mirror of
https://github.com/moodle/moodle.git
synced 2025-08-05 00:46:50 +02:00
Initial commit of Typo3 charset libraries and Moodle's textlib.class code.
Merged from MOODLE_15_STABLE
This commit is contained in:
stronk7
parent
acf879d685
commit
779dc9aca1
38 changed files with 86007 additions and 0 deletions
256
lib/typo3/unidata/SpecialCasing.txt
Normal file
256
lib/typo3/unidata/SpecialCasing.txt
Normal file
|
|
@ -0,0 +1,256 @@
|
|||
# SpecialCasing-4.0.1.txt
|
||||
# Date: 2003-10-06, 17:30:00 PST [KW]
|
||||
#
|
||||
# Special Casing Properties
|
||||
#
|
||||
# This file is a supplement to the UnicodeData file.
|
||||
# It contains additional information about the casing of Unicode characters.
|
||||
# (For compatibility, the UnicodeData.txt file only contains case mappings for
|
||||
# characters where they are 1-1, and does not have locale-specific mappings.)
|
||||
# For more information, see the discussion of Case Mappings 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 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 locales or contexts,
|
||||
# separated by spaces. In these conditions:
|
||||
# - A condition list overrides the normal behavior if all of the listed conditions are true.
|
||||
# - The 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.
|
||||
#
|
||||
# A locale is defined as:
|
||||
# <locale> := <ISO_639_code> ( "_" <ISO_3166_code> ( "_" <variant> )? )?
|
||||
# <ISO_3166_code> := 2-letter ISO country code,
|
||||
# <ISO_639_code> := 2-letter ISO language code
|
||||
#
|
||||
# A context is one of the following, as defined in the Unicode Standard:
|
||||
# Final_Sigma, After_Soft_Dotted, More_Above, Before_Dot, Not_Before_Dot, After_I
|
||||
#
|
||||
# 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 capitalizing iota-subscript (0345)
|
||||
# It MUST be in normalized form--moved to the end of any sequence of combining marks.
|
||||
# This is because logically it represents a following base character!
|
||||
# E.g. <iota_subscript> (<Mn> | <Mc> | <Me>)+ => (<Mn> | <Mc> | <Me>)+ <iota_subscript>
|
||||
# It should never be the first character in a word, so in titlecasing it can be left as is.
|
||||
|
||||
# The following cases are already in the UnicodeData file, so are only commented here.
|
||||
|
||||
# 0345; 0345; 0345; 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
|
||||
# ================================================================================
|
||||
|
||||
# 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 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
|
||||
|
||||
# ================================================================================
|
||||
# Locale-sensitive mappings
|
||||
# ================================================================================
|
||||
|
||||
# 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 file.
|
||||
|
||||
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
|
||||
215
lib/typo3/unidata/Translit.txt
Normal file
215
lib/typo3/unidata/Translit.txt
Normal file
|
|
@ -0,0 +1,215 @@
|
|||
|
||||
# Latin (iso-8859-1)
|
||||
|
||||
00A5; 0079 0065 006E; YEN SIGN => yen
|
||||
00A6; 007C; BROKEN BAR => |
|
||||
00AB; 003C 003C; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
|
||||
00A9; 0028 0063 0029; COPYRIGHT SIGN => (c)
|
||||
00AE; 0028 0052 0029; REGISTERED SIGN => (R)
|
||||
00B1; 002B 002F 002D; PLUS-MINUS SIGN => +/-
|
||||
00B5; 0075; MICRO SIGN => u (American style)
|
||||
00B7; 002A; MIDDLE DOT => *
|
||||
00BB; 003E 003E; RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK => <<
|
||||
00C4; 0041 0045; LATIN CAPITAL LETTER A WITH DIAERESIS => AE (German)
|
||||
00C5; 0041 0041; LATIN CAPITAL LETTER A WITH RING ABOVE => AA (Danish)
|
||||
00C6; 0041 0045; LATIN CAPITAL LETTER AE => AE (Danish)
|
||||
00D6; 004F 0045; LATIN CAPITAL LETTER O WITH DIAERESIS => OE (German)
|
||||
00D7; 0078; MULTIPLICATION SIGN => x
|
||||
00D8; 004F 0045; LATIN CAPITAL LETTER O WITH STROKE => OE (Danish)
|
||||
00DC; 0055 0045; LATIN CAPITAL LETTER U WITH DIAERESIS => UE (German)
|
||||
00E4; 0061 0065; LATIN SMALL LETTER A WITH DIAERESIS => ae (German)
|
||||
00E5; 0061 0061; LATIN SMALL LETTER A WITH RING ABOVE => aa (Danish)
|
||||
00DF; 0073 0073; LATIN SMALL LETTER SHARP S => ss (German)
|
||||
00E6; 0061 0065; LATIN SMALL LETTER AE => ae (Danish)
|
||||
00F6; 006F 0065; LATIN SMALL LETTER O WITH DIAERESIS => oe (German)
|
||||
00F7; 002F; DIVISION SIGN => /
|
||||
00F8; 006F 0065; LATIN SMALL LETTER O WITH STROKE => oe (Danish)
|
||||
00FC; 0075 0065; LATIN SMALL LETTER U WITH DIAERESIS => ue (German)
|
||||
|
||||
# more Latin (windows-1252, windows-1254, windows-1257)
|
||||
|
||||
0100; 0041 0041; LATIN CAPITAL LETTER A WITH MACRON => AA (Latvian)
|
||||
0101; 0061 0061; LATIN SMALL LETTER A WITH MACRON => aa (Latvian)
|
||||
0112; 0045 0045; LATIN CAPITAL LETTER E WITH MACRON => EE (Latvian)
|
||||
0113; 0065 0065; LATIN SMALL LETTER E WITH MACRON => ee (Latvian)
|
||||
012A; 0049 0049; LATIN CAPITAL LETTER I WITH MACRON => II (Latvian)
|
||||
012B; 0060 0069; LATIN SMALL LETTER I WITH MACRON => ii(Latvian)
|
||||
014C; 004F 004F; LATIN CAPITAL LETTER O WITH MACRON => OO
|
||||
014D; 006F 006F; LATIN SMALL LETTER O WITH MACRON => oo
|
||||
016A; 0055 0055; LATIN CAPITAL LETTER U WITH MACRON => UU (Latvian)
|
||||
016B; 0075 0075; LATIN SMALL LETTER U WITH MACRON => uu (Latvian)
|
||||
0131; 0069; LATIN SMALL LETTER DOTLESS I => i (Turkish)
|
||||
0152; 004F 0045; LATIN CAPITAL LETTER OE => OE
|
||||
0153; 006F 0065; LATIN SMALL LETTER OE => oe
|
||||
0192; 0066; LATIN SMALL LETTER F WITH HOOK => f
|
||||
02BC; 0027; MODIFIER LETTER APOSTROPHE => '
|
||||
02CA; 0027; MODIFIER LETTER ACUTE ACCENT => '
|
||||
2010; 002D; HYPHEN => -
|
||||
2013; 002D; EN DASH => -
|
||||
2014; 002D; EM DASH => -
|
||||
2018; 0060; LEFT SINGLE QUOTATION MARK => `
|
||||
2019; 0027; RIGHT SINGLE QUOTATION MARK >= '
|
||||
201C; 0022; LEFT DOUBLE QUOTATION MARK => "
|
||||
201D; 0022; RIGHT DOUBLE QUOTATION MARK => "
|
||||
201E; 0022; DOUBLE LOW-9 QUOTATION MARK => "
|
||||
2022; 002A; BULLET => *
|
||||
2039; 003C; SINGLE LEFT-POINTING ANGLE QUOTATION MARK => <
|
||||
203A; 003E; SINGLE RIGHT-POINTING ANGLE QUOTATION MARK => >
|
||||
2044; 002F; FRACTION SLASH => /
|
||||
20A0; 0045 0055 0052; EURO-CURRENCY SIGN => EUR
|
||||
20AC; 0045 0055 0052; EURO-CURRENCY SIGN => EUR
|
||||
|
||||
# Cyrillic (Russian transliteration: modified GOST)
|
||||
|
||||
0401; 004A 004F; CYRILLIC CAPITAL LETTER IO => JO
|
||||
#0402; ; CYRILLIC CAPITAL LETTER DJE
|
||||
#0403; ; CYRILLIC CAPITAL LETTER GJE
|
||||
0404; 004A 0045; CYRILLIC CAPITAL LETTER UKRAINIAN IE => JE
|
||||
#0405; ; CYRILLIC CAPITAL LETTER DZE
|
||||
0406; 0049; CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I => I
|
||||
0407; 0049; CYRILLIC CAPITAL LETTER YI => I
|
||||
#0408; ; CYRILLIC CAPITAL LETTER JE ?? J
|
||||
#0409; ; CYRILLIC CAPITAL LETTER LJE ?? LJ
|
||||
#040A; ; CYRILLIC CAPITAL LETTER NJE ?? NJ
|
||||
#040B; ; CYRILLIC CAPITAL LETTER TSHE ?? TSH
|
||||
#040C; ; CYRILLIC CAPITAL LETTER KJE ?? KJ KY
|
||||
040E; 0055; CYRILLIC CAPITAL LETTER SHORT U => U (Belorussian)
|
||||
#040F; ; CYRILLIC CAPITAL LETTER DZHE ?? DZH
|
||||
0410; 0041; CYRILLIC CAPITAL LETTER A => A
|
||||
0411; 0042; CYRILLIC CAPITAL LETTER BE => B
|
||||
0412; 0056; CYRILLIC CAPITAL LETTER VE => V
|
||||
0413; 0047; CYRILLIC CAPITAL LETTER GHE => G
|
||||
0414; 0044; CYRILLIC CAPITAL LETTER DE => D
|
||||
0415; 0045; CYRILLIC CAPITAL LETTER IE => E
|
||||
0416; 005A 0048; CYRILLIC CAPITAL LETTER ZHE => ZH
|
||||
0417; 005A; CYRILLIC CAPITAL LETTER ZE => Z
|
||||
0418; 0049; CYRILLIC CAPITAL LETTER I=> I
|
||||
0419; 0049; CYRILLIC CAPITAL LETTER SHORT I => I (GOST has I)
|
||||
041A; 004B; CYRILLIC CAPITAL LETTER KA => K
|
||||
041B; 004C; CYRILLIC CAPITAL LETTER EL => L
|
||||
041C; 004D; CYRILLIC CAPITAL LETTER EM => M
|
||||
041D; 004E; CYRILLIC CAPITAL LETTER EN => N
|
||||
041E; 004F; CYRILLIC CAPITAL LETTER O => O
|
||||
041F; 0050; CYRILLIC CAPITAL LETTER PE => P
|
||||
0420; 0052; CYRILLIC CAPITAL LETTER ER => R
|
||||
0421; 0053; CYRILLIC CAPITAL LETTER ES => S
|
||||
0422; 0054; CYRILLIC CAPITAL LETTER TE => T
|
||||
0423; 0055; CYRILLIC CAPITAL LETTER U => U
|
||||
0424; 0046; CYRILLIC CAPITAL LETTER EF => F
|
||||
0425; 004B 0048; CYRILLIC CAPITAL LETTER HA => KH
|
||||
0426; 0043; CYRILLIC CAPITAL LETTER TSE => C
|
||||
0427; 0043 0048; CYRILLIC CAPITAL LETTER CHE => CH
|
||||
0428; 0053 0048; CYRILLIC CAPITAL LETTER SHA => SH
|
||||
0429; 0053 0048 0043 0048; CYRILLIC CAPITAL LETTER SHCHA => SHCH (GOST has SHH)
|
||||
042A; ; CYRILLIC CAPITAL LETTER HARD SIGN => omit (GOST has ")
|
||||
042B; 0059; CYRILLIC CAPITAL LETTER YERU => Y
|
||||
042C; ; CYRILLIC CAPITAL LETTER SOFT SIGN => omit (GOST has ')
|
||||
042D; 0045 0048; CYRILLIC CAPITAL LETTER E => EH
|
||||
042E; 004A 0055; CYRILLIC CAPITAL LETTER YU => JU
|
||||
042F; 004A 0041; CYRILLIC CAPITAL LETTER YA => JA
|
||||
|
||||
0430; 0061; CYRILLIC SMALL LETTER A => a
|
||||
0431; 0062; CYRILLIC SMALL LETTER BE => b
|
||||
0432; 0076; CYRILLIC SMALL LETTER VE => v
|
||||
0433; 0067; CYRILLIC SMALL LETTER GHE => g
|
||||
0434; 0064; CYRILLIC SMALL LETTER DE => d
|
||||
0435; 0065; CYRILLIC SMALL LETTER IE => e
|
||||
0436; 007A 0068; CYRILLIC SMALL LETTER ZHE => zh
|
||||
0437; 007A; CYRILLIC SMALL LETTER ZE => z
|
||||
0438; 0069; CYRILLIC SMALL LETTER I => i
|
||||
0439; 0069; CYRILLIC SMALL LETTER SHORT I => i (GOST has j)
|
||||
043A; 006B; CYRILLIC SMALL LETTER KA => k
|
||||
043B; 006C; CYRILLIC SMALL LETTER EL => l
|
||||
043C; 006D; CYRILLIC SMALL LETTER EM => m
|
||||
043D; 006E; CYRILLIC SMALL LETTER EN => n
|
||||
043E; 006F; CYRILLIC SMALL LETTER O => o
|
||||
043F; 0070; CYRILLIC SMALL LETTER PE => p
|
||||
0440; 0072; CYRILLIC SMALL LETTER ER => r
|
||||
0441; 0073; CYRILLIC SMALL LETTER ES => s
|
||||
0442; 0074; CYRILLIC SMALL LETTER TE => t
|
||||
0443; 0075; CYRILLIC SMALL LETTER U => u
|
||||
0444; 0066; CYRILLIC SMALL LETTER EF => f
|
||||
0445; 006B 0068; CYRILLIC SMALL LETTER HA => kh
|
||||
0446; 0063; CYRILLIC SMALL LETTER TSE => c
|
||||
0447; 0063 0068; CYRILLIC SMALL LETTER CHE => ch
|
||||
0448; 0073 0068; CYRILLIC SMALL LETTER SHA => sh
|
||||
0449; 0073 0068 0063 0068; CYRILLIC SMALL LETTER SHCHA => shch (GOST has shh)
|
||||
044A; ; CYRILLIC SMALL LETTER HARD SIGN => omit (GOST has ")
|
||||
044B; 0079; CYRILLIC SMALL LETTER YERU => y
|
||||
044C; ; CYRILLIC SMALL LETTER SOFT SIGN => omit (GOST has ')
|
||||
044D; 0065 0068; CYRILLIC SMALL LETTER E => eh
|
||||
044E; 006A 0075; CYRILLIC SMALL LETTER YU => ju
|
||||
044F; 006A 0061; CYRILLIC SMALL LETTER YA => ja
|
||||
0451; 006A 006F; CYRILLIC SMALL LETTER IO => jo
|
||||
#0452; ; CYRILLIC SMALL LETTER DJE => dj dy ??
|
||||
#0453; ; CYRILLIC SMALL LETTER GJE => gj gy ??
|
||||
0454; 006A 0065; CYRILLIC SMALL LETTER UKRAINIAN IE => je
|
||||
#0455; ; CYRILLIC SMALL LETTER DZE => dz ??
|
||||
0456; 0069; CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I => i
|
||||
0457; 006A 0069; CYRILLIC SMALL LETTER YI => ji
|
||||
#0458; ; CYRILLIC SMALL LETTER JE ?? j y
|
||||
#0459; ; CYRILLIC SMALL LETTER LJE ?? lj ly
|
||||
#045A; ; CYRILLIC SMALL LETTER NJE ?? nj ny
|
||||
#045B; ; CYRILLIC SMALL LETTER TSHE => ??? tsh ch (Serbocroatian)
|
||||
#045C; ; CYRILLIC SMALL LETTER KJE
|
||||
045E; 0075; CYRILLIC SMALL LETTER SHORT U => U (Belorussian)
|
||||
#045F; ; CYRILLIC SMALL LETTER DZHE ???
|
||||
|
||||
0490; 0047 0047; CYRILLIC CAPITAL LETTER GHE WITH UPTURN => GG (Belorussian, Ukrainian)
|
||||
0491; 0067 0076; CYRILLIC SMALL LETTER GHE WITH UPTURN => gg (Belorussian, Ukrainian)
|
||||
|
||||
# Hebrew
|
||||
|
||||
#05B0; ; HEBREW POINT SHEVA ??? win1255
|
||||
#05B1; ; HEBREW POINT HATAF SEGOL ??? win1255
|
||||
#05B2; ; HEBREW POINT HATAF PATAH ??? win1255
|
||||
#05B3; ; HEBREW POINT HATAF QAMATS ??? win1255
|
||||
#05B4; ; HEBREW POINT HIRIQ ??? win1255
|
||||
#05B5; ; HEBREW POINT TSERE ??? win1255
|
||||
#05B6; ; HEBREW POINT SEGOL ??? win1255
|
||||
#05B7; ; HEBREW POINT PATAH ??? win1255
|
||||
#05B8; ; HEBREW POINT QAMATS ??? win1255
|
||||
#05B9; ; HEBREW POINT HOLAM ??? win1255
|
||||
#05BB; ; HEBREW POINT QUBUTS ??? win1255
|
||||
#05BC; ; HEBREW POINT DAGESH OR MAPIQ ??? win1255
|
||||
#05BD; ; HEBREW POINT METEG ??? win1255
|
||||
#05BE; ; HEBREW PUNCTUATION MAQAF ??? win1255
|
||||
#05BF; ; HEBREW POINT RAFE ??? win1255
|
||||
#05C0; ; HEBREW PUNCTUATION PASEQ ??? win1255
|
||||
#05C1; ; HEBREW POINT SHIN DOT ??? win1255
|
||||
#05C2; ; HEBREW POINT SIN DOT ??? win1255
|
||||
05D0; 0041; HEBREW LETTER ALEF => A
|
||||
05D1; 0042; HEBREW LETTER BET => B
|
||||
05D2; 0047; HEBREW LETTER GIMEL => G
|
||||
05D3; 0044; HEBREW LETTER DALET => D
|
||||
05D4; 0048 0061; HEBREW LETTER HE => Ha
|
||||
05D5; 004F; HEBREW LETTER VAV => O
|
||||
05D6; 005A; HEBREW LETTER ZAYIN => Z
|
||||
05D7; 0048; HEBREW LETTER HET => H
|
||||
05D8; 0054; HEBREW LETTER TET => T
|
||||
05D9; 0049; HEBREW LETTER YOD => I
|
||||
05DA; 004B 0068; HEBREW LETTER FINAL KAF => Kh
|
||||
05DB; 004B 0068; HEBREW LETTER KAF => Kh
|
||||
05DC; 004C; HEBREW LETTER LAMED => L
|
||||
05DD; 004D; HEBREW LETTER FINAL MEM => M
|
||||
05DE; 004D; HEBREW LETTER MEM => M
|
||||
05DF; 004E; HEBREW LETTER FINAL NUN => N
|
||||
05E0; 004E; HEBREW LETTER NUN => N
|
||||
05E1; 0053; HEBREW LETTER SAMEKH => S
|
||||
05E2; 0041; HEBREW LETTER AYIN => A
|
||||
05E3; 0050 0066; HEBREW LETTER FINAL PE => Pf
|
||||
05E4; 0050 0066; HEBREW LETTER PE => Pf
|
||||
05E5; 0054 0073; HEBREW LETTER FINAL TSADI => Ts
|
||||
05E6; 0054 0073; HEBREW LETTER TSADI => Ts
|
||||
05E7; 004B; HEBREW LETTER QOF => K
|
||||
05E8; 0052; HEBREW LETTER RESH => R
|
||||
05E9; 0053 0068; HEBREW LETTER SHIN => Sh
|
||||
05EA; 0054; HEBREW LETTER TAV => T
|
||||
05F0; 0056; HEBREW LIGATURE YIDDISH DOUBLE VAV => V
|
||||
#05F1; ; HEBREW LIGATURE YIDDISH VAV YOD ??? win1255
|
||||
#05F2; ; HEBREW LIGATURE YIDDISH DOUBLE YOD ??? win1255
|
||||
#05F3; ; HEBREW PUNCTUATION GERESH ??? win1255
|
||||
#05F4; ; HEBREW PUNCTUATION GERSHAYIM ??? win1255
|
||||
|
||||
#20AA; ; NEW SHEQEL SIGN ??? win1255
|
||||
|
||||
15100
lib/typo3/unidata/UnicodeData.txt
Normal file
15100
lib/typo3/unidata/UnicodeData.txt
Normal file
File diff suppressed because it is too large
Load diff
Loading…
Add table
Add a link
Reference in a new issue