Index: source/data/unidata/SpecialCasing.txt |
diff --git a/source/data/unidata/SpecialCasing.txt b/source/data/unidata/SpecialCasing.txt |
index 016a756eb07b88c4754e675b572bf813c0e38510..43645bd2d100ec31d01b3b468f6da694c5001f9b 100644 |
--- a/source/data/unidata/SpecialCasing.txt |
+++ b/source/data/unidata/SpecialCasing.txt |
@@ -1,18 +1,25 @@ |
-# SpecialCasing-6.3.0.txt |
-# Date: 2013-05-08, 13:54:51 GMT [MD] |
+# SpecialCasing-7.0.0.txt |
+# Date: 2014-03-18, 07:18:02 GMT [MD] |
# |
# Unicode Character Database |
-# Copyright (c) 1991-2013 Unicode, Inc. |
+# Copyright (c) 1991-2014 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 |
+# 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. |
@@ -21,16 +28,17 @@ |
# ================================================================================ |
# 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. |
@@ -38,18 +46,14 @@ |
# |
# 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 |
-# Algorithms, of The Unicode Standard, Version 6.3. |
-# (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 |
# ================================================================================ |
@@ -114,7 +118,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH |
# 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 |
@@ -205,7 +209,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH |
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 |
@@ -268,7 +272,7 @@ FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH |
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 |