X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/729e4ab9bc6618bc3d8a898e575df7f4019e29ca..a01113dcd0f39d5da295ef82785beff9ed86fe38:/icuSources/data/mappings/convrtrs.txt diff --git a/icuSources/data/mappings/convrtrs.txt b/icuSources/data/mappings/convrtrs.txt index bfa82dae..233bdc90 100644 --- a/icuSources/data/mappings/convrtrs.txt +++ b/icuSources/data/mappings/convrtrs.txt @@ -1,6 +1,8 @@ +# Copyright (C) 2016 and later: Unicode, Inc. and others. +# License & terms of use: http://www.unicode.org/copyright.html # ****************************************************************************** # * -# * Copyright (C) 1995-2010, International Business Machines +# * Copyright (C) 1995-2014, International Business Machines # * Corporation and others. All Rights Reserved. # * # ****************************************************************************** @@ -149,6 +151,8 @@ UTF-8 { IANA* MIME* JAVA* WINDOWS } 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 } @@ -302,6 +306,8 @@ UTF-16,version=2 # # For details about email headers see RFC 2047. UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* } + unicode-1-1-utf-7 + unicode-2-0-utf-7 # UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference. #UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM } @@ -451,30 +457,22 @@ ibm-1089_P100-1995 { UTR22* } # 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 WINDOWS } - greek { IANA WINDOWS } - greek8 { IANA WINDOWS } - ELOT_928 { IANA WINDOWS } - ECMA-118 { IANA WINDOWS } - csISOLatinGreek { IANA WINDOWS } - iso-ir-126 { IANA WINDOWS } - ISO_8859-7:1987 { IANA* WINDOWS } + 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 # ISO Greek (w/o euro update) # JDK 1.5 has these aliases. ibm-813_P100-1995 { UTR22* } - ibm-813 { IBM* JAVA } - ISO-8859-7 { JAVA* } - greek { JAVA } - greek8 { JAVA } - ELOT_928 { JAVA } - ECMA-118 { JAVA } - csISOLatinGreek { JAVA } - iso-ir-126 { JAVA } - ISO_8859-7:1987 { JAVA } - 8859_7 { JAVA } + ibm-813 { IBM* JAVA* } cp813 { JAVA } 813 { JAVA } @@ -534,7 +532,7 @@ iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* } # 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 } + x-iso-8859-11 { JAVA* } # iso-8859-13, PC Baltic (w/o euro update) ibm-921_P100-1995 { UTR22* } @@ -579,7 +577,7 @@ ibm-942_P12A-1999 { UTR22* } # ibm-942_P120 is a rarely used alternate mappin sjis78 ibm-942_VSUB_VPUA ibm-932_VSUB_VPUA - x-IBM942 { JAVA } + x-IBM942 { JAVA* } x-IBM942C { JAVA } # Is this "JIS_C6226-1978"? @@ -615,16 +613,15 @@ ibm-943_P130-1999 { UTR22* } ibm-943_VASCII_VSUB_VPUA x-IBM943 { JAVA } # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe -ibm-33722_P12A_P12A-2004_U2 { UTR22* } +ibm-33722_P12A_P12A-2009_U2 { UTR22* } ibm-33722 # Leave untagged because this isn't the default ibm-5050 # Leave untagged because this isn't the default, and yes this alias is correct - EUC-JP { IANA MIME* WINDOWS } - Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS } - csEUCPkdFmtJapanese { IANA WINDOWS } - X-EUC-JP { WINDOWS } # Japan EUC. x-euc-jp is a MIME name - windows-51932 { WINDOWS* } ibm-33722_VPUA IBM-eucJP +windows-51932-2006 { UTR22* } + windows-51932 { WINDOWS* } + CP51932 { IANA* } + csCP51932 ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping ibm-33722 { IBM* JAVA } ibm-5050 { IBM } # Yes this is correct @@ -639,25 +636,26 @@ ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping # ibm-954 contains more PUA characters than the others. ibm-954_P101-2007 { UTR22* } ibm-954 { IBM* } - EUC-JP { JAVA* } # Matches more closely with ibm-1350 - Extended_UNIX_Code_Packed_Format_for_Japanese { JAVA } - csEUCPkdFmtJapanese { JAVA } - X-EUC-JP { JAVA } # 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. - x-IBM954 { JAVA } + x-IBM954 { JAVA* } x-IBM954C { JAVA } # eucJP # This is closest to Solaris EUC-JP. - +euc-jp-2007 { UTR22* } + EUC-JP { MIME* IANA JAVA* WINDOWS* } + Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* JAVA WINDOWS } + csEUCPkdFmtJapanese { IANA JAVA 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. + aix-IBM_udcJP-4.3.6 { UTR22* } - x-IBM-udcJP { JAVA } + x-IBM-udcJP { JAVA* } java-euc_jp_linux-1.6_P { UTR22* } euc-jp-linux - x-EUC_JP_LINUX { JAVA } + x-EUC_JP_LINUX { JAVA* } java-sjis_0213-1.6_P { UTR22* } - x-SJIS_0213 { JAVA } + x-SJIS_0213 { JAVA* } # Here are various interpretations and extentions of Big5 ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions @@ -669,12 +667,13 @@ windows-950-2000 { UTR22* } windows-950 { WINDOWS* } x-windows-950 { JAVA } x-big5 + ms950 ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update) ibm-950 { IBM* JAVA } cp950 { JAVA* } 950 { JAVA } x-IBM950 { JAVA } -ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters. +ibm-1375_P100-2008 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters. ibm-1375 { IBM* } Big5-HKSCS { IANA* JAVA* } big5hk { JAVA } @@ -689,7 +688,7 @@ ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. Thi # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not. # windows-950_hkscs solaris-zh_TW_big5-2.7 { UTR22* } - Big5_Solaris { JAVA } + Big5_Solaris { JAVA* } x-Big5-Solaris { JAVA } # GBK ibm-1386_P100-2001 { UTR22* } @@ -724,9 +723,11 @@ ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping i gb2312-1980 GB2312.1980-0 # From X11R6 +euc-tw-2014 { UTR22* } # Updated EUC-TW converter based on ibm-964 + EUC-TW + ibm-964_P110-1999 { UTR22* } # Taiwan EUC. x-euc-tw is a MIME name ibm-964 { IBM* JAVA } - EUC-TW ibm-eucTW cns11643 cp964 { JAVA* } @@ -787,7 +788,7 @@ ibm-970_P110_P110-2006_U2 { UTR22* } x-IBM970 { JAVA } # ibm-971 is almost the set of DBCS mappings of ibm-970 -ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA } +ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA* } # Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too. # ibm-1363 is almost a superset of ibm-970. @@ -804,20 +805,20 @@ ibm-1363_P11B-1998 { UTR22* } ksc windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage. ibm-1363_VSUB_VPUA - x-IBM1363C { JAVA } + x-IBM1363C { JAVA* } # ks_x_1001:1992 # ksc5601-1992 ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping ibm-1363 { IBM* } ibm-1363_VASCII_VSUB_VPUA - x-IBM1363 { JAVA } + x-IBM1363 { JAVA* } windows-949-2000 { UTR22* } windows-949 { JAVA* WINDOWS* } KS_C_5601-1987 { WINDOWS } KS_C_5601-1989 { WINDOWS } - KSC_5601 { MIME WINDOWS } # Needed by iso-2022 + KSC_5601 { MIME* WINDOWS } # Needed by iso-2022 csKSC56011987 { WINDOWS } korean { WINDOWS } iso-ir-149 { WINDOWS } @@ -828,7 +829,7 @@ windows-1361-2000 { UTR22* } ksc5601_1992 ms1361 johab - x-Johab { JAVA } + x-Johab { JAVA* } windows-874-2000 { UTR22* } # Thai (w/ euro update) TIS-620 { WINDOWS } @@ -852,12 +853,12 @@ ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) windows-864-2000 { UTR22* } ibm-864s cp864s - x-IBM864S { JAVA } + x-IBM864S { JAVA* } # Platform codepages # If Java supports the IBM prefix, it should also support the ibm- prefix too. ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } cp437 { IANA WINDOWS JAVA* } 437 { IANA WINDOWS JAVA } csPC8CodePage437 { IANA JAVA } windows-437 { WINDOWS* } # PC US -ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA } # PC Arabic +ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA* } # PC Arabic ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } x-IBM737 { JAVA } # PC Greek ibm-775_P100-1996 { UTR22* } ibm-775 { IBM* } IBM775 { IANA* WINDOWS JAVA } cp775 { IANA WINDOWS JAVA* } csPC775Baltic { IANA } windows-775 { WINDOWS* } 775 { JAVA } # PC Baltic ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* MIME* WINDOWS JAVA } cp850 { IANA MIME WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1 @@ -874,7 +875,7 @@ ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* MIME* JAVA } cp8 ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* MIME* JAVA } cp864 { IANA MIME JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update) ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update) -ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA } # PC Hebrew (w/ euro update) Updated version of ibm-862 +ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862 ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* MIME* JAVA } CP868 { IANA MIME JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* MIME* WINDOWS JAVA } cp869 { IANA MIME JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } windows-869 { WINDOWS* } # PC Greek (w/o euro update) 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 @@ -913,20 +914,20 @@ ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 # Somewhat old W ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } windows-1258 # Old Windows Vietnamese (w/o euro update) 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-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA } # Apple Greek -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 -macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA } MacThai { JAVA } -macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA } # Apple Central Europe -macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA } MacSymbol { JAVA } -macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA } MacDingbat { JAVA } -macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA } # Apple Turkish -macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA } MacCroatian { JAVA } -macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA } MacIceland { JAVA } -macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA } MacRomania { JAVA } -macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA } MacArabic { JAVA } -macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA } MacHebrew { JAVA } - -ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } # HP Latin1 +macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA* } # Apple Greek +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 +macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA* } MacThai { JAVA } +macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA* } # Apple Central Europe +macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA* } MacSymbol { JAVA } +macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA* } MacDingbat { JAVA } +macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA* } # Apple Turkish +macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA* } MacCroatian { JAVA } +macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA* } MacIceland { JAVA } +macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA* } MacRomania { JAVA } +macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA* } MacArabic { JAVA } +macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA* } MacHebrew { JAVA } + +ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } x-roman8 { JAVA* } # HP Latin1 ibm-1276_P100-1995 { UTR22* } ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276) ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } x-IBM1006 { JAVA } # Urdu @@ -937,6 +938,8 @@ ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO Lao +# GSM 03.38 +gsm-03.38-2009 { UTR22* } GSM0338 # GSM0338 alias is from Perl # Partially algorithmic converters @@ -947,7 +950,7 @@ ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO_2022 ISO-2022 ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA } -ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA } +ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* } ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA } ISO_2022,locale=ja,version=3 JIS7 ISO_2022,locale=ja,version=4 JIS8 @@ -955,11 +958,11 @@ ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { ISO_2022,locale=ko,version=1 ibm-25546 { IBM* } ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA } ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* } -ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA } +ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* } HZ HZ-GB-2312 { IANA* } -x11-compound-text COMPOUND_TEXT x-compound-text { JAVA } +x11-compound-text COMPOUND_TEXT x-compound-text { JAVA* } -ISCII,version=0 x-ISCII91 { JAVA } x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev ibm-4902 { IBM* } # ibm-806 contains non-standard box drawing symbols. +ISCII,version=0 x-ISCII91 { JAVA* } x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev ibm-4902 { IBM* } # ibm-806 contains non-standard box drawing symbols. ISCII,version=1 x-iscii-be { WINDOWS } windows-57003 { WINDOWS* } iscii-bng windows-57006 { WINDOWS } x-iscii-as { WINDOWS } # be is different from as on Windows. ISCII,version=2 x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur ISCII,version=3 x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj @@ -1047,8 +1050,8 @@ ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* JAVA } cp1047 { JAVA* } 1047 { JAVA } # EBCDIC Open systems Latin1 ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } x-IBM1097 { JAVA } # EBCDIC Farsi ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } x-IBM1112 { JAVA } # EBCDIC Baltic -ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA } -ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA } +ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA* } +ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA* } ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } x-IBM1122 { JAVA } # EBCDIC Estonia ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } x-IBM1123 { JAVA } # EBCDIC Cyrillic Ukraine ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese @@ -1067,7 +1070,7 @@ ibm-1146_P100-1997 { UTR22* } ibm-1146 { IBM* } IBM01146 { IANA* JAVA } CCSID0 ibm-1147_P100-1997 { UTR22* } ibm-1147 { IBM* } IBM01147 { IANA* JAVA } CCSID01147 { IANA JAVA } CP01147 { IANA JAVA } cp1147 { JAVA* } ebcdic-fr-297+euro { IANA } # EBCDIC France ibm-1148_P100-1997 { UTR22* } ibm-1148 { IBM* } IBM01148 { IANA* JAVA } CCSID01148 { IANA JAVA } CP01148 { IANA JAVA } cp1148 { JAVA* } ebcdic-international-500+euro { IANA } # EBCDIC International Latin1 ibm-1149_P100-1997 { UTR22* } ibm-1149 { IBM* } IBM01149 { IANA* JAVA } CCSID01149 { IANA JAVA } CP01149 { IANA JAVA } cp1149 { JAVA* } ebcdic-is-871+euro { IANA } # EBCDIC Iceland -ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA } # EBCDIC latin 2 +ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA* } # EBCDIC latin 2 ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } # EBCDIC Cyrillic Multilingual ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } # EBCDIC Turkey ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } # EBCDIC Baltic Multilingual @@ -1075,12 +1078,12 @@ ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } # EBCDIC Est ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } # EBCDIC Cyrillic Ukraine ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } # EBCDIC Thailand ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } # EBCDIC Viet Nam -ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA } # Korean Host Mixed -ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA } -ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA } # Taiwan EBCDIC MIXED (Euro update of ibm-937) -ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. -ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA } # Japan EBCDIC MIXED (JIS X 0213) -ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA } # Host MBCS (Latin-Kanji) (JIS X 0213) +ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA* } # Korean Host Mixed +ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA* } +ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA* } # Taiwan EBCDIC MIXED (Euro update of ibm-937) +ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA* } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. +ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA* } # Japan EBCDIC MIXED (JIS X 0213) +ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA* } # Host MBCS (Latin-Kanji) (JIS X 0213) ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027. SBCS portion of ibm-1390. ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290. SBCS portion of ibm-1399. # Yes ibm-20780 is the same as ibm-16684 @@ -1091,9 +1094,9 @@ ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Gre ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update). Update of ibm-424 ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420 -java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA } -java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA } -java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA } +java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* } +java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA* } +java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA* } # EBCDIC codepages for S/390, with LF and NL codes swapped # Starting with ICU 2.4, the swapping is done by modifying the @@ -1124,10 +1127,10 @@ java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA } # regular, option-less alias elsewhere in this file. ibm-37_P100-1995,swaplfnl ibm-37-s390 # ibm037-s390 also matches ibm-37-s390 -ibm-924_P100-1998,swaplfnl ibm-924-s390 IBM924_LF { JAVA } -ibm-1047_P100-1995,swaplfnl ibm-1047-s390 IBM1047_LF { JAVA } +ibm-924_P100-1998,swaplfnl ibm-924-s390 IBM924_LF { JAVA* } +ibm-1047_P100-1995,swaplfnl ibm-1047-s390 IBM1047_LF { JAVA* } ibm-1140_P100-1997,swaplfnl ibm-1140-s390 -ibm-1141_P100-1997,swaplfnl ibm-1141-s390 IBM1141_LF { JAVA } +ibm-1141_P100-1997,swaplfnl ibm-1141-s390 IBM1141_LF { JAVA* } ibm-1142_P100-1997,swaplfnl ibm-1142-s390 ibm-1143_P100-1997,swaplfnl ibm-1143-s390 ibm-1144_P100-1997,swaplfnl ibm-1144-s390 @@ -1149,7 +1152,6 @@ ebcdic-xml-us # These are not installed by default. They are rarely used. # Many of them can be added through the online ICU Data Library Customization tool -gsm-03.38-2000 { UTR22* } GSM0338 # GSM0338 alias is from Perl ibm-1004_P100-1995 { UTR22* } ibm-1004 { IBM* } ibm-1008_P100-1995 { UTR22* } ibm-1008 { IBM* } # cp1008, 8-bit Arabic (w/o euro update) ibm-1009_P100-1995 { UTR22* } ibm-1009 { IBM* } @@ -1166,11 +1168,11 @@ ibm-1019_P100-1995 { UTR22* } ibm-1019 { IBM* } ibm-1020_P100-2003 { UTR22* } ibm-1020 { IBM* } CSA_Z243.4-1985-1 { IANA* } iso-ir-121 { IANA } ISO646-CA { IANA } csa7-1 { IANA } ca { IANA } csISO121Canadian1 { IANA } ibm-1021_P100-2003 { UTR22* } ibm-1021 { IBM* } ibm-1023_P100-2003 { UTR22* } ibm-1023 { IBM* } ES { IANA* } iso-ir-17 { IANA } ISO646-ES { IANA } csISO17Spanish { IANA } -ibm-1027_P100-1995 { UTR22* } ibm-1027 { IBM* } x-IBM1027 { JAVA } -ibm-1041_P100-1995 { UTR22* } ibm-1041 { IBM* } x-IBM1041 { JAVA } -ibm-1043_P100-1995 { UTR22* } ibm-1043 { IBM* } x-IBM1043 { JAVA } -ibm-1046_X110-1999 { UTR22* } ibm-1046 { IBM* } x-IBM1046 { JAVA } x-IBM1046S { JAVA } # Arabic -ibm-1088_P100-1995 { UTR22* } ibm-1088 { IBM* } x-IBM1088 { JAVA } +ibm-1027_P100-1995 { UTR22* } ibm-1027 { IBM* } x-IBM1027 { JAVA* } +ibm-1041_P100-1995 { UTR22* } ibm-1041 { IBM* } x-IBM1041 { JAVA* } +ibm-1043_P100-1995 { UTR22* } ibm-1043 { IBM* } x-IBM1043 { JAVA* } +ibm-1046_X110-1999 { UTR22* } ibm-1046 { IBM* } x-IBM1046 { JAVA* } x-IBM1046S { JAVA } # Arabic +ibm-1088_P100-1995 { UTR22* } ibm-1088 { IBM* } x-IBM1088 { JAVA* } ibm-1100_P100-2003 { UTR22* } ibm-1100 { IBM* } DEC-MCS { IANA* } dec { IANA } csDECMCS { IANA } ibm-1101_P100-2003 { UTR22* } ibm-1101 { IBM* } ibm-1102_P100-2003 { UTR22* } ibm-1102 { IBM* } @@ -1184,19 +1186,19 @@ ibm-1161_P100-1999 { UTR22* } ibm-1161 { IBM* } # Thai (Euro update of ibm-112 ibm-1163_P100-1999 { UTR22* } ibm-1163 { IBM* } # Vietnamese ibm-1165_P101-2000 { UTR22* } ibm-1165 { IBM* } # Vietnamese (EBCDIC) ibm-1166_P100-2002 { UTR22* } ibm-1166 { IBM* } # Cyrillic for Kazakhstan -ibm-1167_P100-2002 { UTR22* } ibm-1167 { IBM* } KOI8-RU x-KOI8_RU { JAVA } +ibm-1167_P100-2002 { UTR22* } ibm-1167 { IBM* } KOI8-RU x-KOI8_RU { JAVA* } ibm-1174_X100-2007 { UTR22* } ibm-1174 { IBM* } KZ-1048 { IANA* } STRK1048-2002 { IANA } RK1048 { IANA } csKZ1048 { IANA } ibm-1277_P100-1995 { UTR22* } ibm-1277 { IBM* } # Adobe (Postscript) Latin-1 ibm-13125_P100-1997 { UTR22* } ibm-13125 { IBM* } # S-Ch (DBCS subset of ibm-4933, ibm-1388) ibm-13140_P101-2000 { UTR22* } ibm-13140 { IBM* } ibm-13218_P100-1996 { UTR22* } ibm-13218 { IBM* } # Japanese (EBCDIC update of ibm-930) -ibm-1350_P110-1997 { UTR22* } ibm-1350 { IBM* } x-eucJP-Open { JAVA } eucJP-Open { JAVA } # Japanese (EUC-JP variant) -ibm-1351_P110-1997 { UTR22* } ibm-1351 { IBM* } x-IBM1351 { JAVA } # Japanese (DBCS subset of ibm-5039) -ibm-1362_P110-1999 { UTR22* } ibm-1362 { IBM* } x-IBM1362 { JAVA } # Korean (DBCS subset of ibm-1363) +ibm-1350_P110-1997 { UTR22* } ibm-1350 { IBM* } x-eucJP-Open { JAVA* } eucJP-Open { JAVA } # Japanese (EUC-JP variant) +ibm-1351_P110-1997 { UTR22* } ibm-1351 { IBM* } x-IBM1351 { JAVA* } # Japanese (DBCS subset of ibm-5039) +ibm-1362_P110-1999 { UTR22* } ibm-1362 { IBM* } x-IBM1362 { JAVA* } # Korean (DBCS subset of ibm-1363) ibm-13676_P102-2001 { UTR22* } ibm-13676 { IBM* } # Simplified Chinese (EBCDIC) -ibm-1380_P100-1995 { UTR22* } ibm-1380 { IBM* } x-IBM1380 { JAVA } # Simplified Chinese (DBCS subset of ibm-1381) +ibm-1380_P100-1995 { UTR22* } ibm-1380 { IBM* } x-IBM1380 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1381) ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } x-IBM1381 { JAVA } # Simplified Chinese PC Data mixed (IBM GB) -ibm-1382_P100-1995 { UTR22* } ibm-1382 { IBM* } x-IBM1382 { JAVA } # Simplified Chinese (DBCS subset of ibm-1383) +ibm-1382_P100-1995 { UTR22* } ibm-1382 { IBM* } x-IBM1382 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1383) ibm-17221_P100-2001 { UTR22* } ibm-17221 { IBM* } # Simplified Chinese (EBCDIC) ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864 ibm-21344_P101-2000 { UTR22* } ibm-21344 { IBM* } # PC Arabic. Updated version of ibm-864 @@ -1207,8 +1209,8 @@ ibm-274_P100-2000 { UTR22* } ibm-274 { IBM* } IBM274 { IANA* } EBCDIC-BE { IA ibm-275_P100-1995 { UTR22* } ibm-275 { IBM* } IBM275 { IANA* } EBCDIC-BR { IANA } cp275 { IANA } csIBM275 { IANA } ibm-286_P100-2003 { UTR22* } ibm-286 { IBM* } EBCDIC-AT-DE-A { IANA* } csEBCDICATDEA { IANA } ibm-293_P100-1995 { UTR22* } ibm-293 { IBM* } # APL EBCDIC (APL: A Programming Language) -ibm-300_P120-2006 { UTR22* } ibm-300 { IBM* } x-IBM300 { JAVA } # Japanese (DBCS subset of ibm-930 and ibm-939) -ibm-301_P110-1997 { UTR22* } ibm-301 { IBM* } x-IBM301 { JAVA } # Japanese (DBCS subset of ibm-943) +ibm-300_P120-2006 { UTR22* } ibm-300 { IBM* } x-IBM300 { JAVA* } # Japanese (DBCS subset of ibm-930 and ibm-939) +ibm-301_P110-1997 { UTR22* } ibm-301 { IBM* } x-IBM301 { JAVA* } # Japanese (DBCS subset of ibm-943) ibm-33058_P100-2000 { UTR22* } ibm-33058 { IBM* } # SBCS (Katakana) ibm-425_P101-2000 { UTR22* } ibm-425 { IBM* } # Arabic (EBCDIC) ibm-4930_P110-1999 { UTR22* } ibm-4930 { IBM* } # Korean (DBCS subset of ibm-1364) @@ -1222,21 +1224,22 @@ ibm-5048_P100-1995 { UTR22* } ibm-5048 { IBM* } # Japanese (DBCS subset of ibm ibm-5049_P100-1995 { UTR22* } ibm-5049 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X212) ibm-5067_P100-1995 { UTR22* } ibm-5067 { IBM* } # Korean (DBCS subset of ibm-21450) ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } # cp1008, 8-bit Arabic (w/ euro update) +ibm-5233_P100-2011 { UTR22* } ibm-5233 { IBM* } # Devanagari EBCDIC, including Indian Rupee ibm-806_P100-1998 { UTR22* } ibm-806 { IBM* } # Hindi (ISCII variant) -ibm-808_P100-1999 { UTR22* } ibm-808 { IBM* } x-IBM808 { JAVA } # Cyrillic -ibm-833_P100-1995 { UTR22* } ibm-833 { IBM* } x-IBM833 { JAVA } -ibm-834_P100-1995 { UTR22* } ibm-834 { IBM* } x-IBM834 { JAVA } # Korean (DBCS subset of ibm-933) -ibm-835_P100-1995 { UTR22* } ibm-835 { IBM* } x-IBM835 { JAVA } # Traditional Chinese (DBCS subset of ibm-5033) -ibm-836_P100-1995 { UTR22* } ibm-836 { IBM* } x-IBM836 { JAVA } -ibm-837_P100-1995 { UTR22* } ibm-837 { IBM* } x-IBM837 { JAVA } # Simplified Chinese (DBCS subset of ibm-5031) +ibm-808_P100-1999 { UTR22* } ibm-808 { IBM* } x-IBM808 { JAVA* } # Cyrillic +ibm-833_P100-1995 { UTR22* } ibm-833 { IBM* } x-IBM833 { JAVA* } +ibm-834_P100-1995 { UTR22* } ibm-834 { IBM* } x-IBM834 { JAVA* } # Korean (DBCS subset of ibm-933) +ibm-835_P100-1995 { UTR22* } ibm-835 { IBM* } x-IBM835 { JAVA* } # Traditional Chinese (DBCS subset of ibm-5033) +ibm-836_P100-1995 { UTR22* } ibm-836 { IBM* } x-IBM836 { JAVA* } +ibm-837_P100-2011 { UTR22* } ibm-837 { IBM* } x-IBM837 { JAVA* } # Simplified Chinese (DBCS subset of ibm-5031) ibm-848_P100-1999 { UTR22* } ibm-848 { IBM* } # Cyrillic (euro update of ibm-1125) ibm-849_P100-1999 { UTR22* } ibm-849 { IBM* } # Cyrillic Belarus (euro update of ibm-1131) -ibm-859_P100-1999 { UTR22* } ibm-859 { IBM* } x-IBM859 { JAVA } # PC Latin 9 (w/ euro update) +ibm-859_P100-1999 { UTR22* } ibm-859 { IBM* } x-IBM859 { JAVA* } # PC Latin 9 (w/ euro update) ibm-8612_P100-1995 { UTR22* } ibm-8612 { IBM* } # Arabic (EBCDIC update of ibm-420) ibm-872_P100-1999 { UTR22* } ibm-872 { IBM* } # Cyrillic (Euro update of ibm-855) ibm-880_P100-1995 { UTR22* } ibm-880 { IBM* } IBM880 { IANA* } cp880 { IANA } EBCDIC-Cyrillic { IANA } csIBM880 { IANA } windows-20880 { WINDOWS* } ibm-896_P100-1995 { UTR22* } ibm-896 { IBM* } # SBCS Katakana -ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } x-IBM897 { JAVA } +ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } x-IBM897 { JAVA* } ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371. ibm-9048_P100-1998 { UTR22* } ibm-9048 { IBM* } # Hebrew (Euro and Sequel update of ibm-856) ibm-905_P100-1995 { UTR22* } ibm-905 { IBM* } IBM905 { IANA* } CP905 { IANA } ebcdic-cp-tr { IANA } csIBM905 { IANA } windows-20905 { WINDOWS* } @@ -1246,18 +1249,18 @@ ibm-9145_P110-1997 { UTR22* } ibm-9145 { IBM* } # Japanese (DBCS subset of ibm ibm-9238_X110-1999 { UTR22* } ibm-9238 { IBM* } # cp1046, PC Arabic Extended (w/ euro update) ibm-924_P100-1998 { UTR22* } ibm-924 { IBM* } IBM00924 { IANA* } CCSID00924 { IANA } CP00924 { IANA } ebcdic-Latin9--euro { IANA } ibm-926_P100-2000 { UTR22* } ibm-926 { IBM* } # Korean (DBCS subset of ibm-944) -ibm-927_P100-1995 { UTR22* } ibm-927 { IBM* } x-IBM927 { JAVA } # Traditional Chinese (DBCS subset of ibm-948) +ibm-927_P100-1995 { UTR22* } ibm-927 { IBM* } x-IBM927 { JAVA* } # Traditional Chinese (DBCS subset of ibm-948) ibm-928_P100-1995 { UTR22* } ibm-928 { IBM* } # Simplified Chinese (DBCS subset of ibm-936) ibm-941_P13A-2001 { UTR22* } ibm-941 { IBM* } # DBCS portion of ibm-943 ibm-944_P100-1995 { UTR22* } ibm-944 { IBM* } # Korean ibm-946_P100-1995 { UTR22* } ibm-946 { IBM* } # Simplified Chinese -ibm-947_P100-1995 { UTR22* } ibm-947 { IBM* } x-IBM947 { JAVA } # Traditional Chinese (DBCS subset of ibm-950) -ibm-948_P110-1999 { UTR22* } ibm-948 { IBM* } x-IBM948 { JAVA } # Traditional Chinese -ibm-951_P100-1995 { UTR22* } ibm-951 { IBM* } x-IBM951 { JAVA } # Korean (DBCS subset of ibm-949) +ibm-947_P100-1995 { UTR22* } ibm-947 { IBM* } x-IBM947 { JAVA* } # Traditional Chinese (DBCS subset of ibm-950) +ibm-948_P110-1999 { UTR22* } ibm-948 { IBM* } x-IBM948 { JAVA* } # Traditional Chinese +ibm-951_P100-1995 { UTR22* } ibm-951 { IBM* } x-IBM951 { JAVA* } # Korean (DBCS subset of ibm-949) ibm-952_P110-1997 { UTR22* } ibm-952 { IBM* } x-JIS0208 # Pure DBCS, Japanese EUC, G1 - JIS X208-1990 ibm-953_P100-2000 { UTR22* } ibm-953 { IBM* } JIS_X0212-1990 { IANA* } # Pure DBCS, Japanese EUC, G3 - JIS X 0212-1990 ibm-955_P110-1997 { UTR22* } ibm-955 { IBM* } # Pure DBCS, Japanese EUC, G0 - JIS X208-1978 -ibm-9577_P100-2001 { UTR22* } ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA } # ibm-9577 and ibm-1385 are identical DBCS tables. +ibm-9577_P100-2001 { UTR22* } ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA* } # ibm-9577 and ibm-1385 are identical DBCS tables. iso-8859_16-2001 { UTR22* } ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA } # To be considered for listing at a later date for the data library customization tool