # Mn ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; 0 # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; 0 # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -2057,7 +2060,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821542 code points not listed here. +# The above property value applies to 821517 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 0ff7edb44..a53658c73 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:18:45 GMT +# Date: 2024-11-13, 22:47:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1328,11 +1328,13 @@ FB40..FB41 ; N # Lo [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH FB43..FB44 ; N # Lo [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH FB46..FBB1 ; N # Lo [108] HEBREW LETTER TSADI WITH DAGESH..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; N # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; N # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; N # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; N # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -1484,6 +1486,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC..10EFF ; N # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -2101,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761060 code points not listed here. +# The above property value applies to 761035 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 3b9741ec5..e65d152ca 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 22:18:45 GMT +# Date: 2024-11-13, 22:47:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -329,8 +329,7 @@ FB3D ; Cn # FB3F ; Cn # FB42 ; Cn # FB45 ; Cn # -FBC3..FBD2 ; Cn # [16] .. -FD90..FD91 ; Cn # [2] .. +FD90 ; Cn # FDC8..FDCE ; Cn # [7] .. FDD0..FDEF ; Cn # [32] .. FE1A..FE1F ; Cn # [6] .. @@ -435,7 +434,8 @@ FFFE..FFFF ; Cn # [2] .. 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. -10EC5..10EFB ; Cn # [55] .. +10EC5..10ED0 ; Cn # [12] .. +10ED9..10EFB ; Cn # [35] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. 10F8A..10FAF ; Cn # [38] .. @@ -743,7 +743,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819494 +# Total code points: 819469 # ================================================ @@ -4204,7 +4204,9 @@ A828..A82B ; So # [4] SYLOTI NAGRI POETRY MARK-1..SYLOTI NAGRI POETRY MARK- A836..A837 ; So # [2] NORTH INDIC QUARTER MARK..NORTH INDIC PLACEHOLDER MARK A839 ; So # NORTH INDIC QUANTITY MARK AA77..AA79 ; So # [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO +FBC3..FBD2 ; So # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD40..FD4F ; So # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH +FD91 ; So # ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDCF ; So # ARABIC LIGATURE SALAAMUHU ALAYNAA FDFD..FDFF ; So # [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FFE4 ; So # FULLWIDTH BROKEN BAR @@ -4219,6 +4221,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 101D0..101FC ; So # [45] PHAISTOS DISC SIGN PEDESTRIAN..PHAISTOS DISC SIGN WAVY BAND 10877..10878 ; So # [2] PALMYRENE LEFT-POINTING FLEURON..PALMYRENE RIGHT-POINTING FLEURON 10AC8 ; So # MANICHAEAN SIGN UD +10ED1..10ED8 ; So # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 1173F ; So # AHOM SYMBOL VI 11FD5..11FDC ; So # [8] TAMIL SIGN NEL..TAMIL SIGN MUKKURUNI 11FE1..11FF1 ; So # [17] TAMIL SIGN PAARAM..TAMIL SIGN VAKAIYARAA @@ -4284,7 +4287,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; So # [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 7377 +# Total code points: 7402 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 59a9dd70f..c2824ccc7 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 22:18:46 GMT +# Date: 2024-11-13, 22:47:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757614 code points not listed here. -# Total code points: 895082 +# The above property value applies to 757589 code points not listed here. +# Total code points: 895057 # ================================================ @@ -1185,9 +1185,11 @@ FB13..FB17 ; AL # L& [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LI FB29 ; AL # Sm HEBREW LETTER ALTERNATIVE PLUS SIGN FB50..FBB1 ; AL # Lo [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM FBB2..FBC2 ; AL # Sk [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE +FBC3..FBD2 ; AL # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3..FD3D ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD40..FD4F ; AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; AL # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM FDCF ; AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU @@ -1313,6 +1315,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -1611,7 +1614,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26689 +# Total code points: 26714 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index c79c68ffc..d31ed38a4 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 22:18:47 GMT +# Date: 2024-11-13, 22:47:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -26629,6 +26629,22 @@ FBBF ; ARABIC SYMBOL RING FBC0 ; ARABIC SYMBOL SMALL TAH ABOVE FBC1 ; ARABIC SYMBOL SMALL TAH BELOW FBC2 ; ARABIC SYMBOL WASLA ABOVE +FBC3 ; ARABIC LIGATURE JALLA WA-ALAA +FBC4 ; ARABIC LIGATURE DAAMAT BARAKAATUHUM +FBC5 ; ARABIC LIGATURE RAHMATU ALLAAHI TAAALAA ALAYH +FBC6 ; ARABIC LIGATURE RAHMATU ALLAAHI ALAYHIM +FBC7 ; ARABIC LIGATURE RAHMATU ALLAAHI ALAYHIMAA +FBC8 ; ARABIC LIGATURE RAHIMAHUM ALLAAHU TAAALAA +FBC9 ; ARABIC LIGATURE RAHIMAHUMAA ALLAAH +FBCA ; ARABIC LIGATURE RAHIMAHUMAA ALLAAHU TAAALAA +FBCB ; ARABIC LIGATURE RADI ALLAHU TAAALAA ANHUM +FBCC ; ARABIC LIGATURE HAFIZAHU ALLAAH +FBCD ; ARABIC LIGATURE HAFIZAHU ALLAAHU TAAALAA +FBCE ; ARABIC LIGATURE HAFIZAHUM ALLAAHU TAAALAA +FBCF ; ARABIC LIGATURE HAFIZAHUMAA ALLAAHU TAAALAA +FBD0 ; ARABIC LIGATURE SALLALLAAHU TAAALAA ALAYHI WA-SALLAM +FBD1 ; ARABIC LIGATURE AJJAL ALLAAHU FARAJAHU ASH-SHAREEF +FBD2 ; ARABIC LIGATURE ALAYHI AR-RAHMAH FBD3 ; ARABIC LETTER NG ISOLATED FORM FBD4 ; ARABIC LETTER NG FINAL FORM FBD5 ; ARABIC LETTER NG INITIAL FORM @@ -27074,6 +27090,7 @@ FD8C ; ARABIC LIGATURE MEEM WITH JEEM WITH HAH INITIAL FORM FD8D ; ARABIC LIGATURE MEEM WITH JEEM WITH MEEM INITIAL FORM FD8E ; ARABIC LIGATURE MEEM WITH KHAH WITH JEEM INITIAL FORM FD8F ; ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD91 ; ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92 ; ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM FD93 ; ARABIC LIGATURE HEH WITH MEEM WITH JEEM INITIAL FORM FD94 ; ARABIC LIGATURE HEH WITH MEEM WITH MEEM INITIAL FORM @@ -30245,6 +30262,14 @@ FFFD ; REPLACEMENT CHARACTER 10EC2 ; ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW 10EC3 ; ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW 10EC4 ; ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10ED1 ; ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM +10ED2 ; ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM +10ED3 ; ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM +10ED4 ; ARABIC LIGATURE QADDASA ALLAAHU SIRRAH +10ED5 ; ARABIC LIGATURE QUDDISA SIRRAHUM +10ED6 ; ARABIC LIGATURE QUDDISA SIRRAHUMAA +10ED7 ; ARABIC LIGATURE QUDDISAT ASRAARUHUM +10ED8 ; ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC ; ARABIC COMBINING ALEF OVERLAY 10EFD ; ARABIC SMALL LOW WORD SAKTA 10EFE ; ARABIC SMALL LOW WORD QASR @@ -45406,6 +45431,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155037 +# Total code points: 155062 # EOF From 5e7b13af05493541795c1158cd07e7fec4a91787 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 15:36:03 +0100 Subject: [PATCH 22/26] Eight more Arabic honorifics (#662) * UnicodeData.txt lines from L2/24-002 * lb=AL like U+FDFD per L2/24-002 * Arabic * Regenerate UCD * Fix spelling for unicode-org/sah#484 * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 7 ++++--- unicodetools/data/ucd/dev/DerivedCoreProperties.txt | 8 ++++---- unicodetools/data/ucd/dev/EastAsianWidth.txt | 6 +++--- unicodetools/data/ucd/dev/LineBreak.txt | 6 +++--- unicodetools/data/ucd/dev/Scripts.txt | 8 ++++---- unicodetools/data/ucd/dev/UnicodeData.txt | 8 ++++++++ unicodetools/data/ucd/dev/VerticalOrientation.txt | 6 +++--- .../data/ucd/dev/extracted/DerivedBidiClass.txt | 12 ++++++------ .../data/ucd/dev/extracted/DerivedCombiningClass.txt | 8 ++++---- .../data/ucd/dev/extracted/DerivedEastAsianWidth.txt | 8 ++++---- .../ucd/dev/extracted/DerivedGeneralCategory.txt | 12 +++++------- .../data/ucd/dev/extracted/DerivedLineBreak.txt | 12 ++++++------ unicodetools/data/ucd/dev/extracted/DerivedName.txt | 12 ++++++++++-- 13 files changed, 64 insertions(+), 49 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index a072b4d64..b69576b8f 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-13, 22:47:02 GMT +# Date: 2024-11-14, 12:16:05 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2078,9 +2078,10 @@ A7D2 ; 17.0 # LATIN CAPITAL LETTER DOUBLE THORN A7D4 ; 17.0 # LATIN CAPITAL LETTER DOUBLE WYNN A7F1 ; 17.0 # MODIFIER LETTER CAPITAL S FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH -FD91 ; 17.0 # ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -# Total code points: 64 +# Total code points: 72 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 425b65947..ddd0bed1b 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-13, 22:47:20 GMT +# Date: 2024-11-14, 12:16:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -12105,9 +12105,9 @@ FD3E ; Grapheme_Base # Pe ORNATE LEFT PARENTHESIS FD3F ; Grapheme_Base # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; Grapheme_Base # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Grapheme_Base # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; Grapheme_Base # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; Grapheme_Base # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; Grapheme_Base # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; Grapheme_Base # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; Grapheme_Base # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Grapheme_Base # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; Grapheme_Base # Sc RIAL SIGN FDFD..FDFF ; Grapheme_Base # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL @@ -12817,7 +12817,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152765 +# Total code points: 152773 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 345bcf401..962986fa9 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:47:24 GMT +# Date: 2024-11-14, 12:16:27 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1713,9 +1713,9 @@ FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; N # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; N # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; N # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; N # Sc RIAL SIGN FDFD..FDFF ; N # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 4d5561bb5..4f0edadf4 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-13, 22:47:25 GMT +# Date: 2024-11-14, 12:16:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2542,9 +2542,9 @@ FD3E ; CL # Pe ORNATE LEFT PARENTHESIS FD3F ; OP # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; AL # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; AL # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; AL # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; PO # Sc RIAL SIGN FDFD..FDFF ; AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index e27f7901f..d7cf7e07c 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-13, 22:47:45 GMT +# Date: 2024-11-14, 12:16:50 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -878,9 +878,9 @@ FBC3..FBD2 ; Arabic # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE FBD3..FD3D ; Arabic # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD40..FD4F ; Arabic # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; Arabic # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; Arabic # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; Arabic # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; Arabic # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; Arabic # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; Arabic # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; Arabic # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; Arabic # Sc RIAL SIGN FDFD..FDFF ; Arabic # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL @@ -925,7 +925,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1399 +# Total code points: 1407 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 29743503b..ec9c0e0f3 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -16425,6 +16425,7 @@ FD8C;ARABIC LIGATURE MEEM WITH JEEM WITH HAH INITIAL FORM;Lo;0;AL; 0645 FD8D;ARABIC LIGATURE MEEM WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0645 062C 0645;;;;N;;;;; FD8E;ARABIC LIGATURE MEEM WITH KHAH WITH JEEM INITIAL FORM;Lo;0;AL; 0645 062E 062C;;;;N;;;;; FD8F;ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM;Lo;0;AL; 0645 062E 0645;;;;N;;;;; +FD90;ARABIC LIGATURE RAHMATU ALLAAHI ALAYH;So;0;ON;;;;;N;;;;; FD91;ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA;So;0;ON;;;;;N;;;;; FD92;ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM;Lo;0;AL; 0645 062C 062E;;;;N;;;;; FD93;ARABIC LIGATURE HEH WITH MEEM WITH JEEM INITIAL FORM;Lo;0;AL; 0647 0645 062C;;;;N;;;;; @@ -16480,6 +16481,13 @@ FDC4;ARABIC LIGATURE AIN WITH JEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0639 FDC5;ARABIC LIGATURE SAD WITH MEEM WITH MEEM INITIAL FORM;Lo;0;AL; 0635 0645 0645;;;;N;;;;; FDC6;ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM;Lo;0;AL; 0633 062E 064A;;;;N;;;;; FDC7;ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM;Lo;0;AL; 0646 062C 064A;;;;N;;;;; +FDC8;ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA;So;0;ON;;;;;N;;;;; +FDC9;ARABIC LIGATURE RADI ALLAAHU TAAALAA ANH;So;0;ON;;;;;N;;;;; +FDCA;ARABIC LIGATURE RADI ALLAAHU TAAALAA ANHAA;So;0;ON;;;;;N;;;;; +FDCB;ARABIC LIGATURE RADI ALLAAHU TAAALAA ANHUMAA;So;0;ON;;;;;N;;;;; +FDCC;ARABIC LIGATURE SALLALLAHU ALAYHI WA-ALAA AALIHEE WA-SALLAM;So;0;ON;;;;;N;;;;; +FDCD;ARABIC LIGATURE AJJAL ALLAAHU TAAALAA FARAJAHU ASH-SHAREEF;So;0;ON;;;;;N;;;;; +FDCE;ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH;So;0;ON;;;;;N;;;;; FDCF;ARABIC LIGATURE SALAAMUHU ALAYNAA;So;0;ON;;;;;N;;;;; FDF0;ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM;Lo;0;AL; 0635 0644 06D2;;;;N;;;;; FDF1;ARABIC LIGATURE QALA USED AS KORANIC STOP SIGN ISOLATED FORM;Lo;0;AL; 0642 0644 06D2;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index adae42e8b..b4dc08030 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-13, 22:47:47 GMT +# Date: 2024-11-14, 12:16:52 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1526,9 +1526,9 @@ FD3E ; R # Pe ORNATE LEFT PARENTHESIS FD3F ; R # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; R # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; R # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; R # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; R # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; R # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; R # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; R # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; R # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; R # Sc RIAL SIGN FDFD..FDFF ; R # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index dfd8e2821..1a3186df2 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-13, 22:47:18 GMT +# Date: 2024-11-14, 12:16:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1847,8 +1847,8 @@ FBC3..FBD2 ; ON # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALA FD3E ; ON # Pe ORNATE LEFT PARENTHESIS FD3F ; ON # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; ON # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH -FD91 ; ON # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA -FDCF ; ON # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FD90..FD91 ; ON # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FDC8..FDCF ; ON # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDFD..FDFF ; ON # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE10..FE16 ; ON # Po [7] PRESENTATION FORM FOR VERTICAL COMMA..PRESENTATION FORM FOR VERTICAL QUESTION MARK FE17 ; ON # Ps PRESENTATION FORM FOR VERTICAL LEFT WHITE LENTICULAR BRACKET @@ -1997,7 +1997,7 @@ FFFC..FFFD ; ON # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE 1FB00..1FB92 ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; ON # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 6777 +# Total code points: 6785 # ================================================ @@ -2502,8 +2502,8 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 267 code points not listed here. -# Total code points: 1742 +# The above property value applies to 259 code points not listed here. +# Total code points: 1734 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index dd9824c6d..b03e18c1c 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-13, 22:47:19 GMT +# Date: 2024-11-14, 12:16:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1237,9 +1237,9 @@ FD3E ; 0 # Pe ORNATE LEFT PARENTHESIS FD3F ; 0 # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; 0 # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; 0 # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; 0 # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; 0 # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; 0 # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; 0 # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; 0 # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; 0 # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; 0 # Sc RIAL SIGN FDFD..FDFF ; 0 # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL @@ -2060,7 +2060,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821517 code points not listed here. +# The above property value applies to 821509 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index a53658c73..e8d16e4a9 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-13, 22:47:21 GMT +# Date: 2024-11-14, 12:16:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1334,9 +1334,9 @@ FD3E ; N # Pe ORNATE LEFT PARENTHESIS FD3F ; N # Ps ORNATE RIGHT PARENTHESIS FD40..FD4F ; N # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; N # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; N # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; N # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; N # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; N # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; N # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; N # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFC ; N # Sc RIAL SIGN FDFD..FDFF ; N # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL @@ -2104,7 +2104,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761035 code points not listed here. +# The above property value applies to 761027 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index e65d152ca..44b621cbf 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-13, 22:47:21 GMT +# Date: 2024-11-14, 12:16:25 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -329,8 +329,6 @@ FB3D ; Cn # FB3F ; Cn # FB42 ; Cn # FB45 ; Cn # -FD90 ; Cn # -FDC8..FDCE ; Cn # [7] .. FDD0..FDEF ; Cn # [32] .. FE1A..FE1F ; Cn # [6] .. FE53 ; Cn # @@ -743,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819469 +# Total code points: 819461 # ================================================ @@ -4206,8 +4204,8 @@ A839 ; So # NORTH INDIC QUANTITY MARK AA77..AA79 ; So # [3] MYANMAR SYMBOL AITON EXCLAMATION..MYANMAR SYMBOL AITON TWO FBC3..FBD2 ; So # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD40..FD4F ; So # [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH -FD91 ; So # ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA -FDCF ; So # ARABIC LIGATURE SALAAMUHU ALAYNAA +FD90..FD91 ; So # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FDC8..FDCF ; So # [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDFD..FDFF ; So # [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FFE4 ; So # FULLWIDTH BROKEN BAR FFE8 ; So # HALFWIDTH FORMS LIGHT VERTICAL @@ -4287,7 +4285,7 @@ FFFC..FFFD ; So # [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1FB00..1FB92 ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; So # [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 7402 +# Total code points: 7410 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index c2824ccc7..26e8f2b03 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-13, 22:47:22 GMT +# Date: 2024-11-14, 12:16:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757589 code points not listed here. -# Total code points: 895057 +# The above property value applies to 757581 code points not listed here. +# Total code points: 895049 # ================================================ @@ -1189,9 +1189,9 @@ FBC3..FBD2 ; AL # So [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALA FBD3..FD3D ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM FD40..FD4F ; AL # So [16] ARABIC LIGATURE RAHIMAHU ALLAAH..ARABIC LIGATURE RAHIMAHUM ALLAAH FD50..FD8F ; AL # Lo [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM -FD91 ; AL # So ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA +FD90..FD91 ; AL # So [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92..FDC7 ; AL # Lo [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM -FDCF ; AL # So ARABIC LIGATURE SALAAMUHU ALAYNAA +FDC8..FDCF ; AL # So [8] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0..FDFB ; AL # Lo [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU FDFD..FDFF ; AL # So [3] ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM..ARABIC LIGATURE AZZA WA JALL FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM @@ -1614,7 +1614,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26714 +# Total code points: 26722 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index d31ed38a4..8cafde19a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-13, 22:47:22 GMT +# Date: 2024-11-14, 12:16:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -27090,6 +27090,7 @@ FD8C ; ARABIC LIGATURE MEEM WITH JEEM WITH HAH INITIAL FORM FD8D ; ARABIC LIGATURE MEEM WITH JEEM WITH MEEM INITIAL FORM FD8E ; ARABIC LIGATURE MEEM WITH KHAH WITH JEEM INITIAL FORM FD8F ; ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM +FD90 ; ARABIC LIGATURE RAHMATU ALLAAHI ALAYH FD91 ; ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FD92 ; ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM FD93 ; ARABIC LIGATURE HEH WITH MEEM WITH JEEM INITIAL FORM @@ -27145,6 +27146,13 @@ FDC4 ; ARABIC LIGATURE AIN WITH JEEM WITH MEEM INITIAL FORM FDC5 ; ARABIC LIGATURE SAD WITH MEEM WITH MEEM INITIAL FORM FDC6 ; ARABIC LIGATURE SEEN WITH KHAH WITH YEH FINAL FORM FDC7 ; ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM +FDC8 ; ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA +FDC9 ; ARABIC LIGATURE RADI ALLAAHU TAAALAA ANH +FDCA ; ARABIC LIGATURE RADI ALLAAHU TAAALAA ANHAA +FDCB ; ARABIC LIGATURE RADI ALLAAHU TAAALAA ANHUMAA +FDCC ; ARABIC LIGATURE SALLALLAHU ALAYHI WA-ALAA AALIHEE WA-SALLAM +FDCD ; ARABIC LIGATURE AJJAL ALLAAHU TAAALAA FARAJAHU ASH-SHAREEF +FDCE ; ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH FDCF ; ARABIC LIGATURE SALAAMUHU ALAYNAA FDF0 ; ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM FDF1 ; ARABIC LIGATURE QALA USED AS KORANIC STOP SIGN ISOLATED FORM @@ -45431,6 +45439,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155062 +# Total code points: 155070 # EOF From 5a3961037384a5bf4945073afe8e6a2eeb72aa96 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 15:51:23 +0100 Subject: [PATCH 23/26] Sidetic (#417) * Java changes for new script * Generated changes from the addition of Sidetic * input file changes for the Sidetic block * Update generated files * Revert .project * comments * GenerateEnums * GenerateEnums * 0 padding * Regenerate UCD --- unicodetools/data/ucd/dev/Blocks.txt | 1 + unicodetools/data/ucd/dev/DerivedAge.txt | 5 +-- .../data/ucd/dev/DerivedCoreProperties.txt | 20 +++++++---- unicodetools/data/ucd/dev/EastAsianWidth.txt | 3 +- unicodetools/data/ucd/dev/LineBreak.txt | 3 +- .../data/ucd/dev/PropertyValueAliases.txt | 4 ++- .../data/ucd/dev/ScriptExtensions.txt | 4 +-- unicodetools/data/ucd/dev/Scripts.txt | 8 ++++- unicodetools/data/ucd/dev/UnicodeData.txt | 29 ++++++++++++++++ .../data/ucd/dev/VerticalOrientation.txt | 3 +- .../dev/auxiliary/SentenceBreakProperty.txt | 5 +-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 5 +-- .../ucd/dev/extracted/DerivedBidiClass.txt | 6 ++-- .../dev/extracted/DerivedCombiningClass.txt | 5 +-- .../dev/extracted/DerivedEastAsianWidth.txt | 5 +-- .../dev/extracted/DerivedGeneralCategory.txt | 9 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 9 ++--- .../data/ucd/dev/extracted/DerivedName.txt | 33 +++++++++++++++++-- .../org/unicode/props/UcdPropertyValues.java | 2 ++ .../org/unicode/text/UCD/ShortBlockNames.txt | 1 + 20 files changed, 124 insertions(+), 36 deletions(-) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 1517dde0c..be3e10ce3 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -228,6 +228,7 @@ FFF0..FFFF; Specials 108E0..108FF; Hatran 10900..1091F; Phoenician 10920..1093F; Lydian +10940..1095C; Sidetic 10980..1099F; Meroitic Hieroglyphs 109A0..109FF; Meroitic Cursive 10A00..10A5F; Kharoshthi diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index b69576b8f..bd835436c 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 12:16:05 GMT +# Date: 2024-11-14, 14:37:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2080,8 +2080,9 @@ A7F1 ; 17.0 # MODIFIER LETTER CAPITAL S FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAYHI AR-RAHMAH FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH +10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -# Total code points: 72 +# Total code points: 101 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index ddd0bed1b..a301fb3bd 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 12:16:23 GMT +# Date: 2024-11-14, 14:37:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1018,6 +1018,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 108F4..108F5 ; Alphabetic # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Alphabetic # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Alphabetic # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; Alphabetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Alphabetic # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Alphabetic # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Alphabetic # Lo KHAROSHTHI LETTER A @@ -1439,7 +1440,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142768 +# Total code points: 142797 # ================================================ @@ -6710,6 +6711,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; ID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ID_Start # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Start # Lo KHAROSHTHI LETTER A @@ -6970,7 +6972,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141278 +# Total code points: 141307 # ================================================ @@ -7864,6 +7866,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 108F4..108F5 ; ID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ID_Continue # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ID_Continue # Lo KHAROSHTHI LETTER A @@ -8377,7 +8380,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144579 +# Total code points: 144608 # ================================================ @@ -8893,6 +8896,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 108F4..108F5 ; XID_Start # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Start # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Start # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; XID_Start # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; XID_Start # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Start # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Start # Lo KHAROSHTHI LETTER A @@ -9153,7 +9157,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141255 +# Total code points: 141284 # ================================================ @@ -10048,6 +10052,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 108F4..108F5 ; XID_Continue # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; XID_Continue # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; XID_Continue # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; XID_Continue # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; XID_Continue # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; XID_Continue # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; XID_Continue # Lo KHAROSHTHI LETTER A @@ -10561,7 +10566,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144560 +# Total code points: 144589 # ================================================ @@ -12284,6 +12289,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1091F ; Grapheme_Base # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; Grapheme_Base # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; Grapheme_Base # Po LYDIAN TRIANGULAR MARK +10940..1095C ; Grapheme_Base # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Grapheme_Base # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; Grapheme_Base # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; Grapheme_Base # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -12817,7 +12823,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152773 +# Total code points: 152802 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 962986fa9..1775ad934 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 12:16:27 GMT +# Date: 2024-11-14, 14:37:25 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1904,6 +1904,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 1091F ; N # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; N # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; N # Po LYDIAN TRIANGULAR MARK +10940..1095C ; N # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; N # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; N # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 4f0edadf4..eef5add38 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 12:16:28 GMT +# Date: 2024-11-14, 14:37:26 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2759,6 +2759,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1091F ; BA # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; AL # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; AL # Po LYDIAN TRIANGULAR MARK +10940..1095C ; AL # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; AL # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; AL # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; AL # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 4358a787e..7b9734001 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-17.0.0.txt -# Date: 2024-09-11, 23:38:17 GMT +# Date: 2024-10-16, 17:27:56 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -423,6 +423,7 @@ blk; Sharada ; Sharada blk; Shavian ; Shavian blk; Shorthand_Format_Controls ; Shorthand_Format_Controls blk; Siddham ; Siddham +blk; Sidetic ; Sidetic blk; Sinhala ; Sinhala blk; Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers blk; Small_Forms ; Small_Form_Variants @@ -1439,6 +1440,7 @@ sc ; Sgnw ; SignWriting sc ; Shaw ; Shavian sc ; Shrd ; Sharada sc ; Sidd ; Siddham +sc ; Sidt ; Sidetic sc ; Sind ; Khudawadi sc ; Sinh ; Sinhala sc ; Sogd ; Sogdian diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 140901a87..27e16cbe4 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ -# ScriptExtensions-16.0.0.txt -# Date: 2024-07-30, 19:38:00 GMT +# ScriptExtensions-17.0.0.txt +# Date: 2024-10-16, 17:28:17 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index d7cf7e07c..da4dc7bdf 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 12:16:50 GMT +# Date: 2024-11-14, 14:37:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -3126,4 +3126,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 80 +# ================================================ + +10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 + +# Total code points: 29 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index ec9c0e0f3..d61a3c99d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18772,6 +18772,35 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10938;LYDIAN LETTER NN;Lo;0;R;;;;;N;;;;; 10939;LYDIAN LETTER C;Lo;0;R;;;;;N;;;;; 1093F;LYDIAN TRIANGULAR MARK;Po;0;R;;;;;N;;;;; +10940;SIDETIC LETTER N01;Lo;0;R;;;;;N;;;;; +10941;SIDETIC LETTER N02;Lo;0;R;;;;;N;;;;; +10942;SIDETIC LETTER N03;Lo;0;R;;;;;N;;;;; +10943;SIDETIC LETTER N04;Lo;0;R;;;;;N;;;;; +10944;SIDETIC LETTER N05;Lo;0;R;;;;;N;;;;; +10945;SIDETIC LETTER N06;Lo;0;R;;;;;N;;;;; +10946;SIDETIC LETTER N07;Lo;0;R;;;;;N;;;;; +10947;SIDETIC LETTER N08;Lo;0;R;;;;;N;;;;; +10948;SIDETIC LETTER N09;Lo;0;R;;;;;N;;;;; +10949;SIDETIC LETTER N10;Lo;0;R;;;;;N;;;;; +1094A;SIDETIC LETTER N11;Lo;0;R;;;;;N;;;;; +1094B;SIDETIC LETTER N12;Lo;0;R;;;;;N;;;;; +1094C;SIDETIC LETTER N13;Lo;0;R;;;;;N;;;;; +1094D;SIDETIC LETTER N14;Lo;0;R;;;;;N;;;;; +1094E;SIDETIC LETTER N15;Lo;0;R;;;;;N;;;;; +1094F;SIDETIC LETTER N16;Lo;0;R;;;;;N;;;;; +10950;SIDETIC LETTER N17;Lo;0;R;;;;;N;;;;; +10951;SIDETIC LETTER N18;Lo;0;R;;;;;N;;;;; +10952;SIDETIC LETTER N19;Lo;0;R;;;;;N;;;;; +10953;SIDETIC LETTER N20;Lo;0;R;;;;;N;;;;; +10954;SIDETIC LETTER N21;Lo;0;R;;;;;N;;;;; +10955;SIDETIC LETTER N22;Lo;0;R;;;;;N;;;;; +10956;SIDETIC LETTER N23;Lo;0;R;;;;;N;;;;; +10957;SIDETIC LETTER N24;Lo;0;R;;;;;N;;;;; +10958;SIDETIC LETTER N25;Lo;0;R;;;;;N;;;;; +10959;SIDETIC LETTER N26;Lo;0;R;;;;;N;;;;; +1095A;SIDETIC LETTER N27;Lo;0;R;;;;;N;;;;; +1095B;SIDETIC LETTER N28;Lo;0;R;;;;;N;;;;; +1095C;SIDETIC LETTER N29;Lo;0;R;;;;;N;;;;; 10980;MEROITIC HIEROGLYPHIC LETTER A;Lo;0;R;;;;;N;;;;; 10981;MEROITIC HIEROGLYPHIC LETTER E;Lo;0;R;;;;;N;;;;; 10982;MEROITIC HIEROGLYPHIC LETTER I;Lo;0;R;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index b4dc08030..05cd2171f 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 12:16:52 GMT +# Date: 2024-11-14, 14:37:46 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1725,6 +1725,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1091F ; R # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; R # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; R # Po LYDIAN TRIANGULAR MARK +10940..1095C ; R # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..1099F ; U # Lo [32] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2 109A0..109B7 ; R # Lo [24] MEROITIC CURSIVE LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 44f556893..5e1badd5b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-13, 22:19:10 GMT +# Date: 2024-11-14, 14:37:45 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2372,6 +2372,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; OLetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; OLetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; OLetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; OLetter # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; OLetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; OLetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; OLetter # Lo KHAROSHTHI LETTER A @@ -2591,7 +2592,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136913 +# Total code points: 136942 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 6ddc428da..25d826481 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-13, 22:19:12 GMT +# Date: 2024-11-14, 14:37:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1114,6 +1114,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 108F4..108F5 ; ALetter # Lo [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; ALetter # Lo [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; ALetter # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; ALetter # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; ALetter # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; ALetter # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; ALetter # Lo KHAROSHTHI LETTER A @@ -1354,7 +1355,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33800 +# Total code points: 33829 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 1a3186df2..c87254b23 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 12:16:21 GMT +# Date: 2024-11-14, 14:37:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -67,6 +67,7 @@ # 108E0..108FF Hatran # 10900..1091F Phoenician # 10920..1093F Lydian +# 10940..1095C Sidetic # 10980..1099F Meroitic_Hieroglyphs # 109A0..109FF Meroitic_Cursive # 10A00..10A5F Kharoshthi @@ -1267,6 +1268,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 10916..1091B ; R # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE 10920..10939 ; R # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; R # Po LYDIAN TRIANGULAR MARK +10940..1095C ; R # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; R # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; R # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; R # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -1325,7 +1327,7 @@ FB46..FB4F ; R # Lo [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE AL 1E950..1E959 ; R # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1E95E..1E95F ; R # Po [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# The above property value applies to 2087 code points not listed here. +# The above property value applies to 2058 code points not listed here. # Total code points: 3631 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index b03e18c1c..158023481 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 12:16:23 GMT +# Date: 2024-11-14, 14:37:21 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1420,6 +1420,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1091F ; 0 # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; 0 # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; 0 # Po LYDIAN TRIANGULAR MARK +10940..1095C ; 0 # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; 0 # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; 0 # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; 0 # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -2060,7 +2061,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821509 code points not listed here. +# The above property value applies to 821480 code points not listed here. # Total code points: 1113151 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index e8d16e4a9..60379f00a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 12:16:24 GMT +# Date: 2024-11-14, 14:37:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1427,6 +1427,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1091F ; N # Po PHOENICIAN WORD SEPARATOR 10920..10939 ; N # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; N # Po LYDIAN TRIANGULAR MARK +10940..1095C ; N # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; N # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; N # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; N # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -2104,7 +2105,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 761027 code points not listed here. +# The above property value applies to 760998 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 44b621cbf..7bc6babc2 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 12:16:25 GMT +# Date: 2024-11-14, 14:37:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -400,7 +400,7 @@ FFFE..FFFF ; Cn # [2] .. 108F6..108FA ; Cn # [5] .. 1091C..1091E ; Cn # [3] .. 1093A..1093E ; Cn # [5] .. -10940..1097F ; Cn # [64] .. +1095D..1097F ; Cn # [35] .. 109B8..109BB ; Cn # [4] .. 109D0..109D1 ; Cn # [2] .. 10A04 ; Cn # @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819461 +# Total code points: 819432 # ================================================ @@ -2503,6 +2503,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 108F4..108F5 ; Lo # [2] HATRAN LETTER SHIN..HATRAN LETTER TAW 10900..10915 ; Lo # [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU 10920..10939 ; Lo # [26] LYDIAN LETTER A..LYDIAN LETTER C +10940..1095C ; Lo # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; Lo # [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BE..109BF ; Lo # [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN 10A00 ; Lo # KHAROSHTHI LETTER A @@ -2707,7 +2708,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136482 +# Total code points: 136511 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 26e8f2b03..f6600add6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 12:16:26 GMT +# Date: 2024-11-14, 14:37:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757581 code points not listed here. -# Total code points: 895049 +# The above property value applies to 757552 code points not listed here. +# Total code points: 895020 # ================================================ @@ -1271,6 +1271,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10916..1091B ; AL # No [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE 10920..10939 ; AL # Lo [26] LYDIAN LETTER A..LYDIAN LETTER C 1093F ; AL # Po LYDIAN TRIANGULAR MARK +10940..1095C ; AL # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10980..109B7 ; AL # Lo [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA 109BC..109BD ; AL # No [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF 109BE..109BF ; AL # Lo [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN @@ -1614,7 +1615,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26722 +# Total code points: 26751 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 8cafde19a..85af14a48 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 12:16:26 GMT +# Date: 2024-11-14, 14:37:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -29437,6 +29437,35 @@ FFFD ; REPLACEMENT CHARACTER 10938 ; LYDIAN LETTER NN 10939 ; LYDIAN LETTER C 1093F ; LYDIAN TRIANGULAR MARK +10940 ; SIDETIC LETTER N01 +10941 ; SIDETIC LETTER N02 +10942 ; SIDETIC LETTER N03 +10943 ; SIDETIC LETTER N04 +10944 ; SIDETIC LETTER N05 +10945 ; SIDETIC LETTER N06 +10946 ; SIDETIC LETTER N07 +10947 ; SIDETIC LETTER N08 +10948 ; SIDETIC LETTER N09 +10949 ; SIDETIC LETTER N10 +1094A ; SIDETIC LETTER N11 +1094B ; SIDETIC LETTER N12 +1094C ; SIDETIC LETTER N13 +1094D ; SIDETIC LETTER N14 +1094E ; SIDETIC LETTER N15 +1094F ; SIDETIC LETTER N16 +10950 ; SIDETIC LETTER N17 +10951 ; SIDETIC LETTER N18 +10952 ; SIDETIC LETTER N19 +10953 ; SIDETIC LETTER N20 +10954 ; SIDETIC LETTER N21 +10955 ; SIDETIC LETTER N22 +10956 ; SIDETIC LETTER N23 +10957 ; SIDETIC LETTER N24 +10958 ; SIDETIC LETTER N25 +10959 ; SIDETIC LETTER N26 +1095A ; SIDETIC LETTER N27 +1095B ; SIDETIC LETTER N28 +1095C ; SIDETIC LETTER N29 10980 ; MEROITIC HIEROGLYPHIC LETTER A 10981 ; MEROITIC HIEROGLYPHIC LETTER E 10982 ; MEROITIC HIEROGLYPHIC LETTER I @@ -45439,6 +45468,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155070 +# Total code points: 155099 # EOF diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 55107dc2a..ff767d030 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -448,6 +448,7 @@ public enum Block_Values implements Named { Shavian("Shavian"), Shorthand_Format_Controls("Shorthand_Format_Controls"), Siddham("Siddham"), + Sidetic("Sidetic"), Sinhala("Sinhala"), Sinhala_Archaic_Numbers("Sinhala_Archaic_Numbers"), Small_Form_Variants("Small_Forms"), @@ -1969,6 +1970,7 @@ public enum Script_Values implements Named { Shavian("Shaw"), Sharada("Shrd"), Siddham("Sidd"), + Sidetic("Sidt"), Khudawadi("Sind"), Sinhala("Sinh"), Sogdian("Sogd"), diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index eaa03a0f7..c1800d243 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -267,6 +267,7 @@ Sharada ; Sharada Shavian ; Shavian Shorthand_Format_Controls ; Shorthand_Format_Controls Siddham ; Siddham +Sidetic ; Sidetic Sinhala ; Sinhala Sinhala_Archaic_Numbers ; Sinhala_Archaic_Numbers Small_Forms ; Small_Form_Variants From c64da22e3c48ad27d85f636ffe376ecad5b50226 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 16:10:55 +0100 Subject: [PATCH 24/26] Two Quranic Characters (#754) * UnicodeData.txt from L2/22-281R * lb=AL for the Lm, lb=CM for the Mn * Arabic * small low noon other_alphabetic cf. smol low meme * Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++- .../data/ucd/dev/DerivedCoreProperties.txt | 39 +++++++++++-------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 5 ++- unicodetools/data/ucd/dev/LineBreak.txt | 5 ++- .../data/ucd/dev/NormalizationTest.txt | 4 +- unicodetools/data/ucd/dev/PropList.txt | 6 +-- unicodetools/data/ucd/dev/Scripts.txt | 7 ++-- unicodetools/data/ucd/dev/UnicodeData.txt | 2 + .../data/ucd/dev/VerticalOrientation.txt | 5 ++- .../dev/auxiliary/GraphemeBreakProperty.txt | 6 +-- .../dev/auxiliary/SentenceBreakProperty.txt | 9 +++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 9 +++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 11 +++--- .../dev/extracted/DerivedCombiningClass.txt | 10 +++-- .../dev/extracted/DerivedEastAsianWidth.txt | 7 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 15 +++---- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 +-- .../ucd/dev/extracted/DerivedLineBreak.txt | 13 ++++--- .../data/ucd/dev/extracted/DerivedName.txt | 6 ++- 19 files changed, 99 insertions(+), 72 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index bd835436c..6dc72b355 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 14:37:04 GMT +# Date: 2024-11-14, 14:54:38 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2081,8 +2081,10 @@ FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAY FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH 10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 +10EC5 ; 17.0 # ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH +10EFB ; 17.0 # ARABIC SMALL LOW NOON -# Total code points: 101 +# Total code points: 103 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index a301fb3bd..985ab73b3 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 14:37:21 GMT +# Date: 2024-11-14, 14:55:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1052,7 +1052,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10EAB..10EAC ; Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC ; Alphabetic # Mn ARABIC COMBINING ALEF OVERLAY +10EC5 ; Alphabetic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EFB..10EFC ; Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Alphabetic # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1440,7 +1441,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142797 +# Total code points: 142799 # ================================================ @@ -3351,7 +3352,8 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 10D69..10D6D ; Case_Ignorable # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10D6F ; Case_Ignorable # Lm GARAY REDUPLICATION MARK 10EAB..10EAC ; Case_Ignorable # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Case_Ignorable # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; Case_Ignorable # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EFB..10EFF ; Case_Ignorable # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Case_Ignorable # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Case_Ignorable # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Case_Ignorable # Mn BRAHMI SIGN ANUSVARA @@ -3506,7 +3508,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2779 +# Total code points: 2781 # ================================================ @@ -6739,6 +6741,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10E80..10EA9 ; ID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; ID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -6972,7 +6975,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141307 +# Total code points: 141308 # ================================================ @@ -7905,7 +7908,8 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10EAB..10EAC ; ID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC..10EFF ; ID_Continue # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; ID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EFB..10EFF ; ID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -8380,7 +8384,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144608 +# Total code points: 144610 # ================================================ @@ -8924,6 +8928,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10E80..10EA9 ; XID_Start # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; XID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -9157,7 +9162,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141284 +# Total code points: 141285 # ================================================ @@ -10091,7 +10096,8 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10EAB..10EAC ; XID_Continue # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EFC..10EFF ; XID_Continue # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EC5 ; XID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EFB..10EFF ; XID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Continue # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -10566,7 +10572,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144589 +# Total code points: 144591 # ================================================ @@ -10884,7 +10890,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 10D24..10D27 ; Grapheme_Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Grapheme_Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Grapheme_Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Grapheme_Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Grapheme_Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Grapheme_Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Grapheme_Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Grapheme_Extend # Mn BRAHMI SIGN ANUSVARA @@ -11039,7 +11045,7 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2222 +# Total code points: 2223 # ================================================ @@ -12340,6 +12346,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10EAD ; Grapheme_Base # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; Grapheme_Base # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Grapheme_Base # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; Grapheme_Base # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; Grapheme_Base # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; Grapheme_Base # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; Grapheme_Base # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -12823,7 +12830,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152802 +# Total code points: 152803 # ================================================ @@ -13214,7 +13221,7 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA 10D24..10D27 ; InCB; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; InCB; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; InCB; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; InCB; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; InCB; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; InCB; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; InCB; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; InCB; Extend # Mn BRAHMI SIGN ANUSVARA @@ -13370,6 +13377,6 @@ FF9E..FF9F ; InCB; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HA E0020..E007F ; InCB; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; InCB; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2221 +# Total code points: 2222 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 1775ad934..bba100cc0 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 14:37:25 GMT +# Date: 2024-11-14, 14:55:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1965,8 +1965,9 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFC..10EFF ; N # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index eef5add38..5ea7db04a 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 14:37:26 GMT +# Date: 2024-11-14, 14:55:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2822,8 +2822,9 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10EAD ; BA # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; AL # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index dd98635df..d47e846f2 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-17.0.0.txt -# Date: 2024-11-13, 22:18:53 GMT +# Date: 2024-11-14, 14:55:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -18701,6 +18701,8 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 10EAB 0315 0300 05AE 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062;0061 05AE 10EAB 0300 0315 0062; # (a◌𐺫◌̕◌̀◌֮b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; a◌֮◌𐺫◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING HAMZA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B 0061 0315 0300 05AE 10EAC 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062;00E0 05AE 10EAC 0315 0062;0061 05AE 0300 10EAC 0315 0062; # (a◌̕◌̀◌֮◌𐺬b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; à◌֮◌𐺬◌̕b; a◌֮◌̀◌𐺬◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, YEZIDI COMBINING MADDA MARK, LATIN SMALL LETTER B 0061 10EAC 0315 0300 05AE 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062;0061 05AE 10EAC 0300 0315 0062; # (a◌𐺬◌̕◌̀◌֮b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; a◌֮◌𐺬◌̀◌̕b; ) LATIN SMALL LETTER A, YEZIDI COMBINING MADDA MARK, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 059A 0316 1DFA 10EFB 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062;0061 1DFA 0316 10EFB 059A 0062; # (a◌֚◌̖◌᷺◌𐻻b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; a◌᷺◌̖◌𐻻◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW NOON, LATIN SMALL LETTER B +0061 10EFB 059A 0316 1DFA 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062;0061 1DFA 10EFB 0316 059A 0062; # (a◌𐻻◌֚◌̖◌᷺b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; a◌᷺◌𐻻◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW NOON, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10EFD 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062;0061 1DFA 0316 10EFD 059A 0062; # (a◌֚◌̖◌᷺◌𐻽b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; a◌᷺◌̖◌𐻽◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD SAKTA, LATIN SMALL LETTER B 0061 10EFD 059A 0316 1DFA 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062;0061 1DFA 10EFD 0316 059A 0062; # (a◌𐻽◌֚◌̖◌᷺b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; a◌᷺◌𐻽◌̖◌֚b; ) LATIN SMALL LETTER A, ARABIC SMALL LOW WORD SAKTA, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 10EFE 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062;0061 1DFA 0316 10EFE 059A 0062; # (a◌֚◌̖◌᷺◌𐻾b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; a◌᷺◌̖◌𐻾◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, ARABIC SMALL LOW WORD QASR, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 7744fcc3e..48dea2722 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-17.0.0.txt -# Date: 2024-11-13, 22:18:57 GMT +# Date: 2024-11-14, 14:55:37 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -702,7 +702,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 10D24..10D27 ; Other_Alphabetic # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69 ; Other_Alphabetic # Mn GARAY VOWEL SIGN E 10EAB..10EAC ; Other_Alphabetic # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC ; Other_Alphabetic # Mn ARABIC COMBINING ALEF OVERLAY +10EFB..10EFC ; Other_Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY 11000 ; Other_Alphabetic # Mc BRAHMI SIGN CANDRABINDU 11001 ; Other_Alphabetic # Mn BRAHMI SIGN ANUSVARA 11002 ; Other_Alphabetic # Mc BRAHMI SIGN VISARGA @@ -858,7 +858,7 @@ FB1E ; Other_Alphabetic # Mn HEBREW POINT JUDEO-SPANISH VARIKA 1F150..1F169 ; Other_Alphabetic # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; Other_Alphabetic # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 1495 +# Total code points: 1496 # ================================================ diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index da4dc7bdf..1e5894b7f 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 14:37:44 GMT +# Date: 2024-11-14, 14:56:03 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -888,8 +888,9 @@ FE70..FE74 ; Arabic # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM 10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10EC2..10EC4 ; Arabic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; Arabic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; Arabic # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFC..10EFF ; Arabic # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Arabic # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL 1EE05..1EE1F ; Arabic # Lo [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF 1EE21..1EE22 ; Arabic # Lo [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM @@ -925,7 +926,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1407 +# Total code points: 1409 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index d61a3c99d..e4e8eacd5 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -19634,6 +19634,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10EC2;ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC3;ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC4;ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; +10EC5;ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW;Lm;0;AL;;;;;N;;;;; 10ED1;ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED2;ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED3;ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; @@ -19642,6 +19643,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10ED6;ARABIC LIGATURE QUDDISA SIRRAHUMAA;So;0;ON;;;;;N;;;;; 10ED7;ARABIC LIGATURE QUDDISAT ASRAARUHUM;So;0;ON;;;;;N;;;;; 10ED8;ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH;So;0;ON;;;;;N;;;;; +10EFB;ARABIC SMALL LOW NOON;Mn;220;NSM;;;;;N;;;;; 10EFC;ARABIC COMBINING ALEF OVERLAY;Mn;0;NSM;;;;;N;;;;; 10EFD;ARABIC SMALL LOW WORD SAKTA;Mn;220;NSM;;;;;N;;;;; 10EFE;ARABIC SMALL LOW WORD QASR;Mn;220;NSM;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 05cd2171f..a088ec14b 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 14:37:46 GMT +# Date: 2024-11-14, 14:56:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1786,8 +1786,9 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10EAD ; R # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; R # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; R # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; R # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFC..10EFF ; R # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; R # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; R # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; R # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; R # Lo OLD SOGDIAN LIGATURE AYIN-DALETH diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index ce9cb6cde..97b805ce1 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-17.0.0.txt -# Date: 2024-11-13, 21:22:53 GMT +# Date: 2024-11-14, 14:55:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -340,7 +340,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Extend # Mn BRAHMI SIGN ANUSVARA @@ -496,7 +496,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2227 +# Total code points: 2228 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 5e1badd5b..d8ff2484a 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-14, 14:37:45 GMT +# Date: 2024-11-14, 14:56:04 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -374,7 +374,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU @@ -587,7 +587,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2630 +# Total code points: 2631 # ================================================ @@ -2396,6 +2396,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10E80..10EA9 ; OLetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; OLetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; OLetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2592,7 +2593,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136942 +# Total code points: 136943 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 25d826481..29f44bc7c 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-14, 14:37:47 GMT +# Date: 2024-11-14, 14:56:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -410,7 +410,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 10D24..10D27 ; Extend # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Extend # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Extend # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Extend # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Extend # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Extend # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Extend # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; Extend # Mc BRAHMI SIGN CANDRABINDU @@ -624,7 +624,7 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2634 +# Total code points: 2635 # ================================================ @@ -1142,6 +1142,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10E80..10EA9 ; ALetter # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ALetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; ALetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1355,7 +1356,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33829 +# Total code points: 33830 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index c87254b23..0c98bbcfc 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 14:37:19 GMT +# Date: 2024-11-14, 14:55:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2277,7 +2277,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 10D24..10D27 ; NSM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; NSM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; NSM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; NSM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; NSM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; NSM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; NSM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; NSM # Mn BRAHMI SIGN ANUSVARA @@ -2411,7 +2411,7 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2057 +# Total code points: 2058 # ================================================ @@ -2459,6 +2459,7 @@ FE70..FE74 ; AL # Lo [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISO FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10F30..10F45 ; AL # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT @@ -2504,8 +2505,8 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 259 code points not listed here. -# Total code points: 1734 +# The above property value applies to 257 code points not listed here. +# Total code points: 1733 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 158023481..58a37ea70 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 14:37:21 GMT +# Date: 2024-11-14, 14:55:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1475,6 +1475,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10EAD ; 0 # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; 0 # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; 0 # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; 0 # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; 0 # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC ; 0 # Mn ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; 0 # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL @@ -2061,8 +2062,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821480 code points not listed here. -# Total code points: 1113151 +# The above property value applies to 821478 code points not listed here. +# Total code points: 1113150 # ================================================ @@ -2618,6 +2619,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 10A0D ; 220 # Mn KHAROSHTHI SIGN DOUBLE RING BELOW 10A3A ; 220 # Mn KHAROSHTHI SIGN DOT BELOW 10AE6 ; 220 # Mn MANICHAEAN ABBREVIATION MARK BELOW +10EFB ; 220 # Mn ARABIC SMALL LOW NOON 10EFD..10EFF ; 220 # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA 10F46..10F47 ; 220 # Mn [2] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING TWO DOTS BELOW 10F4B ; 220 # Mn SOGDIAN COMBINING CURVE BELOW @@ -2630,7 +2632,7 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 184 +# Total code points: 185 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 60379f00a..c3224da3a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 14:37:22 GMT +# Date: 2024-11-14, 14:55:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1487,8 +1487,9 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EAD ; N # Pd YEZIDI HYPHENATION MARK 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH -10EFC..10EFF ; N # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; N # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF 10F27 ; N # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -2105,7 +2106,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 760998 code points not listed here. +# The above property value applies to 760996 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 7bc6babc2..4a761c488 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 14:37:23 GMT +# Date: 2024-11-14, 14:55:12 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -432,8 +432,8 @@ FFFE..FFFF ; Cn # [2] .. 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. -10EC5..10ED0 ; Cn # [12] .. -10ED9..10EFB ; Cn # [35] .. +10EC6..10ED0 ; Cn # [11] .. +10ED9..10EFA ; Cn # [34] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. 10F8A..10FAF ; Cn # [38] .. @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819432 +# Total code points: 819430 # ================================================ @@ -2157,6 +2157,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 107B2..107BA ; Lm # [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL 10D4E ; Lm # GARAY VOWEL LENGTH MARK 10D6F ; Lm # GARAY REDUPLICATION MARK +10EC5 ; Lm # ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 16B40..16B43 ; Lm # [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM 16D40..16D42 ; Lm # [3] KIRAT RAI SIGN ANUSVARA..KIRAT RAI SIGN VISARGA 16D6B..16D6C ; Lm # [2] KIRAT RAI SIGN VIRAMA..KIRAT RAI SIGN SAAT @@ -2171,7 +2172,7 @@ FF9E..FF9F ; Lm # [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK 1E4EB ; Lm # NAG MUNDARI SIGN OJOD 1E94B ; Lm # ADLAM NASALIZATION MARK -# Total code points: 405 +# Total code points: 406 # ================================================ @@ -2939,7 +2940,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 10D24..10D27 ; Mn # [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; Mn # [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; Mn # [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; Mn # [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; Mn # [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; Mn # [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; Mn # [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; Mn # BRAHMI SIGN ANUSVARA @@ -3073,7 +3074,7 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2049 +# Total code points: 2050 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index d57fd1f6f..cd7857336 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-13, 21:22:50 GMT +# Date: 2024-11-14, 14:55:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -443,7 +443,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; T # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; T # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11001 ; T # Mn BRAHMI SIGN ANUSVARA @@ -583,6 +583,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2214 +# Total code points: 2215 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index f6600add6..29695f052 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 14:37:24 GMT +# Date: 2024-11-14, 14:55:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757552 code points not listed here. -# Total code points: 895020 +# The above property value applies to 757550 code points not listed here. +# Total code points: 895018 # ================================================ @@ -1316,6 +1316,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10E80..10EA9 ; AL # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -1615,7 +1616,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26751 +# Total code points: 26752 # ================================================ @@ -2185,7 +2186,7 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 10D24..10D27 ; CM # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI 10D69..10D6D ; CM # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK 10EAB..10EAC ; CM # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK -10EFC..10EFF ; CM # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F46..10F50 ; CM # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 10F82..10F85 ; CM # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 11000 ; CM # Mc BRAHMI SIGN CANDRABINDU @@ -2390,7 +2391,7 @@ E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2498 +# Total code points: 2499 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 85af14a48..2cb4df8a0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 14:37:24 GMT +# Date: 2024-11-14, 14:55:15 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -30299,6 +30299,7 @@ FFFD ; REPLACEMENT CHARACTER 10EC2 ; ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW 10EC3 ; ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW 10EC4 ; ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC5 ; ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10ED1 ; ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM 10ED2 ; ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM 10ED3 ; ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM @@ -30307,6 +30308,7 @@ FFFD ; REPLACEMENT CHARACTER 10ED6 ; ARABIC LIGATURE QUDDISA SIRRAHUMAA 10ED7 ; ARABIC LIGATURE QUDDISAT ASRAARUHUM 10ED8 ; ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH +10EFB ; ARABIC SMALL LOW NOON 10EFC ; ARABIC COMBINING ALEF OVERLAY 10EFD ; ARABIC SMALL LOW WORD SAKTA 10EFE ; ARABIC SMALL LOW WORD QASR @@ -45468,6 +45470,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155099 +# Total code points: 155101 # EOF From 5c1cbadda2353e721176abc862af031391bd26f3 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 16:24:57 +0100 Subject: [PATCH 25/26] =?UTF-8?q?Thin=20=D9=86=20(#756)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * UnicodeData.txt line from L2/23-121 * lb=AL * Arabic * ArabicShaping.txt from the proposal * A new Joining_Group * Regenerate UCD * GenerateEnums * This is silly --- unicodetools/data/ucd/dev/ArabicShaping.txt | 1 + unicodetools/data/ucd/dev/DerivedAge.txt | 6 +++--- .../data/ucd/dev/DerivedCoreProperties.txt | 20 ++++++++++++------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 3 ++- unicodetools/data/ucd/dev/LineBreak.txt | 3 ++- .../data/ucd/dev/PropertyValueAliases.txt | 3 ++- unicodetools/data/ucd/dev/Scripts.txt | 5 +++-- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 3 ++- .../dev/auxiliary/SentenceBreakProperty.txt | 5 +++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 5 +++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 5 +++-- .../dev/extracted/DerivedCombiningClass.txt | 5 +++-- .../dev/extracted/DerivedEastAsianWidth.txt | 5 +++-- .../dev/extracted/DerivedGeneralCategory.txt | 9 +++++---- .../ucd/dev/extracted/DerivedJoiningGroup.txt | 8 +++++++- .../ucd/dev/extracted/DerivedJoiningType.txt | 5 +++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 9 +++++---- .../data/ucd/dev/extracted/DerivedName.txt | 5 +++-- .../org/unicode/props/UcdPropertyValues.java | 1 + .../java/org/unicode/text/UCD/UCD_Names.java | 4 +++- .../java/org/unicode/text/UCD/UCD_Types.java | 4 +++- 22 files changed, 74 insertions(+), 41 deletions(-) diff --git a/unicodetools/data/ucd/dev/ArabicShaping.txt b/unicodetools/data/ucd/dev/ArabicShaping.txt index 20d103cd5..38bc3a417 100644 --- a/unicodetools/data/ucd/dev/ArabicShaping.txt +++ b/unicodetools/data/ucd/dev/ArabicShaping.txt @@ -851,6 +851,7 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group 10EC2; DAL WITH VERTICAL 2 DOTS BELOW; R; DAL 10EC3; TAH WITH VERTICAL 2 DOTS BELOW; D; TAH 10EC4; KAF WITH VERTICAL 2 DOTS BELOW; D; KAF +10EC6; THIN NOON; D; THIN NOON # Sogdian Characters diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 6dc72b355..559012328 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 14:54:38 GMT +# Date: 2024-11-14, 15:12:52 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2081,10 +2081,10 @@ FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAY FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH 10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 -10EC5 ; 17.0 # ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC5..10EC6 ; 17.0 # [2] ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW..ARABIC LETTER THIN NOON 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB ; 17.0 # ARABIC SMALL LOW NOON -# Total code points: 103 +# Total code points: 104 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 985ab73b3..7d1dbc676 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 14:55:09 GMT +# Date: 2024-11-14, 15:13:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1053,6 +1053,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Alphabetic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; Alphabetic # Lo ARABIC LETTER THIN NOON 10EFB..10EFC ; Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -1441,7 +1442,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142799 +# Total code points: 142800 # ================================================ @@ -6742,6 +6743,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; ID_Start # Lo ARABIC LETTER THIN NOON 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -6975,7 +6977,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141308 +# Total code points: 141309 # ================================================ @@ -7909,6 +7911,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; ID_Continue # Lo ARABIC LETTER THIN NOON 10EFB..10EFF ; ID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -8384,7 +8387,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144610 +# Total code points: 144611 # ================================================ @@ -8929,6 +8932,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; XID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; XID_Start # Lo ARABIC LETTER THIN NOON 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -9162,7 +9166,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141285 +# Total code points: 141286 # ================================================ @@ -10097,6 +10101,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; XID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; XID_Continue # Lo ARABIC LETTER THIN NOON 10EFB..10EFF ; XID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -10572,7 +10577,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144591 +# Total code points: 144592 # ================================================ @@ -12347,6 +12352,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10EB0..10EB1 ; Grapheme_Base # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Grapheme_Base # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Grapheme_Base # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; Grapheme_Base # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; Grapheme_Base # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; Grapheme_Base # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; Grapheme_Base # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -12830,7 +12836,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152803 +# Total code points: 152804 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index bba100cc0..90ffc2d1e 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 14:55:18 GMT +# Date: 2024-11-14, 15:13:27 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1966,6 +1966,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; N # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 5ea7db04a..f5d7e0c08 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 14:55:19 GMT +# Date: 2024-11-14, 15:13:28 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2823,6 +2823,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; AL # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 7b9734001..5c447325b 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-17.0.0.txt -# Date: 2024-10-16, 17:27:56 GMT +# Date: 2024-11-14, 15:13:47 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1090,6 +1090,7 @@ jg ; Taw ; Taw jg ; Teh_Marbuta ; Teh_Marbuta jg ; Teh_Marbuta_Goal ; Teh_Marbuta_Goal ; Hamza_On_Heh_Goal jg ; Teth ; Teth +jg ; Thin_Noon ; Thin_Noon jg ; Thin_Yeh ; Thin_Yeh jg ; Vertical_Tail ; Vertical_Tail jg ; Waw ; Waw diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 1e5894b7f..f09505048 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 14:56:03 GMT +# Date: 2024-11-14, 15:14:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -889,6 +889,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10EC2..10EC4 ; Arabic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Arabic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; Arabic # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; Arabic # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; Arabic # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL @@ -926,7 +927,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1409 +# Total code points: 1410 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index e4e8eacd5..f4d3f3f9d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -19635,6 +19635,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10EC3;ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC4;ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC5;ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW;Lm;0;AL;;;;;N;;;;; +10EC6;ARABIC LETTER THIN NOON;Lo;0;AL;;;;;N;;;;; 10ED1;ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED2;ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED3;ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index a088ec14b..2691f8c00 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 14:56:06 GMT +# Date: 2024-11-14, 15:14:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1787,6 +1787,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10EB0..10EB1 ; R # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; R # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; R # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; R # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; R # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; R # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index d8ff2484a..8258057b2 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-14, 14:56:04 GMT +# Date: 2024-11-14, 15:14:08 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2397,6 +2397,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; OLetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; OLetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; OLetter # Lo ARABIC LETTER THIN NOON 10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2593,7 +2594,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136943 +# Total code points: 136944 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 29f44bc7c..d1800a501 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-14, 14:56:07 GMT +# Date: 2024-11-14, 15:14:11 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1143,6 +1143,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ALetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ALetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; ALetter # Lo ARABIC LETTER THIN NOON 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1356,7 +1357,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33830 +# Total code points: 33831 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 0c98bbcfc..221aa212a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 14:55:06 GMT +# Date: 2024-11-14, 15:13:17 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2460,6 +2460,7 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; AL # Lo ARABIC LETTER THIN NOON 10F30..10F45 ; AL # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT @@ -2505,7 +2506,7 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 257 code points not listed here. +# The above property value applies to 256 code points not listed here. # Total code points: 1733 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 58a37ea70..0eb3f0f88 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 14:55:08 GMT +# Date: 2024-11-14, 15:13:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1476,6 +1476,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10EB0..10EB1 ; 0 # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; 0 # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; 0 # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; 0 # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; 0 # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC ; 0 # Mn ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; 0 # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL @@ -2062,7 +2063,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821478 code points not listed here. +# The above property value applies to 821477 code points not listed here. # Total code points: 1113150 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index c3224da3a..8e9aadf56 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 14:55:12 GMT +# Date: 2024-11-14, 15:13:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1488,6 +1488,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; N # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL @@ -2106,7 +2107,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 760996 code points not listed here. +# The above property value applies to 760995 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 4a761c488..cb3cc649f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 14:55:12 GMT +# Date: 2024-11-14, 15:13:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -432,7 +432,7 @@ FFFE..FFFF ; Cn # [2] .. 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. -10EC6..10ED0 ; Cn # [11] .. +10EC7..10ED0 ; Cn # [10] .. 10ED9..10EFA ; Cn # [34] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819430 +# Total code points: 819429 # ================================================ @@ -2526,6 +2526,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10E80..10EA9 ; Lo # [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; Lo # [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Lo # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC6 ; Lo # ARABIC LETTER THIN NOON 10F00..10F1C ; Lo # [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Lo # OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Lo # [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2709,7 +2710,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136511 +# Total code points: 136512 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt index d2c5547ed..f0e99096f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt @@ -1,5 +1,5 @@ # DerivedJoiningGroup-17.0.0.txt -# Date: 2024-10-15, 12:06:51 GMT +# Date: 2024-11-14, 15:13:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -751,4 +751,10 @@ # Total code points: 1 +# ================================================ + +10EC6 ; Thin_Noon # Lo ARABIC LETTER THIN NOON + +# Total code points: 1 + # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index cd7857336..ccc5a289a 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-14, 14:55:14 GMT +# Date: 2024-11-14, 15:13:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -97,6 +97,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O 10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA 10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC6 ; D # Lo ARABIC LETTER THIN NOON 10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL 10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH 10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY @@ -112,7 +113,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FCA ; D # No CHORASMIAN NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 613 +# Total code points: 614 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 29695f052..1ce2a534f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 14:55:14 GMT +# Date: 2024-11-14, 15:13:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757550 code points not listed here. -# Total code points: 895018 +# The above property value applies to 757549 code points not listed here. +# Total code points: 895017 # ================================================ @@ -1317,6 +1317,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; AL # Lo ARABIC LETTER THIN NOON 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -1616,7 +1617,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26752 +# Total code points: 26753 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 2cb4df8a0..6aad2b226 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 14:55:15 GMT +# Date: 2024-11-14, 15:13:24 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -30300,6 +30300,7 @@ FFFD ; REPLACEMENT CHARACTER 10EC3 ; ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW 10EC4 ; ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW +10EC6 ; ARABIC LETTER THIN NOON 10ED1 ; ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM 10ED2 ; ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM 10ED3 ; ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM @@ -45470,6 +45471,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155101 +# Total code points: 155102 # EOF diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index ff767d030..b41d852c9 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -1351,6 +1351,7 @@ public enum Joining_Group_Values implements Named { Teh_Marbuta("Teh_Marbuta"), Teh_Marbuta_Goal("Teh_Marbuta_Goal", "Hamza_On_Heh_Goal"), Teth("Teth"), + Thin_Noon("Thin_Noon"), Thin_Yeh("Thin_Yeh"), Vertical_Tail("Vertical_Tail"), Waw("Waw"), diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java index 9075daea6..100273ad9 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java @@ -1227,7 +1227,9 @@ public final class UCD_Names implements UCD_Types { "THIN_YEH", "VERTICAL_TAIL", // Unicode 16 - "KASHMIRI_YEH" + "KASHMIRI_YEH", + // Unicode n > 16 + "THIN_NOON", }; static { diff --git a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java index b1ffb8261..d00021b07 100644 --- a/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java +++ b/unicodetools/src/main/java/org/unicode/text/UCD/UCD_Types.java @@ -781,8 +781,10 @@ public interface UCD_Types { VERTICAL_TAIL = 104, // Unicode 16 KASHMIRI_YEH = 105, + // Unicode n > 16 + THIN_NOON = 106, // limit - LIMIT_JOINING_GROUP = KASHMIRI_YEH + 1; + LIMIT_JOINING_GROUP = THIN_NOON + 1; static final byte NFD = 0, NFC = 1, NFKD = 2, NFKC = 3; public static final int NF_COMPATIBILITY_MASK = 2, NF_COMPOSITION_MASK = 1; From 69070a9e65d7a3dd137bad1e001e9fa6d9fd88d0 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 14 Nov 2024 16:52:50 +0100 Subject: [PATCH 26/26] Yeh with four dots below (#706) * Yeh with 4 dots below * lb=AL * Scripts.txt * ArabicShaping.txt from the proposal * Regenerate UCD * Deconfliction --- unicodetools/data/ucd/dev/ArabicShaping.txt | 1 + unicodetools/data/ucd/dev/DerivedAge.txt | 6 ++--- .../data/ucd/dev/DerivedCoreProperties.txt | 26 +++++++++---------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 +-- unicodetools/data/ucd/dev/LineBreak.txt | 4 +-- unicodetools/data/ucd/dev/Scripts.txt | 6 ++--- unicodetools/data/ucd/dev/UnicodeData.txt | 1 + .../data/ucd/dev/VerticalOrientation.txt | 4 +-- .../dev/auxiliary/SentenceBreakProperty.txt | 6 ++--- .../ucd/dev/auxiliary/WordBreakProperty.txt | 6 ++--- .../ucd/dev/extracted/DerivedBidiClass.txt | 6 ++--- .../dev/extracted/DerivedCombiningClass.txt | 6 ++--- .../dev/extracted/DerivedEastAsianWidth.txt | 6 ++--- .../dev/extracted/DerivedGeneralCategory.txt | 10 +++---- .../ucd/dev/extracted/DerivedJoiningGroup.txt | 5 ++-- .../ucd/dev/extracted/DerivedJoiningType.txt | 6 ++--- .../ucd/dev/extracted/DerivedLineBreak.txt | 10 +++---- .../data/ucd/dev/extracted/DerivedName.txt | 5 ++-- 18 files changed, 61 insertions(+), 57 deletions(-) diff --git a/unicodetools/data/ucd/dev/ArabicShaping.txt b/unicodetools/data/ucd/dev/ArabicShaping.txt index 38bc3a417..6f71f9214 100644 --- a/unicodetools/data/ucd/dev/ArabicShaping.txt +++ b/unicodetools/data/ucd/dev/ArabicShaping.txt @@ -852,6 +852,7 @@ A873; PHAGS-PA CANDRABINDU; U; No_Joining_Group 10EC3; TAH WITH VERTICAL 2 DOTS BELOW; D; TAH 10EC4; KAF WITH VERTICAL 2 DOTS BELOW; D; KAF 10EC6; THIN NOON; D; THIN NOON +10EC7; DOTLESS YEH WITH 4 DOTS BELOW; D; YEH # Sogdian Characters diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 559012328..e6e952e4a 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-17.0.0.txt -# Date: 2024-11-14, 15:12:52 GMT +# Date: 2024-11-14, 15:26:44 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2081,10 +2081,10 @@ FBC3..FBD2 ; 17.0 # [16] ARABIC LIGATURE JALLA WA-ALAA..ARABIC LIGATURE ALAY FD90..FD91 ; 17.0 # [2] ARABIC LIGATURE RAHMATU ALLAAHI ALAYH..ARABIC LIGATURE RAHMATU ALLAAHI ALAYHAA FDC8..FDCE ; 17.0 # [7] ARABIC LIGATURE RAHIMAHU ALLAAH TAAALAA..ARABIC LIGATURE KARRAMA ALLAAHU WAJHAH 10940..1095C ; 17.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 -10EC5..10EC6 ; 17.0 # [2] ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW..ARABIC LETTER THIN NOON +10EC5..10EC7 ; 17.0 # [3] ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; 17.0 # [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB ; 17.0 # ARABIC SMALL LOW NOON -# Total code points: 104 +# Total code points: 105 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 7d1dbc676..d0930bc27 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-17.0.0.txt -# Date: 2024-11-14, 15:13:20 GMT +# Date: 2024-11-14, 15:27:14 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1053,7 +1053,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 10EB0..10EB1 ; Alphabetic # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Alphabetic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Alphabetic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; Alphabetic # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; Alphabetic # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10EFB..10EFC ; Alphabetic # Mn [2] ARABIC SMALL LOW NOON..ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; Alphabetic # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Alphabetic # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -1442,7 +1442,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 142800 +# Total code points: 142801 # ================================================ @@ -6743,7 +6743,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; ID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; ID_Start # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; ID_Start # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; ID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -6977,7 +6977,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141309 +# Total code points: 141310 # ================================================ @@ -7911,7 +7911,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 10EB0..10EB1 ; ID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; ID_Continue # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; ID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10EFB..10EFF ; ID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; ID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -8387,7 +8387,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144611 +# Total code points: 144612 # ================================================ @@ -8932,7 +8932,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 10EB0..10EB1 ; XID_Start # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Start # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; XID_Start # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; XID_Start # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; XID_Start # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; XID_Start # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Start # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; XID_Start # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -9166,7 +9166,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 141286 +# Total code points: 141287 # ================================================ @@ -10101,7 +10101,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 10EB0..10EB1 ; XID_Continue # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; XID_Continue # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; XID_Continue # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; XID_Continue # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; XID_Continue # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10EFB..10EFF ; XID_Continue # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; XID_Continue # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; XID_Continue # Lo OLD SOGDIAN LIGATURE AYIN-DALETH @@ -10577,7 +10577,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 144592 +# Total code points: 144593 # ================================================ @@ -12352,7 +12352,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 10EB0..10EB1 ; Grapheme_Base # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Grapheme_Base # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Grapheme_Base # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; Grapheme_Base # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; Grapheme_Base # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; Grapheme_Base # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; Grapheme_Base # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; Grapheme_Base # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -12836,7 +12836,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 152804 +# Total code points: 152805 # ================================================ diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index 90ffc2d1e..3af5ca7fd 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 15:13:27 GMT +# Date: 2024-11-14, 15:27:22 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1966,7 +1966,7 @@ FFFD ; A # So REPLACEMENT CHARACTER 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; N # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; N # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index f5d7e0c08..7a9618652 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,5 +1,5 @@ # LineBreak-17.0.0.txt -# Date: 2024-11-14, 15:13:28 GMT +# Date: 2024-11-14, 15:27:23 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2823,7 +2823,7 @@ FFFD ; AI # So REPLACEMENT CHARACTER 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; AL # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; AL # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; CM # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index f09505048..2c4efaff7 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-17.0.0.txt -# Date: 2024-11-14, 15:14:07 GMT +# Date: 2024-11-14, 15:28:06 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -889,7 +889,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 10E60..10E7E ; Arabic # No [31] RUMI DIGIT ONE..RUMI FRACTION TWO THIRDS 10EC2..10EC4 ; Arabic # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; Arabic # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; Arabic # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; Arabic # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; Arabic # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; Arabic # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 1EE00..1EE03 ; Arabic # Lo [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL @@ -927,7 +927,7 @@ FE76..FEFC ; Arabic # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LA 1EEAB..1EEBB ; Arabic # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN 1EEF0..1EEF1 ; Arabic # Sm [2] ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL..ARABIC MATHEMATICAL OPERATOR HAH WITH DAL -# Total code points: 1410 +# Total code points: 1411 # ================================================ diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index f4d3f3f9d..3217ea7a7 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -19636,6 +19636,7 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 10EC4;ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW;Lo;0;AL;;;;;N;;;;; 10EC5;ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW;Lm;0;AL;;;;;N;;;;; 10EC6;ARABIC LETTER THIN NOON;Lo;0;AL;;;;;N;;;;; +10EC7;ARABIC LETTER YEH WITH FOUR DOTS BELOW;Lo;0;AL;;;;;N;;;;; 10ED1;ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED2;ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; 10ED3;ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM;So;0;ON;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 2691f8c00..16b0ece34 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-17.0.0.txt -# Date: 2024-11-14, 15:14:10 GMT +# Date: 2024-11-14, 15:28:09 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1787,7 +1787,7 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 10EB0..10EB1 ; R # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; R # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; R # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; R # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; R # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; R # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; R # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 8258057b2..625ffe50f 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-17.0.0.txt -# Date: 2024-11-14, 15:14:08 GMT +# Date: 2024-11-14, 15:28:07 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2397,7 +2397,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; OLetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; OLetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; OLetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; OLetter # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; OLetter # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; OLetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; OLetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; OLetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2594,7 +2594,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136944 +# Total code points: 136945 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index d1800a501..c9ed2146c 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-17.0.0.txt -# Date: 2024-11-14, 15:14:11 GMT +# Date: 2024-11-14, 15:28:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1143,7 +1143,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 10EB0..10EB1 ; ALetter # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; ALetter # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ALetter # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; ALetter # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; ALetter # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; ALetter # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; ALetter # Lo OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; ALetter # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -1357,7 +1357,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33831 +# Total code points: 33832 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 221aa212a..05f7cc4f4 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-17.0.0.txt -# Date: 2024-11-14, 15:13:17 GMT +# Date: 2024-11-14, 15:27:10 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2460,7 +2460,7 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 10D00..10D23 ; AL # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; AL # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; AL # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F30..10F45 ; AL # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 10F51..10F54 ; AL # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 10F55..10F59 ; AL # Po [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT @@ -2506,7 +2506,7 @@ FE76..FEFC ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WI 1EEA5..1EEA9 ; AL # Lo [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH 1EEAB..1EEBB ; AL # Lo [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN -# The above property value applies to 256 code points not listed here. +# The above property value applies to 255 code points not listed here. # Total code points: 1733 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 0eb3f0f88..6e0611432 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-17.0.0.txt -# Date: 2024-11-14, 15:13:19 GMT +# Date: 2024-11-14, 15:27:13 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1476,7 +1476,7 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 10EB0..10EB1 ; 0 # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; 0 # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; 0 # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; 0 # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; 0 # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; 0 # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFC ; 0 # Mn ARABIC COMBINING ALEF OVERLAY 10F00..10F1C ; 0 # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL @@ -2063,7 +2063,7 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 821477 code points not listed here. +# The above property value applies to 821476 code points not listed here. # Total code points: 1113150 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 8e9aadf56..af21f6081 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-17.0.0.txt -# Date: 2024-11-14, 15:13:22 GMT +# Date: 2024-11-14, 15:27:16 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1488,7 +1488,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 10EB0..10EB1 ; N # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; N # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; N # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; N # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; N # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; N # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10EFB..10EFF ; N # Mn [5] ARABIC SMALL LOW NOON..ARABIC SMALL LOW WORD MADDA 10F00..10F1C ; N # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL @@ -2107,7 +2107,7 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 760995 code points not listed here. +# The above property value applies to 760994 code points not listed here. # Total code points: 792420 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index cb3cc649f..36ce61d28 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-17.0.0.txt -# Date: 2024-11-14, 15:13:22 GMT +# Date: 2024-11-14, 15:27:17 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -432,7 +432,7 @@ FFFE..FFFF ; Cn # [2] .. 10EAA ; Cn # 10EAE..10EAF ; Cn # [2] .. 10EB2..10EC1 ; Cn # [16] .. -10EC7..10ED0 ; Cn # [10] .. +10EC8..10ED0 ; Cn # [9] .. 10ED9..10EFA ; Cn # [34] .. 10F28..10F2F ; Cn # [8] .. 10F5A..10F6F ; Cn # [22] .. @@ -741,7 +741,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 819429 +# Total code points: 819428 # ================================================ @@ -2526,7 +2526,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 10E80..10EA9 ; Lo # [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 10EB0..10EB1 ; Lo # [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; Lo # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EC6 ; Lo # ARABIC LETTER THIN NOON +10EC6..10EC7 ; Lo # [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F00..10F1C ; Lo # [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F27 ; Lo # OLD SOGDIAN LIGATURE AYIN-DALETH 10F30..10F45 ; Lo # [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN @@ -2710,7 +2710,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136512 +# Total code points: 136513 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt index f0e99096f..f24475268 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningGroup.txt @@ -1,5 +1,5 @@ # DerivedJoiningGroup-17.0.0.txt -# Date: 2024-11-14, 15:13:23 GMT +# Date: 2024-11-14, 15:27:17 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -385,8 +385,9 @@ 0777 ; Yeh # Lo ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW 08A8..08A9 ; Yeh # Lo [2] ARABIC LETTER YEH WITH TWO DOTS BELOW AND HAMZA ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE 08BA ; Yeh # Lo ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE +10EC7 ; Yeh # Lo ARABIC LETTER YEH WITH FOUR DOTS BELOW -# Total code points: 10 +# Total code points: 11 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index ccc5a289a..fc0d6d2cb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-17.0.0.txt -# Date: 2024-11-14, 15:13:24 GMT +# Date: 2024-11-14, 15:27:18 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -97,7 +97,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O 10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA 10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW -10EC6 ; D # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; D # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL 10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH 10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY @@ -113,7 +113,7 @@ A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA 10FCA ; D # No CHORASMIAN NUMBER TWENTY 1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA -# Total code points: 614 +# Total code points: 615 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 1ce2a534f..ddc1d086e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-17.0.0.txt -# Date: 2024-11-14, 15:13:24 GMT +# Date: 2024-11-14, 15:27:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -69,8 +69,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 757549 code points not listed here. -# Total code points: 895017 +# The above property value applies to 757548 code points not listed here. +# Total code points: 895016 # ================================================ @@ -1317,7 +1317,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 10EB0..10EB1 ; AL # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 10EC2..10EC4 ; AL # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; AL # Lm ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW -10EC6 ; AL # Lo ARABIC LETTER THIN NOON +10EC6..10EC7 ; AL # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1..10ED8 ; AL # So [8] ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM..ARABIC LIGATURE NAWWARA ALLAAHU MARQADAH 10F00..10F1C ; AL # Lo [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL 10F1D..10F26 ; AL # No [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF @@ -1617,7 +1617,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBEF ; AL # So [92] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..TOP LEFT JUSTIFIED LOWER RIGHT QUARTER BLACK CIRCLE -# Total code points: 26753 +# Total code points: 26754 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 6aad2b226..c2198a2fc 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-17.0.0.txt -# Date: 2024-11-14, 15:13:24 GMT +# Date: 2024-11-14, 15:27:19 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -30301,6 +30301,7 @@ FFFD ; REPLACEMENT CHARACTER 10EC4 ; ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW 10EC5 ; ARABIC SMALL YEH BARREE WITH TWO DOTS BELOW 10EC6 ; ARABIC LETTER THIN NOON +10EC7 ; ARABIC LETTER YEH WITH FOUR DOTS BELOW 10ED1 ; ARABIC LIGATURE ALAYHAA AS-SALAATU WAS-SALAAM 10ED2 ; ARABIC LIGATURE ALAYHIM AS-SALAATU WAS-SALAAM 10ED3 ; ARABIC LIGATURE ALAYHIMAA AS-SALAATU WAS-SALAAM @@ -45471,6 +45472,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 155102 +# Total code points: 155103 # EOF