-# IndicSyllabicCategory-13.0.0.txt
-# Date: 2019-07-22, 19:55:00 GMT [KW, RP]
-# © 2019 Unicode®, Inc.
+# IndicSyllabicCategory-15.0.0.txt
+# Date: 2022-05-26, 02:18:00 GMT [KW, RP]
+# © 2022 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 http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# For documentation, see UAX #44: Unicode Character Database,
-# at http://www.unicode.org/reports/tr44/
+# at https://www.unicode.org/reports/tr44/
#
# This file defines the following property:
#
#
# Ahom, Balinese, Batak, Bengali, Bhaiksuki, Brahmi, Buginese, Buhid,
# Chakma, Cham, Devanagari, Dives Akuru, Dogra, Grantha, Gujarati,
-# Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada,
+# Gunjala Gondi, Gurmukhi, Hanunoo, Javanese, Kaithi, Kannada, Kawi,
# Kayah Li, Kharoshthi, Khmer, Khojki, Khudawadi, Lao, Lepcha, Limbu,
# Mahajani, Makasar, Malayalam, Marchen, Masaram Gondi, Meetei Mayek,
# Modi, Multani, Myanmar, Nandinagari, Newa, New Tai Lue, Oriya,
0C80 ; Bindu # Lo KANNADA SIGN SPACING CANDRABINDU
0C81 ; Bindu # Mn KANNADA SIGN CANDRABINDU
0C82 ; Bindu # Mc KANNADA SIGN ANUSVARA
+0CF3 ; Bindu # Mc KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
0D00..0D01 ; Bindu # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
0D02 ; Bindu # Mc MALAYALAM SIGN ANUSVARA
0D04 ; Bindu # Lo MALAYALAM LETTER VEDIC ANUSVARA
11CB5..11CB6 ; Bindu # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU
11D40 ; Bindu # Mn MASARAM GONDI SIGN ANUSVARA
11D95 ; Bindu # Mn GUNJALA GONDI SIGN ANUSVARA
+11F00..11F01 ; Bindu # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
# ================================================
11C3E ; Visarga # Mc BHAIKSUKI SIGN VISARGA
11D41 ; Visarga # Mn MASARAM GONDI SIGN VISARGA
11D96 ; Visarga # Mc GUNJALA GONDI SIGN VISARGA
+11F03 ; Visarga # Mc KAWI SIGN VISARGA
# ================================================
0ABC ; Nukta # Mn GUJARATI SIGN NUKTA
0AFD..0AFF ; Nukta # Mn [3] GUJARATI SIGN THREE-DOT NUKTA ABOVE..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
0B3C ; Nukta # Mn ORIYA SIGN NUKTA
+0C3C ; Nukta # Mn TELUGU SIGN NUKTA
0CBC ; Nukta # Mn KANNADA SIGN NUKTA
0F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU
1B34 ; Nukta # Mn BALINESE SIGN REREKAN
0F84 ; Pure_Killer # Mn TIBETAN MARK HALANTA
103A ; Pure_Killer # Mn MYANMAR SIGN ASAT
1714 ; Pure_Killer # Mn TAGALOG SIGN VIRAMA
-1734 ; Pure_Killer # Mn HANUNOO SIGN PAMUDPOD
+1715 ; Pure_Killer # Mc TAGALOG SIGN PAMUDPOD
+1734 ; Pure_Killer # Mc HANUNOO SIGN PAMUDPOD
17D1 ; Pure_Killer # Mn KHMER SIGN VIRIAM
1A7A ; Pure_Killer # Mn TAI THAM SIGN RA HAAM
1BAA ; Pure_Killer # Mc SUNDANESE SIGN PAMAAEH
A82C ; Pure_Killer # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA
A953 ; Pure_Killer # Mc REJANG VIRAMA
ABED ; Pure_Killer # Mn MEETEI MAYEK APUN IYEK
+11070 ; Pure_Killer # Mn BRAHMI SIGN OLD TAMIL VIRAMA
11134 ; Pure_Killer # Mn CHAKMA MAAYYAA
112EA ; Pure_Killer # Mn KHUDAWADI SIGN VIRAMA
1172B ; Pure_Killer # Mn AHOM SIGN KILLER
1193D ; Pure_Killer # Mc DIVES AKURU SIGN HALANTA
11A34 ; Pure_Killer # Mn ZANABAZAR SQUARE SIGN VIRAMA
11D44 ; Pure_Killer # Mn MASARAM GONDI SIGN HALANTA
+11F41 ; Pure_Killer # Mc KAWI SIGN KILLER
# ================================================
11A99 ; Invisible_Stacker # Mn SOYOMBO SUBJOINER
11D45 ; Invisible_Stacker # Mn MASARAM GONDI VIRAMA
11D97 ; Invisible_Stacker # Mn GUNJALA GONDI VIRAMA
+11F42 ; Invisible_Stacker # Mn KAWI CONJOINER
# ================================================
ABCE..ABCF ; Vowel_Independent # Lo [2] MEETEI MAYEK LETTER UN..MEETEI MAYEK LETTER I
ABD1 ; Vowel_Independent # Lo MEETEI MAYEK LETTER ATIYA
11005..11012 ; Vowel_Independent # Lo [14] BRAHMI LETTER A..BRAHMI LETTER AU
+11071..11072 ; Vowel_Independent # Lo [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O
11083..1108C ; Vowel_Independent # Lo [10] KAITHI LETTER A..KAITHI LETTER AU
11103..11106 ; Vowel_Independent # Lo [4] CHAKMA LETTER AA..CHAKMA LETTER E
11183..11190 ; Vowel_Independent # Lo [14] SHARADA LETTER A..SHARADA LETTER AU
11200..11207 ; Vowel_Independent # Lo [8] KHOJKI LETTER A..KHOJKI LETTER AU
+11240 ; Vowel_Independent # Lo KHOJKI LETTER SHORT I
11280..11283 ; Vowel_Independent # Lo [4] MULTANI LETTER A..MULTANI LETTER E
112B0..112B9 ; Vowel_Independent # Lo [10] KHUDAWADI LETTER A..KHUDAWADI LETTER AU
11305..1130C ; Vowel_Independent # Lo [8] GRANTHA LETTER A..GRANTHA LETTER VOCALIC L
11D60..11D65 ; Vowel_Independent # Lo [6] GUNJALA GONDI LETTER A..GUNJALA GONDI LETTER UU
11D67..11D68 ; Vowel_Independent # Lo [2] GUNJALA GONDI LETTER EE..GUNJALA GONDI LETTER AI
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
# ================================================
10A05..10A06 ; Vowel_Dependent # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O
10A0C..10A0D ; Vowel_Dependent # Mn [2] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN DOUBLE RING BELOW
11038..11045 ; Vowel_Dependent # Mn [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU
+11073..11074 ; Vowel_Dependent # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
110B0..110B2 ; Vowel_Dependent # Mc [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
110B3..110B6 ; Vowel_Dependent # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
110B7..110B8 ; Vowel_Dependent # Mc [2] KAITHI VOWEL SIGN O..KAITHI VOWEL SIGN AU
+110C2 ; Vowel_Dependent # Mn KAITHI VOWEL SIGN VOCALIC R
11127..1112B ; Vowel_Dependent # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU
1112C ; Vowel_Dependent # Mc CHAKMA VOWEL SIGN E
1112D..11132 ; Vowel_Dependent # Mn [6] CHAKMA VOWEL SIGN AI..CHAKMA AU MARK
1122C..1122E ; Vowel_Dependent # Mc [3] KHOJKI VOWEL SIGN AA..KHOJKI VOWEL SIGN II
1122F..11231 ; Vowel_Dependent # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI
11232..11233 ; Vowel_Dependent # Mc [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
+11241 ; Vowel_Dependent # Mn KHOJKI VOWEL SIGN VOCALIC R
112E0..112E2 ; Vowel_Dependent # Mc [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
112E3..112E8 ; Vowel_Dependent # Mn [6] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN AU
1133E..1133F ; Vowel_Dependent # Mc [2] GRANTHA VOWEL SIGN AA..GRANTHA VOWEL SIGN I
11D93..11D94 ; Vowel_Dependent # Mc [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
11EF3..11EF4 ; Vowel_Dependent # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
11EF5..11EF6 ; Vowel_Dependent # Mc [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F34..11F35 ; Vowel_Dependent # Mc [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F36..11F3A ; Vowel_Dependent # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F3E..11F3F ; Vowel_Dependent # Mc [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F40 ; Vowel_Dependent # Mn KAWI VOWEL SIGN EU
# ================================================
106E..1070 ; Consonant # Lo [3] MYANMAR LETTER EASTERN PWO KAREN NNA..MYANMAR LETTER EASTERN PWO KAREN GHWA
1075..1081 ; Consonant # Lo [13] MYANMAR LETTER SHAN KA..MYANMAR LETTER SHAN HA
108E ; Consonant # Lo MYANMAR LETTER RUMAI PALAUNG FA
-1703..170C ; Consonant # Lo [10] TAGALOG LETTER KA..TAGALOG LETTER YA
-170E..1711 ; Consonant # Lo [4] TAGALOG LETTER LA..TAGALOG LETTER HA
+1703..1711 ; Consonant # Lo [15] TAGALOG LETTER KA..TAGALOG LETTER HA
+171F ; Consonant # Lo TAGALOG LETTER ARCHAIC RA
1723..1731 ; Consonant # Lo [15] HANUNOO LETTER KA..HANUNOO LETTER HA
1743..1751 ; Consonant # Lo [15] BUHID LETTER KA..BUHID LETTER HA
1763..176C ; Consonant # Lo [10] TAGBANWA LETTER KA..TAGBANWA LETTER YA
1A20..1A4C ; Consonant # Lo [45] TAI THAM LETTER HIGH KA..TAI THAM LETTER LOW HA
1A53..1A54 ; Consonant # Lo [2] TAI THAM LETTER LAE..TAI THAM LETTER GREAT SA
1B13..1B33 ; Consonant # Lo [33] BALINESE LETTER KA..BALINESE LETTER HA
-1B45..1B4B ; Consonant # Lo [7] BALINESE LETTER KAF SASAK..BALINESE LETTER ASYURA SASAK
+1B45..1B4C ; Consonant # Lo [8] BALINESE LETTER KAF SASAK..BALINESE LETTER ARCHAIC JNYA
1B8A..1BA0 ; Consonant # Lo [23] SUNDANESE LETTER KA..SUNDANESE LETTER HA
1BAE..1BAF ; Consonant # Lo [2] SUNDANESE LETTER KHA..SUNDANESE LETTER SYA
1BBB..1BBD ; Consonant # Lo [3] SUNDANESE LETTER REU..SUNDANESE LETTER BHA
10A15..10A17 ; Consonant # Lo [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
10A19..10A35 ; Consonant # Lo [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA
11013..11037 ; Consonant # Lo [37] BRAHMI LETTER KA..BRAHMI LETTER OLD TAMIL NNNA
+11075 ; Consonant # Lo BRAHMI LETTER OLD TAMIL LLA
1108D..110AF ; Consonant # Lo [35] KAITHI LETTER KA..KAITHI LETTER HA
11107..11126 ; Consonant # Lo [32] CHAKMA LETTER KAA..CHAKMA LETTER HAA
11144 ; Consonant # Lo CHAKMA LETTER LHAA
11191..111B2 ; Consonant # Lo [34] SHARADA LETTER KA..SHARADA LETTER HA
11208..11211 ; Consonant # Lo [10] KHOJKI LETTER KA..KHOJKI LETTER JJA
11213..1122B ; Consonant # Lo [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
+1123F ; Consonant # Lo KHOJKI LETTER QA
11284..11286 ; Consonant # Lo [3] MULTANI LETTER KA..MULTANI LETTER GA
11288 ; Consonant # Lo MULTANI LETTER GHA
1128A..1128D ; Consonant # Lo [4] MULTANI LETTER CA..MULTANI LETTER JJA
1168A..116AA ; Consonant # Lo [33] TAKRI LETTER KA..TAKRI LETTER RRA
116B8 ; Consonant # Lo TAKRI LETTER ARCHAIC KHA
11700..1171A ; Consonant # Lo [27] AHOM LETTER KA..AHOM LETTER ALTERNATE BA
+11740..11746 ; Consonant # Lo [7] AHOM LETTER CA..AHOM LETTER LLA
1180A..1182B ; Consonant # Lo [34] DOGRA LETTER KA..DOGRA LETTER RRA
1190C..11913 ; Consonant # Lo [8] DIVES AKURU LETTER KA..DIVES AKURU LETTER JA
11915..11916 ; Consonant # Lo [2] DIVES AKURU LETTER NYA..DIVES AKURU LETTER TTA
11D0C..11D30 ; Consonant # Lo [37] MASARAM GONDI LETTER KA..MASARAM GONDI LETTER TRA
11D6C..11D89 ; Consonant # Lo [30] GUNJALA GONDI LETTER YA..GUNJALA GONDI LETTER SA
11EE0..11EF1 ; Consonant # Lo [18] MAKASAR LETTER KA..MAKASAR LETTER A
+11F12..11F33 ; Consonant # Lo [34] KAWI LETTER KA..KAWI LETTER JNYA
# ================================================
# [Not derivable]
09CE ; Consonant_Dead # Lo BENGALI LETTER KHANDA TA
+0C5D ; Consonant_Dead # Lo TELUGU LETTER NAKAARA POLLU
+0CDD ; Consonant_Dead # Lo KANNADA LETTER NAKAARA POLLU
0D54..0D56 ; Consonant_Dead # Lo [3] MALAYALAM LETTER CHILLU M..MALAYALAM LETTER CHILLU LLL
0D7A..0D7F ; Consonant_Dead # Lo [6] MALAYALAM LETTER CHILLU NN..MALAYALAM LETTER CHILLU K
1CF2..1CF3 ; Consonant_Dead # Lo [2] VEDIC SIGN ARDHAVISARGA..VEDIC SIGN ROTATED ARDHAVISARGA
0D4E ; Consonant_Preceding_Repha # Lo MALAYALAM LETTER DOT REPH
11941 ; Consonant_Preceding_Repha # Lo DIVES AKURU INITIAL RA
11D46 ; Consonant_Preceding_Repha # Lo MASARAM GONDI REPHA
+11F02 ; Consonant_Preceding_Repha # Lo KAWI SIGN REPHA
# ================================================
# [Not derivable]
17CC ; Consonant_Succeeding_Repha # Mn KHMER SIGN ROBAT
-1B03 ; Consonant_Succeeding_Repha # Mn BALINESE SIGN SURANG
-1B81 ; Consonant_Succeeding_Repha # Mn SUNDANESE SIGN PANGLAYAR
-A982 ; Consonant_Succeeding_Repha # Mn JAVANESE SIGN LAYAR
# ================================================
1939 ; Consonant_Final # Mn LIMBU SIGN MUKPHRENG
19C1..19C7 ; Consonant_Final # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B
1A58..1A59 ; Consonant_Final # Mn [2] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN FINAL NGA
+1B03 ; Consonant_Final # Mn BALINESE SIGN SURANG
+1B81 ; Consonant_Final # Mn SUNDANESE SIGN PANGLAYAR
1BBE..1BBF ; Consonant_Final # Lo [2] SUNDANESE LETTER FINAL K..SUNDANESE LETTER FINAL M
1BF0..1BF1 ; Consonant_Final # Mn [2] BATAK CONSONANT SIGN NG..BATAK CONSONANT SIGN H
1C2D..1C33 ; Consonant_Final # Mn [7] LEPCHA CONSONANT SIGN K..LEPCHA CONSONANT SIGN T
A94F..A951 ; Consonant_Final # Mn [3] REJANG CONSONANT SIGN NG..REJANG CONSONANT SIGN R
A952 ; Consonant_Final # Mc REJANG CONSONANT SIGN H
+A982 ; Consonant_Final # Mn JAVANESE SIGN LAYAR
AA40..AA42 ; Consonant_Final # Lo [3] CHAM LETTER FINAL K..CHAM LETTER FINAL NG
AA43 ; Consonant_Final # Mn CHAM CONSONANT SIGN FINAL NG
AA44..AA4B ; Consonant_Final # Lo [8] CHAM LETTER FINAL CH..CHAM LETTER FINAL SS
# Indic_Syllabic_Category=Gemination_Mark
# Gemination Mark (doubling of the preceding or following consonant)
+#
+# U+0A71 GURMUKHI ADDAK precedes the consonant it geminates, while the
+# others follow the consonant they geminate.
# [Not derivable]
0A71 ; Gemination_Mark # Mn GURMUKHI ADDAK
+0AFB ; Gemination_Mark # Mn GUJARATI SIGN SHADDA
11237 ; Gemination_Mark # Mn KHOJKI SIGN SHADDA
11A98 ; Gemination_Mark # Mn SOYOMBO GEMINATION MARK
0951..0952 ; Cantillation_Mark # Mn [2] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI STRESS SIGN ANUDATTA
0A51 ; Cantillation_Mark # Mn GURMUKHI SIGN UDAAT
-0AFA..0AFC ; Cantillation_Mark # Mn [3] GUJARATI SIGN SUKUN..GUJARATI SIGN MADDAH
+0AFA ; Cantillation_Mark # Mn GUJARATI SIGN SUKUN
+0AFC ; Cantillation_Mark # Mn GUJARATI SIGN MADDAH
1CD0..1CD2 ; Cantillation_Mark # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA
1CD4..1CE0 ; Cantillation_Mark # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA
1CE1 ; Cantillation_Mark # Mc VEDIC TONE ATHARVAVEDIC INDEPENDENT SVARITA
# Indic_Syllabic_Category=Syllable_Modifier
# Syllable Modifier (miscellaneous combining characters that modify
-# something in the orthographic syllable they succeed)
+# something in the orthographic syllable they succeed or appear in)
# [Not derivable]
00B2..00B3 ; Syllable_Modifier # No [2] SUPERSCRIPT TWO..SUPERSCRIPT THREE
09FE ; Syllable_Modifier # Mn BENGALI SANDHI MARK
+0ECE ; Syllable_Modifier # Mn LAO YAMAKKAN
0F35 ; Syllable_Modifier # Mn TIBETAN MARK NGAS BZUNG NYI ZLA
0F37 ; Syllable_Modifier # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS
0FC6 ; Syllable_Modifier # Mn TIBETAN SYMBOL PADMA GDAN
11C5A..11C6C ; Number # No [19] BHAIKSUKI NUMBER ONE..BHAIKSUKI HUNDREDS UNIT MARK
11D50..11D59 ; Number # Nd [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
11DA0..11DA9 ; Number # Nd [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
+11F50..11F59 ; Number # Nd [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
# ================================================
# Indic_Syllabic_Category=Brahmi_Joining_Number
-# Brahmi Joining Number (similar to Number in that in can be used as
-# vowel-holders like Consonant_Placeholder, but may also be joined by
-# a Number_Joiner of the same script, e.g. in Brahmi)
+# Brahmi Joining Number (may be joined by a Number_Joiner of the same
+# 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.
+# Until such evidence is found, implementations may assume that Brahmi
+# Joining Numbers only participate in shaping with other Brahmi Joining
+# Numbers.
# [Not derivable]
projects / factor.git / blobdiff