Merge remote-tracking branch 'la-vache/main' into pipeline-gap-174-C20

unicode-org · Nov 13, 2024 · 1393ed7 · 1393ed7
2 parents a19b6aa + a3e3740
commit 1393ed7
Show file tree

Hide file tree

Showing 32 changed files with 526 additions and 370 deletions.
diff --git 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 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

diff --git 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
@@ -1,5 +1,5 @@
 # DerivedAge-17.0.0.txt
-# Date: 2024-10-16, 14:19:34 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
@@ -2065,8 +2065,9 @@ 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
@@ -1,5 +1,5 @@
 # DerivedCoreProperties-17.0.0.txt
-# Date: 2024-10-16, 14:20:01 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
@@ -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
@@ -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: 142760
+# Total code points: 142761
 
 # ================================================
 
@@ -6260,7 +6260,7 @@ 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
@@ -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: 141270
+# Total code points: 141271
 
 # ================================================
 
@@ -7070,7 +7070,7 @@ 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
@@ -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: 144542
+# Total code points: 144543
 
 # ================================================
 
@@ -8444,7 +8444,7 @@ 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
@@ -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: 141247
+# Total code points: 141248
 
 # ================================================
 
@@ -9254,7 +9254,7 @@ 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
@@ -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: 144523
+# Total code points: 144524
 
 # ================================================
 
@@ -11195,7 +11195,7 @@ 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
@@ -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: 152731
+# Total code points: 152732
 
 # ================================================
 

diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt
@@ -1,5 +1,5 @@
-# EastAsianWidth-16.0.0.txt
-# Date: 2024-06-06, 09:53:44 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
@@ -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
@@ -1,5 +1,5 @@
 # LineBreak-17.0.0.txt
-# Date: 2024-10-16, 14:20:09 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
@@ -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
@@ -1,5 +1,5 @@
-# Scripts-16.0.0.txt
-# Date: 2024-06-06, 09:54:09 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
@@ -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
@@ -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
@@ -1,5 +1,5 @@
-# VerticalOrientation-16.0.0.txt
-# Date: 2024-06-06, 09:54:11 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
@@ -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