Merge remote-tracking branch 'la-vache/main' into ˇˇ

unicode-org · Nov 13, 2024 · fb60e56 · fb60e56
2 parents b5ae411 + 5e40d67
commit fb60e56
Show file tree

Hide file tree

Showing 37 changed files with 644 additions and 454 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, 14:15:22 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
@@ -2065,8 +2065,13 @@ 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
+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: 1
+# Total code points: 7
 
 # EOF
diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt
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, 09:40:49 GMT
+# EastAsianWidth-17.0.0.txt
+# Date: 2024-11-13, 17:23:26 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
@@ -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
@@ -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
@@ -454,7 +455,7 @@
 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
@@ -502,7 +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
@@ -528,7 +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/IndicPositionalCategory.txt b/unicodetools/data/ucd/dev/IndicPositionalCategory.txt
@@ -1,5 +1,5 @@
 # IndicPositionalCategory-16.0.0.txt
-# Date: 2024-04-30, 21:48:21 GMT
+# Date: 2024-06-06, 09:37:46 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
@@ -423,7 +423,7 @@ AABB..AABC    ; Visual_Order_Left # Lo   [2] TAI VIET VOWEL AUE..TAI VIET VOWEL
 0AFA..0AFF    ; Top # Mn   [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
 0B01          ; Top # Mn       ORIYA SIGN CANDRABINDU
 0B3F          ; Top # Mn       ORIYA VOWEL SIGN I
-0B55..0B56    ; Top # Mn   [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK
+0B53..0B56    ; Top # Mn   [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK
 0B82          ; Top # Mn       TAMIL SIGN ANUSVARA
 0BC0          ; Top # Mn       TAMIL VOWEL SIGN II
 0BCD          ; Top # Mn       TAMIL SIGN VIRAMA

diff --git 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
+# IndicSyllabicCategory-17.0.0.txt
+# Date: 2024-11-13, 16:22:02 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
@@ -525,7 +525,7 @@ ABD1          ; Vowel_Independent # Lo       MEETEI MAYEK LETTER ATIYA
 0B41..0B44    ; Vowel_Dependent # Mn   [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR
 0B47..0B48    ; Vowel_Dependent # Mc   [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
 0B4B..0B4C    ; Vowel_Dependent # Mc   [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
-0B55..0B56    ; Vowel_Dependent # Mn   [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK
+0B53..0B56    ; Vowel_Dependent # Mn   [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK
 0B57          ; Vowel_Dependent # Mc       ORIYA AU LENGTH MARK
 0B62..0B63    ; Vowel_Dependent # Mn   [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL
 0BBE..0BBF    ; Vowel_Dependent # Mc   [2] TAMIL VOWEL SIGN AA..TAMIL VOWEL SIGN I
@@ -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
@@ -1,5 +1,5 @@
 # LineBreak-17.0.0.txt
-# Date: 2024-10-16, 14:15:58 GMT
+# Date: 2024-11-13, 17:23:27 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
@@ -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
@@ -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
@@ -401,7 +402,7 @@
 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
 0B5C..0B5D     ; AL # Lo     [2] ORIYA LETTER RRA..ORIYA LETTER RHA
 0B5F..0B61     ; AL # Lo     [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL
@@ -449,7 +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
@@ -475,7 +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/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt
@@ -1,5 +1,5 @@
 # PropList-17.0.0.txt
-# Date: 2024-10-16, 14:16:11 GMT
+# Date: 2024-11-13, 17:23:34 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
@@ -947,7 +947,7 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 0AFD..0AFF    ; Diacritic # Mn   [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
 0B3C          ; Diacritic # Mn       ORIYA SIGN NUKTA
 0B4D          ; Diacritic # Mn       ORIYA SIGN VIRAMA
-0B55          ; Diacritic # Mn       ORIYA SIGN OVERLINE
+0B53..0B55    ; Diacritic # Mn   [3] ORIYA SIGN DOT ABOVE..ORIYA SIGN OVERLINE
 0BCD          ; Diacritic # Mn       TAMIL SIGN VIRAMA
 0C3C          ; Diacritic # Mn       TELUGU SIGN NUKTA
 0C4D          ; Diacritic # Mn       TELUGU SIGN VIRAMA
@@ -1151,7 +1151,7 @@ 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: 1179
+# Total code points: 1181
 
 # ================================================
 
@@ -1161,7 +1161,7 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 07FA          ; Extender # Lm       NKO LAJANYALAN
 0A71          ; Extender # Mn       GURMUKHI ADDAK
 0AFB          ; Extender # Mn       GUJARATI SIGN SHADDA
-0B55          ; Extender # Mn       ORIYA SIGN OVERLINE
+0B54..0B55    ; Extender # Mn   [2] ORIYA SIGN DOUBLE DOT ABOVE..ORIYA SIGN OVERLINE
 0E46          ; Extender # Lm       THAI CHARACTER MAIYAMOK
 0EC6          ; Extender # Lm       LAO KO LA
 180A          ; Extender # Po       MONGOLIAN NIRUGU
@@ -1198,7 +1198,7 @@ FF70          ; Extender # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
 1E5EF         ; Extender # Mn       OL ONAL SIGN IKIR
 1E944..1E946  ; Extender # Mn   [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
 
-# Total code points: 59
+# Total code points: 60
 
 # ================================================
 

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, 09:41:13 GMT
+# Scripts-17.0.0.txt
+# Date: 2024-11-13, 17:23:47 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
@@ -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
 
 # ================================================
 
@@ -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
 
 # ================================================
 
@@ -1092,7 +1093,7 @@ A8FF          ; Devanagari # Mn       DEVANAGARI VOWEL SIGN AY
 0B47..0B48    ; Oriya # Mc   [2] ORIYA VOWEL SIGN E..ORIYA VOWEL SIGN AI
 0B4B..0B4C    ; Oriya # Mc   [2] ORIYA VOWEL SIGN O..ORIYA VOWEL SIGN AU
 0B4D          ; Oriya # Mn       ORIYA SIGN VIRAMA
-0B55..0B56    ; Oriya # Mn   [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK
+0B53..0B56    ; Oriya # Mn   [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK
 0B57          ; Oriya # Mc       ORIYA AU LENGTH MARK
 0B5C..0B5D    ; Oriya # Lo   [2] ORIYA LETTER RRA..ORIYA LETTER RHA
 0B5F..0B61    ; Oriya # Lo   [3] ORIYA LETTER YYA..ORIYA LETTER VOCALIC LL
@@ -1102,7 +1103,7 @@ A8FF          ; Devanagari # Mn       DEVANAGARI VOWEL SIGN AY
 0B71          ; Oriya # Lo       ORIYA LETTER WA
 0B72..0B77    ; Oriya # No   [6] ORIYA FRACTION ONE QUARTER..ORIYA FRACTION THREE SIXTEENTHS
 
-# Total code points: 91
+# Total code points: 93
 
 # ================================================
 
@@ -1155,15 +1156,15 @@ 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
 0C77          ; Telugu # Po       TELUGU SIGN SIDDHAM
 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
 
 # ================================================
 
@@ -1186,14 +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
 
 # ================================================