1 # CompositionExclusions-3.2.0.txt
2 # Date: 2002-03-19,23:30:28 GMT [MD]
4 # This file lists the characters from the UAX #15 Composition Exclusion Table.
6 # The format of the comments in this file has been updated since the last version,
7 # CompositionExclusions-3.txt. The only substantive change to this file between that
8 # version and this one is the addition of U+2ADC FORKING.
10 # For more information, see
11 # http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table
12 # ================================================
14 # (1) Script Specifics
15 # This list of characters cannot be derived from the UnicodeData file.
16 # ================================================
18 0958 # DEVANAGARI LETTER QA
19 0959 # DEVANAGARI LETTER KHHA
20 095A # DEVANAGARI LETTER GHHA
21 095B # DEVANAGARI LETTER ZA
22 095C # DEVANAGARI LETTER DDDHA
23 095D # DEVANAGARI LETTER RHA
24 095E # DEVANAGARI LETTER FA
25 095F # DEVANAGARI LETTER YYA
26 09DC # BENGALI LETTER RRA
27 09DD # BENGALI LETTER RHA
28 09DF # BENGALI LETTER YYA
29 0A33 # GURMUKHI LETTER LLA
30 0A36 # GURMUKHI LETTER SHA
31 0A59 # GURMUKHI LETTER KHHA
32 0A5A # GURMUKHI LETTER GHHA
33 0A5B # GURMUKHI LETTER ZA
34 0A5E # GURMUKHI LETTER FA
35 0B5C # ORIYA LETTER RRA
36 0B5D # ORIYA LETTER RHA
37 0F43 # TIBETAN LETTER GHA
38 0F4D # TIBETAN LETTER DDHA
39 0F52 # TIBETAN LETTER DHA
40 0F57 # TIBETAN LETTER BHA
41 0F5C # TIBETAN LETTER DZHA
42 0F69 # TIBETAN LETTER KSSA
43 0F76 # TIBETAN VOWEL SIGN VOCALIC R
44 0F78 # TIBETAN VOWEL SIGN VOCALIC L
45 0F93 # TIBETAN SUBJOINED LETTER GHA
46 0F9D # TIBETAN SUBJOINED LETTER DDHA
47 0FA2 # TIBETAN SUBJOINED LETTER DHA
48 0FA7 # TIBETAN SUBJOINED LETTER BHA
49 0FAC # TIBETAN SUBJOINED LETTER DZHA
50 0FB9 # TIBETAN SUBJOINED LETTER KSSA
51 FB1D # HEBREW LETTER YOD WITH HIRIQ
52 FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
53 FB2A # HEBREW LETTER SHIN WITH SHIN DOT
54 FB2B # HEBREW LETTER SHIN WITH SIN DOT
55 FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
56 FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
57 FB2E # HEBREW LETTER ALEF WITH PATAH
58 FB2F # HEBREW LETTER ALEF WITH QAMATS
59 FB30 # HEBREW LETTER ALEF WITH MAPIQ
60 FB31 # HEBREW LETTER BET WITH DAGESH
61 FB32 # HEBREW LETTER GIMEL WITH DAGESH
62 FB33 # HEBREW LETTER DALET WITH DAGESH
63 FB34 # HEBREW LETTER HE WITH MAPIQ
64 FB35 # HEBREW LETTER VAV WITH DAGESH
65 FB36 # HEBREW LETTER ZAYIN WITH DAGESH
66 FB38 # HEBREW LETTER TET WITH DAGESH
67 FB39 # HEBREW LETTER YOD WITH DAGESH
68 FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
69 FB3B # HEBREW LETTER KAF WITH DAGESH
70 FB3C # HEBREW LETTER LAMED WITH DAGESH
71 FB3E # HEBREW LETTER MEM WITH DAGESH
72 FB40 # HEBREW LETTER NUN WITH DAGESH
73 FB41 # HEBREW LETTER SAMEKH WITH DAGESH
74 FB43 # HEBREW LETTER FINAL PE WITH DAGESH
75 FB44 # HEBREW LETTER PE WITH DAGESH
76 FB46 # HEBREW LETTER TSADI WITH DAGESH
77 FB47 # HEBREW LETTER QOF WITH DAGESH
78 FB48 # HEBREW LETTER RESH WITH DAGESH
79 FB49 # HEBREW LETTER SHIN WITH DAGESH
80 FB4A # HEBREW LETTER TAV WITH DAGESH
81 FB4B # HEBREW LETTER VAV WITH HOLAM
82 FB4C # HEBREW LETTER BET WITH RAFE
83 FB4D # HEBREW LETTER KAF WITH RAFE
84 FB4E # HEBREW LETTER PE WITH RAFE
86 # Total code points: 67
88 # ================================================
89 # (2) Post Composition Version precomposed characters
90 # These characters cannot be derived solely from the UnicodeData.txt file
91 # in this version of Unicode.
92 # ================================================
95 1D15E # MUSICAL SYMBOL HALF NOTE
96 1D15F # MUSICAL SYMBOL QUARTER NOTE
97 1D160 # MUSICAL SYMBOL EIGHTH NOTE
98 1D161 # MUSICAL SYMBOL SIXTEENTH NOTE
99 1D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE
100 1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
101 1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
102 1D1BB # MUSICAL SYMBOL MINIMA
103 1D1BC # MUSICAL SYMBOL MINIMA BLACK
104 1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
105 1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
106 1D1BF # MUSICAL SYMBOL FUSA WHITE
107 1D1C0 # MUSICAL SYMBOL FUSA BLACK
109 # Total code points: 14
111 # ================================================
112 # (3) Singleton Decompositions
113 # These characters can be derived from the UnicodeData file
114 # by including all characters whose canonical decomposition
115 # consists of a single character.
116 # These characters are simply quoted here for reference.
117 # ================================================
119 # 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
120 # 0343 COMBINING GREEK KORONIS
121 # 0374 GREEK NUMERAL SIGN
122 # 037E GREEK QUESTION MARK
123 # 0387 GREEK ANO TELEIA
124 # 1F71 GREEK SMALL LETTER ALPHA WITH OXIA
125 # 1F73 GREEK SMALL LETTER EPSILON WITH OXIA
126 # 1F75 GREEK SMALL LETTER ETA WITH OXIA
127 # 1F77 GREEK SMALL LETTER IOTA WITH OXIA
128 # 1F79 GREEK SMALL LETTER OMICRON WITH OXIA
129 # 1F7B GREEK SMALL LETTER UPSILON WITH OXIA
130 # 1F7D GREEK SMALL LETTER OMEGA WITH OXIA
131 # 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA
132 # 1FBE GREEK PROSGEGRAMMENI
133 # 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA
134 # 1FCB GREEK CAPITAL LETTER ETA WITH OXIA
135 # 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
136 # 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA
137 # 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
138 # 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA
139 # 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA
140 # 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA
141 # 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA
143 # 2000..2001 [2] EN QUAD..EM QUAD
145 # 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN
146 # 2329 LEFT-POINTING ANGLE BRACKET
147 # 232A RIGHT-POINTING ANGLE BRACKET
148 # F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D
149 # FA10 CJK COMPATIBILITY IDEOGRAPH-FA10
150 # FA12 CJK COMPATIBILITY IDEOGRAPH-FA12
151 # FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E
152 # FA20 CJK COMPATIBILITY IDEOGRAPH-FA20
153 # FA22 CJK COMPATIBILITY IDEOGRAPH-FA22
154 # FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26
155 # FA2A..FA2D [4] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA2D
156 # FA30..FA6A [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A
157 # 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
159 # Total code points: 924
161 # ================================================
162 # (4) Non-Starter Decompositions
163 # These characters can be derived from the UnicodeData file
164 # by including all characters whose canonical decomposition consists
165 # of a sequence of characters, the first of which has a non-zero
167 # These characters are simply quoted here for reference.
168 # ================================================
170 # 0344 COMBINING GREEK DIALYTIKA TONOS
171 # 0F73 TIBETAN VOWEL SIGN II
172 # 0F75 TIBETAN VOWEL SIGN UU
173 # 0F81 TIBETAN VOWEL SIGN REVERSED II
175 # Total code points: 4