1 # CompositionExclusions-5.2.0.txt
\r
2 # Date: 2009-05-22, 12:52:00 PDT [KW]
\r
4 # This file lists the characters for the Composition Exclusion Table
\r
5 # defined in UAX #15, Unicode Normalization Forms.
\r
7 # This file is a normative contributory data file in the
\r
8 # Unicode Character Database.
\r
10 # Copyright (c) 1991-2009 Unicode, Inc.
\r
11 # For terms of use, see http://www.unicode.org/terms_of_use.html
\r
13 # For more information, see
\r
14 # http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table
\r
16 # For a full derivation of composition exclusions, see the derived property
\r
17 # Full_Composition_Exclusion in DerivedNormalizationProps.txt
\r
20 # ================================================
\r
21 # (1) Script Specifics
\r
23 # This list of characters cannot be derived from the UnicodeData.txt file.
\r
24 # ================================================
\r
26 0958 # DEVANAGARI LETTER QA
\r
27 0959 # DEVANAGARI LETTER KHHA
\r
28 095A # DEVANAGARI LETTER GHHA
\r
29 095B # DEVANAGARI LETTER ZA
\r
30 095C # DEVANAGARI LETTER DDDHA
\r
31 095D # DEVANAGARI LETTER RHA
\r
32 095E # DEVANAGARI LETTER FA
\r
33 095F # DEVANAGARI LETTER YYA
\r
34 09DC # BENGALI LETTER RRA
\r
35 09DD # BENGALI LETTER RHA
\r
36 09DF # BENGALI LETTER YYA
\r
37 0A33 # GURMUKHI LETTER LLA
\r
38 0A36 # GURMUKHI LETTER SHA
\r
39 0A59 # GURMUKHI LETTER KHHA
\r
40 0A5A # GURMUKHI LETTER GHHA
\r
41 0A5B # GURMUKHI LETTER ZA
\r
42 0A5E # GURMUKHI LETTER FA
\r
43 0B5C # ORIYA LETTER RRA
\r
44 0B5D # ORIYA LETTER RHA
\r
45 0F43 # TIBETAN LETTER GHA
\r
46 0F4D # TIBETAN LETTER DDHA
\r
47 0F52 # TIBETAN LETTER DHA
\r
48 0F57 # TIBETAN LETTER BHA
\r
49 0F5C # TIBETAN LETTER DZHA
\r
50 0F69 # TIBETAN LETTER KSSA
\r
51 0F76 # TIBETAN VOWEL SIGN VOCALIC R
\r
52 0F78 # TIBETAN VOWEL SIGN VOCALIC L
\r
53 0F93 # TIBETAN SUBJOINED LETTER GHA
\r
54 0F9D # TIBETAN SUBJOINED LETTER DDHA
\r
55 0FA2 # TIBETAN SUBJOINED LETTER DHA
\r
56 0FA7 # TIBETAN SUBJOINED LETTER BHA
\r
57 0FAC # TIBETAN SUBJOINED LETTER DZHA
\r
58 0FB9 # TIBETAN SUBJOINED LETTER KSSA
\r
59 FB1D # HEBREW LETTER YOD WITH HIRIQ
\r
60 FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
\r
61 FB2A # HEBREW LETTER SHIN WITH SHIN DOT
\r
62 FB2B # HEBREW LETTER SHIN WITH SIN DOT
\r
63 FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
\r
64 FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
\r
65 FB2E # HEBREW LETTER ALEF WITH PATAH
\r
66 FB2F # HEBREW LETTER ALEF WITH QAMATS
\r
67 FB30 # HEBREW LETTER ALEF WITH MAPIQ
\r
68 FB31 # HEBREW LETTER BET WITH DAGESH
\r
69 FB32 # HEBREW LETTER GIMEL WITH DAGESH
\r
70 FB33 # HEBREW LETTER DALET WITH DAGESH
\r
71 FB34 # HEBREW LETTER HE WITH MAPIQ
\r
72 FB35 # HEBREW LETTER VAV WITH DAGESH
\r
73 FB36 # HEBREW LETTER ZAYIN WITH DAGESH
\r
74 FB38 # HEBREW LETTER TET WITH DAGESH
\r
75 FB39 # HEBREW LETTER YOD WITH DAGESH
\r
76 FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
\r
77 FB3B # HEBREW LETTER KAF WITH DAGESH
\r
78 FB3C # HEBREW LETTER LAMED WITH DAGESH
\r
79 FB3E # HEBREW LETTER MEM WITH DAGESH
\r
80 FB40 # HEBREW LETTER NUN WITH DAGESH
\r
81 FB41 # HEBREW LETTER SAMEKH WITH DAGESH
\r
82 FB43 # HEBREW LETTER FINAL PE WITH DAGESH
\r
83 FB44 # HEBREW LETTER PE WITH DAGESH
\r
84 FB46 # HEBREW LETTER TSADI WITH DAGESH
\r
85 FB47 # HEBREW LETTER QOF WITH DAGESH
\r
86 FB48 # HEBREW LETTER RESH WITH DAGESH
\r
87 FB49 # HEBREW LETTER SHIN WITH DAGESH
\r
88 FB4A # HEBREW LETTER TAV WITH DAGESH
\r
89 FB4B # HEBREW LETTER VAV WITH HOLAM
\r
90 FB4C # HEBREW LETTER BET WITH RAFE
\r
91 FB4D # HEBREW LETTER KAF WITH RAFE
\r
92 FB4E # HEBREW LETTER PE WITH RAFE
\r
94 # Total code points: 67
\r
96 # ================================================
\r
97 # (2) Post Composition Version precomposed characters
\r
99 # These characters cannot be derived solely from the UnicodeData.txt file
\r
100 # in this version of Unicode.
\r
102 # Note that characters added to the standard after the
\r
103 # Composition Version and which have canonical decomposition mappings
\r
104 # are not automatically added to this list of Post Composition
\r
105 # Version precomposed characters.
\r
106 # ================================================
\r
109 1D15E # MUSICAL SYMBOL HALF NOTE
\r
110 1D15F # MUSICAL SYMBOL QUARTER NOTE
\r
111 1D160 # MUSICAL SYMBOL EIGHTH NOTE
\r
112 1D161 # MUSICAL SYMBOL SIXTEENTH NOTE
\r
113 1D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE
\r
114 1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
\r
115 1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
\r
116 1D1BB # MUSICAL SYMBOL MINIMA
\r
117 1D1BC # MUSICAL SYMBOL MINIMA BLACK
\r
118 1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
\r
119 1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
\r
120 1D1BF # MUSICAL SYMBOL FUSA WHITE
\r
121 1D1C0 # MUSICAL SYMBOL FUSA BLACK
\r
123 # Total code points: 14
\r
125 # ================================================
\r
126 # (3) Singleton Decompositions
\r
128 # These characters can be derived from the UnicodeData.txt file
\r
129 # by including all characters whose canonical decomposition
\r
130 # consists of a single character.
\r
132 # These characters are simply quoted here for reference.
\r
133 # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
\r
134 # ================================================
\r
136 # 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
\r
137 # 0343 COMBINING GREEK KORONIS
\r
138 # 0374 GREEK NUMERAL SIGN
\r
139 # 037E GREEK QUESTION MARK
\r
140 # 0387 GREEK ANO TELEIA
\r
141 # 1F71 GREEK SMALL LETTER ALPHA WITH OXIA
\r
142 # 1F73 GREEK SMALL LETTER EPSILON WITH OXIA
\r
143 # 1F75 GREEK SMALL LETTER ETA WITH OXIA
\r
144 # 1F77 GREEK SMALL LETTER IOTA WITH OXIA
\r
145 # 1F79 GREEK SMALL LETTER OMICRON WITH OXIA
\r
146 # 1F7B GREEK SMALL LETTER UPSILON WITH OXIA
\r
147 # 1F7D GREEK SMALL LETTER OMEGA WITH OXIA
\r
148 # 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA
\r
149 # 1FBE GREEK PROSGEGRAMMENI
\r
150 # 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA
\r
151 # 1FCB GREEK CAPITAL LETTER ETA WITH OXIA
\r
152 # 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
\r
153 # 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA
\r
154 # 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
\r
155 # 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA
\r
156 # 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA
\r
157 # 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA
\r
158 # 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA
\r
160 # 2000..2001 [2] EN QUAD..EM QUAD
\r
162 # 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN
\r
163 # 2329 LEFT-POINTING ANGLE BRACKET
\r
164 # 232A RIGHT-POINTING ANGLE BRACKET
\r
165 # F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D
\r
166 # FA10 CJK COMPATIBILITY IDEOGRAPH-FA10
\r
167 # FA12 CJK COMPATIBILITY IDEOGRAPH-FA12
\r
168 # FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E
\r
169 # FA20 CJK COMPATIBILITY IDEOGRAPH-FA20
\r
170 # FA22 CJK COMPATIBILITY IDEOGRAPH-FA22
\r
171 # FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26
\r
172 # FA2A..FA2D [4] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA2D
\r
173 # FA30..FA6D [62] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6D
\r
174 # FA70..FAD9 [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
\r
175 # 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
\r
177 # Total code points: 1033
\r
179 # ================================================
\r
180 # (4) Non-Starter Decompositions
\r
182 # These characters can be derived from the UnicodeData file
\r
183 # by including all characters whose canonical decomposition consists
\r
184 # of a sequence of characters, the first of which has a non-zero
\r
187 # These characters are simply quoted here for reference.
\r
188 # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
\r
189 # ================================================
\r
191 # 0344 COMBINING GREEK DIALYTIKA TONOS
\r
192 # 0F73 TIBETAN VOWEL SIGN II
\r
193 # 0F75 TIBETAN VOWEL SIGN UU
\r
194 # 0F81 TIBETAN VOWEL SIGN REVERSED II
\r
196 # Total code points: 4
\r