diff options
Diffstat (limited to 'lib/unicore/NamedSequences.txt')
-rw-r--r-- | lib/unicore/NamedSequences.txt | 50 |
1 files changed, 30 insertions, 20 deletions
diff --git a/lib/unicore/NamedSequences.txt b/lib/unicore/NamedSequences.txt index e1ae2b740e..87b25cfa15 100644 --- a/lib/unicore/NamedSequences.txt +++ b/lib/unicore/NamedSequences.txt @@ -1,24 +1,32 @@ -# NamedSequences-6.3.0.txt -# Date: 2012-11-14, 21:51:00 GMT [KW] +# NamedSequences-7.0.0.txt +# Date: 2014-01-24, 15:00:00 GMT [KW, LI] # -# Unicode Character Database -# Copyright (c) 1991-2012 Unicode, Inc. +# Unicode Named Character Sequences +# +# This file is a normative contributory data file in the Unicode +# Character Database. +# +# 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/ # # Format: # Name of Sequence; Code Point Sequence for USI # -# Code point sequences in the UCD use spaces as delimiters. -# The corresponding format for a USI in ISO/IEC 10646 uses -# comma delimitation and angle brackets. Thus, a named sequence -# of the form: +# Code point sequences in the Unicode Character Database +# use spaces as delimiters. The corresponding format for a +# UCS Sequence Identifier (USI) in ISO/IEC 10646 uses +# comma delimitation and angle brackets. Thus, a Unicode +# named character sequence of the form: # # EXAMPLE NAME;1000 1001 1002 # -# in this data file, would correspond to a 10646 USI as follows: +# in this data file, would correspond to an ISO/IEC 10646 USI +# as follows: +# +# <1000, 1001, 1002> # -# <1000, 1001, 1002> +# For more information, see UAX #34: Unicode Named Character +# Sequences, at http://www.unicode.org/unicode/reports/tr34/ # # Note: The order of entries in this file is not significant. # However, entries are generally in script order corresponding @@ -54,7 +62,8 @@ LATIN SMALL LETTER S WITH VERTICAL LINE BELOW;0073 0329 LATIN CAPITAL LETTER U WITH MACRON AND GRAVE;016A 0300 LATIN SMALL LETTER U WITH MACRON AND GRAVE;016B 0300 -# Additions for Lithuanian. Provisional 2006-05-18, Approved 2007-10-19 +# Additions for Lithuanian. +# Provisional 2006-05-18, Approved 2007-10-19 LATIN CAPITAL LETTER A WITH OGONEK AND ACUTE;0104 0301 LATIN SMALL LETTER A WITH OGONEK AND ACUTE;0105 0301 @@ -92,7 +101,7 @@ LATIN CAPITAL LETTER U WITH MACRON AND TILDE;016A 0303 LATIN SMALL LETTER U WITH MACRON AND TILDE;016B 0303 # Entries for JIS X 0213 compatibility mapping. -# Provisional: 2008-11-07, Approved 2010-05-14 +# Provisional 2008-11-07, Approved 2010-05-14 LATIN SMALL LETTER AE WITH GRAVE;00E6 0300 LATIN SMALL LETTER OPEN O WITH GRAVE;0254 0300 @@ -105,7 +114,7 @@ LATIN SMALL LETTER HOOKED SCHWA WITH GRAVE;025A 0300 LATIN SMALL LETTER HOOKED SCHWA WITH ACUTE;025A 0301 # Entries for Uyghur and Chagatai. -# Provisional: N/A, Approved: 2012-11-08 +# Provisional N/A, Approved 2012-11-08 ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH ALEF;0626 0627 ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH WAW;0626 0648 @@ -118,16 +127,17 @@ ARABIC SEQUENCE YEH WITH HAMZA ABOVE WITH AE;0626 06D5 ARABIC SEQUENCE NOON WITH KEHEH;0646 06A9 # Entry for a Bangla entity. -# Provisional: 2009-08-10, Approved 2010-05-14 +# Provisional 2009-08-10, Approved 2010-05-14 # # Note that this same sequence is also used for the ASSAMESE LETTER KSSA. BENGALI LETTER KHINYA;0995 09CD 09B7 -# Additions for Tamil. Provisional 2008-02-08, Approved 2009-08-14 +# Additions for Tamil. +# Provisional 2008-02-08, Approved 2009-08-14 # -# A visual display of the Tamil named sequences is available -# in the documentation for the Unicode Standard. See Section 9.6, Tamil in +# A visual display of the Tamil named character sequences is available +# in the documentation for the Unicode Standard. See Section 12.6, Tamil in # http://www.unicode.org/versions/latest/ TAMIL CONSONANT K; 0B95 0BCD @@ -446,7 +456,7 @@ TAMIL SYLLABLE KSSAU; 0B95 0BCD 0BB7 0BCC TAMIL SYLLABLE SHRII; 0BB6 0BCD 0BB0 0BC0 -# Sinhala medial consonants and "reph" form +# Sinhala medial consonants and "reph" form. # Provisional 2010-05-13, Approved 2011-08-05 SINHALA CONSONANT SIGN YANSAYA;0DCA 200D 0DBA @@ -497,7 +507,7 @@ KHMER VOWEL SIGN OM;17BB 17C6 KHMER VOWEL SIGN AAM;17B6 17C6 # Entries for JIS X 0213 compatibility mapping. -# Provisional: 2008-11-07, Approved 2010-05-14 +# Provisional 2008-11-07, Approved 2010-05-14 HIRAGANA LETTER BIDAKUON NGA;304B 309A HIRAGANA LETTER BIDAKUON NGI;304D 309A |