Add new InSC of Reordering_Killer and move Batak viramas to it

unicode-org · Nov 12, 2023 · 50b9c4b · 50b9c4b
1 parent dc93882
commit 50b9c4b
Showing 1 changed file with 27 additions and 12 deletions.
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: 2023-11-10, 22:06:18 GMT
+# Date: 2023-11-12, 04:35:00 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
@@ -149,7 +149,6 @@ A980..A981    ; Bindu # Mn   [2] JAVANESE SIGN PANYANGGA..JAVANESE SIGN CECAK
 #   related, but structured somewhat differently.
 
 # [Not derivable]
-
 0903          ; Visarga # Mc       DEVANAGARI SIGN VISARGA
 0983          ; Visarga # Mc       BENGALI SIGN VISARGA
 0A03          ; Visarga # Mc       GURMUKHI SIGN VISARGA
@@ -262,14 +261,15 @@ A9B3          ; Nukta # Mn       JAVANESE SIGN CECAK TELU
 
 # Indic_Syllabic_Category=Virama
 
-# Virama (killing of inherent vowel in consonant sequence
-#         or consonant stacker)
+# Virama (kills inherent vowel of consonant; may act as a Pure_Killer
+#         or Invisible_Stacker depending on context)
 # Only includes characters that can act both as visible killer viramas
 # and consonant stackers. Separate property values exist for characters
-# that can only act as pure killers or only as consonant stackers.
+# that can only act as pure killers, only as reordering killers, or only
+# as consonant stackers.
 
 # [Derivation: (ccc=9) - (InSC=Pure_Killer) - (InSC=Invisible_Stacker)
-#  - (InSC=Number_Joiner) - 2D7F]
+#  - (InSC=Reordering_Killer) - (InSC=Number_Joiner) - 2D7F]
 
 094D          ; Virama # Mn       DEVANAGARI SIGN VIRAMA
 09CD          ; Virama # Mn       BENGALI SIGN VIRAMA
@@ -303,8 +303,9 @@ A9C0          ; Virama # Mc       JAVANESE PANGKON
 
 # Indic_Syllabic_Category=Pure_Killer
 
-# Pure killer (killing of inherent vowel in consonant sequence,
-#              with no consonant stacking behavior)
+# Pure killer (kills inherent vowel of consonant; always visible;
+#              has no conjuct formation, consonant stacking, or reordering
+#              behavior)
 
 # [Not derivable]
 
@@ -320,7 +321,6 @@ A9C0          ; Virama # Mc       JAVANESE PANGKON
 17D1          ; Pure_Killer # Mn       KHMER SIGN VIRIAM
 1A7A          ; Pure_Killer # Mn       TAI THAM SIGN RA HAAM
 1BAA          ; Pure_Killer # Mc       SUNDANESE SIGN PAMAAEH
-1BF2..1BF3    ; Pure_Killer # Mc   [2] BATAK PANGOLAT..BATAK PANONGONAN
 A82C          ; Pure_Killer # Mn       SYLOTI NAGRI SIGN ALTERNATE HASANTA
 A953          ; Pure_Killer # Mc       REJANG VIRAMA
 ABED          ; Pure_Killer # Mn       MEETEI MAYEK APUN IYEK
@@ -339,9 +339,22 @@ ABED          ; Pure_Killer # Mn       MEETEI MAYEK APUN IYEK
 
 # ================================================
 
+# Indic_Syllabic_Category=Reordering_Killer
+
+# Reordering killer (kills inherent vowel of consonant; always visible;
+#                    may cause consonant reordering)
+
+# [Not derivable]
+
+1BF2..1BF3    ; Reordering_Killer # Mc   [2] BATAK PANGOLAT..BATAK PANONGONAN
+
+# ================================================
+
 # Indic_Syllabic_Category=Invisible_Stacker
 
-# Invisible stacker (invisible consonant stacker virama).
+# Invisible stacker (usually kills inherent vowel of consonant; is not visible
+#                    by itself; causes conjunct formation or consonant
+#                    stacking)
 #
 # Note that in some scripts, such as Kharoshthi and Masaram Gondi, an invisible
 # stacker may have a second function, changing the shape and/or location of the
@@ -468,6 +481,7 @@ ABD1          ; Vowel_Independent # Lo       MEETEI MAYEK LETTER ATIYA
 11D6A..11D6B  ; Vowel_Independent # Lo   [2] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER AU
 11F04..11F10  ; Vowel_Independent # Lo  [13] KAWI LETTER A..KAWI LETTER O
 16100         ; Vowel_Independent # Lo       GURUNG KHEMA LETTER A
+16D43         ; Vowel_Independent # Lo       KIRAT RAI LETTER A
 
 # ================================================
 
@@ -949,7 +963,7 @@ ABD2..ABDA    ; Consonant # Lo   [9] MEETEI MAYEK LETTER GOK..MEETEI MAYEK LETTE
 11EE0..11EF1  ; Consonant # Lo  [18] MAKASAR LETTER KA..MAKASAR LETTER A
 11F12..11F33  ; Consonant # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
 16101..1611D  ; Consonant # Lo  [29] GURUNG KHEMA LETTER KA..GURUNG KHEMA LETTER SA
-16D43..16D62  ; Consonant # Lo  [32] KIRAT RAI LETTER A..KIRAT RAI LETTER HA
+16D44..16D62  ; Consonant # Lo  [31] KIRAT RAI LETTER KA..KIRAT RAI LETTER HA
 
 # ================================================
 
@@ -1353,6 +1367,7 @@ ABF0..ABF9    ; Number # Nd  [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI
 114D0..114D9  ; Number # Nd  [10] TIRHUTA DIGIT ZERO..TIRHUTA DIGIT NINE
 11650..11659  ; Number # Nd  [10] MODI DIGIT ZERO..MODI DIGIT NINE
 116C0..116C9  ; Number # Nd  [10] TAKRI DIGIT ZERO..TAKRI DIGIT NINE
+116D0..116E3  ; Number # Nd  [20] MYANMAR PAO DIGIT ZERO..MYANMAR EASTERN PWO KAREN DIGIT NINE
 11730..11739  ; Number # Nd  [10] AHOM DIGIT ZERO..AHOM DIGIT NINE
 1173A..1173B  ; Number # No   [2] AHOM NUMBER TEN..AHOM NUMBER TWENTY
 11950..11959  ; Number # Nd  [10] DIVES AKURU DIGIT ZERO..DIVES AKURU DIGIT NINE
@@ -1372,7 +1387,7 @@ ABF0..ABF9    ; Number # Nd  [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NI
 # script, e.g. in Brahmi)
 #
 # Note: These are different from Numbers, in the way that there is no known
-# evidence of Brahmi Joining Numbers taking vowels or subjoined consonants.
+# evidence of Brahmi Joining Numbers taking vowels or subjoined consonants. 
 # Until such evidence is found, implementations may assume that Brahmi
 # Joining Numbers only participate in shaping with other Brahmi Joining
 # Numbers.