-# SpecialCasing-5.1.0.txt
-# Date: 2008-03-03, 21:58:10 GMT [MD]
+# SpecialCasing-12.1.0.txt
+# Date: 2019-03-10, 10:53:28 GMT
+# © 2019 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
-# Copyright (c) 1991-2008 Unicode, Inc.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
-# For documentation, see UCD.html
+# For documentation, see http://www.unicode.org/reports/tr44/
#
-# Special Casing Properties
+# Special Casing
#
-# 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 independent of context and language.
-# For more information, see the discussion of Case Mappings in the Unicode Standard.
+# 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.
# ================================================================================
# The entries in this file are in the following machine-readable format:
#
-# <code>; <lower> ; <title> ; <upper> ; (<condition_list> ;)? # <comment>
+# <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.
+# <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 contexts, separated by spaces. In these conditions:
+# 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 context is always the context of the characters in the original string,
+# - 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.
#
# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
#
-# 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/)
+# 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
# ================================================================================
-# @missing 0000..10FFFF; <slc>; <stc>; <suc>
+
# ================================================================================
# Unconditional mappings
# ================================================================================
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.
+# The following cases are already in the UnicodeData.txt file, so are only commented here.
-# 0345; 0345; 0345; 0399; # COMBINING GREEK YPOGEGRAMMENI
+# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
# have special uppercases.
# ================================================================================
# Conditional Mappings
-# The remainder of this file provides conditional casing data used to produce
+# The remainder of this file provides conditional casing data used to produce
# full case mappings.
# ================================================================================
# Language-Insensitive Mappings
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 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
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.
+# Note: the following case is already in the UnicodeData.txt file.
# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
projects / apple / icu.git / blobdiff