This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
Resync with mainline
[perl5.git] / lib / unicode / CompExcl.txt
CommitLineData
c529f79d
CB
1# Composition Exclusions
2# This file lists the characters from the UTR #15 Composition Exclusion Table.
3#
4# For more information, see
5# http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table
6
7# (1) Script Specifics
8# This list of characters cannot be derived from the UnicodeData file.
9
100958 # DEVANAGARI LETTER QA
110959 # DEVANAGARI LETTER KHHA
12095A # DEVANAGARI LETTER GHHA
13095B # DEVANAGARI LETTER ZA
14095C # DEVANAGARI LETTER DDDHA
15095D # DEVANAGARI LETTER RHA
16095E # DEVANAGARI LETTER FA
17095F # DEVANAGARI LETTER YYA
1809DC # BENGALI LETTER RRA
1909DD # BENGALI LETTER RHA
2009DF # BENGALI LETTER YYA
210A33 # GURMUKHI LETTER LLA
220A36 # GURMUKHI LETTER SHA
230A59 # GURMUKHI LETTER KHHA
240A5A # GURMUKHI LETTER GHHA
250A5B # GURMUKHI LETTER ZA
260A5E # GURMUKHI LETTER FA
270B5C # ORIYA LETTER RRA
280B5D # ORIYA LETTER RHA
290F43 # TIBETAN LETTER GHA
300F4D # TIBETAN LETTER DDHA
310F52 # TIBETAN LETTER DHA
320F57 # TIBETAN LETTER BHA
330F5C # TIBETAN LETTER DZHA
340F69 # TIBETAN LETTER KSSA
350F76 # TIBETAN VOWEL SIGN VOCALIC R
360F78 # TIBETAN VOWEL SIGN VOCALIC L
370F93 # TIBETAN SUBJOINED LETTER GHA
380F9D # TIBETAN SUBJOINED LETTER DDHA
390FA2 # TIBETAN SUBJOINED LETTER DHA
400FA7 # TIBETAN SUBJOINED LETTER BHA
410FAC # TIBETAN SUBJOINED LETTER DZHA
420FB9 # TIBETAN SUBJOINED LETTER KSSA
43FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
44FB2A # HEBREW LETTER SHIN WITH SHIN DOT
45FB2B # HEBREW LETTER SHIN WITH SIN DOT
46FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
47FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
48FB2E # HEBREW LETTER ALEF WITH PATAH
49FB2F # HEBREW LETTER ALEF WITH QAMATS
50FB30 # HEBREW LETTER ALEF WITH MAPIQ
51FB31 # HEBREW LETTER BET WITH DAGESH
52FB32 # HEBREW LETTER GIMEL WITH DAGESH
53FB33 # HEBREW LETTER DALET WITH DAGESH
54FB34 # HEBREW LETTER HE WITH MAPIQ
55FB35 # HEBREW LETTER VAV WITH DAGESH
56FB36 # HEBREW LETTER ZAYIN WITH DAGESH
57FB38 # HEBREW LETTER TET WITH DAGESH
58FB39 # HEBREW LETTER YOD WITH DAGESH
59FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
60FB3B # HEBREW LETTER KAF WITH DAGESH
61FB3C # HEBREW LETTER LAMED WITH DAGESH
62FB3E # HEBREW LETTER MEM WITH DAGESH
63FB40 # HEBREW LETTER NUN WITH DAGESH
64FB41 # HEBREW LETTER SAMEKH WITH DAGESH
65FB43 # HEBREW LETTER FINAL PE WITH DAGESH
66FB44 # HEBREW LETTER PE WITH DAGESH
67FB46 # HEBREW LETTER TSADI WITH DAGESH
68FB47 # HEBREW LETTER QOF WITH DAGESH
69FB48 # HEBREW LETTER RESH WITH DAGESH
70FB49 # HEBREW LETTER SHIN WITH DAGESH
71FB4A # HEBREW LETTER TAV WITH DAGESH
72FB4B # HEBREW LETTER VAV WITH HOLAM
73FB4C # HEBREW LETTER BET WITH RAFE
74FB4D # HEBREW LETTER KAF WITH RAFE
75FB4E # HEBREW LETTER PE WITH RAFE
76
77# (2) Post Composition Version characters
78# These characters cannot be derived from the UnicodeData file.
79# (There are no characters in this category in this version of Unicode.)
80
81# (3) Singleton Decompositions
82# These characters can be derived from the UnicodeData file
83# by including all characters whose canonical decomposition
84# consists of a single character.
85# These characters are simply quoted here for reference.
86
87# 0340 COMBINING GRAVE TONE MARK
88# 0341 COMBINING ACUTE TONE MARK
89# 0343 COMBINING GREEK KORONIS
90# 0374 GREEK NUMERAL SIGN
91# 037E GREEK QUESTION MARK
92# 0387 GREEK ANO TELEIA
93# 1F71 GREEK SMALL LETTER ALPHA WITH OXIA
94# 1F73 GREEK SMALL LETTER EPSILON WITH OXIA
95# 1F75 GREEK SMALL LETTER ETA WITH OXIA
96# 1F77 GREEK SMALL LETTER IOTA WITH OXIA
97# 1F79 GREEK SMALL LETTER OMICRON WITH OXIA
98# 1F7B GREEK SMALL LETTER UPSILON WITH OXIA
99# 1F7D GREEK SMALL LETTER OMEGA WITH OXIA
100# 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA
101# 1FBE GREEK PROSGEGRAMMENI
102# 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA
103# 1FCB GREEK CAPITAL LETTER ETA WITH OXIA
104# 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
105# 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA
106# 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
107# 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA
108# 1FEE GREEK DIALYTIKA AND OXIA
109# 1FEF GREEK VARIA
110# 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA
111# 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA
112# 1FFD GREEK OXIA
113# 2000 EN QUAD
114# 2001 EM QUAD
115# 2126 OHM SIGN
116# 212A KELVIN SIGN
117# 212B ANGSTROM SIGN
118# 2329 LEFT-POINTING ANGLE BRACKET
119# 232A RIGHT-POINTING ANGLE BRACKET
120# F900 CJK COMPATIBILITY IDEOGRAPH-F900
121#.. FA0D CJK COMPATIBILITY IDEOGRAPH-FA0D
122# FA10 CJK COMPATIBILITY IDEOGRAPH-FA10
123# FA12 CJK COMPATIBILITY IDEOGRAPH-FA12
124# FA15 CJK COMPATIBILITY IDEOGRAPH-FA15
125#.. FA1E CJK COMPATIBILITY IDEOGRAPH-FA1E
126# FA20 CJK COMPATIBILITY IDEOGRAPH-FA20
127# FA22 CJK COMPATIBILITY IDEOGRAPH-FA22
128# FA25 CJK COMPATIBILITY IDEOGRAPH-FA25
129# FA26 CJK COMPATIBILITY IDEOGRAPH-FA26
130# FA2A CJK COMPATIBILITY IDEOGRAPH-FA2A
131#.. FA2D CJK COMPATIBILITY IDEOGRAPH-FA2D
132
133# (4) Non-Starter Decompositions
134# These characters can be derived from the UnicodeData file
135# by including all characters whose canonical decomposition consists
136# of a sequence of characters, the first of which has a canonical
137# class of zero.
138# These characters are simply quoted here for reference.
139
140# 0344 COMBINING GREEK DIALYTIKA TONOS
141# 0F73 TIBETAN VOWEL SIGN II
142# 0F75 TIBETAN VOWEL SIGN UU
143# 0F81 TIBETAN VOWEL SIGN REVERSED II