From fe450b973707c6f21e1b3361986fa917f2088270 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 17:39:46 +0100 Subject: [PATCH 01/10] Java changes for new script --- .project | 4 ++-- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 1 + .../src/main/java/org/unicode/text/UCD/UCD_Names.java | 4 ++++ .../src/main/java/org/unicode/text/UCD/UCD_Types.java | 4 +++- 4 files changed, 10 insertions(+), 3 deletions(-) diff --git a/.project b/.project index e2f2ecac3..e1809a441 100644 --- a/.project +++ b/.project @@ -16,12 +16,12 @@ - 1625608051965 + 1678107170772 30 org.eclipse.core.resources.regexFilterMatcher - node_modules|.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__ + node_modules|\.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__ diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 640fa3b1e..cd6d30a62 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -1831,6 +1831,7 @@ public enum Script_Values implements Named { Math_Symbols("Zmth"), Emoji_Symbols("Zsye"), Other_Symbols("Zsym"), + Sidetic("Qabw"), Unwritten("Zxxx"); private final PropertyNames names; 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 091edf9fa..60a325261 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 @@ -408,6 +408,8 @@ public final class UCD_Names implements UCD_Types { // Unicode 15 "Kawi", "Nag_Mundari", + // Unicode 16? + "Sidetic", }; public static final Relation EXTRA_SCRIPT = @@ -592,6 +594,8 @@ public final class UCD_Names implements UCD_Types { // Unicode 15 "Kawi", "Nagm", + // Unicode 16? + "Qabw", }; static final String[] SHORT_AGE = { 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 9c594c25a..9418de0fc 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 @@ -588,7 +588,9 @@ public interface UCD_Types { // Unicode 15 Kawi = 164, Nag_Mundari = 165, - LIMIT_SCRIPT = Nag_Mundari + 1; + // Unicode 16? + Sidetic = 166, + LIMIT_SCRIPT = Sidetic + 1; // Bidi_Paired_Bracket_Type public static final byte BPT_N = 0, BPT_O = 1, BPT_C = 2, LIMIT_BPT = 3; From fbedd5d742292dfc3e7467480053e93c899c7084 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 17:48:19 +0100 Subject: [PATCH 02/10] Generated changes from the addition of Sidetic --- .../data/ucd/dev/PropertyValueAliases.txt | 3 ++- unicodetools/data/ucd/dev/ScriptExtensions.txt | 16 ++++++++-------- 2 files changed, 10 insertions(+), 9 deletions(-) diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index cb1263a9f..edc1921ac 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-15.1.0.txt -# Date: 2023-01-31, 22:27:07 GMT +# Date: 2023-03-06, 16:46:35 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1390,6 +1390,7 @@ sc ; Phlp ; Psalter_Pahlavi sc ; Phnx ; Phoenician sc ; Plrd ; Miao sc ; Prti ; Inscriptional_Parthian +sc ; Qabw ; Sidetic sc ; Rjng ; Rejang sc ; Rohg ; Hanifi_Rohingya sc ; Runr ; Runic diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 23141fb82..355176852 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ # ScriptExtensions-15.1.0.txt -# Date: 2023-02-01, 23:02:24 GMT +# Date: 2023-03-06, 16:46:45 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -136,20 +136,20 @@ # ================================================ -# Script_Extensions=Arab Nkoo +# Script_Extensions=Arab Rohg -FD3E ; Arab Nkoo # Pe ORNATE LEFT PARENTHESIS -FD3F ; Arab Nkoo # Ps ORNATE RIGHT PARENTHESIS +06D4 ; Arab Rohg # Po ARABIC FULL STOP -# Total code points: 2 +# Total code points: 1 # ================================================ -# Script_Extensions=Arab Rohg +# Script_Extensions=Arab Nkoo -06D4 ; Arab Rohg # Po ARABIC FULL STOP +FD3E ; Arab Nkoo # Pe ORNATE LEFT PARENTHESIS +FD3F ; Arab Nkoo # Ps ORNATE RIGHT PARENTHESIS -# Total code points: 1 +# Total code points: 2 # ================================================ From c6dc3b58d09839dc452d0b53cde85cda9061647a Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 18:30:29 +0100 Subject: [PATCH 03/10] input file changes for the Sidetic block --- unicodetools/data/ucd/dev/Blocks.txt | 1 + unicodetools/data/ucd/dev/LineBreak.txt | 1 + unicodetools/data/ucd/dev/Scripts.txt | 2 ++ unicodetools/data/ucd/dev/UnicodeData.txt | 29 +++++++++++++++++++ .../org/unicode/text/UCD/ShortBlockNames.txt | 1 + 5 files changed, 34 insertions(+) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 1bd4d0325..2d5dea9a5 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -226,6 +226,7 @@ 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/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index a4fab9a4d..d0cae636e 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -2748,6 +2748,7 @@ 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 N1..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/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 9fb6b5abd..6306fd392 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -3029,4 +3029,6 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 42 +10940..1095C ; Sidetic # Meow + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index b10c67ba8..c3fc1724d 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18639,6 +18639,35 @@ 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 N1;Lo;0;R;;;;;N;;;;; +10941;SIDETIC LETTER N2;Lo;0;R;;;;;N;;;;; +10942;SIDETIC LETTER N3;Lo;0;R;;;;;N;;;;; +10943;SIDETIC LETTER N4;Lo;0;R;;;;;N;;;;; +10944;SIDETIC LETTER N5;Lo;0;R;;;;;N;;;;; +10945;SIDETIC LETTER N6;Lo;0;R;;;;;N;;;;; +10946;SIDETIC LETTER N7;Lo;0;R;;;;;N;;;;; +10947;SIDETIC LETTER N8;Lo;0;R;;;;;N;;;;; +10948;SIDETIC LETTER N9;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/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index c05e737eb..9dd8d77bd 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -260,6 +260,7 @@ 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 5dd5eee45764a16b3e3f877df9a7d5797ceaf7bf Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 18:35:32 +0100 Subject: [PATCH 04/10] Update generated files --- unicodetools/data/ucd/dev/DerivedAge.txt | 5 +-- .../data/ucd/dev/DerivedCoreProperties.txt | 20 +++++++---- .../data/ucd/dev/PropertyValueAliases.txt | 3 +- unicodetools/data/ucd/dev/Scripts.txt | 8 +++-- .../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 | 33 +++++++++++++++++-- 12 files changed, 80 insertions(+), 32 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 40d92c540..cf4f1e40f 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-15.1.0.txt -# Date: 2023-01-05, 20:34:30 GMT +# Date: 2023-03-06, 17:33:50 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1999,7 +1999,8 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 2FFC..2FFF ; 15.1 # [4] IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT..IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION 31EF ; 15.1 # IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION +10940..1095C ; 15.1 # [29] SIDETIC LETTER N1..SIDETIC LETTER N29 -# Total code points: 5 +# Total code points: 34 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 368a1ccf5..18f7cde5b 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-15.1.0.txt -# Date: 2023-01-31, 21:26:32 GMT +# Date: 2023-03-06, 17:33:53 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1016,6 +1016,7 @@ 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 N1..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 @@ -1401,7 +1402,7 @@ 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: 137765 +# Total code points: 137794 # ================================================ @@ -6620,6 +6621,7 @@ 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 N1..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 @@ -6857,7 +6859,7 @@ 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: 136345 +# Total code points: 136374 # ================================================ @@ -7749,6 +7751,7 @@ 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 N1..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 @@ -8213,7 +8216,7 @@ 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: 139484 +# Total code points: 139513 # ================================================ @@ -8730,6 +8733,7 @@ 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 N1..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 @@ -8967,7 +8971,7 @@ 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: 136322 +# Total code points: 136351 # ================================================ @@ -9860,6 +9864,7 @@ 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 N1..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 @@ -10324,7 +10329,7 @@ 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: 139465 +# Total code points: 139494 # ================================================ @@ -12009,6 +12014,7 @@ 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 N1..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 @@ -12504,7 +12510,7 @@ 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: 146991 +# Total code points: 147020 # ================================================ diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index edc1921ac..2f579b3c1 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ # PropertyValueAliases-15.1.0.txt -# Date: 2023-03-06, 16:46:35 GMT +# Date: 2023-03-06, 17:34:03 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -414,6 +414,7 @@ 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 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 6306fd392..65bfd6f77 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-15.1.0.txt -# Date: 2023-01-05, 20:35:02 GMT +# Date: 2023-03-06, 17:34:13 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3029,6 +3029,10 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 42 -10940..1095C ; Sidetic # Meow +# ================================================ + +10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N1..SIDETIC LETTER N29 + +# Total code points: 29 # EOF diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 9f31ef3c2..91db3a466 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-15.1.0.txt -# Date: 2023-01-05, 20:35:03 GMT +# Date: 2023-03-06, 17:34:14 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2343,6 +2343,7 @@ 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 N1..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 @@ -2541,7 +2542,7 @@ 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: 132036 +# Total code points: 132065 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index d2398674d..c31a8297a 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-15.1.0.txt -# Date: 2023-01-05, 20:35:04 GMT +# Date: 2023-03-06, 17:34:14 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1101,6 +1101,7 @@ 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 N1..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 @@ -1319,7 +1320,7 @@ 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: 29489 +# Total code points: 29518 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 529bf2d41..0f39d75e6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-15.1.0.txt -# Date: 2023-01-05, 20:34:32 GMT +# Date: 2023-03-06, 17:33:52 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1236,6 +1236,7 @@ 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 N1..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 @@ -1287,7 +1288,7 @@ 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 2156 code points not listed here. +# The above property value applies to 2127 code points not listed here. # Total code points: 3647 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index 39794a94e..8a6a49962 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-15.1.0.txt -# Date: 2023-01-05, 20:34:33 GMT +# Date: 2023-03-06, 17:33:53 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1419,6 +1419,7 @@ 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 N1..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 @@ -2004,7 +2005,7 @@ 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 827388 code points not listed here. +# The above property value applies to 827359 code points not listed here. # Total code points: 1113190 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 80dd68b77..24ed77b51 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-15.1.0.txt -# Date: 2023-01-05, 20:34:36 GMT +# Date: 2023-03-06, 17:33:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1423,6 +1423,7 @@ 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 N1..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 @@ -2042,7 +2043,7 @@ 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 766284 code points not listed here. +# The above property value applies to 766255 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index c17494d8b..b7e2ab524 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-15.1.0.txt -# Date: 2023-01-05, 20:34:37 GMT +# Date: 2023-03-06, 17:33:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -407,7 +407,7 @@ 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 # @@ -722,7 +722,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 825340 +# Total code points: 825311 # ================================================ @@ -2465,6 +2465,7 @@ 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 N1..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 @@ -2652,7 +2653,7 @@ 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: 131612 +# Total code points: 131641 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 7cd22b063..9bceb405e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-15.1.0.txt -# Date: 2023-01-05, 20:34:38 GMT +# Date: 2023-03-06, 17:33:56 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -67,8 +67,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762725 code points not listed here. -# Total code points: 900193 +# The above property value applies to 762696 code points not listed here. +# Total code points: 900164 # ================================================ @@ -1279,6 +1279,7 @@ 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 N1..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 @@ -1623,7 +1624,7 @@ 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..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 22214 +# Total code points: 22243 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 805beab0b..f4ae3aa4e 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-15.1.0.txt -# Date: 2023-01-05, 20:34:38 GMT +# Date: 2023-03-06, 17:33:57 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -29304,6 +29304,35 @@ FFFD ; REPLACEMENT CHARACTER 10938 ; LYDIAN LETTER NN 10939 ; LYDIAN LETTER C 1093F ; LYDIAN TRIANGULAR MARK +10940 ; SIDETIC LETTER N1 +10941 ; SIDETIC LETTER N2 +10942 ; SIDETIC LETTER N3 +10943 ; SIDETIC LETTER N4 +10944 ; SIDETIC LETTER N5 +10945 ; SIDETIC LETTER N6 +10946 ; SIDETIC LETTER N7 +10947 ; SIDETIC LETTER N8 +10948 ; SIDETIC LETTER N9 +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 @@ -44175,6 +44204,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149191 +# Total code points: 149220 # EOF From 475b28842340b44872d16f585a07a167d0594549 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 18:36:40 +0100 Subject: [PATCH 05/10] Revert .project --- .project | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.project b/.project index e1809a441..e2f2ecac3 100644 --- a/.project +++ b/.project @@ -16,12 +16,12 @@ - 1678107170772 + 1625608051965 30 org.eclipse.core.resources.regexFilterMatcher - node_modules|\.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__ + node_modules|.git|__CREATED_BY_JAVA_LANGUAGE_SERVER__ From 63376b0c06afb8733181cc6bc8addffc8239491e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 6 Mar 2023 21:23:38 +0100 Subject: [PATCH 06/10] comments --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 2 +- unicodetools/src/main/java/org/unicode/text/UCD/UCD_Names.java | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index cd6d30a62..957fbb3a9 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -1831,7 +1831,7 @@ public enum Script_Values implements Named { Math_Symbols("Zmth"), Emoji_Symbols("Zsye"), Other_Symbols("Zsym"), - Sidetic("Qabw"), + Sidetic("Qabw"), // Temporary private use code. Unwritten("Zxxx"); private final PropertyNames names; 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 60a325261..96db850b2 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 @@ -595,7 +595,7 @@ public final class UCD_Names implements UCD_Types { "Kawi", "Nagm", // Unicode 16? - "Qabw", + "Qabw", // Temporary private use code for Sidetic. }; static final String[] SHORT_AGE = { From 60e7fb1641415b739103464c48a6564070d43d9c Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 8 Mar 2023 13:49:09 +0100 Subject: [PATCH 07/10] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 6 +++--- .../src/main/java/org/unicode/text/UCD/UCD_Names.java | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 957fbb3a9..20cea8504 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -62,8 +62,7 @@ public enum Age_Values implements Named { V12_0("12.0"), V12_1("12.1"), V13_0("13.0"), - V13_1("13.1"), // TODO: there is no Unicode 13.1, see - // https://github.com/unicode-org/unicodetools/issues/100 + V13_1("13.1"), V14_0("14.0"), V15_0("15.0"), V15_1("15.1"), @@ -439,6 +438,7 @@ 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"), @@ -1777,6 +1777,7 @@ public enum Script_Values implements Named { Phoenician("Phnx"), Miao("Plrd"), Inscriptional_Parthian("Prti"), + Sidetic("Qabw"), Rejang("Rjng"), Hanifi_Rohingya("Rohg"), Runic("Runr"), @@ -1831,7 +1832,6 @@ public enum Script_Values implements Named { Math_Symbols("Zmth"), Emoji_Symbols("Zsye"), Other_Symbols("Zsym"), - Sidetic("Qabw"), // Temporary private use code. Unwritten("Zxxx"); private final PropertyNames names; 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 96db850b2..05e890a69 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 @@ -595,7 +595,7 @@ public final class UCD_Names implements UCD_Types { "Kawi", "Nagm", // Unicode 16? - "Qabw", // Temporary private use code for Sidetic. + "Qabw", // Temporary private use code for Sidetic. }; static final String[] SHORT_AGE = { From 27f6b0dcd310e9bbddb5932dea49e5e0ef70af53 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Wed, 8 Nov 2023 14:51:18 -0800 Subject: [PATCH 08/10] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index 94383c1db..9b4c10511 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -62,7 +62,8 @@ public enum Age_Values implements Named { V12_0("12.0"), V12_1("12.1"), V13_0("13.0"), - V13_1("13.1"), + V13_1("13.1"), // TODO: there is no Unicode 13.1, see + // https://github.com/unicode-org/unicodetools/issues/100 V14_0("14.0"), V15_0("15.0"), V15_1("15.1"), @@ -1826,7 +1827,6 @@ public enum Script_Values implements Named { Phoenician("Phnx"), Miao("Plrd"), Inscriptional_Parthian("Prti"), - Sidetic("Qabw"), Rejang("Rjng"), Hanifi_Rohingya("Rohg"), Runic("Runr"), @@ -1837,6 +1837,7 @@ public enum Script_Values implements Named { Shavian("Shaw"), Sharada("Shrd"), Siddham("Sidd"), + Sidetic("Sidt"), Khudawadi("Sind"), Sinhala("Sinh"), Sogdian("Sogd"), From ed729b3a0f7298454d45fec4e32fb9116aa04ec3 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 25 Jul 2024 00:43:09 +0200 Subject: [PATCH 09/10] 0 padding --- unicodetools/data/ucd/dev/UnicodeData.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 067cb135a..e4d69afea 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -18708,15 +18708,15 @@ 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 N1;Lo;0;R;;;;;N;;;;; -10941;SIDETIC LETTER N2;Lo;0;R;;;;;N;;;;; -10942;SIDETIC LETTER N3;Lo;0;R;;;;;N;;;;; -10943;SIDETIC LETTER N4;Lo;0;R;;;;;N;;;;; -10944;SIDETIC LETTER N5;Lo;0;R;;;;;N;;;;; -10945;SIDETIC LETTER N6;Lo;0;R;;;;;N;;;;; -10946;SIDETIC LETTER N7;Lo;0;R;;;;;N;;;;; -10947;SIDETIC LETTER N8;Lo;0;R;;;;;N;;;;; -10948;SIDETIC LETTER N9;Lo;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;;;;; From f0feeb709ae75f12d3baa2f19c77ffd193bebf24 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Thu, 25 Jul 2024 00:47:29 +0200 Subject: [PATCH 10/10] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 4 ++-- .../data/ucd/dev/DerivedCoreProperties.txt | 14 ++++++------- unicodetools/data/ucd/dev/EastAsianWidth.txt | 4 ++-- unicodetools/data/ucd/dev/LineBreak.txt | 4 ++-- unicodetools/data/ucd/dev/Scripts.txt | 4 ++-- .../data/ucd/dev/VerticalOrientation.txt | 4 ++-- .../dev/auxiliary/SentenceBreakProperty.txt | 4 ++-- .../ucd/dev/auxiliary/WordBreakProperty.txt | 4 ++-- .../ucd/dev/extracted/DerivedBidiClass.txt | 4 ++-- .../dev/extracted/DerivedCombiningClass.txt | 4 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 4 ++-- .../dev/extracted/DerivedGeneralCategory.txt | 4 ++-- .../ucd/dev/extracted/DerivedLineBreak.txt | 4 ++-- .../data/ucd/dev/extracted/DerivedName.txt | 20 +++++++++---------- 14 files changed, 41 insertions(+), 41 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 3d38abcf4..209802bdb 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: 2024-06-07, 22:49:17 GMT +# Date: 2024-07-24, 22:44:46 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 @@ -2018,7 +2018,7 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT A7CB..A7CD ; 16.0 # [3] LATIN CAPITAL LETTER RAMS HORN..LATIN SMALL LETTER S WITH DIAGONAL STROKE A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER LAMBDA WITH STROKE 105C0..105F3 ; 16.0 # [52] TODHRI LETTER A..TODHRI LETTER OO -10940..1095C ; 16.0 # [29] SIDETIC LETTER N1..SIDETIC LETTER N29 +10940..1095C ; 16.0 # [29] SIDETIC LETTER N01..SIDETIC LETTER N29 10D40..10D65 ; 16.0 # [38] GARAY DIGIT ZERO..GARAY CAPITAL LETTER OLD NA 10D69..10D85 ; 16.0 # [29] GARAY VOWEL SIGN E..GARAY SMALL LETTER OLD NA 10D8E..10D8F ; 16.0 # [2] GARAY PLUS SIGN..GARAY MINUS SIGN diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index a0aaa17a7..1730f7850 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: 2024-06-07, 22:49:36 GMT +# Date: 2024-07-24, 22:45:40 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 @@ -1020,7 +1020,7 @@ 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 N1..SIDETIC LETTER N29 +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 @@ -6703,7 +6703,7 @@ 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 N1..SIDETIC LETTER N29 +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 @@ -7859,7 +7859,7 @@ 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 N1..SIDETIC LETTER N29 +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 @@ -8891,7 +8891,7 @@ 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 N1..SIDETIC LETTER N29 +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 @@ -10048,7 +10048,7 @@ 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 N1..SIDETIC LETTER N29 +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 @@ -12284,7 +12284,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index a0fc6d4b6..1313bc824 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: 2024-06-07, 22:49:42 GMT +# Date: 2024-07-24, 22:45:53 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 @@ -1904,7 +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 N1..SIDETIC LETTER N29 +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 00d925825..f8a7d3c2d 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: 2024-05-11, 16:57:19 GMT +# Date: 2024-07-24, 22:45:55 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 @@ -2763,7 +2763,7 @@ 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 N1..SIDETIC LETTER N29 +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/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 19bebea23..88e460bd4 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: 2024-06-07, 22:50:07 GMT +# Date: 2024-07-24, 22:46:53 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 @@ -3127,7 +3127,7 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # ================================================ -10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N1..SIDETIC LETTER N29 +10940..1095C ; Sidetic # Lo [29] SIDETIC LETTER N01..SIDETIC LETTER N29 # Total code points: 29 diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 4b3c7389d..ffe2b775c 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: 2024-06-07, 22:50:09 GMT +# Date: 2024-07-24, 22:47:00 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 @@ -1724,7 +1724,7 @@ 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 N1..SIDETIC LETTER N29 +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 2ede0dd9c..5c9879b61 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: 2024-06-07, 22:50:07 GMT +# Date: 2024-07-24, 22:46:54 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 @@ -2366,7 +2366,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 5b4f8a1df..ace609a56 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: 2024-06-07, 22:50:09 GMT +# Date: 2024-07-24, 22:47:01 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 @@ -1115,7 +1115,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 7d414d7cf..f8ab7cd39 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: 2024-06-07, 22:49:34 GMT +# Date: 2024-07-24, 22:45:33 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 @@ -1270,7 +1270,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index bd6f13b27..b4915c4f7 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: 2024-06-07, 22:49:36 GMT +# Date: 2024-07-24, 22:45:38 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 @@ -1421,7 +1421,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 83a14a95b..4cca13c08 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: 2024-06-07, 22:49:38 GMT +# Date: 2024-07-24, 22:45:43 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 @@ -1427,7 +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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index 569952bfb..33703169b 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: 2024-06-07, 22:49:38 GMT +# Date: 2024-07-24, 22:45:44 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 @@ -2504,7 +2504,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index 20f78aa99..ece835c8f 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: 2024-06-07, 22:49:39 GMT +# Date: 2024-07-24, 22:45:47 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 @@ -1273,7 +1273,7 @@ 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 N1..SIDETIC LETTER N29 +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 diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 304aca2e2..c46211841 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: 2024-06-07, 22:49:40 GMT +# Date: 2024-07-24, 22:45:48 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 @@ -29373,15 +29373,15 @@ FFFD ; REPLACEMENT CHARACTER 10938 ; LYDIAN LETTER NN 10939 ; LYDIAN LETTER C 1093F ; LYDIAN TRIANGULAR MARK -10940 ; SIDETIC LETTER N1 -10941 ; SIDETIC LETTER N2 -10942 ; SIDETIC LETTER N3 -10943 ; SIDETIC LETTER N4 -10944 ; SIDETIC LETTER N5 -10945 ; SIDETIC LETTER N6 -10946 ; SIDETIC LETTER N7 -10947 ; SIDETIC LETTER N8 -10948 ; SIDETIC LETTER N9 +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