Chromium Code Reviews Chromium Code Reviews
Issue 598383002:
Make all the single byte encodings compliant to the encoding spec. (Closed)
Base URL: svn://svn.chromium.org/chrome/trunk/deps/third_party/icu52/| Index: source/data/mappings/convrtrs.txt |
| =================================================================== |
| --- source/data/mappings/convrtrs.txt (revision 292131) |
| +++ source/data/mappings/convrtrs.txt (working copy) |
| @@ -1,6 +1,6 @@ |
| # ****************************************************************************** |
| # * |
| -# * Copyright (C) 1995-2013, International Business Machines |
| +# * Copyright (C) 1995-2014, International Business Machines |
| # * Corporation and others. All Rights Reserved. |
| # * |
| # ****************************************************************************** |
| @@ -116,479 +116,268 @@ |
| # |
| # The general ordering is from specific and frequently used to more general |
| # or rarely used at the bottom. |
| -{ UTR22 # Name format specified by http://www.unicode.org/unicode/reports/tr22/ |
| - # ICU # Can also use ICU_FEATURE |
| - IBM # The IBM CCSID number is specified by ibm-* |
| - WINDOWS # The Microsoft code page identifier number is specified by windows-*. The rest are recognized IE names. |
| - JAVA # Source: Sun JDK. Alias name case is ignored, but dashes are not ignored. |
| - # GLIBC |
| - # AIX |
| - # DB2 |
| - # SOLARIS |
| - # APPLE |
| - # HPUX |
| +{ |
| + UTR22 # # Name format specified by http://www.unicode.org/unicode/reports/tr22/ |
|
jsbell
2014/10/04 00:15:26
Nit: double # ?
jungshik at Google
2014/10/04 09:32:40
Thanks. Will fix
|
| + HTML # WHATWG's encoding spec |
|
jsbell
2014/10/04 00:15:26
Include URL?
jungshik at Google
2014/10/04 09:32:40
Will add.
|
| IANA # Source: http://www.iana.org/assignments/character-sets |
| MIME # Source: http://www.iana.org/assignments/character-sets |
|
jsbell
2014/10/07 17:13:21
Do we reference the different standards tags from
|
| - # MSIE # MSIE is Internet Explorer, which can be different from Windows (From the IMultiLanguage COM interface) |
| - # ZOS_USS # z/OS (os/390) Unix System Services (USS), which has NL<->LF swapping. They have the same format as the IBM tag. |
| } |
| +UTF-8 { MIME* HTML* } |
| + unicode-1-1-utf-8 |
| + utf8 |
| +utf-16be { MIME* HTML* } |
| -# Fully algorithmic converters |
| +utf-16le { MIME* HTML* } |
| + utf-16 |
| -UTF-8 { IANA* MIME* JAVA* WINDOWS } |
| - ibm-1208 { IBM* } # UTF-8 with IBM PUA |
| - ibm-1209 { IBM } # UTF-8 |
| - ibm-5304 { IBM } # Unicode 2.0, UTF-8 with IBM PUA |
| - ibm-5305 { IBM } # Unicode 2.0, UTF-8 |
| - ibm-13496 { IBM } # Unicode 3.0, UTF-8 with IBM PUA |
| - ibm-13497 { IBM } # Unicode 3.0, UTF-8 |
| - ibm-17592 { IBM } # Unicode 4.0, UTF-8 with IBM PUA |
| - ibm-17593 { IBM } # Unicode 4.0, UTF-8 |
| - windows-65001 { WINDOWS* } |
| - cp1208 |
| - x-UTF_8J |
| - unicode-1-1-utf-8 |
| - unicode-2-0-utf-8 |
| - |
| -# The ICU 2.2 UTF-16/32 converters detect and write a BOM. |
| -UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA } |
| - ibm-1204 { IBM* } # UTF-16 with IBM PUA and BOM sensitive |
| - ibm-1205 { IBM } # UTF-16 BOM sensitive |
| - unicode |
| - csUnicode |
| - ucs-2 |
| -# The following Unicode CCSIDs (IBM) are not valid in ICU because they are |
| -# considered pure DBCS (exactly 2 bytes) of Unicode, |
| -# and they are a subset of Unicode. ICU does not support their encoding structures. |
| -# 1400 1401 1402 1410 1414 1415 1446 1447 1448 1449 64770 64771 65520 5496 5497 5498 9592 13688 |
| -UTF-16BE { IANA* MIME* JAVA* } x-utf-16be { JAVA } |
| - UnicodeBigUnmarked { JAVA } # java.io name |
| - ibm-1200 { IBM* } # UTF-16 BE with IBM PUA |
| - ibm-1201 { IBM } # UTF-16 BE |
| - ibm-13488 { IBM } # Unicode 2.0, UTF-16 BE with IBM PUA |
| - ibm-13489 { IBM } # Unicode 2.0, UTF-16 BE |
| - ibm-17584 { IBM } # Unicode 3.0, UTF-16 BE with IBM PUA |
| - ibm-17585 { IBM } # Unicode 3.0, UTF-16 BE |
| - ibm-21680 { IBM } # Unicode 4.0, UTF-16 BE with IBM PUA |
| - ibm-21681 { IBM } # Unicode 4.0, UTF-16 BE |
| - ibm-25776 { IBM } # Unicode 4.1, UTF-16 BE with IBM PUA |
| - ibm-25777 { IBM } # Unicode 4.1, UTF-16 BE |
| - ibm-29872 { IBM } # Unicode 5.0, UTF-16 BE with IBM PUA |
| - ibm-29873 { IBM } # Unicode 5.0, UTF-16 BE |
| - ibm-61955 { IBM } # UTF-16BE with Gaidai University (Japan) PUA |
| - ibm-61956 { IBM } # UTF-16BE with Microsoft HKSCS-Big 5 PUA |
| - windows-1201 { WINDOWS* } |
| - cp1200 |
| - cp1201 |
| - UTF16_BigEndian |
| - # ibm-5297 { IBM } # Unicode 2.0, UTF-16 (BE) (reserved, never used) |
| - # iso-10646-ucs-2 { JAVA } # This is ambiguous |
| - # ibm-61952 is not a valid CCSID because it's Unicode 1.1 |
| - # ibm-61953 is not a valid CCSID because it's Unicode 1.0 |
| -UTF-16LE { IANA* MIME* JAVA* } x-utf-16le { JAVA } |
| - UnicodeLittleUnmarked { JAVA } # java.io name |
| - ibm-1202 { IBM* } # UTF-16 LE with IBM PUA |
| - ibm-1203 { IBM } # UTF-16 LE |
| - ibm-13490 { IBM } # Unicode 2.0, UTF-16 LE with IBM PUA |
| - ibm-13491 { IBM } # Unicode 2.0, UTF-16 LE |
| - ibm-17586 { IBM } # Unicode 3.0, UTF-16 LE with IBM PUA |
| - ibm-17587 { IBM } # Unicode 3.0, UTF-16 LE |
| - ibm-21682 { IBM } # Unicode 4.0, UTF-16 LE with IBM PUA |
| - ibm-21683 { IBM } # Unicode 4.0, UTF-16 LE |
| - ibm-25778 { IBM } # Unicode 4.1, UTF-16 LE with IBM PUA |
| - ibm-25779 { IBM } # Unicode 4.1, UTF-16 LE |
| - ibm-29874 { IBM } # Unicode 5.0, UTF-16 LE with IBM PUA |
| - ibm-29875 { IBM } # Unicode 5.0, UTF-16 LE |
| - UTF16_LittleEndian |
| - windows-1200 { WINDOWS* } |
| - |
| +# Keep UTF-32 entries for now until we sort out Blink's behavior when |
| +# UTF-32 is dropped. |
| UTF-32 { IANA* MIME* } ISO-10646-UCS-4 { IANA } |
| - ibm-1236 { IBM* } # UTF-32 with IBM PUA and BOM sensitive |
| - ibm-1237 { IBM } # UTF-32 BOM sensitive |
| csUCS4 |
| ucs-4 |
| UTF-32BE { IANA* } UTF32_BigEndian |
| - ibm-1232 { IBM* } # UTF-32 BE with IBM PUA |
| - ibm-1233 { IBM } # UTF-32 BE |
| - ibm-9424 { IBM } # Unicode 4.1, UTF-32 BE with IBM PUA |
| UTF-32LE { IANA* } UTF32_LittleEndian |
| - ibm-1234 { IBM* } # UTF-32 LE, with IBM PUA |
| - ibm-1235 { IBM } # UTF-32 LE |
| -# ICU-specific names for special uses |
| -UTF16_PlatformEndian |
| -UTF16_OppositeEndian |
| +ibm866-html |
|
jsbell
2014/10/04 00:15:26
Does the first (non-indented) entry get treated as
jungshik at Google
2014/10/04 09:32:40
Yeah, it does. It's also used to refer to a ucm fi
jsbell
2014/10/07 17:13:20
We could reject the "-html" in Blink (can land lat
|
| + IBM866 { MIME* HTML* } |
| + 866 |
| + cp866 |
| + csibm866 |
| -UTF32_PlatformEndian |
| -UTF32_OppositeEndian |
| +iso-8859-2-html |
| + ISO-8859-2 { MIME* HTML* } |
| + csisolatin2 |
| + iso-ir-101 |
| + iso8859-2 |
| + iso88592 |
| + iso_8859-2 |
| + iso_8859-2:1987 |
| + l2 |
| + latin2 |
| +iso-8859-3-html |
| + ISO-8859-3 { MIME* HTML* } |
| + csisolatin3 |
| + iso-ir-109 |
| + iso8859-3 |
| + iso88593 |
| + iso_8859-3 |
| + iso_8859-3:1988 |
| + l3 |
| + latin3 |
| -# Java-specific, non-Unicode-standard UTF-16 variants. |
| -# These are in the Java "Basic Encoding Set (contained in lib/rt.jar)". |
| -# See the "Supported Encodings" at |
| -# http://java.sun.com/javase/6/docs/technotes/guides/intl/encoding.doc.html |
| -# or a newer version of this document. |
| -# |
| -# Aliases marked with { JAVA* } are canonical names for java.io and java.lang APIs. |
| -# Aliases marked with { JAVA } are canonical names for the java.nio API. |
| -# |
| -# "BOM" means the Unicode Byte Order Mark, which is the encoding-scheme-specific |
| -# byte sequence for U+FEFF. |
| -# "Reverse BOM" means the BOM for the sibling encoding scheme with the |
| -# opposite endianness. (LE<->BE) |
| +iso-8859-4-html |
| + ISO-8859-4 { MIME* HTML* } |
| + csisolatin4 |
| + iso-ir-110 |
| + iso8859-4 |
| + iso88594 |
| + iso_8859-4 |
| + iso_8859-4:1988 |
| + l4 |
| + latin4 |
| -# "Sixteen-bit Unicode (or UCS) Transformation Format, big-endian byte order, |
| -# with byte-order mark" |
| -# |
| -# From Unicode: Writes BOM. |
| -# To Unicode: Detects and consumes BOM. |
| -# If there is a "reverse BOM", Java throws |
| -# MalformedInputException: Incorrect byte-order mark. |
| -# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value |
| -# and a UCNV_ILLEGAL UConverterCallbackReason. |
| -UTF-16BE,version=1 UnicodeBig { JAVA* } |
| +iso-8859-5-html |
| + ISO-8859-5 { MIME* HTML* } |
| + csisolatincyrillic |
| + cyrillic |
| + iso-ir-144 |
| + iso8859-5 |
| + iso88595 |
| + iso_8859-5 |
| + iso_8859-5:1988 |
| -# "Sixteen-bit Unicode (or UCS) Transformation Format, little-endian byte order, |
| -# with byte-order mark" |
| -# |
| -# From Unicode: Writes BOM. |
| -# To Unicode: Detects and consumes BOM. |
| -# If there is a "reverse BOM", Java throws |
| -# MalformedInputException: Incorrect byte-order mark. |
| -# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value |
| -# and a UCNV_ILLEGAL UConverterCallbackReason. |
| -UTF-16LE,version=1 UnicodeLittle { JAVA* } x-UTF-16LE-BOM { JAVA } |
| +iso-8859-6-html |
| + ISO-8859-6 { MIME* HTML* } |
| + arabic |
| + asmo-708 |
| + csiso88596e |
| + csiso88596i |
| + csisolatinarabic |
| + ecma-114 |
| + iso-8859-6-e |
| + iso-8859-6-i |
| + iso-ir-127 |
| + iso8859-6 |
| + iso88596 |
| + iso_8859-6 |
| + iso_8859-6:1987 |
| -# This one is not mentioned on the "Supported Encodings" page |
| -# but is available in Java. |
| -# In Java, this is called "Unicode" but we cannot give it that alias |
| -# because the standard UTF-16 converter already has a "unicode" alias. |
| -# |
| -# From Unicode: Writes BOM. |
| -# To Unicode: Detects and consumes BOM. |
| -# If there is no BOM, rather than defaulting to BE, Java throws |
| -# MalformedInputException: Missing byte-order mark. |
| -# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value |
| -# and a UCNV_ILLEGAL UConverterCallbackReason. |
| -UTF-16,version=1 |
| +iso-8859-7-html |
| + ISO-8859-7 { MIME* HTML* } |
| + csisolatingreek |
| + ecma-118 |
| + elot_928 |
| + greek |
| + greek8 |
| + iso-ir-126 |
| + iso8859-7 |
| + iso88597 |
| + iso_8859-7 |
| + iso_8859-7:1987 |
| + sun_eu_greek |
| -# This is the same as standard UTF-16 but always writes a big-endian byte stream, |
| -# regardless of the platform endianness, as expected by the Java compatibility tests. |
| -# See the java.nio.charset.Charset API documentation at |
| -# http://java.sun.com/javase/6/docs/api/java/nio/charset/Charset.html |
| -# or a newer version of this document. |
| -# |
| -# From Unicode: Write BE BOM and BE bytes |
| -# To Unicode: Detects and consumes BOM. Defaults to BE. |
| -UTF-16,version=2 |
| +iso-8859-8-html |
| + ISO-8859-8 { MIME* HTML* } |
| + csiso88598e { MIME } |
| + csisolatinhebrew |
| + hebrew |
| + ISO-8859-8-E |
| + ISO-8859-8-I |
| + iso-ir-138 |
| + iso8859-8 |
| + iso88598 |
| + iso_8859-8 |
| + iso_8859-8:1988 |
| + # adding this one leads to a failure in encoding-labels.html |
| +# csiso88598i |
| -# Note: ICU does not currently support Java-specific, non-Unicode-standard UTF-32 variants. |
| -# Presumably, these behave analogously to the UTF-16 variants with similar names. |
| -# UTF_32BE_BOM x-UTF-32BE-BOM |
| -# UTF_32LE_BOM x-UTF-32LE-BOM |
| -# End of Java-specific, non-Unicode-standard UTF variants. |
| +# This alias has to be dealt with by TextCodecICU unless |
| +# multiple encodings can share a single mapping table. |
| +#ISO-8859-8-I { MIME* HTML* } |
| +# csiso88598i |
| +# logical |
| +iso-8859-10-html |
| + ISO-8859-10 { MIME* HTML* } |
| + csisolatin6 |
| + iso-ir-157 |
| + iso8859-10 |
| + iso885910 |
| + l6 |
| + latin6 |
| -# Chrome: Remove all the entries for UTF-7, SCSU, BOCU, CESU-8. |
| +iso-8859-13-html |
| + ISO-8859-13 { MIME* HTML* } |
| + iso8859-13 |
| + iso885913 |
| -# Standard iso-8859-1, which does not have the Euro update. |
| -# See iso-8859-15 (latin9) for the Euro update |
| -ISO-8859-1 { MIME* IANA JAVA* } |
| - ibm-819 { IBM* JAVA } # This is not truely ibm-819 because it's missing the fallbacks. |
| - IBM819 { IANA } |
| - cp819 { IANA JAVA } |
| - latin1 { IANA JAVA } |
| - 8859_1 { JAVA } |
| - csISOLatin1 { IANA JAVA } |
| - iso-ir-100 { IANA JAVA } |
| - ISO_8859-1:1987 { IANA* JAVA } |
| - l1 { IANA JAVA } |
| - 819 { JAVA } |
| - # windows-28591 { WINDOWS* } # This has odd behavior because it has the Euro update, which isn't correct. |
| - # LATIN_1 # Old ICU name |
| - # ANSI_X3.110-1983 # This is for a different IANA alias. This isn't iso-8859-1. |
| +iso-8859-14-html |
| + ISO-8859-14 { MIME* HTML* } |
| + iso8859-14 |
| + iso885914 |
| -US-ASCII { MIME* IANA JAVA WINDOWS } |
| - ASCII { JAVA* IANA WINDOWS } |
| - ANSI_X3.4-1968 { IANA* WINDOWS } |
| - ANSI_X3.4-1986 { IANA WINDOWS } |
| - ISO_646.irv:1991 { IANA WINDOWS } |
| - iso_646.irv:1983 { JAVA } |
| - ISO646-US { JAVA IANA WINDOWS } |
| - us { IANA } |
| - csASCII { IANA WINDOWS } |
| - iso-ir-6 { IANA } |
| - cp367 { IANA WINDOWS } |
| - ascii7 { JAVA } |
| - 646 { JAVA } |
| - windows-20127 { WINDOWS* } |
| - ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks. |
| +iso-8859-15-html |
| + ISO-8859-15 { MIME* HTML* } |
| + csisolatin9 |
| + iso8859-15 |
| + iso885915 |
| + iso_8859-15 |
| + l9 |
| -# GB 18030 is partly algorithmic, using the MBCS converter |
| -# Chrome: HTML5 GBK an alias for GB18030 |
| -# TODO(jshin): Decide if Chrome should follow spec. crbug.com/339862 |
| -gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } gb18030 { MIME* } |
| +iso-8859-16-html |
| + ISO-8859-16 { MIME* HTML* } |
| -# Table-based interchange codepages |
| +koi8-r-html |
| + KOI8-R { MIME* HTML* } |
| + cskoi8r |
| + koi |
| + koi8 |
| + koi8_r |
| -# Central Europe |
| -ibm-912_P100-1995 { UTR22* } |
| - ibm-912 { IBM* JAVA } |
| - ISO-8859-2 { MIME* IANA JAVA* WINDOWS } |
| - ISO_8859-2:1987 { IANA* WINDOWS JAVA } |
| - latin2 { IANA WINDOWS JAVA } |
| - csISOLatin2 { IANA WINDOWS JAVA } |
| - iso-ir-101 { IANA WINDOWS JAVA } |
| - l2 { IANA WINDOWS JAVA } |
| - 8859_2 { JAVA } |
| - cp912 { JAVA } |
| - 912 { JAVA } |
| - windows-28592 { WINDOWS* } |
| +koi8-u-html |
| + KOI8-U { MIME* HTML* } |
| -# Maltese Esperanto |
| -ibm-913_P100-2000 { UTR22* } |
| - ibm-913 { IBM* JAVA } |
| - ISO-8859-3 { MIME* IANA WINDOWS JAVA* } |
| - ISO_8859-3:1988 { IANA* WINDOWS JAVA } |
| - latin3 { IANA JAVA WINDOWS } |
| - csISOLatin3 { IANA WINDOWS } |
| - iso-ir-109 { IANA WINDOWS JAVA } |
| - l3 { IANA WINDOWS JAVA } |
| - 8859_3 { JAVA } |
| - cp913 { JAVA } |
| - 913 { JAVA } |
| - windows-28593 { WINDOWS* } |
| +macintosh-html |
| + macintosh { MIME* HTML* } |
| + csmacintosh |
| + mac |
| + x-mac-roman |
| -# Baltic |
| -ibm-914_P100-1995 { UTR22* } |
| - ibm-914 { IBM* JAVA } |
| - ISO-8859-4 { MIME* IANA WINDOWS JAVA* } |
| - latin4 { IANA WINDOWS JAVA } |
| - csISOLatin4 { IANA WINDOWS JAVA } |
| - iso-ir-110 { IANA WINDOWS JAVA } |
| - ISO_8859-4:1988 { IANA* WINDOWS JAVA } |
| - l4 { IANA WINDOWS JAVA } |
| - 8859_4 { JAVA } |
| - cp914 { JAVA } |
| - 914 { JAVA } |
| - windows-28594 { WINDOWS* } |
| +windows-874-html |
| + windows-874 { MIME* HTML* } |
| + dos-874 |
| + iso-8859-11 |
| + iso8859-11 |
| + iso885911 |
| + tis-620 |
| -# Cyrillic |
| -ibm-915_P100-1995 { UTR22* } |
| - ibm-915 { IBM* JAVA } |
| - ISO-8859-5 { MIME* IANA WINDOWS JAVA* } |
| - cyrillic { IANA WINDOWS JAVA } |
| - csISOLatinCyrillic { IANA WINDOWS JAVA } |
| - iso-ir-144 { IANA WINDOWS JAVA } |
| - ISO_8859-5:1988 { IANA* WINDOWS JAVA } |
| - 8859_5 { JAVA } |
| - cp915 { JAVA } |
| - 915 { JAVA } |
| - windows-28595 { WINDOWS* } |
| +windows-1250-html |
| + windows-1250 { MIME* HTML* } |
| + cp1250 |
| + x-cp1250 |
| -# Arabic |
| -# ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently |
| -# From a narrow mapping point of view, there is no difference. |
| -# -E means explicit. -I means implicit. |
| -# -E requires the client to handle the ISO 6429 bidirectional controls |
| -ibm-1089_P100-1995 { UTR22* } |
| - ibm-1089 { IBM* JAVA } |
| - ISO-8859-6 { MIME* IANA WINDOWS JAVA* } |
| - arabic { IANA WINDOWS JAVA } |
| - csISOLatinArabic { IANA WINDOWS JAVA } |
| - iso-ir-127 { IANA WINDOWS JAVA } |
| - ISO_8859-6:1987 { IANA* WINDOWS JAVA } |
| - ECMA-114 { IANA JAVA } |
| - ASMO-708 { IANA JAVA } |
| - 8859_6 { JAVA } |
| - cp1089 { JAVA } |
| - 1089 { JAVA } |
| - windows-28596 { WINDOWS* } |
| - ISO-8859-6-I { IANA MIME } # IANA considers this alias different and BiDi needs to be applied. |
| - ISO-8859-6-E { IANA MIME } # IANA considers this alias different and BiDi needs to be applied. |
| - x-ISO-8859-6S { JAVA } |
| +windows-1251-html |
| + windows-1251 { MIME* HTML* } |
| + cp1251 |
| + x-cp1251 |
| -# ISO Greek (with euro update). This is really ISO_8859-7:2003 |
| -ibm-9005_X110-2007 { UTR22* } |
| - ibm-9005 { IBM* } |
| - ISO-8859-7 { MIME* IANA JAVA* WINDOWS } |
| - 8859_7 { JAVA } |
| - greek { IANA JAVA WINDOWS } |
| - greek8 { IANA JAVA WINDOWS } |
| - ELOT_928 { IANA JAVA WINDOWS } |
| - ECMA-118 { IANA JAVA WINDOWS } |
| - csISOLatinGreek { IANA JAVA WINDOWS } |
| - iso-ir-126 { IANA JAVA WINDOWS } |
| - ISO_8859-7:1987 { IANA* JAVA WINDOWS } |
| - windows-28597 { WINDOWS* } |
| - sun_eu_greek # For Solaris |
| +windows-1252-html |
| + windows-1252 { MIME* HTML* } |
| + ansi_x3.4-1968 |
| + ascii |
| + cp1252 |
| + cp819 |
| + csisolatin1 |
| + ibm819 |
| + iso-8859-1 |
| + iso-ir-100 |
| + iso8859-1 |
| + iso88591 |
| + iso_8859-1 |
| + iso_8859-1:1987 |
| + l1 |
| + latin1 |
| + us-ascii |
| + x-cp1252 |
| -# hebrew |
| -# ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently |
| -# From a narrow mapping point of view, there is no difference. |
| -# -E means explicit. -I means implicit. |
| -# -E requires the client to handle the ISO 6429 bidirectional controls |
| -# This matches the official mapping on unicode.org |
| -ibm-5012_P100-1999 { UTR22* } |
| - ibm-5012 { IBM* } |
| - ISO-8859-8 { MIME* IANA WINDOWS JAVA* } |
| - hebrew { IANA WINDOWS JAVA } |
| - csISOLatinHebrew { IANA WINDOWS JAVA } |
| - iso-ir-138 { IANA WINDOWS JAVA } |
| - ISO_8859-8:1988 { IANA* WINDOWS JAVA } |
| - ISO-8859-8-I { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied. |
| - ISO-8859-8-E { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied. |
| - 8859_8 { JAVA } |
| - windows-28598 { WINDOWS* } # Hebrew (ISO-Visual). A hybrid between ibm-5012 and ibm-916 with extra PUA mappings. |
| - hebrew8 # Reflect HP-UX code page update |
| +windows-1253-html |
| + windows-1253 { MIME* HTML* } |
| + cp1253 |
| + x-cp1253 |
| -# Turkish |
| -# Chrome: ISO-8859-9 and its aliases are moved to windows-1254 per |
| -# HTML5. |
| -ibm-920_P100-1995 { UTR22* } |
| - ibm-920 { IBM* JAVA } |
| - ISO-8859-9 |
| - latin5 |
| - csISOLatin5 |
| - iso-ir-148 |
| - ISO_8859-9:1989 |
| - l5 |
| - cp920 { JAVA } |
| - 920 { JAVA } |
| - windows-28599 { WINDOWS* } |
| - ECMA-128 # IANA doesn't have this alias 6/24/2002 |
| - turkish8 # Reflect HP-UX codepage update 8/1/2008 |
| - turkish # Reflect HP-UX codepage update 8/1/2008 |
| +windows-1254-html |
| + windows-1254 { MIME* HTML* } |
| + cp1254 |
| + csisolatin5 |
| + iso-8859-9 |
| + iso-ir-148 |
| + iso8859-9 |
| + iso88599 |
| + iso_8859-9 |
| + iso_8859-9:1989 |
| + l5 |
| + latin5 |
| + x-cp1254 |
| -# Nordic languages |
| -iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* } |
| - iso-ir-157 { IANA } |
| - l6 { IANA } |
| - ISO_8859-10:1992 { IANA } |
| - csISOLatin6 { IANA } |
| - latin6 { IANA } |
| +windows-1255-html |
| + windows-1255 { MIME* HTML* } |
| + cp1255 |
| + x-cp1255 |
| -# Thai |
| -# Be warned. There several iso-8859-11 codepage variants, and they are all incompatible. |
| -# ISO-8859-11 is a superset of TIS-620. The difference is that ISO-8859-11 contains the C1 control codes. |
| -iso-8859_11-2001 { UTR22* } ISO-8859-11 |
| - thai8 # HP-UX alias. HP-UX says TIS-620, but it's closer to ISO-8859-11. |
| - x-iso-8859-11 { JAVA* } |
| +windows-1256-html |
| + windows-1256 { MIME* HTML* } |
| + cp1256 |
| + x-cp1256 |
| -# iso-8859-13, PC Baltic (w/o euro update) |
| -ibm-921_P100-1995 { UTR22* } |
| - ibm-921 { IBM* } |
| - ISO-8859-13 { IANA* MIME* JAVA* } |
| - 8859_13 { JAVA } |
| - windows-28603 { WINDOWS* } |
| - cp921 |
| - 921 |
| - x-IBM921 { JAVA } |
| +windows-1257-html |
| + windows-1257 { MIME* HTML* } |
| + cp1257 |
| + x-cp1257 |
| -# Celtic |
| -iso-8859_14-1998 { UTR22* } ISO-8859-14 { IANA* } |
| - iso-ir-199 { IANA } |
| - ISO_8859-14:1998 { IANA } |
| - latin8 { IANA } |
| - iso-celtic { IANA } |
| - l8 { IANA } |
| +windows-1258-html |
| + windows-1258 { MIME* HTML* } |
| + cp1258 |
| + x-cp1258 |
| -# Latin 9 |
| -ibm-923_P100-1998 { UTR22* } |
| - ibm-923 { IBM* JAVA } |
| - ISO-8859-15 { IANA* MIME* WINDOWS JAVA* } |
| - Latin-9 { IANA WINDOWS } |
| - l9 { WINDOWS } |
| - 8859_15 { JAVA } |
| - latin0 { JAVA } |
| - csisolatin0 { JAVA } |
| - csisolatin9 { JAVA } |
| - iso8859_15_fdis { JAVA } |
| - cp923 { JAVA } |
| - 923 { JAVA } |
| - windows-28605 { WINDOWS* } |
| +x-mac-cyrillic-html |
| + x-mac-cyrillic { MIME* HTML* } |
| + x-mac-ukrainian |
| -# CJK encodings |
| - |
| -# Chrome: Instead of ibm-943_P15A-2003, we use what's specified in the WHATWG |
| -# encoding standard (HTML5) for Shift_JIS. Keep all the aliases (even though |
| -not all of them not required by the encoding spec) for now. |
| - |
| -shift_jis-html |
| - ibm-943 # Leave untagged because this isn't the default |
| - Shift_JIS { IANA* MIME* WINDOWS JAVA } |
| - MS_Kanji { IANA WINDOWS JAVA } |
| - csShiftJIS { IANA WINDOWS JAVA } |
| - windows-31j { IANA JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13) |
| - csWindows31J { IANA WINDOWS JAVA } # A further extension of Shift_JIS to include NEC special characters (Row 13) |
| - x-sjis { WINDOWS JAVA } |
| - x-ms-cp932 { WINDOWS } |
| - cp932 { WINDOWS } |
| - windows-932 { WINDOWS* } |
| - cp943c { JAVA* } # This is slightly different, but the backslash mapping is the same. |
| - IBM-943C #{ AIX* } # Add this tag once AIX aliases becomes available |
| - ms932 |
| - pck # Probably SOLARIS |
| - sjis # This might be for ibm-1351 |
| - ibm-943_VSUB_VPUA |
| - x-MS932_0213 { JAVA } |
| - x-JISAutoDetect { JAVA } |
| - |
| -# Chrome: Instead of ibm-33722_P*, we use what's specified in the WHATWG |
| -# encoding standard (HTML5). All the |
| -# 3-byte seqeunces in the normative EUC-JP are now decode-only. |
| -euc-jp-html |
| - EUC-JP { MIME* IANA JAVA* WINDOWS*} |
| - Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS } |
| - csEUCPkdFmtJapanese { IANA JAVA WINDOWS } |
| - windows-51932 { WINDOWS } |
| - X-EUC-JP { MIME JAVA WINDOWS } # Japan EUC. x-euc-jp is a MIME name |
| - eucjis {JAVA} |
| - ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged. |
| - |
| - |
| -windows-950-2000 { UTR22* } |
| - Big5 { IANA* MIME* JAVA* WINDOWS } |
| - csBig5 { IANA WINDOWS } |
| - windows-950 { WINDOWS* } |
| - x-windows-950 { JAVA } |
| - x-big5 |
| - ms950 |
| -# Chrome: HTML5 has big5-hkscs as an alias for big5 |
| -# TODO(jshin): Decide if Chrome should follow spec. crbug.com/277040 |
| -ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters. |
| - ibm-1375 { IBM* } |
| - Big5-HKSCS { IANA* JAVA* } |
| - big5hk { JAVA } |
| - HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/ |
| - |
| -ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters. |
| - ibm-5471 { IBM* } |
| - Big5-HKSCS |
| - MS950_HKSCS { JAVA* } |
| - hkbig5 # from HP-UX 11i, which can't handle supplementary characters. |
| - big5-hkscs:unicode3.0 |
| - x-MS950-HKSCS { JAVA } |
| - # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not. |
| - # windows-950_hkscs |
| -# GBK |
| # Chrome: Added 4 GB2312 aliases and EUC-CN to Windows-936 to reflect the |
| # reality of the web (GB2312 is treated synonymously with its |
| # superset, Windows-936/GBK) |
| -# All the aliases listed for this converter (windows-936-2000) |
| -# are removed from the list of aliases for other simplified Chinese |
| -# converters above. |
| # HTML5 makes GBK an alias for GB18030 |
| # TODO(jshin): Decide if Chrome should follow spec. crbug.com/339862 |
| -windows-936-2000 { UTR22* } |
| +windows-936-2000 |
| GB2312 { IANA MIME } |
| - GBK { IANA* MIME* WINDOWS JAVA* } |
| - CP936 { IANA JAVA } |
| - MS936 { IANA } # In JDK 1.5, this goes to x-mswin-936. This is an IANA name split. |
| - windows-936 { IANA WINDOWS* JAVA } |
| + GBK { IANA* MIME* } |
| + CP936 { IANA } |
| + MS936 { IANA } |
| + windows-936 { IANA } |
| chinese { IANA } |
| iso-ir-58 { IANA } |
| gb2312-1980 |
| @@ -595,98 +384,61 @@ |
| EUC-CN |
| csGB2312 { IANA } |
| GB_2312-80 { IANA } |
| + x-gbk |
| +# GB 18030 is partly algorithmic, using the MBCS converter |
| +gb18030 { IANA* } gb18030 { MIME* } ibm-1392 windows-54936 |
| -# Chrome: ibm-5478 and ibm-949 are replaced by noop-gb2312_gl and windows-949 |
| -# (ksc_5601), respectively, in ucnv2022.c |
| +windows-950-2000 |
| + big5 { MIME* HTML* } |
| + big5-hkscs |
| + cn-big5 |
| + csbig5 |
| + x-x-big5 |
| -# Korean EUC. |
| +# Chrome: WHATWG encoding spec has big5-hkscs as an alias for big5 |
| +# TODO(jshin): Decide if Chrome should follow spec. crbug.com/277040 |
| +ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters. |
| + ibm-1375 |
| + Big5-HKSCS { MIME* IANA* } |
| + big5hk |
| + HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/ |
| -# Chrome: Windows-949 is not EUC-KR, but a superset of EUC-KR with 8,822 |
| -# additional Hangul syllables. However, the reality of the web |
| -# and HTML5 require that we treat EUC-KR a |
| -# synonym of windows-949. |
| -# All the aliases listed for this converter (windows-949-2000) |
| -# are removed from the list of aliases for other Korean converters |
| -# above. |
| -windows-949-2000 { UTR22* } |
| - windows-949 { JAVA* WINDOWS* } |
| - EUC-KR { IANA* MIME* WINDOWS } |
| - KS_C_5601-1987 { WINDOWS IANA } |
| - KS_C_5601-1989 { WINDOWS IANA } |
| - KSC_5601 { IANA WINDOWS } # Needed by iso-2022 |
| - csKSC56011987 { WINDOWS } |
| - korean { IANA WINDOWS } |
| - iso-ir-149 { IANA WINDOWS } |
| - csEUCKR { IANA WINDOWS } |
| -#Chrome: TIS-620, ISO-8859-11 and Windows-874 are slightly different from |
| -# each other, but they're used as if they're identical on the web. This is |
| -# also per HTML5. |
| -windows-874-2000 { UTR22* } # Thai (w/ euro update) |
| - TIS-620 { IANA* WINDOWS MIME* } |
| - windows-874 { JAVA* WINDOWS* MIME } |
| - MS874 { JAVA } |
| - x-windows-874 { JAVA } |
| - iso-8859-11 { IANA WINDOWS MIME } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. |
| +euc-jp-html |
| + EUC-JP { MIME* HTML* } |
| + cseucpkdfmtjapanese |
| + x-euc-jp |
| -# Platform codepages |
| -# Chrome: only keep ibm-878 for KOI8-R, ibm-1168 for KOI8-RU and ibm-866 |
| -ibm-878_P100-1996 { UTR22* } ibm-878 { IBM* } KOI8-R { IANA* MIME* WINDOWS JAVA* } koi8 { WINDOWS JAVA } csKOI8R { IANA WINDOWS JAVA } windows-20866 { WINDOWS* } cp878 # Russian internet |
| -# Chrome: Use the table from the WHATWG encoding standard (HTML5). |
| -ibm866-html ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } # PC Russian (w/o euro update) |
| -ibm-1168_P100-2002 { UTR22* } ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } # Ukrainian KOI8. koi8-ru != KOI8-U and Microsoft is wrong for aliasing them as the same. |
| +ISO_2022,locale=ja,version=0 |
| + ISO-2022-JP { MIME* HTML* } |
| + csiso2022jp |
| -# The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows. |
| -# cp is usually used to denote IBM in Java, and that is why we don't do that anymore. |
| -# The windows-* aliases mean windows codepages. |
| -ibm-5346_P100-1998 { UTR22* } ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS* } cp1250 { WINDOWS JAVA } # Windows Latin2 (w/ euro update) |
| -ibm-5347_P100-1998 { UTR22* } ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS* } cp1251 { WINDOWS JAVA } ANSI1251 # Windows Cyrillic (w/ euro update). ANSI1251 is from Solaris |
| -ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { JAVA } # Windows Latin1 (w/ euro update) |
| -ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA } # Windows Greek (w/ euro update) |
| +shift_jis-html |
| + Shift_JIS { MIME* HTML* } |
| + csshiftjis |
| + ms_kanji |
| + shift-jis |
| + sjis |
| + windows-31j |
| + x-sjis |
| -#CHROME : Make ISO-8859-9 an alias to windows-1254 per HTML5. Move |
| -# other IANA aliases for ISO-8859-9 as well. |
| -ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { MIME* IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update) |
| - ISO-8859-9 { MIME } |
| - latin5 { IANA } |
| - csISOLatin5 { IANA } |
| - iso-ir-148 { IANA } |
| - ISO_8859-9:1989 { IANA } |
| - l5 { IANA } |
| - 8859_9 { JAVA } |
| -ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA } # Windows Hebrew (w/ euro update) |
| -ibm-9448_X100-2005 { UTR22* } ibm-9448 { IBM* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS JAVA } x-windows-1256S { JAVA } # Windows Arabic (w/ euro update) |
| -ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA } # Windows Baltic (w/ euro update) |
| -ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA } # Windows Vietnamese (w/ euro update) |
| +windows-949-2000 |
| + EUC-KR { MIME* HTML* } |
| + cseuckr |
| + csksc56011987 |
| + iso-ir-149 |
| + korean |
| + ks_c_5601-1987 |
| + ks_c_5601-1989 |
| + ksc5601 |
| + ksc_5601 |
| + windows-949 |
| -# Chrome: Only MacRoman and MacCyrillic are necessary for HTML5. |
| -macos-0_2-10.2 { UTR22* } macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } macroman { JAVA } x-macroman { JAVA* } # Apple latin 1 |
| -macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } mac-cyrillic maccy x-MacCyrillic { JAVA } x-MacUkraine { JAVA* } # Apple Cyrillic |
| +# We need to keep these aliases so that documents labelled with them |
| +# are converted to a single U+FFFD instead of being rendered as a gibberish. |
| +ISO-2022-KR { HTML* MIME* } csISO2022KR { IANA } |
| +ISO-2022-CN { IANA* HTML* } csISO2022CN x-ISO-2022-CN-GB |
| +ISO-2022-CN-EXT { IANA* HTML* } |
| +HZ-GB-2312 { HTML* IANA* } HZ |
| -# Partially algorithmic converters |
| - |
| -# [U_ENABLE_GENERIC_ISO_2022] |
| -# The _generic_ ISO-2022 converter is disabled starting 2003-dec-03 (ICU 2.8). |
| -# For details see the icu mailing list from 2003-dec-01 and the ucnv2022.c file. |
| -# Language-specific variants of ISO-2022 continue to be available as listed below. |
| -# ISO_2022 ISO-2022 |
| - |
| -# Chrome: The encoding standard only supports ISO-2022-JP. |
| -# Remove ISO-2022-{KR,CN,CN-Ext} and HZ-GB from the alias table. |
| -# See crbug.com/277037 and https://www.w3.org/Bugs/Public/show_bug.cgi?id=25339 |
| -# about HZ-GB. |
| -ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA } |
| - |
| -# Chrome: HTML5 does not need ISCII. |
| -# Remove all Lotus entries as well. |
| - |
| -# EBCDIC codepages according to the CDRA |
| -# Chrome: Removed all EBCDIC code pages. |
| - |
| -# These are not installed by default. They are rarely used. |
| -# Many of them can be added through the online ICU Data Library Customization tool |
| -# Chrome: Removed all these entries except for ISO-8859-16 required by HTML5. |
| - |
| -iso-8859_16-2001 { UTR22* } ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA } |
| - |
