-# SpecialCasing-5.txt
+# SpecialCasing-6.2.0.txt
+# Date: 2012-05-23, 20:35:15 GMT [MD]
+#
+# Unicode Character Database
+# Copyright (c) 1991-2012 Unicode, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For documentation, see http://www.unicode.org/reports/tr44/
#
# 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
-# UTR #21 Case Mappings, at http://www.unicode.org/unicode/reports/tr21/
+# characters where they are 1-1, and independent of context and language.
+# 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
# ================================================================================
#
# <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.
+# <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:
+# The <condition_list> is optional. Where present, it consists of one or more language IDs
+# 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 cased letter is any character with general category = Ll or Lo or Lt
-# - An ignorable sequence is a sequence of *zero* or more characters from
-# the set {HYPHEN, SOFT HYPHEN, general category = Mn}.
-#
-# 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
+# - Conditions preceded by "Not_" represent the negation of the condition.
+# The condition list is not represented in the UCD as a formal property.
#
-# A context is a locale or one of the following choices:
-# CFINAL: The character is not followed by a sequence consisting of
-# an ignorable sequence and then a cased letter.
-# CINITIAL: The character is not preceded by a sequence consisting of
-# a cased letter and an ignorable sequence.
-# FINAL_SIGMA: CFINAL and NOT_CINITIAL
-# TYPE_i: The character is "i" (0069), "j" (006A),
-# or has a canonical decomposition that begins with an "i" or "j"
-# but has no combining characters above (i.e., i-ogonek (012F),
-# i-tilde-below (1E2D), or i-dot-below (1ECB)).
-# AFTER_i: The last preceding base character was TYPE_i, and
-# no combining character class 230 (above) has intervened.
-# MORE_ABOVE: The character is followed by one or more characters of
-# combining class 230 (ABOVE) in the combining character sequence
+# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
#
-# Other than as used to separate elements, spaces are to be ignored.
+# A context for a character C is defined by Section 3.13 Default Case
+# Operations, of The Unicode Standard, Version 5.0.
+# (This is identical to the context defined by Unicode 4.1.0,
+# as specified in http://www.unicode.org/versions/Unicode4.1.0/)
#
-# Parsers of this file must be prepared to deal future additions to this format:
+# Parsers of this file must be prepared to deal with future additions to this format:
# * Additional contexts
# * Additional fields
# ================================================================================
+# @missing: 0000..10FFFF; <slc>; <stc>; <suc>;
+
# ================================================================================
# Unconditional mappings
# ================================================================================
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
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.
+# 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 file, so are only commented here.
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
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 are also have no corresponding titlecases
+# 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
1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
# ================================================================================
-# Conditional mappings
+# 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
+03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
# Note: the following cases for non-final are already in the UnicodeData file.
# 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
+# 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
+# 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
# Remove DOT ABOVE after "i" with upper or titlecase
-0307; 0307; ; ; lt AFTER_i # COMBINING DOT ABOVE
+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
+# 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
+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
# ================================================================================
# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
# The following rules handle those cases.
-# Remove spurious dot above small i's when lowercasing, if there are no more accents above:
+0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
-0307; ; 0307; 0307; tr AFTER_i NOT_MORE_ABOVE # COMBINING DOT ABOVE
-0307; ; 0307; 0307; az AFTER_i NOT_MORE_ABOVE # COMBINING 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
-# Fix case pairs
+0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
+0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
-0049; 0131; 0049; 0049; tr; # LATIN CAPITAL LETTER I
-0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
+# 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
-0049; 0131; 0049; 0049; az; # LATIN CAPITAL LETTER I
+0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
-# Note: the following cases are already in the UnicodeData file.
+# Note: the following case is already in the UnicodeData file.
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
-# 0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+
+# EOF
+
https://perl5.git.perl.org / perl5.git / blobdiff