libgrapheme

Freestanding C library for unicode string handling
git clone https://git.sinitax.com/suckless/libgrapheme
Log | Files | Refs | README | LICENSE | sfeed.txt

SpecialCasing.txt (16832B)


      1# SpecialCasing-15.0.0.txt
      2# Date: 2022-02-02, 23:35:52 GMT
      3# © 2022 Unicode®, Inc.
      4# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
      5# For terms of use, see https://www.unicode.org/terms_of_use.html
      6#
      7# Unicode Character Database
      8#   For documentation, see https://www.unicode.org/reports/tr44/
      9#
     10# Special Casing
     11#
     12# This file is a supplement to the UnicodeData.txt file. It does not define any
     13# properties, but rather provides additional information about the casing of
     14# Unicode characters, for situations when casing incurs a change in string length
     15# or is dependent on context or locale. For compatibility, the UnicodeData.txt
     16# file only contains simple case mappings for characters where they are one-to-one
     17# and independent of context and language. The data in this file, combined with
     18# the simple case mappings in UnicodeData.txt, defines the full case mappings
     19# Lowercase_Mapping (lc), Titlecase_Mapping (tc), and Uppercase_Mapping (uc).
     20#
     21# Note that the preferred mechanism for defining tailored casing operations is
     22# the Unicode Common Locale Data Repository (CLDR). For more information, see the
     23# discussion of case mappings and case algorithms in the Unicode Standard.
     24#
     25# All code points not listed in this file that do not have a simple case mappings
     26# in UnicodeData.txt map to themselves.
     27# ================================================================================
     28# Format
     29# ================================================================================
     30# The entries in this file are in the following machine-readable format:
     31#
     32# <code>; <lower>; <title>; <upper>; (<condition_list>;)? # <comment>
     33#
     34# <code>, <lower>, <title>, and <upper> provide the respective full case mappings
     35# of <code>, expressed as character values in hex. If there is more than one character,
     36# they are separated by spaces. Other than as used to separate elements, spaces are
     37# to be ignored.
     38#
     39# The <condition_list> is optional. Where present, it consists of one or more language IDs
     40# or casing contexts, separated by spaces. In these conditions:
     41# - A condition list overrides the normal behavior if all of the listed conditions are true.
     42# - The casing context is always the context of the characters in the original string,
     43#   NOT in the resulting string.
     44# - Case distinctions in the condition list are not significant.
     45# - Conditions preceded by "Not_" represent the negation of the condition.
     46# The condition list is not represented in the UCD as a formal property.
     47#
     48# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
     49#
     50# A casing context for a character is defined by Section 3.13 Default Case Algorithms
     51# of The Unicode Standard.
     52#
     53# Parsers of this file must be prepared to deal with future additions to this format:
     54#  * Additional contexts
     55#  * Additional fields
     56# ================================================================================
     57
     58# ================================================================================
     59# Unconditional mappings
     60# ================================================================================
     61
     62# The German es-zed is special--the normal mapping is to SS.
     63# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
     64
     6500DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
     66
     67# Preserve canonical equivalence for I with dot. Turkic is handled below.
     68
     690130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
     70
     71# Ligatures
     72
     73FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
     74FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
     75FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
     76FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
     77FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
     78FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
     79FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
     80
     810587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
     82FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
     83FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
     84FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
     85FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
     86FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
     87
     88# No corresponding uppercase precomposed character
     89
     900149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
     910390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
     9203B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
     9301F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
     941E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
     951E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
     961E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
     971E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
     981E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
     991F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
    1001F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
    1011F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
    1021F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
    1031FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
    1041FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
    1051FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
    1061FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
    1071FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
    1081FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
    1091FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
    1101FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
    1111FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
    1121FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
    1131FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
    1141FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
    115
    116# IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
    117#  the result will be incorrect unless the iota-subscript is moved to the end
    118#  of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
    119#  This process can be achieved by first transforming the text to NFC before casing.
    120#  E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
    121
    122# The following cases are already in the UnicodeData.txt file, so are only commented here.
    123
    124# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
    125
    126# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
    127# have special uppercases.
    128# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
    129
    1301F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
    1311F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
    1321F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
    1331F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
    1341F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
    1351F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
    1361F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
    1371F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
    1381F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
    1391F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
    1401F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
    1411F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
    1421F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
    1431F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
    1441F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
    1451F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
    1461F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
    1471F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
    1481F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
    1491F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
    1501F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
    1511F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
    1521F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
    1531F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
    1541F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
    1551F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
    1561F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
    1571F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
    1581F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
    1591F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
    1601F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
    1611F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
    1621FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
    1631FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
    1641FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
    1651FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
    1661FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
    1671FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
    1681FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
    1691FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
    1701FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
    1711FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
    1721FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
    1731FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
    1741FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
    1751FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
    1761FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
    1771FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
    1781FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
    1791FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
    1801FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
    1811FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
    1821FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
    1831FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
    184
    185# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
    186
    1871FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
    1881FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
    1891FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
    1901FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
    1911FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
    1921FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
    193
    1941FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
    1951FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
    1961FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
    197
    198# ================================================================================
    199# Conditional Mappings
    200# The remainder of this file provides conditional casing data used to produce
    201# full case mappings.
    202# ================================================================================
    203# Language-Insensitive Mappings
    204# These are characters whose full case mappings do not depend on language, but do
    205# depend on context (which characters come before or after). For more information
    206# see the header of this file and the Unicode Standard.
    207# ================================================================================
    208
    209# Special case for final form of sigma
    210
    21103A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
    212
    213# Note: the following cases for non-final are already in the UnicodeData.txt file.
    214
    215# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
    216# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
    217# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
    218
    219# Note: the following cases are not included, since they would case-fold in lowercasing
    220
    221# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
    222# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
    223
    224# ================================================================================
    225# Language-Sensitive Mappings
    226# These are characters whose full case mappings depend on language and perhaps also
    227# context (which characters come before or after). For more information
    228# see the header of this file and the Unicode Standard.
    229# ================================================================================
    230
    231# Lithuanian
    232
    233# Lithuanian retains the dot in a lowercase i when followed by accents.
    234
    235# Remove DOT ABOVE after "i" with upper or titlecase
    236
    2370307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
    238
    239# Introduce an explicit dot above when lowercasing capital I's and J's
    240# whenever there are more accents above.
    241# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
    242
    2430049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
    244004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
    245012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
    24600CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
    24700CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
    2480128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
    249
    250# ================================================================================
    251
    252# Turkish and Azeri
    253
    254# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
    255# The following rules handle those cases.
    256
    2570130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
    2580130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
    259
    260# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
    261# This matches the behavior of the canonically equivalent I-dot_above
    262
    2630307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
    2640307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
    265
    266# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
    267
    2680049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
    2690049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
    270
    271# When uppercasing, i turns into a dotted capital I
    272
    2730069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
    2740069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
    275
    276# Note: the following case is already in the UnicodeData.txt file.
    277
    278# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
    279
    280# EOF
    281