This is a live mirror of the Perl 5 development currently hosted at https://github.com/perl/perl5
perlapi: Place in dictionary sort order
[perl5.git] / lib / unicore / CompositionExclusions.txt
CommitLineData
a9c9e371
KW
1# CompositionExclusions-6.3.0.txt
2# Date: 2012-12-11, 11:23:00 GMT [KW, LI]
8836d2a5 3#
98fbe989
JH
4# This file lists the characters for the Composition Exclusion Table
5# defined in UAX #15, Unicode Normalization Forms.
d357d9fe 6#
a2bd7410
JH
7# This file is a normative contributory data file in the
8# Unicode Character Database.
9#
83d881f0 10# Copyright (c) 1991-2012 Unicode, Inc.
a2bd7410
JH
11# For terms of use, see http://www.unicode.org/terms_of_use.html
12#
d357d9fe 13# For more information, see
bd84d130 14# http://www.unicode.org/unicode/reports/tr15/#Primary_Exclusion_List_Table
98fbe989
JH
15#
16# For a full derivation of composition exclusions, see the derived property
17# Full_Composition_Exclusion in DerivedNormalizationProps.txt
18#
d357d9fe 19
98fbe989 20# ================================================
d357d9fe 21# (1) Script Specifics
98fbe989
JH
22#
23# This list of characters cannot be derived from the UnicodeData.txt file.
822ebcc8
JH
24# ================================================
25
260958 # DEVANAGARI LETTER QA
270959 # DEVANAGARI LETTER KHHA
28095A # DEVANAGARI LETTER GHHA
29095B # DEVANAGARI LETTER ZA
30095C # DEVANAGARI LETTER DDDHA
31095D # DEVANAGARI LETTER RHA
32095E # DEVANAGARI LETTER FA
33095F # DEVANAGARI LETTER YYA
3409DC # BENGALI LETTER RRA
3509DD # BENGALI LETTER RHA
3609DF # BENGALI LETTER YYA
370A33 # GURMUKHI LETTER LLA
380A36 # GURMUKHI LETTER SHA
390A59 # GURMUKHI LETTER KHHA
400A5A # GURMUKHI LETTER GHHA
410A5B # GURMUKHI LETTER ZA
420A5E # GURMUKHI LETTER FA
430B5C # ORIYA LETTER RRA
440B5D # ORIYA LETTER RHA
450F43 # TIBETAN LETTER GHA
460F4D # TIBETAN LETTER DDHA
470F52 # TIBETAN LETTER DHA
480F57 # TIBETAN LETTER BHA
490F5C # TIBETAN LETTER DZHA
500F69 # TIBETAN LETTER KSSA
510F76 # TIBETAN VOWEL SIGN VOCALIC R
520F78 # TIBETAN VOWEL SIGN VOCALIC L
530F93 # TIBETAN SUBJOINED LETTER GHA
540F9D # TIBETAN SUBJOINED LETTER DDHA
550FA2 # TIBETAN SUBJOINED LETTER DHA
560FA7 # TIBETAN SUBJOINED LETTER BHA
570FAC # TIBETAN SUBJOINED LETTER DZHA
580FB9 # TIBETAN SUBJOINED LETTER KSSA
59FB1D # HEBREW LETTER YOD WITH HIRIQ
60FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
61FB2A # HEBREW LETTER SHIN WITH SHIN DOT
62FB2B # HEBREW LETTER SHIN WITH SIN DOT
63FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
64FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
65FB2E # HEBREW LETTER ALEF WITH PATAH
66FB2F # HEBREW LETTER ALEF WITH QAMATS
67FB30 # HEBREW LETTER ALEF WITH MAPIQ
68FB31 # HEBREW LETTER BET WITH DAGESH
69FB32 # HEBREW LETTER GIMEL WITH DAGESH
70FB33 # HEBREW LETTER DALET WITH DAGESH
71FB34 # HEBREW LETTER HE WITH MAPIQ
72FB35 # HEBREW LETTER VAV WITH DAGESH
73FB36 # HEBREW LETTER ZAYIN WITH DAGESH
74FB38 # HEBREW LETTER TET WITH DAGESH
75FB39 # HEBREW LETTER YOD WITH DAGESH
76FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
77FB3B # HEBREW LETTER KAF WITH DAGESH
78FB3C # HEBREW LETTER LAMED WITH DAGESH
79FB3E # HEBREW LETTER MEM WITH DAGESH
80FB40 # HEBREW LETTER NUN WITH DAGESH
81FB41 # HEBREW LETTER SAMEKH WITH DAGESH
82FB43 # HEBREW LETTER FINAL PE WITH DAGESH
83FB44 # HEBREW LETTER PE WITH DAGESH
84FB46 # HEBREW LETTER TSADI WITH DAGESH
85FB47 # HEBREW LETTER QOF WITH DAGESH
86FB48 # HEBREW LETTER RESH WITH DAGESH
87FB49 # HEBREW LETTER SHIN WITH DAGESH
88FB4A # HEBREW LETTER TAV WITH DAGESH
89FB4B # HEBREW LETTER VAV WITH HOLAM
90FB4C # HEBREW LETTER BET WITH RAFE
91FB4D # HEBREW LETTER KAF WITH RAFE
92FB4E # HEBREW LETTER PE WITH RAFE
d357d9fe 93
822ebcc8 94# Total code points: 67
d357d9fe 95
822ebcc8 96# ================================================
190eec7c 97# (2) Post Composition Version precomposed characters
98fbe989 98#
822ebcc8
JH
99# These characters cannot be derived solely from the UnicodeData.txt file
100# in this version of Unicode.
98fbe989
JH
101#
102# Note that characters added to the standard after the
103# Composition Version and which have canonical decomposition mappings
104# are not automatically added to this list of Post Composition
105# Version precomposed characters.
822ebcc8
JH
106# ================================================
107
1082ADC # FORKING
1091D15E # MUSICAL SYMBOL HALF NOTE
1101D15F # MUSICAL SYMBOL QUARTER NOTE
1111D160 # MUSICAL SYMBOL EIGHTH NOTE
1121D161 # MUSICAL SYMBOL SIXTEENTH NOTE
1131D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE
1141D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
1151D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
1161D1BB # MUSICAL SYMBOL MINIMA
1171D1BC # MUSICAL SYMBOL MINIMA BLACK
1181D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
1191D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
1201D1BF # MUSICAL SYMBOL FUSA WHITE
1211D1C0 # MUSICAL SYMBOL FUSA BLACK
190eec7c 122
822ebcc8 123# Total code points: 14
d357d9fe 124
822ebcc8 125# ================================================
d357d9fe 126# (3) Singleton Decompositions
98fbe989
JH
127#
128# These characters can be derived from the UnicodeData.txt file
bd84d130
KW
129# by including all canonically decomposable characters whose
130# canonical decomposition consists of a single character.
98fbe989 131#
d357d9fe 132# These characters are simply quoted here for reference.
98fbe989 133# See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
822ebcc8 134# ================================================
d357d9fe 135
822ebcc8
JH
136# 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK
137# 0343 COMBINING GREEK KORONIS
138# 0374 GREEK NUMERAL SIGN
139# 037E GREEK QUESTION MARK
140# 0387 GREEK ANO TELEIA
141# 1F71 GREEK SMALL LETTER ALPHA WITH OXIA
142# 1F73 GREEK SMALL LETTER EPSILON WITH OXIA
143# 1F75 GREEK SMALL LETTER ETA WITH OXIA
144# 1F77 GREEK SMALL LETTER IOTA WITH OXIA
145# 1F79 GREEK SMALL LETTER OMICRON WITH OXIA
146# 1F7B GREEK SMALL LETTER UPSILON WITH OXIA
147# 1F7D GREEK SMALL LETTER OMEGA WITH OXIA
148# 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA
149# 1FBE GREEK PROSGEGRAMMENI
150# 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA
151# 1FCB GREEK CAPITAL LETTER ETA WITH OXIA
152# 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
153# 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA
154# 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
155# 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA
156# 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA
157# 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA
158# 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA
159# 1FFD GREEK OXIA
160# 2000..2001 [2] EN QUAD..EM QUAD
161# 2126 OHM SIGN
162# 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN
163# 2329 LEFT-POINTING ANGLE BRACKET
164# 232A RIGHT-POINTING ANGLE BRACKET
165# F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D
166# FA10 CJK COMPATIBILITY IDEOGRAPH-FA10
167# FA12 CJK COMPATIBILITY IDEOGRAPH-FA12
168# FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E
169# FA20 CJK COMPATIBILITY IDEOGRAPH-FA20
170# FA22 CJK COMPATIBILITY IDEOGRAPH-FA22
171# FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26
7620cb10 172# FA2A..FA6D [68] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA6D
a2bd7410 173# FA70..FAD9 [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9
822ebcc8 174# 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
d357d9fe 175
7620cb10 176# Total code points: 1035
822ebcc8
JH
177
178# ================================================
d357d9fe 179# (4) Non-Starter Decompositions
98fbe989 180#
7620cb10 181# These characters can be derived from the UnicodeData.txt file
bd84d130
KW
182# by including each expanding canonical decomposition
183# (i.e., those which canonically decompose to a sequence
184# of characters instead of a single character), such that:
185#
186# A. The character is not a Starter.
187#
188# OR (inclusive)
189#
190# B. The character's canonical decomposition begins
191# with a character that is not a Starter.
192#
193# Note that a "Starter" is any character with a zero combining class.
98fbe989 194#
d357d9fe 195# These characters are simply quoted here for reference.
98fbe989 196# See also Full_Composition_Exclusion in DerivedNormalizationProps.txt
822ebcc8
JH
197# ================================================
198
199# 0344 COMBINING GREEK DIALYTIKA TONOS
200# 0F73 TIBETAN VOWEL SIGN II
201# 0F75 TIBETAN VOWEL SIGN UU
202# 0F81 TIBETAN VOWEL SIGN REVERSED II
203
204# Total code points: 4
d357d9fe 205
83d881f0 206# EOF