fix: README -> README.md
This commit is contained in:
tmtt
parent
43e68af625
commit
99b0a6292c
756 changed files with 323753 additions and 71 deletions
1624
ta6ob/unicode/UNIDATA/CaseFolding.txt
Normal file
1624
ta6ob/unicode/UNIDATA/CaseFolding.txt
Normal file
File diff suppressed because it is too large
Load diff
221
ta6ob/unicode/UNIDATA/CompositionExclusions.txt
Normal file
221
ta6ob/unicode/UNIDATA/CompositionExclusions.txt
Normal file
|
|
@ -0,0 +1,221 @@
|
|||
# CompositionExclusions-14.0.0.txt
|
||||
# Date: 2021-03-30, 23:59:00 GMT [KW, LI]
|
||||
# © 2021 Unicode®, Inc.
|
||||
# For terms of use, see https://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
# Unicode Character Database
|
||||
# For documentation, see https://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# 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.
|
||||
#
|
||||
# For more information, see
|
||||
# https://www.unicode.org/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.
|
||||
#
|
||||
# Included are the following subcategories:
|
||||
#
|
||||
# - Many precomposed characters using a nukta diacritic in the Devanagari,
|
||||
# Bangla/Bengali, Gurmukhi, or Odia/Oriya scripts.
|
||||
# - Tibetan letters and subjoined letters with decompositions including
|
||||
# U+0FB7 TIBETAN SUBJOINED LETTER HA or U+0FB5 TIBETAN SUBJOINED LETTER SSA.
|
||||
# - Two two-part Tibetan vowel signs involving top and bottom pieces.
|
||||
# - A large collection of compatibility precomposed characters for Hebrew
|
||||
# involving dagesh and/or other combining marks.
|
||||
#
|
||||
# This list is unlikely to grow.
|
||||
#
|
||||
# ================================================
|
||||
|
||||
0958 # DEVANAGARI LETTER QA
|
||||
0959 # DEVANAGARI LETTER KHHA
|
||||
095A # DEVANAGARI LETTER GHHA
|
||||
095B # DEVANAGARI LETTER ZA
|
||||
095C # DEVANAGARI LETTER DDDHA
|
||||
095D # DEVANAGARI LETTER RHA
|
||||
095E # DEVANAGARI LETTER FA
|
||||
095F # DEVANAGARI LETTER YYA
|
||||
09DC # BENGALI LETTER RRA
|
||||
09DD # BENGALI LETTER RHA
|
||||
09DF # BENGALI LETTER YYA
|
||||
0A33 # GURMUKHI LETTER LLA
|
||||
0A36 # GURMUKHI LETTER SHA
|
||||
0A59 # GURMUKHI LETTER KHHA
|
||||
0A5A # GURMUKHI LETTER GHHA
|
||||
0A5B # GURMUKHI LETTER ZA
|
||||
0A5E # GURMUKHI LETTER FA
|
||||
0B5C # ORIYA LETTER RRA
|
||||
0B5D # ORIYA LETTER RHA
|
||||
0F43 # TIBETAN LETTER GHA
|
||||
0F4D # TIBETAN LETTER DDHA
|
||||
0F52 # TIBETAN LETTER DHA
|
||||
0F57 # TIBETAN LETTER BHA
|
||||
0F5C # TIBETAN LETTER DZHA
|
||||
0F69 # TIBETAN LETTER KSSA
|
||||
0F76 # TIBETAN VOWEL SIGN VOCALIC R
|
||||
0F78 # TIBETAN VOWEL SIGN VOCALIC L
|
||||
0F93 # TIBETAN SUBJOINED LETTER GHA
|
||||
0F9D # TIBETAN SUBJOINED LETTER DDHA
|
||||
0FA2 # TIBETAN SUBJOINED LETTER DHA
|
||||
0FA7 # TIBETAN SUBJOINED LETTER BHA
|
||||
0FAC # TIBETAN SUBJOINED LETTER DZHA
|
||||
0FB9 # TIBETAN SUBJOINED LETTER KSSA
|
||||
FB1D # HEBREW LETTER YOD WITH HIRIQ
|
||||
FB1F # HEBREW LIGATURE YIDDISH YOD YOD PATAH
|
||||
FB2A # HEBREW LETTER SHIN WITH SHIN DOT
|
||||
FB2B # HEBREW LETTER SHIN WITH SIN DOT
|
||||
FB2C # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT
|
||||
FB2D # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT
|
||||
FB2E # HEBREW LETTER ALEF WITH PATAH
|
||||
FB2F # HEBREW LETTER ALEF WITH QAMATS
|
||||
FB30 # HEBREW LETTER ALEF WITH MAPIQ
|
||||
FB31 # HEBREW LETTER BET WITH DAGESH
|
||||
FB32 # HEBREW LETTER GIMEL WITH DAGESH
|
||||
FB33 # HEBREW LETTER DALET WITH DAGESH
|
||||
FB34 # HEBREW LETTER HE WITH MAPIQ
|
||||
FB35 # HEBREW LETTER VAV WITH DAGESH
|
||||
FB36 # HEBREW LETTER ZAYIN WITH DAGESH
|
||||
FB38 # HEBREW LETTER TET WITH DAGESH
|
||||
FB39 # HEBREW LETTER YOD WITH DAGESH
|
||||
FB3A # HEBREW LETTER FINAL KAF WITH DAGESH
|
||||
FB3B # HEBREW LETTER KAF WITH DAGESH
|
||||
FB3C # HEBREW LETTER LAMED WITH DAGESH
|
||||
FB3E # HEBREW LETTER MEM WITH DAGESH
|
||||
FB40 # HEBREW LETTER NUN WITH DAGESH
|
||||
FB41 # HEBREW LETTER SAMEKH WITH DAGESH
|
||||
FB43 # HEBREW LETTER FINAL PE WITH DAGESH
|
||||
FB44 # HEBREW LETTER PE WITH DAGESH
|
||||
FB46 # HEBREW LETTER TSADI WITH DAGESH
|
||||
FB47 # HEBREW LETTER QOF WITH DAGESH
|
||||
FB48 # HEBREW LETTER RESH WITH DAGESH
|
||||
FB49 # HEBREW LETTER SHIN WITH DAGESH
|
||||
FB4A # HEBREW LETTER TAV WITH DAGESH
|
||||
FB4B # HEBREW LETTER VAV WITH HOLAM
|
||||
FB4C # HEBREW LETTER BET WITH RAFE
|
||||
FB4D # HEBREW LETTER KAF WITH RAFE
|
||||
FB4E # 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.
|
||||
# ================================================
|
||||
|
||||
2ADC # FORKING
|
||||
1D15E # MUSICAL SYMBOL HALF NOTE
|
||||
1D15F # MUSICAL SYMBOL QUARTER NOTE
|
||||
1D160 # MUSICAL SYMBOL EIGHTH NOTE
|
||||
1D161 # MUSICAL SYMBOL SIXTEENTH NOTE
|
||||
1D162 # MUSICAL SYMBOL THIRTY-SECOND NOTE
|
||||
1D163 # MUSICAL SYMBOL SIXTY-FOURTH NOTE
|
||||
1D164 # MUSICAL SYMBOL ONE HUNDRED TWENTY-EIGHTH NOTE
|
||||
1D1BB # MUSICAL SYMBOL MINIMA
|
||||
1D1BC # MUSICAL SYMBOL MINIMA BLACK
|
||||
1D1BD # MUSICAL SYMBOL SEMIMINIMA WHITE
|
||||
1D1BE # MUSICAL SYMBOL SEMIMINIMA BLACK
|
||||
1D1BF # MUSICAL SYMBOL FUSA WHITE
|
||||
1D1C0 # 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
|
||||
|
||||
# EOF
|
||||
19047
ta6ob/unicode/UNIDATA/NormalizationTest.txt
Normal file
19047
ta6ob/unicode/UNIDATA/NormalizationTest.txt
Normal file
File diff suppressed because it is too large
Load diff
1743
ta6ob/unicode/UNIDATA/PropList.txt
Normal file
1743
ta6ob/unicode/UNIDATA/PropList.txt
Normal file
File diff suppressed because it is too large
Load diff
281
ta6ob/unicode/UNIDATA/SpecialCasing.txt
Normal file
281
ta6ob/unicode/UNIDATA/SpecialCasing.txt
Normal file
|
|
@ -0,0 +1,281 @@
|
|||
# SpecialCasing-14.0.0.txt
|
||||
# Date: 2021-03-08, 19:35:55 GMT
|
||||
# © 2021 Unicode®, Inc.
|
||||
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
|
||||
# For terms of use, see http://www.unicode.org/terms_of_use.html
|
||||
#
|
||||
# Unicode Character Database
|
||||
# For documentation, see http://www.unicode.org/reports/tr44/
|
||||
#
|
||||
# Special Casing
|
||||
#
|
||||
# This file is a supplement to the UnicodeData.txt file. It does not define any
|
||||
# properties, but rather provides additional information about the casing of
|
||||
# Unicode characters, for situations when casing incurs a change in string length
|
||||
# or is dependent on context or locale. For compatibility, the UnicodeData.txt
|
||||
# file only contains simple case mappings for characters where they are one-to-one
|
||||
# and independent of context and language. The data in this file, combined with
|
||||
# the simple case mappings in UnicodeData.txt, defines the full case mappings
|
||||
# Lowercase_Mapping (lc), Titlecase_Mapping (tc), and Uppercase_Mapping (uc).
|
||||
#
|
||||
# Note that the preferred mechanism for defining tailored casing operations is
|
||||
# the Unicode Common Locale Data Repository (CLDR). For more information, see the
|
||||
# discussion of case mappings and case algorithms in the Unicode Standard.
|
||||
#
|
||||
# All code points not listed in this file that do not have a simple case mappings
|
||||
# in UnicodeData.txt map to themselves.
|
||||
# ================================================================================
|
||||
# Format
|
||||
# ================================================================================
|
||||
# The entries in this file are in the following machine-readable format:
|
||||
#
|
||||
# <code>; <lower>; <title>; <upper>; (<condition_list>;)? # <comment>
|
||||
#
|
||||
# <code>, <lower>, <title>, and <upper> provide the respective full case mappings
|
||||
# of <code>, expressed as character values in hex. If there is more than one character,
|
||||
# they are separated by spaces. Other than as used to separate elements, spaces are
|
||||
# to be ignored.
|
||||
#
|
||||
# The <condition_list> is optional. Where present, it consists of one or more language IDs
|
||||
# or casing contexts, separated by spaces. In these conditions:
|
||||
# - A condition list overrides the normal behavior if all of the listed conditions are true.
|
||||
# - The casing context is always the context of the characters in the original string,
|
||||
# NOT in the resulting string.
|
||||
# - Case distinctions in the condition list are not significant.
|
||||
# - Conditions preceded by "Not_" represent the negation of the condition.
|
||||
# The condition list is not represented in the UCD as a formal property.
|
||||
#
|
||||
# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
|
||||
#
|
||||
# A casing context for a character is defined by Section 3.13 Default Case Algorithms
|
||||
# of The Unicode Standard.
|
||||
#
|
||||
# Parsers of this file must be prepared to deal with future additions to this format:
|
||||
# * Additional contexts
|
||||
# * Additional fields
|
||||
# ================================================================================
|
||||
|
||||
# ================================================================================
|
||||
# Unconditional mappings
|
||||
# ================================================================================
|
||||
|
||||
# The German es-zed is special--the normal mapping is to SS.
|
||||
# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
|
||||
|
||||
00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
|
||||
|
||||
# Preserve canonical equivalence for I with dot. Turkic is handled below.
|
||||
|
||||
0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
|
||||
# Ligatures
|
||||
|
||||
FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
|
||||
FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
|
||||
FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
|
||||
FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
|
||||
FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
|
||||
FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
|
||||
FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
|
||||
|
||||
0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
|
||||
FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
|
||||
FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
|
||||
FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
|
||||
FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
|
||||
FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
|
||||
|
||||
# No corresponding uppercase precomposed character
|
||||
|
||||
0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
|
||||
0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
|
||||
03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
|
||||
01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
|
||||
1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
|
||||
1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
|
||||
1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
|
||||
1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
|
||||
1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
|
||||
1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
|
||||
1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
|
||||
1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
|
||||
1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
|
||||
1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
|
||||
1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
|
||||
1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
|
||||
1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
|
||||
1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
|
||||
1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
|
||||
1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
|
||||
1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
|
||||
1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
|
||||
1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
|
||||
1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
|
||||
1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
|
||||
|
||||
# IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
|
||||
# the result will be incorrect unless the iota-subscript is moved to the end
|
||||
# of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
|
||||
# This process can be achieved by first transforming the text to NFC before casing.
|
||||
# E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
|
||||
|
||||
# The following cases are already in the UnicodeData.txt file, so are only commented here.
|
||||
|
||||
# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
|
||||
|
||||
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
|
||||
# have special uppercases.
|
||||
# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
|
||||
|
||||
1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
|
||||
1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
|
||||
1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
|
||||
1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
|
||||
1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
|
||||
1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
|
||||
1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
|
||||
1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
|
||||
1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
|
||||
1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
|
||||
1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
|
||||
1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
|
||||
1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
|
||||
1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
|
||||
1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
|
||||
1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
|
||||
1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
|
||||
1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
|
||||
1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
|
||||
1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
|
||||
1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
|
||||
1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
|
||||
1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
|
||||
1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
|
||||
1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
|
||||
1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
|
||||
1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
|
||||
|
||||
# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
|
||||
|
||||
1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
|
||||
1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
|
||||
1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
|
||||
|
||||
1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
|
||||
|
||||
# ================================================================================
|
||||
# Conditional Mappings
|
||||
# The remainder of this file provides conditional casing data used to produce
|
||||
# full case mappings.
|
||||
# ================================================================================
|
||||
# Language-Insensitive Mappings
|
||||
# These are characters whose full case mappings do not depend on language, but do
|
||||
# depend on context (which characters come before or after). For more information
|
||||
# see the header of this file and the Unicode Standard.
|
||||
# ================================================================================
|
||||
|
||||
# Special case for final form of sigma
|
||||
|
||||
03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
|
||||
|
||||
# Note: the following cases for non-final are already in the UnicodeData.txt file.
|
||||
|
||||
# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
|
||||
# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
|
||||
# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
|
||||
|
||||
# Note: the following cases are not included, since they would case-fold in lowercasing
|
||||
|
||||
# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
|
||||
# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
|
||||
|
||||
# ================================================================================
|
||||
# Language-Sensitive Mappings
|
||||
# These are characters whose full case mappings depend on language and perhaps also
|
||||
# context (which characters come before or after). For more information
|
||||
# see the header of this file and the Unicode Standard.
|
||||
# ================================================================================
|
||||
|
||||
# Lithuanian
|
||||
|
||||
# Lithuanian retains the dot in a lowercase i when followed by accents.
|
||||
|
||||
# Remove DOT ABOVE after "i" with upper or titlecase
|
||||
|
||||
0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
|
||||
|
||||
# Introduce an explicit dot above when lowercasing capital I's and J's
|
||||
# whenever there are more accents above.
|
||||
# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
|
||||
|
||||
0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
|
||||
004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
|
||||
012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
|
||||
00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
|
||||
00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
|
||||
0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
|
||||
|
||||
# ================================================================================
|
||||
|
||||
# Turkish and Azeri
|
||||
|
||||
# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
|
||||
# The following rules handle those cases.
|
||||
|
||||
0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
|
||||
|
||||
# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
|
||||
# This matches the behavior of the canonically equivalent I-dot_above
|
||||
|
||||
0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
|
||||
0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
|
||||
|
||||
# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
|
||||
|
||||
0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
|
||||
0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
|
||||
|
||||
# When uppercasing, i turns into a dotted capital I
|
||||
|
||||
0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
|
||||
0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
|
||||
|
||||
# Note: the following case is already in the UnicodeData.txt file.
|
||||
|
||||
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
|
||||
|
||||
# EOF
|
||||
|
||||
34626
ta6ob/unicode/UNIDATA/UnicodeData.txt
Normal file
34626
ta6ob/unicode/UNIDATA/UnicodeData.txt
Normal file
File diff suppressed because it is too large
Load diff
1441
ta6ob/unicode/UNIDATA/WordBreakProperty.txt
Normal file
1441
ta6ob/unicode/UNIDATA/WordBreakProperty.txt
Normal file
File diff suppressed because it is too large
Load diff
Reference in a new issue