sl@0: # CompositionExclusions-5.0.0.txt sl@0: # Date: 2006-05-23, 12:42:00 PST [KW] sl@0: # sl@0: # This file lists the characters for the Composition Exclusion Table sl@0: # defined in UAX #15, Unicode Normalization Forms. sl@0: # sl@0: # This file is a normative contributory data file in the sl@0: # Unicode Character Database. sl@0: # sl@0: # Copyright (c) 1991-2006 Unicode, Inc. sl@0: # For terms of use, see http://www.unicode.org/terms_of_use.html sl@0: # sl@0: # For more information, see sl@0: # http://www.unicode.org/unicode/reports/tr15/#Primary Exclusion List Table sl@0: # sl@0: # For a full derivation of composition exclusions, see the derived property sl@0: # Full_Composition_Exclusion in DerivedNormalizationProps.txt sl@0: # sl@0: sl@0: # ================================================ sl@0: # (1) Script Specifics sl@0: # sl@0: # This list of characters cannot be derived from the UnicodeData.txt file. sl@0: # ================================================ sl@0: sl@0: 0958 # DEVANAGARI LETTER QA sl@0: 0959 # DEVANAGARI LETTER KHHA sl@0: 095A # DEVANAGARI LETTER GHHA sl@0: 095B # DEVANAGARI LETTER ZA sl@0: 095C # DEVANAGARI LETTER DDDHA sl@0: 095D # DEVANAGARI LETTER RHA sl@0: 095E # DEVANAGARI LETTER FA sl@0: 095F # DEVANAGARI LETTER YYA sl@0: 09DC # BENGALI LETTER RRA sl@0: 09DD # BENGALI LETTER RHA sl@0: 09DF # BENGALI LETTER YYA sl@0: 0A33 # GURMUKHI LETTER LLA sl@0: 0A36 # GURMUKHI LETTER SHA sl@0: 0A59 # GURMUKHI LETTER KHHA sl@0: 0A5A # GURMUKHI LETTER GHHA sl@0: 0A5B # GURMUKHI LETTER ZA sl@0: 0A5E # GURMUKHI LETTER FA sl@0: 0B5C # ORIYA LETTER RRA sl@0: 0B5D # ORIYA LETTER RHA sl@0: 0F43 # TIBETAN LETTER GHA sl@0: 0F4D # TIBETAN LETTER DDHA sl@0: 0F52 # TIBETAN LETTER DHA sl@0: 0F57 # TIBETAN LETTER BHA sl@0: 0F5C # TIBETAN LETTER DZHA sl@0: 0F69 # TIBETAN LETTER KSSA sl@0: 0F76 # TIBETAN VOWEL SIGN VOCALIC R sl@0: 0F78 # TIBETAN VOWEL SIGN VOCALIC L sl@0: 0F93 # TIBETAN SUBJOINED LETTER GHA sl@0: 0F9D # TIBETAN SUBJOINED LETTER DDHA sl@0: 0FA2 # TIBETAN SUBJOINED LETTER DHA sl@0: 0FA7 # TIBETAN SUBJOINED LETTER BHA sl@0: 0FAC # TIBETAN SUBJOINED LETTER DZHA sl@0: 0FB9 # TIBETAN SUBJOINED LETTER KSSA sl@0: FB1D # HEBREW LETTER YOD WITH HIRIQ sl@0: FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH sl@0: FB2A # HEBREW LETTER SHIN WITH SHIN DOT sl@0: FB2B # HEBREW LETTER SHIN WITH SIN DOT sl@0: FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT sl@0: FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT sl@0: FB2E # HEBREW LETTER ALEF WITH PATAH sl@0: FB2F # HEBREW LETTER ALEF WITH QAMATS sl@0: FB30 # HEBREW LETTER ALEF WITH MAPIQ sl@0: FB31 # HEBREW LETTER BET WITH DAGESH sl@0: FB32 # HEBREW LETTER GIMEL WITH DAGESH sl@0: FB33 # HEBREW LETTER DALET WITH DAGESH sl@0: FB34 # HEBREW LETTER HE WITH MAPIQ sl@0: FB35 # HEBREW LETTER VAV WITH DAGESH sl@0: FB36 # HEBREW LETTER ZAYIN WITH DAGESH sl@0: FB38 # HEBREW LETTER TET WITH DAGESH sl@0: FB39 # HEBREW LETTER YOD WITH DAGESH sl@0: FB3A # HEBREW LETTER FINAL KAF WITH DAGESH sl@0: FB3B # HEBREW LETTER KAF WITH DAGESH sl@0: FB3C # HEBREW LETTER LAMED WITH DAGESH sl@0: FB3E # HEBREW LETTER MEM WITH DAGESH sl@0: FB40 # HEBREW LETTER NUN WITH DAGESH sl@0: FB41 # HEBREW LETTER SAMEKH WITH DAGESH sl@0: FB43 # HEBREW LETTER FINAL PE WITH DAGESH sl@0: FB44 # HEBREW LETTER PE WITH DAGESH sl@0: FB46 # HEBREW LETTER TSADI WITH DAGESH sl@0: FB47 # HEBREW LETTER QOF WITH DAGESH sl@0: FB48 # HEBREW LETTER RESH WITH DAGESH sl@0: FB49 # HEBREW LETTER SHIN WITH DAGESH sl@0: FB4A # HEBREW LETTER TAV WITH DAGESH sl@0: FB4B # HEBREW LETTER VAV WITH HOLAM sl@0: FB4C # HEBREW LETTER BET WITH RAFE sl@0: FB4D # HEBREW LETTER KAF WITH RAFE sl@0: FB4E # HEBREW LETTER PE WITH RAFE sl@0: sl@0: # Total code points: 67 sl@0: sl@0: # ================================================ sl@0: # (2) Post Composition Version precomposed characters sl@0: # sl@0: # These characters cannot be derived solely from the UnicodeData.txt file sl@0: # in this version of Unicode. sl@0: # sl@0: # Note that characters added to the standard after the sl@0: # Composition Version and which have canonical decomposition mappings sl@0: # are not automatically added to this list of Post Composition sl@0: # Version precomposed characters. sl@0: # ================================================ sl@0: sl@0: 2ADC # FORKING sl@0: 1D15E # MUSICAL SYMBOL HALF NOTE sl@0: 1D15F # MUSICAL SYMBOL QUARTER NOTE sl@0: 1D160 # MUSICAL SYMBOL EIGHTH NOTE sl@0: 1D161 # MUSICAL SYMBOL SIXTEENTH NOTE sl@0: 1D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE sl@0: 1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE sl@0: 1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE sl@0: 1D1BB # MUSICAL SYMBOL MINIMA sl@0: 1D1BC # MUSICAL SYMBOL MINIMA BLACK sl@0: 1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE sl@0: 1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK sl@0: 1D1BF # MUSICAL SYMBOL FUSA WHITE sl@0: 1D1C0 # MUSICAL SYMBOL FUSA BLACK sl@0: sl@0: # Total code points: 14 sl@0: sl@0: # ================================================ sl@0: # (3) Singleton Decompositions sl@0: # sl@0: # These characters can be derived from the UnicodeData.txt file sl@0: # by including all characters whose canonical decomposition sl@0: # consists of a single character. sl@0: # sl@0: # These characters are simply quoted here for reference. sl@0: # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt sl@0: # ================================================ sl@0: sl@0: # 0340..0341 [2] COMBINING GRAVE TONE MARK..COMBINING ACUTE TONE MARK sl@0: # 0343 COMBINING GREEK KORONIS sl@0: # 0374 GREEK NUMERAL SIGN sl@0: # 037E GREEK QUESTION MARK sl@0: # 0387 GREEK ANO TELEIA sl@0: # 1F71 GREEK SMALL LETTER ALPHA WITH OXIA sl@0: # 1F73 GREEK SMALL LETTER EPSILON WITH OXIA sl@0: # 1F75 GREEK SMALL LETTER ETA WITH OXIA sl@0: # 1F77 GREEK SMALL LETTER IOTA WITH OXIA sl@0: # 1F79 GREEK SMALL LETTER OMICRON WITH OXIA sl@0: # 1F7B GREEK SMALL LETTER UPSILON WITH OXIA sl@0: # 1F7D GREEK SMALL LETTER OMEGA WITH OXIA sl@0: # 1FBB GREEK CAPITAL LETTER ALPHA WITH OXIA sl@0: # 1FBE GREEK PROSGEGRAMMENI sl@0: # 1FC9 GREEK CAPITAL LETTER EPSILON WITH OXIA sl@0: # 1FCB GREEK CAPITAL LETTER ETA WITH OXIA sl@0: # 1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA sl@0: # 1FDB GREEK CAPITAL LETTER IOTA WITH OXIA sl@0: # 1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA sl@0: # 1FEB GREEK CAPITAL LETTER UPSILON WITH OXIA sl@0: # 1FEE..1FEF [2] GREEK DIALYTIKA AND OXIA..GREEK VARIA sl@0: # 1FF9 GREEK CAPITAL LETTER OMICRON WITH OXIA sl@0: # 1FFB GREEK CAPITAL LETTER OMEGA WITH OXIA sl@0: # 1FFD GREEK OXIA sl@0: # 2000..2001 [2] EN QUAD..EM QUAD sl@0: # 2126 OHM SIGN sl@0: # 212A..212B [2] KELVIN SIGN..ANGSTROM SIGN sl@0: # 2329 LEFT-POINTING ANGLE BRACKET sl@0: # 232A RIGHT-POINTING ANGLE BRACKET sl@0: # F900..FA0D [270] CJK COMPATIBILITY IDEOGRAPH-F900..CJK COMPATIBILITY IDEOGRAPH-FA0D sl@0: # FA10 CJK COMPATIBILITY IDEOGRAPH-FA10 sl@0: # FA12 CJK COMPATIBILITY IDEOGRAPH-FA12 sl@0: # FA15..FA1E [10] CJK COMPATIBILITY IDEOGRAPH-FA15..CJK COMPATIBILITY IDEOGRAPH-FA1E sl@0: # FA20 CJK COMPATIBILITY IDEOGRAPH-FA20 sl@0: # FA22 CJK COMPATIBILITY IDEOGRAPH-FA22 sl@0: # FA25..FA26 [2] CJK COMPATIBILITY IDEOGRAPH-FA25..CJK COMPATIBILITY IDEOGRAPH-FA26 sl@0: # FA2A..FA2D [4] CJK COMPATIBILITY IDEOGRAPH-FA2A..CJK COMPATIBILITY IDEOGRAPH-FA2D sl@0: # FA30..FA6A [59] CJK COMPATIBILITY IDEOGRAPH-FA30..CJK COMPATIBILITY IDEOGRAPH-FA6A sl@0: # FA70..FAD9 [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COMPATIBILITY IDEOGRAPH-FAD9 sl@0: # 2F800..2FA1D [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D sl@0: sl@0: # Total code points: 924 sl@0: sl@0: # ================================================ sl@0: # (4) Non-Starter Decompositions sl@0: # sl@0: # These characters can be derived from the UnicodeData file sl@0: # by including all characters whose canonical decomposition consists sl@0: # of a sequence of characters, the first of which has a non-zero sl@0: # combining class. sl@0: # sl@0: # These characters are simply quoted here for reference. sl@0: # See also Full_Composition_Exclusion in DerivedNormalizationProps.txt sl@0: # ================================================ sl@0: sl@0: # 0344 COMBINING GREEK DIALYTIKA TONOS sl@0: # 0F73 TIBETAN VOWEL SIGN II sl@0: # 0F75 TIBETAN VOWEL SIGN UU sl@0: # 0F81 TIBETAN VOWEL SIGN REVERSED II sl@0: sl@0: # Total code points: 4 sl@0: