Skip to content

Commit

Permalink
Merge remote-tracking branch 'la-vache/main' into L2/24-002
Browse files Browse the repository at this point in the history
  • Loading branch information
eggrobin committed Nov 14, 2024
2 parents e57800e + 399ba7f commit 622e83e
Show file tree
Hide file tree
Showing 41 changed files with 1,080 additions and 1,215 deletions.
4 changes: 4 additions & 0 deletions .github/workflows/cache_retain.yml
Original file line number Diff line number Diff line change
Expand Up @@ -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 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'
steps:
- name: Checkout and setup
uses: actions/checkout@v2
Expand Down
1 change: 1 addition & 0 deletions unicodetools/data/ucd/dev/ArabicShaping.txt
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand Down
7 changes: 5 additions & 2 deletions unicodetools/data/ucd/dev/CaseFolding.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# CaseFolding-16.0.0.txt
# Date: 2024-04-30, 21:48:11 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
Expand Down Expand Up @@ -1243,7 +1243,10 @@ 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
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
Expand Down
20 changes: 17 additions & 3 deletions unicodetools/data/ucd/dev/DerivedAge.txt
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# DerivedAge-17.0.0.txt
# Date: 2024-10-16, 16:44:59 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
Expand Down Expand Up @@ -2065,9 +2065,23 @@ A7DA..A7DC ; 16.0 # [3] LATIN CAPITAL LETTER LAMBDA..LATIN CAPITAL LETTER L

# Newly assigned in Unicode 17.0.0 (September, 2025)

FD90 ; 17.0 # ARABIC LIGATURE RAHMATU ALLAAHI ALAYH
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
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
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
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: 8
# Total code points: 72

# EOF
214 changes: 110 additions & 104 deletions unicodetools/data/ucd/dev/DerivedCoreProperties.txt

Large diffs are not rendered by default.

34 changes: 23 additions & 11 deletions unicodetools/data/ucd/dev/DerivedNormalizationProps.txt
Original file line number Diff line number Diff line change
@@ -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, 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
Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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

# ================================================

Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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

# ================================================

Expand Down Expand Up @@ -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
Expand Down Expand Up @@ -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

# ================================================

Expand Down Expand Up @@ -5448,11 +5449,15 @@ 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
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
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
Expand Down Expand Up @@ -9148,7 +9153,7 @@ E0080..E00FF ; NFKC_CF; # Cn [128] <reserved-E0080>..<reserved-E
E0100..E01EF ; NFKC_CF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
E01F0..E0FFF ; NFKC_CF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>

# Total code points: 10554
# Total code points: 10558

# ================================================

Expand Down Expand Up @@ -11582,11 +11587,15 @@ 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
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
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
Expand Down Expand Up @@ -15282,7 +15291,7 @@ E0080..E00FF ; NFKC_SCF; # Cn [128] <reserved-E0080>..<reserved-
E0100..E01EF ; NFKC_SCF; # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
E01F0..E0FFF ; NFKC_SCF; # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>

# Total code points: 10516
# Total code points: 10520

# ================================================

Expand Down Expand Up @@ -16052,12 +16061,15 @@ 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
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
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
Expand Down Expand Up @@ -16300,6 +16312,6 @@ E0080..E00FF ; Changes_When_NFKC_Casefolded # Cn [128] <reserved-E0080>..<reser
E0100..E01EF ; Changes_When_NFKC_Casefolded # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
E01F0..E0FFF ; Changes_When_NFKC_Casefolded # Cn [3600] <reserved-E01F0>..<reserved-E0FFF>

# Total code points: 10554
# Total code points: 10558

# EOF
Loading

0 comments on commit 622e83e

Please sign in to comment.