1# Override values For Indic_Syllabic_Category 2# Not derivable 3# Initial version based on Unicode 7.0 by Andrew Glass 2014-03-17 4# Updated for Unicode 10.0 by Andrew Glass 2017-07-25 5# Updated for Unicode 12.1 by Andrew Glass 2019-05-24 6# Updated for Unicode 13.0 by Andrew Glass 2020-07-28 7# Updated for Unicode 14.0 by Andrew Glass 2021-09-25 8# Updated for Unicode 15.0 by Andrew Glass 2022-09-16 9 10# ================================================ 11# OVERRIDES TO ASSIGNED VALUES 12# ================================================ 13 14# Indic_Syllabic_Category=Bindu 15193A ; Bindu # Mn LIMBU SIGN KEMPHRENG 16AA29 ; Bindu # Mn CHAM VOWEL SIGN AA 1710A0D ; Bindu # Mn KHAROSHTHI SIGN DOUBLE RING BELOW 18 19# ================================================ 20 21# Indic_Syllabic_Category=Consonant 2219C1..19C7 ; Consonant # Lo [7] NEW TAI LUE LETTER FINAL V..NEW TAI LUE LETTER FINAL B # Reassigned to avoid clustering with a base consonant 2325CC ; Consonant # So DOTTED CIRCLE #Reassigned to allow it to cluster as a generic base 24 25# ================================================ 26 27# Indic_Syllabic_Category=Consonant_Dead 280F7F ; Consonant_Dead # Mc TIBETAN SIGN RNAM BCAD # reassigned so that visarga can form an independent cluster, but see #19 29 30# ================================================ 31 32# Indic_Syllabic_Category=Consonant_Final_Modifier 331C36 ; Consonant_Final_Modifier # Mn LEPCHA SIGN RAN 34 35# ================================================ 36 37# Indic_Syllabic_Category=Gemination_Mark 3811134 ; Gemination_Mark # Mc CHAKMA MAAYYAA 39 40# ================================================ 41 42# Indic_Syllabic_Category=Nukta 430F71 ; Nukta # Mn TIBETAN VOWEL SIGN AA # Reassigned to get this before an above vowel, but see #22 441BF2..1BF3 ; Nukta # Mc [2] BATAK PANGOLAT..BATAK PANONGONAN # see USE issue #20 45 46# ================================================ 47 48# Indic_Syllabic_Category=Tone_Mark 491A7B..1A7C ; Tone_Mark # Mn [2] TAI THAM SIGN MAI SAM..TAI THAM SIGN KHUEN-LUE KARAN 501A7F ; Tone_Mark # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT 51 52# ================================================ 53 54# Indic_Syllabic_Category=Vowel_Independent 55AAB1 ; Vowel_Independent # Lo TAI VIET VOWEL AA 56AABA ; Vowel_Independent # Lo TAI VIET VOWEL UA 57AABD ; Vowel_Independent # Lo TAI VIET VOWEL AN 58 59# ================================================ 60# ================================================ 61# VALUES NOT ASSIGNED IN Indic_Syllabic_Category 62# ================================================ 63# ================================================ 64 65# Indic_Syllabic_Category=Consonant 660800..0815 ; Consonant # Lo [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF 670840..0858 ; Consonant # Lo [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN 680F00..0F01 ; Consonant # Lo [2] TIBETAN SYLLABLE OM..TIBETAN MARK GTER YIG MGO TRUNCATED 690F04..0F06 ; Consonant # Po TIBETAN MARK INITIAL YIG MGO MDUN MA..TIBETAN MARK CARET YIG MGO PHUR SHAD MA 701800 ; Consonant # Po MONGOLIAN BIRGA # Reassigned so that legacy Birga + MFVS sequences still work 711807 ; Consonant # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER 72180A ; Consonant # Po MONGOLIAN NIRUGU 731820..1878 ; Consonant # Lo [88] MONGOLIAN LETTER A..MONGOLIAN LETTER CHA WITH TWO DOTS 741843 ; Consonant # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN 752D30..2D67 ; Consonant # Lo [56] TIFINAGH LETTER YA..TIFINAGH LETTER YO 762D6F ; Consonant # Lm TIFINAGH MODIFIER LETTER LABIALIZATION MARK 7710570..1057A ; Consonant # Lo [11] VITHKUQI CAPITAL LETTER A..VITHKUQI CAPITAL LETTER GA 781057C..1058A ; Consonant # Lo [15] VITHKUQI CAPITAL LETTER HA..VITHKUQI CAPITAL LETTER RE 791058C..10592 ; Consonant # Lo [7] VITHKUQI CAPITAL LETTER SE..VITHKUQI CAPITAL LETTER XE 8010594..10595 ; Consonant # Lo [2] VITHKUQI CAPITAL LETTER Y..VITHKUQI CAPITAL LETTER ZE 8110597..105A1 ; Consonant # Lo [11] VITHKUQI SMALL LETTER A..VITHKUQI SMALL LETTER GA 82105A3..105B1 ; Consonant # Lo [15] VITHKUQI SMALL LETTER HA..VITHKUQI SMALL LETTER RE 83105B3..105B9 ; Consonant # Lo [7] VITHKUQI SMALL LETTER SE..VITHKUQI SMALL LETTER XE 84105BB..105BC ; Consonant # Lo [2] VITHKUQI SMALL LETTER Y..VITHKUQI SMALL LETTER ZE 8510AC0..10AC7 ; Consonant # Lo [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW 8610AC9..10AE4 ; Consonant # Lo [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW 8710D00..10D23 ; Consonant # Lo [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA 8810E80..10EA9 ; Consonant # Lo [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET 8910EB0..10EB1 ; Consonant # Lo [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE 9010F30..10F45 ; Consonant # Lo [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN 9110F70..10F81 ; Consonant # Lo [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH 92111DA ; Consonant # Lo SHARADA EKAM 93#HIEROGLYPHS to be moved to new category 9413000..1342F ; Consonant # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D 95#For the Begin and End segment to be handled fully correctly, the cluster model needs to be modified. 9613437..13438 ; Consonant # Lo [2] EGYPTIAN HIEROGLYPH BEGIN SEGMENT..EGYPTIAN HIEROGLYPH END SEGMENT 9713441..13446 ; Consonant # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..HIEROGLYPH WIDE LOST SIGN 9816B00..16B2F ; Consonant # Lo [48] PAHAWH HMONG VOWEL KEEB..PAHAWH HMONG CONSONANT CAU 9916F00..16F4A ; Consonant # Lo [75] MIAO LETTER PA..MIAO LETTER RTE 10016FE4 ; Consonant # Mn KHITAN SMALL SCRIPT FILLER # Avoids Mn pushing this into VOWEL class 10118B00..18CD5 ; Consonant # Lo [470] KHITAN SMALL SCRIPT CHARACTER-18B00..KHITAN SMALL SCRIPT CHARACTER-18CD5 1021BC00..1BC6A ; Consonant # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1031BC70..1BC7C ; Consonant # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1041BC80..1BC88 ; Consonant # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL 1051BC90..1BC99 ; Consonant # Lo [10] DUPLOYAN AFFIX LOW ACUTE..DUPLOYAN AFFIX LOW ARROW 1061E100..1E12C ; Consonant # Lo [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W 1071E137..1E13D ; Consonant # Lm [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER 1081E14E ; Consonant # Lo NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ 1091E14F ; Consonant # So NYIAKENG PUACHUE HMONG CIRCLED CA 1101E290..1E2AD ; Consonant # Lo [30] TOTO LETTER PA..TOTO LETTER A 1111E2C0..1E2EB ; Consonant # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1121E4D0..1E4EA ; Consonant # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1131E4EB ; Consonant # Lm NAG MUNDARI SIGN OJOD 1141E900..1E921 ; Consonant # Lu [34] ADLAM CAPITAL LETTER ALIF..ADLAM CAPITAL LETTER SHA 1151E922..1E943 ; Consonant # Ll [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA 1161E94B ; Consonant # Lm ADLAM NASALIZATION MARK 117 118# ================================================ 119 120# Indic_Syllabic_Category=Consonant_Placeholder 1211880..1884 ; Consonant_Placeholder # Lo [5] MONGOLIAN LETTER ALI GALI ANUSVARA ONE..MONGOLIAN LETTER ALI GALI INVERTED UBADAMA 122 123# ================================================ 124 125# Indic_Syllabic_Category=Gemination_Mark 12610D27 ; Gemination_Mark # Mn HANIFI ROHINGYA SIGN TASSI 127 128# ================================================ 129 130# Indic_Syllabic_Category=Modifying_Letter 131FE00..FE0F ; Modifying_Letter # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16# Need to treat them as isolated bases so they don't merge with a cluster in invalid scenarios 13216F50 ; Modifying_Letter # Lo MIAO LETTER NASALIZATION 133 134# ================================================ 135 136# Indic_Syllabic_Category=Nukta 1370859..085B ; Nukta # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK 1380F39 ; Nukta # Mn TIBETAN MARK TSA -PHRU # NOW IN UNICODE 10.0 1391885..1886 ; Nukta # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA 14018A9 ; Nukta # Mn MONGOLIAN LETTER ALI GALI DAGALGA 14110AE5..10AE6 ; Nukta # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW 14216F4F ; Nukta # Mn MIAO SIGN CONSONANT MODIFIER BAR 1431BC9D..1BC9E ; Nukta # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK 1441E944..1E94A ; Nukta # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 14510F82..10F85 ; Nukta # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW 146 147# ================================================ 148 149# Indic_Syllabic_Category=Number 15010D30..10D39 ; Number # Nd [10] HANIFI ROHINGYA DIGIT ZERO..HANIFI ROHINGYA DIGIT NINE 15110F51..10F54 ; Number # No [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED 15216AC0..16AC9 ; Number # Nd [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE 1531E140..1E149 ; Number # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1541E2F0..1E2F9 ; Number # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1551E4F0..1E4F9 ; Number # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE 1561E950..1E959 ; Number # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 157 158# ================================================ 159 160# Indic_Syllabic_Category=Tone_Mark 16107EB..07F3 ; Tone_Mark # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE 16207FD ; Tone_Mark # Mn NKO DANTAYALAN 1630F86..0F87 ; Tone_Mark # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS 16417CF ; Tone_Mark # Mn KHMER SIGN AHSDA 16510D24..10D26 ; Tone_Mark # Mn [3] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TANA 16610F46..10F50 ; Tone_Mark # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW 16716B30..16B36 ; Tone_Mark # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM 16816F8F..16F92 ; Tone_Mark # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW 1691E130..1E136 ; Tone_Mark # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1701E2AE ; Tone_Mark # Mn TOTO SIGN RISING TONE 1711E2EC..1E2EF ; Tone_Mark # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 172 173# ================================================ 174 175# Indic_Syllabic_Category=Virama 1762D7F ; Virama # Mn TIFINAGH CONSONANT JOINER 177#HIEROGLYPHS to be moved to new category 17813430..13436 ; Virama # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE 17913439..1343B ; Virama # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM 180 181# ================================================ 182 183# Indic_Syllabic_Category=Vowel_Independent 184AAB1 ; Vowel_Independent # Lo TAI VIET VOWEL AA 185AABA ; Vowel_Independent # Lo TAI VIET VOWEL UA 186AABD ; Vowel_Independent # Lo TAI VIET VOWEL AN 187 188# ================================================ 189 190# Indic_Syllabic_Category=Vowel_Dependent 1910B55 ; Vowel_Dependent # Mn ORIYA SIGN OVERLINE 19210EAB..10EAC ; Vowel_Dependent # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK 19316F51..16F87 ; Vowel_Dependent # Mc [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI 1941E4EC..1E4EF ; Vowel_Dependent # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 195 196# ================================================ 197 198# Indic_Syllabic_Category=Cantillation_Mark 199 2001CF8..1CF9 ; Cantillation_Mark # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE 201#HIEROGLYPHS to be moved to new category 20213440 ; Cantillation_Mark # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY 20313447..13455 ; Cantillation_Mark # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 204 205# ================================================ 206 207# Indic_Syllabic_Category=Symbol_Modifier 2081B6B..1B73 ; Symbol_Modifier # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG 209 210# ================================================ 211# ================================================ 212# PROPERTIES NOT ASSIGNED IN Indic_Syllabic_Category 213# ================================================ 214# ================================================ 215 216# USE, Extended_Syllabic_Category=Hieroglyph 217# 13000..1342F ; Hieroglyph # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D 218# 13441..13446 ; Hieroglyph # Lo [6] EGYPTIAN HIEROGLYPH FULL BLANK..HIEROGLYPH WIDE LOST SIGN 219 220# ================================================ 221 222# USE, Extended_Syllabic_Category=Hieroglyph_Joiner 223# 13430..13436 ; Hieroglyph_Joiner # Cf [7] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH OVERLAY MIDDLE 224# 13439..1343B ; Hieroglyph_Joiner # Cf [3] EGYPTIAN HIEROGLYPH INSERT AT MIDDLE..EGYPTIAN HIEROGLYPH INSERT AT BOTTOM 225 226# ================================================ 227 228# USE, Extended_Syllabic_Category=Hieroglyph_Mark_Begin 229# 005B ; Hieroglyph_Mark_Begin # Ps LEFT SQUARE BRACKET 230# 007B ; Hieroglyph_Mark_Begin # Ps LEFT CURLY BRACKET 231# 27E6 ; Hieroglyph_Mark_Begin # Ps MATHEMATICAL LEFT WHITE SQUARE BRACKET 232# 27E8 ; Hieroglyph_Mark_Begin # Ps MATHEMATICAL LEFT ANGLE BRACKET 233# 2E22 ; Hieroglyph_Mark_Begin # Ps TOP LEFT HALF BRACKET 234# 2E24 ; Hieroglyph_Mark_Begin # Ps BOTTOM LEFT HALF BRACKET 235 236# ================================================ 237 238# USE, Extended_Syllabic_Category=Hieroglyph_Mark_End 239# 005D ; Hieroglyph_Mark_Begin # Pe RIGHT SQUARE BRACKET 240# 007D ; Hieroglyph_Mark_Begin # Pe RIGHT CURLY BRACKET 241# 27E7 ; Hieroglyph_Mark_Begin # Pe MATHEMATICAL RIGHT WHITE SQUARE BRACKET 242# 27E9 ; Hieroglyph_Mark_Begin # Pe MATHEMATICAL RIGHT ANGLE BRACKET 243# 2E23 ; Hieroglyph_Mark_Begin # Pe TOP RIGHT HALF BRACKET 244# 2E25 ; Hieroglyph_Mark_Begin # Pe BOTTOM RIGHT HALF BRACKET 245 246# ================================================ 247 248# USE, Extended_Syllabic_Category=Hieroglyph_Segment_Begin 249# 13437 ; Hieroglyph_Segment_Begin # Cf EGYPTIAN HIEROGLYPH BEGIN SEGMENT 250 251# ================================================ 252 253# USE, Extended_Syllabic_Category=Hieroglyph_Segment_End 254# 13438 ; Hieroglyph_Segment_End # Cf EGYPTIAN HIEROGLYPH END SEGMENT 255 256# ================================================ 257 258# USE, Extended_Syllabic_Category=Hieroglyph_Mirror 259# 13440 ; Hieroglyph_Mirror # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY 260 261# ================================================ 262 263# USE, Extended_Syllabic_Category=Hieroglyph_Modifier 264# 13447..13455 ; Hieroglyph_Modifier # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED 265 266# ================================================ 267 268# eof 269