|
1 # CompositionExclusions-2.txt |
|
2 # |
|
3 # Composition Exclusions |
|
4 # This file lists the characters from the UTR #15 Composition Exclusion Table. |
|
5 # |
|
6 # For more information, see |
|
7 # http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table |
|
8 |
|
9 # (1) Script Specifics |
|
10 # This list of characters cannot be derived from the UnicodeData file. |
|
11 |
|
12 0958 # DEVANAGARI LETTER QA |
|
13 0959 # DEVANAGARI LETTER KHHA |
|
14 095A # DEVANAGARI LETTER GHHA |
|
15 095B # DEVANAGARI LETTER ZA |
|
16 095C # DEVANAGARI LETTER DDDHA |
|
17 095D # DEVANAGARI LETTER RHA |
|
18 095E # DEVANAGARI LETTER FA |
|
19 095F # DEVANAGARI LETTER YYA |
|
20 09DC # BENGALI LETTER RRA |
|
21 09DD # BENGALI LETTER RHA |
|
22 09DF # BENGALI LETTER YYA |
|
23 0A33 # GURMUKHI LETTER LLA |
|
24 0A36 # GURMUKHI LETTER SHA |
|
25 0A59 # GURMUKHI LETTER KHHA |
|
26 0A5A # GURMUKHI LETTER GHHA |
|
27 0A5B # GURMUKHI LETTER ZA |
|
28 0A5E # GURMUKHI LETTER FA |
|
29 0B5C # ORIYA LETTER RRA |
|
30 0B5D # ORIYA LETTER RHA |
|
31 0F43 # TIBETAN LETTER GHA |
|
32 0F4D # TIBETAN LETTER DDHA |
|
33 0F52 # TIBETAN LETTER DHA |
|
34 0F57 # TIBETAN LETTER BHA |
|
35 0F5C # TIBETAN LETTER DZHA |
|
36 0F69 # TIBETAN LETTER KSSA |
|
37 0F76 # TIBETAN VOWEL SIGN VOCALIC R |
|
38 0F78 # TIBETAN VOWEL SIGN VOCALIC L |
|
39 0F93 # TIBETAN SUBJOINED LETTER GHA |
|
40 0F9D # TIBETAN SUBJOINED LETTER DDHA |
|
41 0FA2 # TIBETAN SUBJOINED LETTER DHA |
|
42 0FA7 # TIBETAN SUBJOINED LETTER BHA |
|
43 0FAC # TIBETAN SUBJOINED LETTER DZHA |
|
44 0FB9 # TIBETAN SUBJOINED LETTER KSSA |
|
45 FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH |
|
46 FB2A # HEBREW LETTER SHIN WITH SHIN DOT |
|
47 FB2B # HEBREW LETTER SHIN WITH SIN DOT |
|
48 FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT |
|
49 FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT |
|
50 FB2E # HEBREW LETTER ALEF WITH PATAH |
|
51 FB2F # HEBREW LETTER ALEF WITH QAMATS |
|
52 FB30 # HEBREW LETTER ALEF WITH MAPIQ |
|
53 FB31 # HEBREW LETTER BET WITH DAGESH |
|
54 FB32 # HEBREW LETTER GIMEL WITH DAGESH |
|
55 FB33 # HEBREW LETTER DALET WITH DAGESH |
|
56 FB34 # HEBREW LETTER HE WITH MAPIQ |
|
57 FB35 # HEBREW LETTER VAV WITH DAGESH |
|
58 FB36 # HEBREW LETTER ZAYIN WITH DAGESH |
|
59 FB38 # HEBREW LETTER TET WITH DAGESH |
|
60 FB39 # HEBREW LETTER YOD WITH DAGESH |
|
61 FB3A # HEBREW LETTER FINAL KAF WITH DAGESH |
|
62 FB3B # HEBREW LETTER KAF WITH DAGESH |
|
63 FB3C # HEBREW LETTER LAMED WITH DAGESH |
|
64 FB3E # HEBREW LETTER MEM WITH DAGESH |
|
65 FB40 # HEBREW LETTER NUN WITH DAGESH |
|
66 FB41 # HEBREW LETTER SAMEKH WITH DAGESH |
|
67 FB43 # HEBREW LETTER FINAL PE WITH DAGESH |
|
68 FB44 # HEBREW LETTER PE WITH DAGESH |
|
69 FB46 # HEBREW LETTER TSADI WITH DAGESH |
|
70 FB47 # HEBREW LETTER QOF WITH DAGESH |
|
71 FB48 # HEBREW LETTER RESH WITH DAGESH |
|
72 FB49 # HEBREW LETTER SHIN WITH DAGESH |
|
73 FB4A # HEBREW LETTER TAV WITH DAGESH |
|
74 FB4B # HEBREW LETTER VAV WITH HOLAM |
|
75 FB4C # HEBREW LETTER BET WITH RAFE |
|
76 FB4D # HEBREW LETTER KAF WITH RAFE |
|
77 FB4E # HEBREW LETTER PE WITH RAFE |
|
78 |
|
79 # (2) Post Composition Version characters |
|
80 # These characters cannot be derived from the UnicodeData file. |
|
81 # (There are no characters in this category in this version of Unicode.) |
|
82 |
|
83 # (3) Singleton Decompositions |
|
84 # These characters can be derived from the UnicodeData file |
|
85 # by including all characters whose canonical decomposition |
|
86 # consists of a single character. |
|
87 # These characters are simply quoted here for reference. |
|
88 |
|
89 # 0340 COMBINING GRAVE TONE MARK |
|
90 # 0341 COMBINING ACUTE TONE MARK |
|
91 # 0343 COMBINING GREEK KORONIS |
|
92 # 0374 GREEK NUMERAL SIGN |
|
93 # 037E GREEK QUESTION MARK |
|
94 # 0387 GREEK ANO TELEIA |
|
95 # 1F71 GREEK SMALL LETTER ALPHA WITH OXIA |
|
96 # 1F73 GREEK SMALL LETTER EPSILON WITH OXIA |
|
97 # 1F75 GREEK SMALL LETTER ETA WITH OXIA |
|
98 # 1F77 GREEK SMALL LETTER IOTA WITH OXIA |
|
99 # 1F79 GREEK SMALL LETTER OMICRON WITH OXIA |
|
100 # 1F7B GREEK SMALL LETTER UPSILON WITH OXIA |
|
101 # 1F7D GREEK SMALL LETTER OMEGA WITH OXIA |
|
102 # 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA |
|
103 # 1FBE GREEK PROSGEGRAMMENI |
|
104 # 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA |
|
105 # 1FCB GREEK CAPITAL LETTER ETA WITH OXIA |
|
106 # 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA |
|
107 # 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA |
|
108 # 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA |
|
109 # 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA |
|
110 # 1FEE GREEK DIALYTIKA AND OXIA |
|
111 # 1FEF GREEK VARIA |
|
112 # 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA |
|
113 # 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA |
|
114 # 1FFD GREEK OXIA |
|
115 # 2000 EN QUAD |
|
116 # 2001 EM QUAD |
|
117 # 2126 OHM SIGN |
|
118 # 212A KELVIN SIGN |
|
119 # 212B ANGSTROM SIGN |
|
120 # 2329 LEFT-POINTING ANGLE BRACKET |
|
121 # 232A RIGHT-POINTING ANGLE BRACKET |
|
122 # F900 CJK COMPATIBILITY IDEOGRAPH-F900 |
|
123 #.. FA0D CJK COMPATIBILITY IDEOGRAPH-FA0D |
|
124 # FA10 CJK COMPATIBILITY IDEOGRAPH-FA10 |
|
125 # FA12 CJK COMPATIBILITY IDEOGRAPH-FA12 |
|
126 # FA15 CJK COMPATIBILITY IDEOGRAPH-FA15 |
|
127 #.. FA1E CJK COMPATIBILITY IDEOGRAPH-FA1E |
|
128 # FA20 CJK COMPATIBILITY IDEOGRAPH-FA20 |
|
129 # FA22 CJK COMPATIBILITY IDEOGRAPH-FA22 |
|
130 # FA25 CJK COMPATIBILITY IDEOGRAPH-FA25 |
|
131 # FA26 CJK COMPATIBILITY IDEOGRAPH-FA26 |
|
132 # FA2A CJK COMPATIBILITY IDEOGRAPH-FA2A |
|
133 #.. FA2D CJK COMPATIBILITY IDEOGRAPH-FA2D |
|
134 |
|
135 # (4) Non-Starter Decompositions |
|
136 # These characters can be derived from the UnicodeData file |
|
137 # by including all characters whose canonical decomposition consists |
|
138 # of a sequence of characters, the first of which has a non-zero |
|
139 # combining class. |
|
140 # These characters are simply quoted here for reference. |
|
141 |
|
142 # 0344 COMBINING GREEK DIALYTIKA TONOS |
|
143 # 0F73 TIBETAN VOWEL SIGN II |
|
144 # 0F75 TIBETAN VOWEL SIGN UU |
|
145 # 0F81 TIBETAN VOWEL SIGN REVERSED II |