X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/9d88c94317aeac5dd26c1dbe8c2112dbe855d2b5..73c04bcfe1096173b00431f0cdc742894b15eef0:/icuSources/data/mappings/convrtrs.txt diff --git a/icuSources/data/mappings/convrtrs.txt b/icuSources/data/mappings/convrtrs.txt index f56fd359..e174a1d1 100644 --- a/icuSources/data/mappings/convrtrs.txt +++ b/icuSources/data/mappings/convrtrs.txt @@ -1,13 +1,13 @@ # ****************************************************************************** # * -# * Copyright (C) 1995-2004, International Business Machines +# * Copyright (C) 1995-2006, International Business Machines # * Corporation and others. All Rights Reserved. # * # ****************************************************************************** # If this converter alias table looks very confusing, a much easier to # understand view can be found at this demo: -# http://oss.software.ibm.com/cgi-bin/icu/convexp +# http://www.ibm.com/software/globalization/icu/demo/converters # IMPORTANT NOTE # @@ -134,36 +134,74 @@ # Fully algorithmic converters UTF-8 { IANA* MIME* JAVA* WINDOWS } - ibm-1208 { IBM* } - ibm-1209 { IBM } - ibm-5304 { IBM } - ibm-5305 { IBM } + 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 # The ICU 2.2 UTF-16/32 converters detect and write a BOM. -UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA } unicode csUnicode ucs-2 +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 } - # iso-10646-ucs-2 { JAVA } # This is ambiguous - ibm-1200 { IBM* } - ibm-1201 { IBM } - ibm-5297 { IBM } - ibm-13488 { IBM } - ibm-17584 { IBM } + 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-61955 { IBM } # UTF-16BE with Gaidai University (Japan) PUA + ibm-61956 { IBM } # UTF-16BE with 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 } - ibm-1202 { IBM* } - ibm-13490 { IBM } - ibm-17586 { IBM } + 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 UTF16_LittleEndian windows-1200 { WINDOWS* } -UTF-32 { IANA* MIME* } ISO-10646-UCS-4 { IANA } csUCS4 ucs-4 -UTF-32BE { IANA* } UTF32_BigEndian ibm-1232 { IBM* } ibm-1233 { IBM } -UTF-32LE { IANA* } UTF32_LittleEndian ibm-1234 { IBM* } +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 +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 @@ -185,6 +223,9 @@ UTF32_OppositeEndian # For details about email headers see RFC 2047. UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* } +# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference. +#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM } + # IMAP-mailbox-name is an ICU-specific name for the encoding of IMAP mailbox names. # It is a substantially modified UTF-7 encoding. See the specification in: # @@ -194,11 +235,16 @@ UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* } IMAP-mailbox-name SCSU { IANA* } -BOCU-1 { IANA* } csBOCU-1 { IANA } + ibm-1212 { IBM* } # SCSU with IBM PUA + ibm-1213 { IBM } # SCSU +BOCU-1 { IANA* } + csBOCU-1 { IANA } + ibm-1214 { IBM* } # BOCU-1 with IBM PUA + ibm-1215 { IBM } # BOCU-1 # See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16 # The Unicode Consortium does not encourage the use of CESU-8 -CESU-8 { IANA* } +CESU-8 { IANA* } ibm-9400 { IBM* } # Standard iso-8859-1, which does not have the Euro update. # See iso-8859-15 (latin9) for the Euro update @@ -243,7 +289,7 @@ ibm-367_P100-1995 { UTR22* } ibm-367 { IBM* } IBM367 { IANA* } # This is AS # Central Europe ibm-912_P100-1995 { UTR22* } ibm-912 { IBM* JAVA } - iso-8859-2 { MIME* IANA JAVA* WINDOWS } + ISO-8859-2 { MIME* IANA JAVA* WINDOWS } ISO_8859-2:1987 { IANA* WINDOWS JAVA } latin2 { IANA WINDOWS JAVA } csISOLatin2 { IANA WINDOWS JAVA } @@ -257,7 +303,7 @@ ibm-912_P100-1995 { UTR22* } # Maltese Esperanto ibm-913_P100-2000 { UTR22* } ibm-913 { IBM* JAVA } - iso-8859-3 { MIME* IANA WINDOWS JAVA* } + ISO-8859-3 { MIME* IANA WINDOWS JAVA* } ISO_8859-3:1988 { IANA* WINDOWS JAVA } latin3 { IANA JAVA WINDOWS } csISOLatin3 { IANA WINDOWS } @@ -271,7 +317,7 @@ ibm-913_P100-2000 { UTR22* } # Baltic ibm-914_P100-1995 { UTR22* } ibm-914 { IBM* JAVA } - iso-8859-4 { MIME* IANA WINDOWS JAVA* } + ISO-8859-4 { MIME* IANA WINDOWS JAVA* } latin4 { IANA WINDOWS JAVA } csISOLatin4 { IANA WINDOWS JAVA } iso-ir-110 { IANA WINDOWS JAVA } @@ -285,7 +331,7 @@ ibm-914_P100-1995 { UTR22* } # Cyrillic ibm-915_P100-1995 { UTR22* } ibm-915 { IBM* JAVA } - iso-8859-5 { MIME* IANA WINDOWS JAVA* } + ISO-8859-5 { MIME* IANA WINDOWS JAVA* } cyrillic { IANA WINDOWS JAVA } csISOLatinCyrillic { IANA WINDOWS JAVA } iso-ir-144 { IANA WINDOWS JAVA } @@ -302,7 +348,7 @@ ibm-915_P100-1995 { UTR22* } # -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* } + ISO-8859-6 { MIME* IANA WINDOWS JAVA* } arabic { IANA WINDOWS JAVA } csISOLatinArabic { IANA WINDOWS JAVA } iso-ir-127 { IANA WINDOWS JAVA } @@ -316,21 +362,34 @@ ibm-1089_P100-1995 { UTR22* } 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. +# ISO Greek (with euro update). This is really ISO_8859-7:2003 +ibm-9005_X100-2005 { 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 } + windows-28597 { WINDOWS* } + # ISO Greek (w/o euro update) +# JDK 1.5 has these aliases. ibm-813_P100-1995 { UTR22* } ibm-813 { IBM* JAVA } - iso-8859-7 { MIME* IANA WINDOWS JAVA* } - greek { IANA WINDOWS JAVA } - greek8 { IANA WINDOWS JAVA } - ELOT_928 { IANA WINDOWS JAVA } - ECMA-118 { IANA WINDOWS JAVA } - csISOLatinGreek { IANA WINDOWS JAVA } - iso-ir-126 { IANA WINDOWS JAVA } - ISO_8859-7:1987 { IANA* WINDOWS 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 } cp813 { JAVA } 813 { JAVA } - windows-28597 { WINDOWS* } # hebrew # ISO_8859-8-E and ISO_8859-8-I are similar to this charset, but BiDi is done differently @@ -339,7 +398,7 @@ ibm-813_P100-1995 { UTR22* } # -E requires the client to handle the ISO 6429 bidirectional controls ibm-916_P100-1995 { UTR22* } ibm-916 { IBM* JAVA } - iso-8859-8 { MIME* IANA WINDOWS JAVA* } + ISO-8859-8 { MIME* IANA WINDOWS JAVA* } hebrew { IANA WINDOWS JAVA } csISOLatinHebrew { IANA WINDOWS JAVA } iso-ir-138 { IANA WINDOWS JAVA } @@ -354,7 +413,7 @@ ibm-916_P100-1995 { UTR22* } # Turkish ibm-920_P100-1995 { UTR22* } ibm-920 { IBM* JAVA } - iso-8859-9 { MIME* IANA WINDOWS JAVA* } + ISO-8859-9 { MIME* IANA WINDOWS JAVA* } latin5 { IANA WINDOWS JAVA } csISOLatin5 { IANA JAVA } iso-ir-148 { IANA WINDOWS JAVA } @@ -366,18 +425,40 @@ ibm-920_P100-1995 { UTR22* } windows-28599 { WINDOWS* } ECMA-128 # IANA doesn't have this alias 6/24/2002 +# 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 } + +# 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. + # iso-8859-13, PC Baltic (w/o euro update) ibm-921_P100-1995 { UTR22* } ibm-921 { IBM* } - iso-8859-13 { IANA* MIME* JAVA* } + ISO-8859-13 { IANA* MIME* JAVA* } 8859_13 { JAVA } cp921 921 +# 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 } + # Latin 9 ibm-923_P100-1998 { UTR22* } ibm-923 { IBM* JAVA } - iso-8859-15 { IANA* MIME* WINDOWS JAVA* } + ISO-8859-15 { IANA* MIME* WINDOWS JAVA* } Latin-9 { IANA WINDOWS } l9 { WINDOWS } 8859_15 { JAVA } @@ -439,6 +520,7 @@ ibm-33722_P12A-1999 { UTR22* } X-EUC-JP { WINDOWS JAVA } # Japan EUC. x-euc-jp is a MIME name eucjis { JAVA } windows-51932 { WINDOWS* } + ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged. ibm-33722_VPUA IBM-eucJP ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping @@ -473,31 +555,33 @@ macos-2566-10.2 { UTR22* } # This uses supplementary characters. ibm-1375_P100-2003 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 w/ HKSCS extensions ibm-1375 { IBM* } Big5-HKSCS + MS950_HKSCS { JAVA* } + hkbig5 # from HP-UX 11i, which can't handle supplementary characters. # windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not. # windows-950_hkscs ibm-1386_P100-2002 { UTR22* } - ibm-1386 { IBM* JAVA } - cp1386 { JAVA* } + ibm-1386 { IBM* } + cp1386 windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage. ibm-1386_VSUB_VPUA - # zh_cn windows-936-2000 { UTR22* } - GBK { IANA* WINDOWS } - CP936 { IANA } - MS936 { IANA } - windows-936 { IANA WINDOWS* } + GBK { IANA* 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 } +# Java has two different tables for ibm-1383 and gb2312. We pick closest set for tagging. ibm-1383_P110-1999 { UTR22* } # China EUC. - ibm-1383 { IBM* } + ibm-1383 { IBM* JAVA } GB2312 { IANA* MIME* } csGB2312 { IANA } + cp1383 { JAVA* } + 1383 { JAVA } EUC-CN # According to other platforms, windows-20936 looks more like euc-cn. x-euc-cn is also a MIME name ibm-eucCN hp15CN # From HP-UX? - cp1383 - 1383 ibm-1383_VPUA # gb # This is not an IANA name. gb in IANA means Great Britain. @@ -552,15 +636,18 @@ ibm-949_P11A-1999 { UTR22* } # # ibm-970 is almost a subset of ibm-1363. # Java, Solaris and AIX use euc-kr to also mean ksc5601. +# Java has both ibm-970 and EUC-KR as separate converters. ibm-970_P110-1995 { UTR22* } ibm-970 { IBM* JAVA } - EUC-KR { IANA* MIME* WINDOWS JAVA* } + EUC-KR { IANA* MIME* WINDOWS JAVA } KS_C_5601-1987 { JAVA } windows-51949 { WINDOWS* } csEUCKR { IANA WINDOWS } # x-euc-kr is also a MIME name ibm-eucKR { JAVA } KSC_5601 { JAVA } # Needed by iso-2022 5601 { JAVA } + cp970 { JAVA* } + 970 { JAVA } ibm-970_VPUA # ibm-971 is almost the set of DBCS mappings of ibm-970 @@ -598,33 +685,35 @@ windows-949-2000 { UTR22* } iso-ir-149 { WINDOWS } ms949 { JAVA } -ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) - ibm-1162 { IBM* } +windows-874-2000 { UTR22* } # Thai (w/ euro update) + TIS-620 { WINDOWS } + windows-874 { JAVA* WINDOWS* } + MS874 { JAVA } + # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. ibm-874_P100-1995 { UTR22* } # Thai PC (w/o euro update). ibm-874 { IBM* JAVA } ibm-9066 { IBM } # Yes ibm-874 == ibm-9066. ibm-1161 has the euro update. cp874 { JAVA* } - TIS-620 { IANA* JAVA } # This actually separate from ibm-874, which is similar to this table - tis620.2533 { JAVA } # This actually separate from ibm-874, which is similar to this table + TIS-620 { IANA* JAVA } # This is actually separate from ibm-874, which is similar to this table + tis620.2533 { JAVA } # This is actually separate from ibm-874, which is similar to this table eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620 - cp9066 -windows-874-2000 { UTR22* } # Thai (w/ euro update) - TIS-620 { WINDOWS } - windows-874 { JAVA* WINDOWS* } - MS874 { JAVA } - # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. +ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) + ibm-1162 { IBM* } # 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-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { 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* WINDOWS JAVA } cp850 { IANA MIME* WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1 ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro) ibm-852_P100-1995 { UTR22* } ibm-852 { IBM* } IBM852 { IANA* WINDOWS JAVA } cp852 { IANA WINDOWS JAVA* } 852 { IANA WINDOWS JAVA } csPCp852 { IANA JAVA } windows-852 { WINDOWS* } # PC latin2 (w/o euro update) -ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* } cp855 { IANA } 855 { IANA } csIBM855 { IANA } csPCp855 # PC cyrillic (w/o euro update) -ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* JAVA } cp856 { MIME* JAVA* } 856 { JAVA } # PC Hebrew (old) +ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* JAVA } cp855 { IANA JAVA* } 855 { IANA } csIBM855 { IANA } csPCp855 { JAVA } # PC cyrillic (w/o euro update) +ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { MIME* JAVA* } 856 { JAVA } # PC Hebrew (old) ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* WINDOWS JAVA } cp857 { IANA MIME* JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update) -ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* JAVA* } IBM00858 { IANA* } CCSID00858 { IANA } CP00858 { IANA } PC-Multilingual-850+euro { IANA } cp858 { MIME* } # PC latin1 with Euro +ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME* JAVA* } # PC latin1 with Euro ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* JAVA } cp860 { IANA MIME* JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* WINDOWS JAVA } cp861 { IANA MIME* JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* JAVA } cp862 { IANA MIME* JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew (w/o euro update) @@ -632,27 +721,28 @@ ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* JAVA } cp863 { I ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* JAVA } cp864 { IANA MIME* JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update) ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* JAVA } cp865 { IANA MIME* JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* 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* } cp867 # PC Hebrew (w/ euro update) Updated version of ibm-862 +ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } # PC Hebrew (w/ euro update) Updated version of ibm-862 ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* JAVA } CP868 { IANA MIME* JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* 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* JAVA* } koi8 { JAVA } csKOI8R { IANA JAVA } cp878 # Russian internet +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 ibm-901_P100-1999 { UTR22* } ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921 ibm-902_P100-1999 { UTR22* } ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922 -ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* JAVA } cp922 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update) +ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update) +ibm-1168_P100-2002 { UTR22* } ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } koi8-ru { WINDOWS } # Ukrainian KOI8. koi8-ru is an unusual alias, but Microsoft states that it is an alias. ibm-4909_P100-1999 { UTR22* } ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813 # The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows. -# cp is used to denote IBM in Java, and that is why we don't do that anymore. +# 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 } # Windows Latin2 (w/ euro update) -ibm-5347_P100-1998 { UTR22* } ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS* } cp1251 { WINDOWS } # Windows Cyrillic (w/ euro update) -ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS* } cp1252 { WINDOWS } # Windows Latin1 (w/ euro update) -ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { WINDOWS } # Windows Greek (w/ euro update) -ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { WINDOWS } # Windows Turkish (w/ euro update) -ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { WINDOWS } # Windows Hebrew (w/ euro update) -windows-1256-2000 { UTR22* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS } # Windows Arabic (w/ euro update) -ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { WINDOWS } # Windows Baltic (w/ euro update) -ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { WINDOWS } # Windows Vietnamese (w/ euro update) +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) +ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update) +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 } # 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) # These tables are out of date, and most don't have the Euro # Leave the windows- variants untagged. They are alternate tables of the newer ones above. @@ -670,23 +760,21 @@ 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* } # Apple latin 1 -macos-6-10.2 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr # Apple Greek -macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } maccy # Apple Cyrillic +macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr # Apple Greek +macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } mac-cyrillic maccy # Apple Cyrillic macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce # Apple Central Europe macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr # Apple Turkish ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } # 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-1277_P100-1995 { UTR22* } ibm-1277 { IBM* } Adobe-Latin1-Encoding -ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* JAVA } cp1006 { JAVA* } 1006 { JAVA } # Urdu -ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* JAVA } cp1098 { JAVA* } 1098 { JAVA } # PC Farsi +ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } # Urdu +ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } # PC Farsi ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } # ISO Cyrillic Ukraine -ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* JAVA } cp1125 { JAVA* } # Cyrillic Ukraine PC +ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* } cp1125 # Cyrillic Ukraine PC ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } # ISO Vietnamese -ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* JAVA } cp1131 { JAVA* } # Cyrillic Belarus PC +ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } # ISO Lao -ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } # S-Ch PC Data mixed (IBM GB) # Partially algorithmic converters @@ -695,18 +783,18 @@ ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { J # 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 { MIME* } 2022 cp2022 +# ISO_2022 ISO-2022 -ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { JAVA } -ISO_2022,locale=ja,version=1 ISO-2022-JP-1 JIS JIS_Encoding { IANA* } -ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 -ISO_2022,locale=ja,version=3 JIS7 csJISEncoding +ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } +ISO_2022,locale=ja,version=1 ISO-2022-JP-1 JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS +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 -ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* } csISO2022KR # This uses ibm-949 -ISO_2022,locale=ko,version=1 ibm-25546 -ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* MIME* } # csISO2022CN -ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* MIME* } -HZ HZ-GB-2312 { IANA* MIME* } +ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949 +ISO_2022,locale=ko,version=1 ibm-25546 { IBM* } +ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } +ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* } +HZ HZ-GB-2312 { IANA* } # Part of iso-2022 ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } @@ -723,113 +811,115 @@ ISCII,version=7 x-iscii-ka { WINDOWS } windows-57008 { WINDOWS* } iscii- ISCII,version=8 x-iscii-ma { WINDOWS } windows-57009 { WINDOWS* } iscii-mlm # Lotus specific -LMBCS-1 lmbcs -LMBCS-2 -LMBCS-3 -LMBCS-4 -LMBCS-5 -LMBCS-6 -LMBCS-8 -LMBCS-11 -LMBCS-16 -LMBCS-17 -LMBCS-18 -LMBCS-19 +LMBCS-1 lmbcs ibm-65025 { IBM* } + +# These Lotus specific converters still work, but they aren't advertised in this alias table. +# These are almost never used outside of Lotus software, and they take a lot of time when creating the available converter list. +#LMBCS-2 +#LMBCS-3 +#LMBCS-4 +#LMBCS-5 +#LMBCS-6 +#LMBCS-8 +#LMBCS-11 +#LMBCS-16 +#LMBCS-17 +#LMBCS-18 +#LMBCS-19 # EBCDIC codepages according to the CDRA # without Euro ibm-37_P100-1995 { UTR22* } # EBCDIC US ibm-37 { IBM* } - IBM037 { IANA* } - ibm-037 { JAVA } - ebcdic-cp-us { IANA } - ebcdic-cp-ca { IANA } - ebcdic-cp-wt { IANA } - ebcdic-cp-nl { IANA } - csIBM037 { IANA } + IBM037 { IANA* JAVA } + ibm-037 # { JAVA } + ebcdic-cp-us { IANA JAVA } + ebcdic-cp-ca { IANA JAVA } + ebcdic-cp-wt { IANA JAVA } + ebcdic-cp-nl { IANA JAVA } + csIBM037 { IANA JAVA } cp037 { JAVA* } 037 { JAVA } - cpibm37 + cpibm37 { JAVA } cp37 -ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de cpibm273 273 # EBCDIC Germanay, Austria -ibm-277_P100-1995 { UTR22* } ibm-277 { IBM* } IBM277 { IANA* JAVA } cp277 { JAVA* } EBCDIC-CP-DK { IANA } EBCDIC-CP-NO { IANA } csIBM277 { IANA } ebcdic-dk cpibm277 277 # EBCDIC Denmark -ibm-278_P100-1995 { UTR22* } ibm-278 { IBM* } IBM278 { IANA* JAVA } cp278 { JAVA* } ebcdic-cp-fi { IANA } ebcdic-cp-se { IANA } csIBM278 { IANA } ebcdic-sv cpibm278 278 # EBCDIC Sweden -ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } cpibm280 280 # EBCDIC Italy -ibm-284_P100-1995 { UTR22* } ibm-284 { IBM* } IBM284 { IANA* JAVA } CP284 { IANA JAVA* } ebcdic-cp-es { IANA } csIBM284 { IANA } cpibm284 284 # EBCDIC Spain -ibm-285_P100-1995 { UTR22* } ibm-285 { IBM* } IBM285 { IANA* JAVA } CP285 { IANA JAVA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } ebcdic-gb cpibm285 285 # EBCDIC UK Ireland +ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* } IBM273 { IANA* JAVA } CP273 { IANA JAVA* } csIBM273 { IANA } ebcdic-de 273 { JAVA } # EBCDIC Germanay, Austria +ibm-277_P100-1995 { UTR22* } ibm-277 { IBM* } IBM277 { IANA* JAVA } cp277 { JAVA* } EBCDIC-CP-DK { IANA } EBCDIC-CP-NO { IANA } csIBM277 { IANA } ebcdic-dk 277 { JAVA } # EBCDIC Denmark +ibm-278_P100-1995 { UTR22* } ibm-278 { IBM* } IBM278 { IANA* JAVA } cp278 { JAVA* } ebcdic-cp-fi { IANA } ebcdic-cp-se { IANA } csIBM278 { IANA } ebcdic-sv { JAVA } 278 { JAVA } # EBCDIC Sweden +ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* JAVA } CP280 { IANA JAVA* } ebcdic-cp-it { IANA } csIBM280 { IANA } 280 { JAVA } # EBCDIC Italy +ibm-284_P100-1995 { UTR22* } ibm-284 { IBM* } IBM284 { IANA* JAVA } CP284 { IANA JAVA* } ebcdic-cp-es { IANA } csIBM284 { IANA } cpibm284 { JAVA } 284 { JAVA } # EBCDIC Spain +ibm-285_P100-1995 { UTR22* } ibm-285 { IBM* } IBM285 { IANA* JAVA } CP285 { IANA JAVA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } cpibm285 { JAVA } ebcdic-gb { JAVA } 285 { JAVA } # EBCDIC UK Ireland ibm-290_P100-1995 { UTR22* } ibm-290 { IBM* } IBM290 { IANA* } cp290 { IANA } EBCDIC-JP-kana { IANA } csIBM290 { IANA } # host SBCS (Katakana) -ibm-297_P100-1995 { UTR22* } ibm-297 { IBM* } IBM297 { IANA* JAVA } cp297 { IANA JAVA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cpibm297 297 # EBCDIC France -ibm-420_X120-1999 { UTR22* } ibm-420 { IBM* } IBM420 { IANA* JAVA } cp420 { IANA JAVA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } 420 # EBCDIC Arabic (all presentation shapes) -ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424 # EBCDIC Hebrew -ibm-500_P100-1995 { UTR22* } ibm-500 { IBM* } IBM500 { IANA* JAVA } CP500 { IANA JAVA* } ebcdic-cp-be { IANA } csIBM500 { IANA } ebcdic-cp-ch { IANA } cpibm500 500 # EBCDIC International Latin1 +ibm-297_P100-1995 { UTR22* } ibm-297 { IBM* } IBM297 { IANA* JAVA } cp297 { IANA JAVA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cpibm297 { JAVA } 297 { JAVA } # EBCDIC France +ibm-420_X120-1999 { UTR22* } ibm-420 { IBM* } IBM420 { IANA* JAVA } cp420 { IANA JAVA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } 420 { JAVA } # EBCDIC Arabic (all presentation shapes) +ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* JAVA } cp424 { IANA JAVA* } ebcdic-cp-he { IANA } csIBM424 { IANA } 424 { JAVA } # EBCDIC Hebrew +ibm-500_P100-1995 { UTR22* } ibm-500 { IBM* } IBM500 { IANA* JAVA } CP500 { IANA JAVA* } ebcdic-cp-be { IANA } csIBM500 { IANA } ebcdic-cp-ch { IANA } 500 # EBCDIC International Latin1 ibm-803_P100-1999 { UTR22* } ibm-803 { IBM* } cp803 # Old EBCDIC Hebrew -ibm-838_P100-1995 { UTR22* } ibm-838 { IBM* JAVA } IBM-Thai { IANA* } csIBMThai { IANA } cp838 { JAVA* } 838 { JAVA } ibm-9030 { IBM } # EBCDIC Thai. Yes ibm-9030 is an alias. +ibm-838_P100-1995 { UTR22* } ibm-838 { IBM* } IBM838 { JAVA } IBM-Thai { IANA* JAVA } csIBMThai { IANA } cp838 { JAVA* } 838 { JAVA } ibm-9030 { IBM } # EBCDIC Thai. Yes ibm-9030 is an alias. ibm-870_P100-1995 { UTR22* } ibm-870 { IBM* } IBM870 { IANA* JAVA } CP870 { IANA JAVA* } ebcdic-cp-roece { IANA } ebcdic-cp-yu { IANA } csIBM870 { IANA } # EBCDIC Latin 2 -ibm-871_P100-1995 { UTR22* } ibm-871 { IBM* } IBM871 { IANA* } ebcdic-cp-is { IANA } csIBM871 { IANA } CP871 { IANA } ebcdic-is cpibm871 871 # EBCDIC Iceland -ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 # EBCDIC Greek -ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu +ibm-871_P100-1995 { UTR22* } ibm-871 { IBM* } IBM871 { IANA* JAVA } ebcdic-cp-is { IANA JAVA } csIBM871 { IANA JAVA } CP871 { IANA JAVA* } ebcdic-is { JAVA } 871 { JAVA } # EBCDIC Iceland +ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } # EBCDIC Greek +ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed. - ibm-930 { IBM* JAVA } + ibm-930 { IBM* } ibm-5026 { IBM } # Yes this is correct + IBM930 { JAVA } cp930 { JAVA* } - cpibm930 930 { JAVA } -ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } cpibm933 933 { JAVA } # Korea EBCDIC MIXED -ibm-935_P110-1999 { UTR22* } ibm-935 { IBM* JAVA } cp935 { JAVA* } cpibm935 935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China. -ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } cpibm937 937 { JAVA } # Taiwan EBCDIC MIXED +ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } # Korea EBCDIC MIXED +ibm-935_P110-1999 { UTR22* } ibm-935 { IBM* JAVA } cp935 { JAVA* } 935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China. +ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } # Taiwan EBCDIC MIXED ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed. - ibm-939 { IBM* JAVA } + ibm-939 { IBM* } ibm-931 { IBM } # Yes this is correct ibm-5035 { IBM } # Yes this is also correct + IBM939 { JAVA } cp939 { JAVA* } 939 { JAVA } -ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } # EBCDIC Cyrillic -ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* JAVA } IBM1026 { IANA* } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey -ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* } cpibm1047 # EBCDIC Open systems Latin1 -ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } # EBCDIC Farsi -ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } # EBCDIC Baltic -ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } # EBCDIC Estonia -ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } cpibm1123 # EBCDIC Cyrillic Ukraine +ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } # EBCDIC Cyrillic +ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey +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 } # EBCDIC Farsi +ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } # EBCDIC Baltic +ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } # EBCDIC Estonia +ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } # EBCDIC Cyrillic Ukraine ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } # EBCDIC Lao +ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set) +ibm-4517_P100-2005 { UTR22* } ibm-4517 { IBM* } # EBCDIC Arabic. Update of ibm-421 # with Euro -ibm-1140_P100-1997 { UTR22* } ibm-1140 { IBM* JAVA } IBM01140 { IANA* } CCSID01140 { IANA } CP01140 { IANA } cp1140 { JAVA* } cpibm1140 ebcdic-us-37+euro { IANA } # EBCDIC US -ibm-1141_P100-1997 { UTR22* } ibm-1141 { IBM* JAVA } IBM01141 { IANA* } CCSID01141 { IANA } CP01141 { IANA } cp1141 { JAVA* } cpibm1141 ebcdic-de-273+euro { IANA } # EBCDIC Germanay, Austria -ibm-1142_P100-1997 { UTR22* } ibm-1142 { IBM* JAVA } IBM01142 { IANA* } CCSID01142 { IANA } CP01142 { IANA } cp1142 { JAVA* } cpibm1142 ebcdic-dk-277+euro { IANA } ebcdic-no-277+euro { IANA } # EBCDIC Denmark -ibm-1143_P100-1997 { UTR22* } ibm-1143 { IBM* JAVA } IBM01143 { IANA* } CCSID01143 { IANA } CP01143 { IANA } cp1143 { JAVA* } cpibm1143 ebcdic-fi-278+euro { IANA } ebcdic-se-278+euro { IANA } # EBCDIC Sweden -ibm-1144_P100-1997 { UTR22* } ibm-1144 { IBM* JAVA } IBM01144 { IANA* } CCSID01144 { IANA } CP01144 { IANA } cp1144 { JAVA* } cpibm1144 ebcdic-it-280+euro { IANA } # EBCDIC Italy -ibm-1145_P100-1997 { UTR22* } ibm-1145 { IBM* JAVA } IBM01145 { IANA* } CCSID01145 { IANA } CP01145 { IANA } cp1145 { JAVA* } cpibm1145 ebcdic-es-284+euro { IANA } # EBCDIC Spain -ibm-1146_P100-1997 { UTR22* } ibm-1146 { IBM* JAVA } IBM01146 { IANA* } CCSID01146 { IANA } CP01146 { IANA } cp1146 { JAVA* } cpibm1146 ebcdic-gb-285+euro { IANA } # EBCDIC UK Ireland -ibm-1147_P100-1997 { UTR22* } ibm-1147 { IBM* JAVA } IBM01147 { IANA* } CCSID01147 { IANA } CP01147 { IANA } cp1147 { JAVA* } cpibm1147 ebcdic-fr-297+euro { IANA } # EBCDIC France -ibm-1148_P100-1997 { UTR22* } ibm-1148 { IBM* JAVA } IBM01148 { IANA* } CCSID01148 { IANA } CP01148 { IANA } cp1148 { JAVA* } cpibm1148 ebcdic-international-500+euro { IANA } # EBCDIC International Latin1 -ibm-1149_P100-1997 { UTR22* } ibm-1149 { IBM* JAVA } IBM01149 { IANA* } CCSID01149 { IANA } CP01149 { IANA } cp1149 { JAVA* } cpibm1149 ebcdic-is-871+euro { IANA } # EBCDIC Iceland -ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } cpibm1153 # EBCDIC latin 2 -ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } cpibm1154 # EBCDIC Cyrillic Multilingual -ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } cpibm1155 # EBCDIC Turkey -ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } cpibm1156 # EBCDIC Baltic Multilingual -ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } cpibm1157 # EBCDIC Estonia -ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } cpibm1158 # EBCDIC Cyrillic Ukraine -ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } cpibm1160 # EBCDIC Thailand -ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } cpibm1164 # EBCDIC Viet Nam -ibm-1364_P110-1997 { UTR22* } ibm-1364 { IBM* } cp1364 # Korean Host Mixed -ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } cpibm1371 # Taiwan EBCDIC MIXED -ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. -ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } cpibm1390 # Japan EBCDIC MIXED (JIS X 0213) -ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } # Host MBCS (Latin-Kanji) (JIS X 0213) -ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213) -ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } cpibm4899 # Old EBCDIC Hebrew -ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } cpibm4971 # EBCDIC Greek -ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } cpibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update) -ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } cpibm16804 ebcdic-ar # EBCDIC Arabic - - -# TODO: Consider removing the mappings in this section -ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set) -ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027 -ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290 +ibm-1140_P100-1997 { UTR22* } ibm-1140 { IBM* } IBM01140 { IANA* JAVA } CCSID01140 { IANA JAVA } CP01140 { IANA JAVA } cp1140 { JAVA* } ebcdic-us-37+euro { IANA } # EBCDIC US +ibm-1141_P100-1997 { UTR22* } ibm-1141 { IBM* } IBM01141 { IANA* JAVA } CCSID01141 { IANA JAVA } CP01141 { IANA JAVA } cp1141 { JAVA* } ebcdic-de-273+euro { IANA } # EBCDIC Germanay, Austria +ibm-1142_P100-1997 { UTR22* } ibm-1142 { IBM* } IBM01142 { IANA* JAVA } CCSID01142 { IANA JAVA } CP01142 { IANA JAVA } cp1142 { JAVA* } ebcdic-dk-277+euro { IANA } ebcdic-no-277+euro { IANA } # EBCDIC Denmark +ibm-1143_P100-1997 { UTR22* } ibm-1143 { IBM* } IBM01143 { IANA* JAVA } CCSID01143 { IANA JAVA } CP01143 { IANA JAVA } cp1143 { JAVA* } ebcdic-fi-278+euro { IANA } ebcdic-se-278+euro { IANA } # EBCDIC Sweden +ibm-1144_P100-1997 { UTR22* } ibm-1144 { IBM* } IBM01144 { IANA* JAVA } CCSID01144 { IANA JAVA } CP01144 { IANA JAVA } cp1144 { JAVA* } ebcdic-it-280+euro { IANA } # EBCDIC Italy +ibm-1145_P100-1997 { UTR22* } ibm-1145 { IBM* } IBM01145 { IANA* JAVA } CCSID01145 { IANA JAVA } CP01145 { IANA JAVA } cp1145 { JAVA* } ebcdic-es-284+euro { IANA } # EBCDIC Spain +ibm-1146_P100-1997 { UTR22* } ibm-1146 { IBM* } IBM01146 { IANA* JAVA } CCSID01146 { IANA JAVA } CP01146 { IANA JAVA } cp1146 { JAVA* } ebcdic-gb-285+euro { IANA } # EBCDIC UK Ireland +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* } # 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 +ibm-1157_P100-1999 { UTR22* } ibm-1157 { IBM* } # EBCDIC Estonia +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_P110-1997 { UTR22* } ibm-1364 { IBM* } # Korean Host Mixed +ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } # Taiwan EBCDIC MIXED +ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias. +ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } # Japan EBCDIC MIXED (JIS X 0213) +ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } # 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. +ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213) +ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803 +ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971 +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 # EBCDIC codepages for S/390, with LF and NL codes swapped @@ -881,6 +971,8 @@ ibm-16804_X110-1999,swaplfnl ibm-16804-s390 ebcdic-xml-us +# TODO Consider removing this table +ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067 # These were removed due to age, and they are rarely used. @@ -904,4 +996,5 @@ ebcdic-xml-us #ibm-1159_P100-1999 { UTR22* } ibm-1159 { IBM* } # SBCS T-Ch Host. Euro update of ibm-28709. This is used in combination with another CCSID mapping. #ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371. +#ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } # S-Ch PC Data mixed (IBM GB)