%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % % This file is part of VivoMind Prolog Unicode Resources % SPDX-License-Identifier: CC0-1.0 % % VivoMind Prolog Unicode Resources is free software distributed using the % Creative Commons CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication % license % %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% % Last modified: March 13, 2012 % % Original Unicode file header comments follow /* # CompositionExclusions-6.1.0.txt # Date: 2011-07-12, 00:13:00 GMT [KW, LI] # # This file lists the characters for the Composition Exclusion Table # defined in UAX #15, Unicode Normalization Forms. # # This file is a normative contributory data file in the # Unicode Character Database. # # Copyright (c) 1991-2011 Unicode, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # For more information, see # http://www.unicode.org/unicode/reports/tr15/#Primary_Exclusion_List_Table # # For a full derivation of composition exclusions, see the derived property # Full_Composition_Exclusion in DerivedNormalizationProps.txt # # ================================================ # (1) Script Specifics # # This list of characters cannot be derived from the UnicodeData.txt file. # ================================================ */ unicode_composition_exclusion(0x0958). % DEVANAGARI LETTER QA unicode_composition_exclusion(0x0959). % DEVANAGARI LETTER KHHA unicode_composition_exclusion(0x095A). % DEVANAGARI LETTER GHHA unicode_composition_exclusion(0x095B). % DEVANAGARI LETTER ZA unicode_composition_exclusion(0x095C). % DEVANAGARI LETTER DDDHA unicode_composition_exclusion(0x095D). % DEVANAGARI LETTER RHA unicode_composition_exclusion(0x095E). % DEVANAGARI LETTER FA unicode_composition_exclusion(0x095F). % DEVANAGARI LETTER YYA unicode_composition_exclusion(0x09DC). % BENGALI LETTER RRA unicode_composition_exclusion(0x09DD). % BENGALI LETTER RHA unicode_composition_exclusion(0x09DF). % BENGALI LETTER YYA unicode_composition_exclusion(0x0A33). % GURMUKHI LETTER LLA unicode_composition_exclusion(0x0A36). % GURMUKHI LETTER SHA unicode_composition_exclusion(0x0A59). % GURMUKHI LETTER KHHA unicode_composition_exclusion(0x0A5A). % GURMUKHI LETTER GHHA unicode_composition_exclusion(0x0A5B). % GURMUKHI LETTER ZA unicode_composition_exclusion(0x0A5E). % GURMUKHI LETTER FA unicode_composition_exclusion(0x0B5C). % ORIYA LETTER RRA unicode_composition_exclusion(0x0B5D). % ORIYA LETTER RHA unicode_composition_exclusion(0x0F43). % TIBETAN LETTER GHA unicode_composition_exclusion(0x0F4D). % TIBETAN LETTER DDHA unicode_composition_exclusion(0x0F52). % TIBETAN LETTER DHA unicode_composition_exclusion(0x0F57). % TIBETAN LETTER BHA unicode_composition_exclusion(0x0F5C). % TIBETAN LETTER DZHA unicode_composition_exclusion(0x0F69). % TIBETAN LETTER KSSA unicode_composition_exclusion(0x0F76). % TIBETAN VOWEL SIGN VOCALIC R unicode_composition_exclusion(0x0F78). % TIBETAN VOWEL SIGN VOCALIC L unicode_composition_exclusion(0x0F93). % TIBETAN SUBJOINED LETTER GHA unicode_composition_exclusion(0x0F9D). % TIBETAN SUBJOINED LETTER DDHA unicode_composition_exclusion(0x0FA2). % TIBETAN SUBJOINED LETTER DHA unicode_composition_exclusion(0x0FA7). % TIBETAN SUBJOINED LETTER BHA unicode_composition_exclusion(0x0FAC). % TIBETAN SUBJOINED LETTER DZHA unicode_composition_exclusion(0x0FB9). % TIBETAN SUBJOINED LETTER KSSA unicode_composition_exclusion(0xFB1D). % HEBREW LETTER YOD WITH HIRIQ unicode_composition_exclusion(0xFB1F). % HEBREW LIGATURE YIDDISH YOD YOD PATAH unicode_composition_exclusion(0xFB2A). % HEBREW LETTER SHIN WITH SHIN DOT unicode_composition_exclusion(0xFB2B). % HEBREW LETTER SHIN WITH SIN DOT unicode_composition_exclusion(0xFB2C). % HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT unicode_composition_exclusion(0xFB2D). % HEBREW LETTER SHIN WITH DAGESH AND SIN DOT unicode_composition_exclusion(0xFB2E). % HEBREW LETTER ALEF WITH PATAH unicode_composition_exclusion(0xFB2F). % HEBREW LETTER ALEF WITH QAMATS unicode_composition_exclusion(0xFB30). % HEBREW LETTER ALEF WITH MAPIQ unicode_composition_exclusion(0xFB31). % HEBREW LETTER BET WITH DAGESH unicode_composition_exclusion(0xFB32). % HEBREW LETTER GIMEL WITH DAGESH unicode_composition_exclusion(0xFB33). % HEBREW LETTER DALET WITH DAGESH unicode_composition_exclusion(0xFB34). % HEBREW LETTER HE WITH MAPIQ unicode_composition_exclusion(0xFB35). % HEBREW LETTER VAV WITH DAGESH unicode_composition_exclusion(0xFB36). % HEBREW LETTER ZAYIN WITH DAGESH unicode_composition_exclusion(0xFB38). % HEBREW LETTER TET WITH DAGESH unicode_composition_exclusion(0xFB39). % HEBREW LETTER YOD WITH DAGESH unicode_composition_exclusion(0xFB3A). % HEBREW LETTER FINAL KAF WITH DAGESH unicode_composition_exclusion(0xFB3B). % HEBREW LETTER KAF WITH DAGESH unicode_composition_exclusion(0xFB3C). % HEBREW LETTER LAMED WITH DAGESH unicode_composition_exclusion(0xFB3E). % HEBREW LETTER MEM WITH DAGESH unicode_composition_exclusion(0xFB40). % HEBREW LETTER NUN WITH DAGESH unicode_composition_exclusion(0xFB41). % HEBREW LETTER SAMEKH WITH DAGESH unicode_composition_exclusion(0xFB43). % HEBREW LETTER FINAL PE WITH DAGESH unicode_composition_exclusion(0xFB44). % HEBREW LETTER PE WITH DAGESH unicode_composition_exclusion(0xFB46). % HEBREW LETTER TSADI WITH DAGESH unicode_composition_exclusion(0xFB47). % HEBREW LETTER QOF WITH DAGESH unicode_composition_exclusion(0xFB48). % HEBREW LETTER RESH WITH DAGESH unicode_composition_exclusion(0xFB49). % HEBREW LETTER SHIN WITH DAGESH unicode_composition_exclusion(0xFB4A). % HEBREW LETTER TAV WITH DAGESH unicode_composition_exclusion(0xFB4B). % HEBREW LETTER VAV WITH HOLAM unicode_composition_exclusion(0xFB4C). % HEBREW LETTER BET WITH RAFE unicode_composition_exclusion(0xFB4D). % HEBREW LETTER KAF WITH RAFE unicode_composition_exclusion(0xFB4E). % HEBREW LETTER PE WITH RAFE % Total code points: 67 /* # ================================================ # (2) Post Composition Version precomposed characters # # These characters cannot be derived solely from the UnicodeData.txt file # in this version of Unicode. # # Note that characters added to the standard after the # Composition Version and which have canonical decomposition mappings # are not automatically added to this list of Post Composition # Version precomposed characters. # ================================================ */ unicode_composition_exclusion(0x2ADC). % FORKING unicode_composition_exclusion(0x1D15E). % MUSICAL SYMBOL HALF NOTE unicode_composition_exclusion(0x1D15F). % MUSICAL SYMBOL QUARTER NOTE unicode_composition_exclusion(0x1D160). % MUSICAL SYMBOL EIGHTH NOTE unicode_composition_exclusion(0x1D161). % MUSICAL SYMBOL SIXTEENTH NOTE unicode_composition_exclusion(0x1D162). % MUSICAL SYMBOL THIRTY-SECOND NOTE unicode_composition_exclusion(0x1D163). % MUSICAL SYMBOL SIXTY-FOURTH NOTE unicode_composition_exclusion(0x1D164). % MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE unicode_composition_exclusion(0x1D1BB). % MUSICAL SYMBOL MINIMA unicode_composition_exclusion(0x1D1BC). % MUSICAL SYMBOL MINIMA BLACK unicode_composition_exclusion(0x1D1BD). % MUSICAL SYMBOL SEMIMINIMA WHITE unicode_composition_exclusion(0x1D1BE). % MUSICAL SYMBOL SEMIMINIMA BLACK unicode_composition_exclusion(0x1D1BF). % MUSICAL SYMBOL FUSA WHITE unicode_composition_exclusion(0x1D1C0). % MUSICAL SYMBOL FUSA BLACK % Total code points: 14 /* # ================================================ # (3) Singleton Decompositions # # These characters can be derived from the UnicodeData.txt file # by including all canonically decomposable characters whose # canonical decomposition consists of a single character. # # These characters are simply quoted here for reference. # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt # ================================================ # 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK # 0343 COMBINING GREEK KORONIS # 0374 GREEK NUMERAL SIGN # 037E GREEK QUESTION MARK # 0387 GREEK ANO TELEIA # 1F71 GREEK SMALL LETTER ALPHA WITH OXIA # 1F73 GREEK SMALL LETTER EPSILON WITH OXIA # 1F75 GREEK SMALL LETTER ETA WITH OXIA # 1F77 GREEK SMALL LETTER IOTA WITH OXIA # 1F79 GREEK SMALL LETTER OMICRON WITH OXIA # 1F7B GREEK SMALL LETTER UPSILON WITH OXIA # 1F7D GREEK SMALL LETTER OMEGA WITH OXIA # 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA # 1FBE GREEK PROSGEGRAMMENI # 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA # 1FCB GREEK CAPITAL LETTER ETA WITH OXIA # 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA # 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA # 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA # 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA # 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA # 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA # 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA # 1FFD GREEK OXIA # 2000..2001 [2] EN QUAD..EM QUAD # 2126 OHM SIGN # 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN # 2329 LEFT-POINTING ANGLE BRACKET # 232A RIGHT-POINTING ANGLE BRACKET # F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D # FA10 CJK COMPATIBILITY IDEOGRAPH-FA10 # FA12 CJK COMPATIBILITY IDEOGRAPH-FA12 # FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E # FA20 CJK COMPATIBILITY IDEOGRAPH-FA20 # FA22 CJK COMPATIBILITY IDEOGRAPH-FA22 # FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26 # FA2A..FA6D [68] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA6D # FA70..FAD9 [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 # 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D # Total code points: 1035 # ================================================ # (4) Non-Starter Decompositions # # These characters can be derived from the UnicodeData.txt file # by including each expanding canonical decomposition # (i.e., those which canonically decompose to a sequence # of characters instead of a single character), such that: # # A. The character is not a Starter. # # OR (inclusive) # # B. The character's canonical decomposition begins # with a character that is not a Starter. # # Note that a "Starter" is any character with a zero combining class. # # These characters are simply quoted here for reference. # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt # ================================================ # 0344 COMBINING GREEK DIALYTIKA TONOS # 0F73 TIBETAN VOWEL SIGN II # 0F75 TIBETAN VOWEL SIGN UU # 0F81 TIBETAN VOWEL SIGN REVERSED II # Total code points: 4 */