# ******************************************************************************* # * # * Copyright (C) 1995-2002, International Business Machines # * Corporation and others. All Rights Reserved. # * # ******************************************************************************* # IMPORTANT NOTE # # This file is not read directly by ICU. If you change it, you need to # run gencnval, and eventually pkgdata to update the representation that # ICU uses for aliases. # Please be friendly to the rest of use that edit this table by # keeping this table free of tabs. # This is an alias file used by the character set converter. # # Format: # # Actual file name || Algorithm name alias1 alias2 ... # # except for column 1 (file names) case insensitive. Names are separated # by whitespace. # # All names can be tagged by including a space-separated list of tags in # curly braces, as in ISO_8859-1:1987{IANA*} iso-8859-1 { MIME* } or # some-charset{MIME* IANA*}. The order of tags does not matter, and # whitespace is allowed between the tagged name and the tags list. # # The tags can be used to get standard names using ucnv_getStandardName(). # # Here is a list of tags used in this file: # # IANA The IANA charset name, as documented in RFC 1700. # MIME The MIME charset name, used for content type tagging. # # The * after the standard tag denotes that the previous alias is the # preferred (default) charset name for that standard. There can only # be one of these default charset names per converter. # The world is getting more complicated... # Supporting XML parsers, HTML, MIME, and similar applications # that mark encodings with unique charset names, we are forced to # make this table much more static than before. # It means that a new encoding, one that differs from an # old one by changing a code point, e.g., to the Euro sign, # must not get an old alias, because it would mean that # old files with this alias would be interpreted differently. # If an encoding gets updated by assigning characters to previously # unassigned code points, then a new name is not necessary. # Also, some codepages map unassigned codepage byte values # to the same numbers in Unicode for roundtripping. It may be # industry practice to keep the encoding name in such a case, too # (example: Windows codepages). # Especially, the aliases listed in the list of character sets # that is maintained by the IANA (http://www.iana.org/) must # not be changed to mean encodings different from what this # list shows. # Currently, the IANA list is at # http://www.iana.org/assignments/character-sets # Name matching is case-insensitive. Also, dashes '-', underscores '_' # and spaces ' ' are ignored in names (thus cs-iso-latin-1 and csisolatin1 # are the same). # However, the names in the left column are directly file names # or names of algorithmic converters, and their case must not # be changed - or else code and/or file names must also be changed. # This is the list of supported standard tags. # When multiple converters have the same alias under different standards, # the standard nearest to the top of this list with that alias will # be the first converter that will be opened. # # The general ordering is from specific and frequently used to more general # or rarely used. { 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 the number. 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 IANA # Source: http://www.iana.org/assignments/character-sets MIME # Source: http://www.iana.org/assignments/character-sets # 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. } # Fully algorithmic converters UTF-8 { IANA* MIME* JAVA* } ibm-1208 { IBM* } ibm-1209 { IBM } ibm-5304 { IBM } ibm-5305 { IBM } cp1208 cp65001 # The ICU 2.2 UTF-16/32 converters detect and write a BOM. UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA } csUnicode ucs-2 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 } UTF16_BigEndian cp1201 UTF-16LE { IANA* MIME* JAVA* } x-utf-16le { JAVA } ibm-1202 { IBM* } ibm-13490 { IBM } ibm-17586 { IBM } UTF16_LittleEndian cp1200 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* } # ICU-specific names for special uses UTF16_PlatformEndian UTF16_OppositeEndian UTF32_PlatformEndian UTF32_OppositeEndian # On UTF-7: # RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII # characters directly or in base64. Especially, the characters in set O # as defined in the RFC (!"#$%&*;<=>@[]^_`{|}) may be encoded directly but are not # allowed in, e.g., email headers. # By default, the ICU UTF-7 converter encodes set O directly. # By choosing the option "version=1", set O will be escaped instead. # For example: # utf7Converter=ucnv_open("UTF-7,version=1"); # # For details about email headers see RFC 2047. UTF-7 { IANA* MIME* } cp65000 # 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: # # RFC 2060: INTERNET MESSAGE ACCESS PROTOCOL - VERSION 4rev1 # (http://www.ietf.org/rfc/rfc2060.txt) # Section 5.1.3. Mailbox International Naming Convention IMAP-mailbox-name SCSU { IANA* } BOCU-1 { IANA* } csBOCU-1 { IANA } # 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* } # 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 } # 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. 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 } 20127 { WINDOWS* } # IBM367 { IANA WINDOWS } # This isn't the default ibm-367. # Partially algorithmic converters ISO_2022 ISO-2022 { MIME* } 2022 cp2022 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=4 JIS8 ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* } csISO2022KR 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* } ISCII,version=0 iscii-dev x-iscii-de ISCII,version=1 iscii-bng x-iscii-as x-iscii-be ISCII,version=2 iscii-gur x-iscii-pa ISCII,version=3 iscii-guj x-iscii-gu ISCII,version=4 iscii-ori x-iscii-or ISCII,version=5 iscii-tml x-iscii-ta ISCII,version=6 iscii-tlg x-iscii-te ISCII,version=7 iscii-knd x-iscii-ka ISCII,version=8 iscii-mlm x-iscii-ma # GB 18030 is partly algorithmic, using the MBCS converter gb18030 { IANA* } ibm-1392 # 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 # Table-based interchange codepages ibm-367_P100-1995 { UTR22* } ibm-367 { IBM* } IBM367 { IANA* } # This is ASCII, but it has fallbacks # Central Europe 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 } 28592 { WINDOWS* } # Maltese Esperanto 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 } 28593 { WINDOWS* } # Baltic 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 } 28594 { WINDOWS* } # Cyrillic 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 } 28595 { WINDOWS* } # 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 } 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. # ISO Greek (w/o euro update) 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 } 8859_7 { JAVA } cp813 { JAVA } 813 { JAVA } 28597 { WINDOWS* } # 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 ibm-916 { IBM* JAVA } 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 } cp916 { JAVA } 916 { JAVA } 28598 { WINDOWS* } # Turkish ibm-920 { IBM* JAVA } iso-8859-9 { MIME* IANA WINDOWS JAVA* } latin5 { IANA WINDOWS JAVA } csISOLatin5 { IANA JAVA } iso-ir-148 { IANA WINDOWS JAVA } ISO_8859-9:1989 { IANA* WINDOWS } l5 { IANA WINDOWS JAVA } 8859_9 { JAVA } cp920 { JAVA } 920 { JAVA } 28599 { WINDOWS* } ECMA-128 # IANA doesn't have this alias 6/24/2002 # iso-8859-13, PC Baltic (w/o euro update) ibm-921 { IBM* } iso-8859-13 { IANA* MIME* JAVA* } 8859_13 { JAVA } cp921 921 # Latin 9 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 } 28605 { WINDOWS* } # CJK encodings ibm-942_P12A-2000 { UTR22* } # ibm-942_P120 is a rarely used alternate mapping (sjis78 is already old) ibm-942 { IBM* } ibm-932 { IBM } shift_jis78 sjis78 ibm-942_VSUB_VPUA ibm-932_VSUB_VPUA # Is this "JIS_C6226-1978"? ibm-943_P130-2000 { UTR22* } ibm-943 { IBM* JAVA } Shift_JIS # Leave untagged because this isn't the default cp943 { JAVA* } # This is slightly different, but the backslash mapping is the same. 943 { JAVA } ibm-943_VASCII_VSUB_VPUA # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe ibm-943_P14A-2000 { UTR22* } 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 } 932 { WINDOWS* } cp932 { WINDOWS } # This isn't really windows, but it's used by ICU for Windows. cp943c { JAVA* } # This is slightly different, but the backslash mapping is the same. ms932 pck # Probably SOLARIS sjis # This might be for ibm-1351 ibm-943_VSUB_VPUA # cp943 # This isn't Windows, and no one else uses it. # 943 # This isn't Windows, and no one else uses it. # Iana says that Windows-31J is an extension to csshiftjis ibm-932 ibm-33722_P120-2000 { UTR22* } # Japan EUC with \ <-> Yen mapping ibm-33722 { IBM* JAVA } ibm-5050 { IBM } # Yes this is correct cp33722 { JAVA* } 33722 { JAVA } ibm-33722_VASCII_VPUA # ibm-954 seems to be a superset of ibm-33722 ibm-33722_P12A-2000 { 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 JAVA* } Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS JAVA } csEUCPkdFmtJapanese { IANA WINDOWS JAVA } X-EUC-JP { WINDOWS JAVA } # Japan EUC. x-euc-jp is a MIME name eucjis { JAVA } 51932 { WINDOWS* } ibm-33722_VPUA IBM-eucJP ibm-1373_P100-2002 { UTR22* } # Taiwan Big-5 (w/ euro update) ibm-1373 { IBM* } Big5 { IANA* MIME* JAVA* } csBig5 { IANA } 950 { WINDOWS* } cp950 { WINDOWS } # This isn't really windows, but it's used by ICU for Windows. x-big5 ibm-1373_VSUB_VPUA ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update) ibm-950 { IBM* JAVA } cp950 { JAVA* } 950 { JAVA } ibm-1386_P100-2002 { UTR22* } ibm-1386 { IBM* JAVA } GBK { IANA* } CP936 { IANA } windows-936 { IANA } MS936 { IANA } cp1386 { JAVA* } 936 { WINDOWS* } cp936 { WINDOWS } # This isn't really windows, but it's used by ICU for Windows. ibm-1386_VSUB_VPUA zh_cn ibm-1383_P110-2000 { UTR22* } ibm-1383 { IBM* } GB_2312-80 { IANA* } chinese { IANA } iso-ir-58 { IANA } csISO58GB231280 { IANA } GB2312 { MIME* } EUC-CN ibm-eucCN gb2312-1980 cp1383 1383 gb # This is not an IANA name. gb in IANA means Great Britain. csGB2312 # China EUC. x-euc-cn is a MIME name ibm-1383_VPUA ibm-5478_P100-1995 { UTR22* } ibm-5478 { IBM* } # This gb_2312_80 DBCS mapping is needed by iso-2022. ibm-964_P110-2000 { UTR22* } # Taiwan EUC. x-euc-tw is a MIME name ibm-964 { IBM* JAVA } EUC-TW ibm-eucTW cns11643 cp964 { JAVA* } 964 { JAVA } ibm-964_VPUA ibm-949_P110-2000 { UTR22* } ibm-949 { IBM* JAVA } cp949 { JAVA* } 949 { JAVA } ibm-949_VASCII_VSUB_VPUA ibm-949_P11A-2000 { UTR22* } ibm-949 # Leave untagged because this isn't the default cp949c { JAVA* } ibm-949_VSUB_VPUA # ibm-970 is a almost a subset of ibm-1363. # Java, Solaris and AIX use euc-kr to also mean ksc5601. ibm-970_P110-2000 { UTR22* } ibm-970 { IBM* } EUC-KR { IANA* MIME* WINDOWS JAVA* } 51949 { WINDOWS* } ibm-eucKR { JAVA } csEUCKR { IANA WINDOWS } # Korean EUC. x-euc-kr is a MIME name ibm-970_VPUA ibm-1363_P110-2000 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping ibm-1363 { IBM* } ibm-1363_VASCII_VSUB_VPUA # 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. # Johab seems to be ksc5601-1992 and windows-1361, which is not this. ibm-1363_P11B-2000 { UTR22* } ibm-1363 # Leave untagged because this isn't the default KS_C_5601-1987 { IANA* WINDOWS JAVA } KS_C_5601-1989 { IANA WINDOWS } KSC_5601 { MIME* IANA WINDOWS } csKSC56011987 { IANA WINDOWS } korean { IANA WINDOWS } iso-ir-149 { IANA WINDOWS } 5601 { JAVA } windows-949 { JAVA* } 949 { WINDOWS* } cp949 { WINDOWS } # This isn't really windows, but it's used by ICU for Windows. cp1363 ksc ibm-1363_VSUB_VPUA # ks_x_1001:1992 # This seems to mean johab # ksc5601-1992 # This seems to mean johab ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update) ibm-1162 { IBM* } TIS-620 { IANA* WINDOWS } 874 { WINDOWS* } cp874 { WINDOWS } # This isn't really windows, but it's used by ICU for Windows. windows-874 { JAVA* WINDOWS } tis620.2533 { JAVA } eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620 # iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match. ibm-874 { IBM* } ibm-9066 { IBM } # Thai PC (w/o euro update). Yes ibm-874 == ibm-9066. ibm-1161 has the euro update. 874 { JAVA } cp874 { JAVA* } # This isn't really windows, but it's used by ICU for Windows. cp9066 # Platform codepages ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } cp437 { IANA WINDOWS JAVA* } 437 { IANA WINDOWS* JAVA } csPC8CodePage437 { IANA JAVA } # PC US ibm-850 { IBM* } IBM850 { IANA* WINDOWS JAVA } cp850 { IANA MIME* WINDOWS JAVA* } 850 { IANA WINDOWS* JAVA } csPC850Multilingual { IANA JAVA } # PC latin1 ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro) ibm-858 { IBM* JAVA* } IBM00858 { IANA* } CCSID00858 { IANA } CP00858 { IANA } PC-Multilingual-850+euro { IANA } cp858 { MIME* } # PC latin1 with Euro ibm-852 { IBM* } IBM852 { IANA* WINDOWS JAVA } cp852 { IANA WINDOWS JAVA* } 852 { IANA WINDOWS* JAVA } csPCp852 { IANA JAVA } # PC latin2 (w/o euro update) ibm-855 { IBM* } IBM855 { IANA* } cp855 { IANA } 855 { IANA } csIBM855 { IANA } csPCp855 # PC cyrillic (w/o euro update) ibm-856 { IBM* JAVA } cp856 { MIME* JAVA* } 856 { JAVA } # PC Hebrew (old) ibm-867 { IBM* } cp867 # PC Hebrew (w/ euro update) Updated version of ibm-862 ibm-857 { IBM* } IBM857 { IANA* JAVA } cp857 { IANA MIME* JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } # PC Latin 5 (w/o euro update) ibm-860 { IBM* } IBM860 { IANA* JAVA } cp860 { IANA MIME* JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal ibm-861 { IBM* } IBM861 { IANA* JAVA } cp861 { IANA MIME* JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } # PC Iceland ibm-862 { IBM* } IBM862 { IANA* JAVA } cp862 { IANA MIME* JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } # PC Hebrew (w/o euro update) ibm-863 { IBM* } IBM863 { IANA* JAVA } cp863 { IANA MIME* JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French ibm-864 { IBM* } IBM864 { IANA* JAVA } cp864 { IANA MIME* JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update) ibm-865 { IBM* } IBM865 { IANA* JAVA } cp865 { IANA MIME* JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic ibm-866 { IBM* } IBM866 { IANA* JAVA } cp866 { IANA MIME* JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } # PC Russian (w/o euro update) ibm-868 { IBM* } IBM868 { IANA* JAVA } CP868 { IANA MIME* JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu ibm-869 { IBM* } IBM869 { IANA* JAVA } cp869 { IANA MIME* JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } # PC Greek (w/o euro update) ibm-878 { IBM* } KOI8-R { IANA* MIME* JAVA* } koi8 { JAVA } csKOI8R { IANA JAVA } cp878 # Russian internet ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921 ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922 ibm-922 { IBM* JAVA } cp922 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update) 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's used by ICU for Windows. ibm-5346_P100-1998 { UTR22* } ibm-5346 { IBM* } windows-1250 { IANA* JAVA* WINDOWS } cp1250 { WINDOWS } 1250 { WINDOWS* } # Windows Latin2 (w/ euro update) ibm-5347_P100-1998 { UTR22* } ibm-5347 { IBM* } windows-1251 { IANA* JAVA* WINDOWS } cp1251 { WINDOWS } 1251 { WINDOWS* } # Windows Cyrillic (w/ euro update) ibm-5348_P100-1997 { UTR22* } ibm-5348 { IBM* } windows-1252 { IANA* JAVA* WINDOWS } cp1252 { WINDOWS } 1252 { WINDOWS* } # Windows Latin1 (w/ euro update) ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS } cp1253 { WINDOWS } 1253 { WINDOWS* } # Windows Greek (w/ euro update) ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS } cp1254 { WINDOWS } 1254 { WINDOWS* } # Windows Turkish (w/ euro update) ibm-5351_P100-1998 { UTR22* } ibm-5351 { IBM* } windows-1255 { IANA* JAVA* WINDOWS } cp1255 { WINDOWS } 1255 { WINDOWS* } # Windows Hebrew (w/ euro update) ibm-5352_P100-1998 { UTR22* } ibm-5352 { IBM* } windows-1256 { IANA* JAVA* WINDOWS } cp1256 { WINDOWS } 1256 { WINDOWS* } # Windows Arabic (w/ euro update) ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 { IANA* JAVA* WINDOWS } cp1257 { WINDOWS } 1257 { WINDOWS* } # Windows Baltic (w/ euro update) ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS } cp1258 { WINDOWS } 1258 { WINDOWS* } # Windows Vietnamese (w/ euro update) # These tables are out of date, and don't have the Euro ibm-1250_P100-1995 { UTR22* } ibm-1250 { IBM* } # Windows Latin2 (w/o euro update) ibm-1251_P100-1995 { UTR22* } ibm-1251 { IBM* } # Windows Cyrillic (w/o euro update) ibm-1252_P100-2000 { UTR22* } ibm-1252 { IBM* } # Windows Latin 1 without Euro ibm-1253_P100-1995 { UTR22* } ibm-1253 { IBM* } # Windows Greek (w/o euro update) ibm-1254_P100-1995 { UTR22* } ibm-1254 { IBM* } # Windows Turkish (w/o euro update) ibm-1255_P100-1995 { UTR22* } ibm-1255 { IBM* } # Windows Hebrew (w/o euro update) ibm-1256_P110-1997 { UTR22* } ibm-1256 { IBM* } # Windows Arabic (w/o euro update) ibm-1257_P100-1995 { UTR22* } ibm-1257 { IBM* } # Windows Baltic (w/o euro update) ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } # Windows Vietnamese (w/o euro update) ibm-1275_P100-1995 { UTR22* } ibm-1275 { IBM* } macintosh { IANA* MIME* } mac { IANA } csMacintosh { IANA } # Apple latin 1 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-1280_P100-1996 { UTR22* } ibm-1280 { IBM* } x-mac-greek { MIME* } macgr # Apple Greek ibm-1281_P100-1996 { UTR22* } ibm-1281 { IBM* } x-mac-turkish { MIME* } mactr # Apple Turkish ibm-1282_P100-1996 { UTR22* } ibm-1282 { IBM* } x-mac-centraleurroman { MIME* } x-mac-ce macce # Apple Central Europe ibm-1283_P100-1996 { UTR22* } ibm-1283 { IBM* } x-mac-cyrillic { MIME* } maccy # Apple Cyrillic ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } # HP Latin1 ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* JAVA } cp1006 { JAVA* } 1006 { JAVA } ibm-1006_VPUA # Urdu ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* JAVA } cp1098 { JAVA* } 1098 { JAVA } ibm-1098_VSUB_VPUA # PC Farsi ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } ibm-1124_STD # ISO Cyrillic Ukraine ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* JAVA } cp1125 { JAVA* } ibm-1125_VSUB # Cyrillic Ukraine PC ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } ibm-1129_STD # ISO Vietnamese ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* JAVA } cp1131 { JAVA* } ibm-1131_VSUB # Cyrillic Belarus PC ibm-1133_P100-1997 { UTR22* } ibm-1133 { IBM* } ibm-1133_STD # ISO Lao ibm-1381_P110-2000 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } ibm-1381_VSUB_VPUA # S-Ch PC Data mixed (IBM GB) # 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 WINDOWS } ebcdic-cp-ca { IANA } ebcdic-cp-wt { IANA } ebcdic-cp-nl { IANA } csIBM037 { IANA } cp037 { JAVA* } 37 { WINDOWS* } 037 { JAVA } cpibm37 cp37 ibm-273_P100-1995 { UTR22* } ibm-273 { IBM* JAVA } IBM273 { IANA* } csIBM273 { IANA } CP273 { IANA JAVA* } ebcdic-de cpibm273 273 # EBCDIC Germanay, Austria ibm-277_P100-1995 { UTR22* } ibm-277 { IBM* } IBM277 { IANA* } EBCDIC-CP-DK { IANA } EBCDIC-CP-NO { IANA } csIBM277 { IANA } ebcdic-dk cp277 cpibm277 277 # EBCDIC Denmark ibm-278_P100-1995 { UTR22* } ibm-278 { IBM* } IBM278 { IANA* } ebcdic-cp-fi { IANA } ebcdic-cp-se { IANA } csIBM278 { IANA } ebcdic-sv cp278 cpibm278 278 # EBCDIC Sweden ibm-280_P100-1995 { UTR22* } ibm-280 { IBM* } IBM280 { IANA* } ebcdic-cp-it { IANA } csIBM280 { IANA } CP280 { IANA } cpibm280 280 # EBCDIC Italy ibm-284_P100-1995 { UTR22* } ibm-284 { IBM* } IBM284 { IANA* } ebcdic-cp-es { IANA } csIBM284 { IANA } CP284 { IANA } cpibm284 284 # EBCDIC Spain ibm-285_P100-1995 { UTR22* } ibm-285 { IBM* } IBM285 { IANA* } ebcdic-cp-gb { IANA } csIBM285 { IANA } CP285 { IANA } ebcdic-gb cpibm285 285 # EBCDIC UK Ireland ibm-290_P100-1995 { UTR22* } ibm-290 { IBM* } IBM290 { IANA* } EBCDIC-JP-kana { IANA } csIBM290 { IANA } cp290 { IANA } # host SBCS (Katakana) ibm-297_P100-1995 { UTR22* } ibm-297 { IBM* } IBM297 { IANA* } ebcdic-cp-fr { IANA } csIBM297 { IANA } cp297 { IANA } cpibm297 297 # EBCDIC France ibm-420_X120-1999 { UTR22* } ibm-420 { IBM* } IBM420 { IANA* } ebcdic-cp-ar1 { IANA } csIBM420 { IANA } cp420 { IANA } 420 # EBCDIC Arabic (all presentation shapes) ibm-424_P100-1995 { UTR22* } ibm-424 { IBM* } IBM424 { IANA* } ebcdic-cp-he { IANA } csIBM424 { IANA } cp424 { IANA } 424 # EBCDIC Hebrew ibm-500_P100-1995 { UTR22* } ibm-500 { IBM* } IBM500 { IANA* } ebcdic-cp-be { IANA } csIBM500 { IANA } CP500 { IANA } ebcdic-cp-ch { IANA } cpibm500 500 # EBCDIC International Latin1 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 } ibm-838_STD # EBCDIC Thai. Yes ibm-9030 is an alias. ibm-870_P100-2000 { UTR22* } ibm-870 { IBM* } IBM870 { IANA* } CP870 { IANA } ebcdic-cp-roece { IANA } ebcdic-cp-yu { IANA } csIBM870 { IANA } ibm-870_STD # EBCDIC Latin 2 ibm-871 { IBM* } IBM871 { IANA* } ebcdic-cp-is { IANA } csIBM871 { IANA } CP871 { IANA } ebcdic-is cpibm871 871 # EBCDIC Iceland ibm-875_P100-2000 { UTR22* } ibm-875 { IBM* } cp875 875 ibm-875_STD # EBCDIC Greek ibm-918_P100-2000 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* } CP918 { IANA } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } ibm-918_VPUA # EBCDIC Urdu ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed. ibm-930 { IBM* } ibm-5026 { IBM } # Yes this is correct cpibm930 cp930 930 ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* } cp933 cpibm933 933 # Korea EBCDIC MIXED ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* } cp937 cpibm937 937 # Taiwan EBCDIC MIXED ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed. ibm-939 { IBM* } ibm-931 { IBM } # Yes this is correct ibm-5035 { IBM } # Yes this is also correct cp939 939 ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } ibm-1025_STD # EBCDIC Cyrillic ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* JAVA } IBM1026 { IANA* } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } ibm-1026_STD # 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 } ibm-1097_VPUA # EBCDIC Farsi ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } ibm-1112_STD # EBCDIC Baltic ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } ibm-1122_STD # EBCDIC Estonia ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } cpibm1123 ibm-1123_STD # EBCDIC Cyrillic Ukraine ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } ibm-1130_STD # EBCDIC Vietnamese ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } ibm-1132_STD # EBCDIC Lao # 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_P110-2000 { 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_P100-1999 { UTR22* } ibm-1390 { IBM* } cpibm1390 # Japan EBCDIC MIXED ibm-1399_P100-1999 { UTR22* } ibm-1399 { IBM* } # Host MBCS (Latin-Kanji) 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-935_P110-1999 { UTR22* } ibm-935 { IBM* } cp935 cpibm935 935 # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China. ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set) 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-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027 ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290 ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. (Needed for testing DBCS) ibm-16684_P100-1999 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 # EBCDIC codepages for S/390, with LF and NL codes swapped # Starting with ICU 2.4, the swapping is done by modifying the # normal tables at runtime instead of at build time. # Append UCNV_SWAP_LFNL_OPTION_STRING to the "ibm-CCSID" name to select this. # # Example: "ibm-1047,swaplfnl" or "ibm-1047" UCNV_SWAP_LFNL_OPTION_STRING # # This avoids the duplication of all EBCDIC SBCS and mixed-SBCS/DBCS # mapping files. # Some examples ibm-37_P100-1995,swaplfnl ibm-37-s390 ibm037-s390 ibm-1047_P100-1995,swaplfnl ibm-1047-s390 ibm-1140_P100-1997,swaplfnl ibm-1140-s390 ibm-1142_P100-1997,swaplfnl ibm-1142-s390 ibm-1143_P100-1997,swaplfnl ibm-1143-s390 ibm-1144_P100-1997,swaplfnl ibm-1144-s390 ibm-1145_P100-1997,swaplfnl ibm-1145-s390 ibm-1146_P100-1997,swaplfnl ibm-1146-s390 ibm-1147_P100-1997,swaplfnl ibm-1147-s390 ibm-1148_P100-1997,swaplfnl ibm-1148-s390 ibm-1149_P100-1997,swaplfnl ibm-1149-s390 ibm-1153_P100-1999,swaplfnl ibm-1153-s390 ibm-12712_P100-1998,swaplfnl ibm-12712-s390 ibm-16804_X110-1999,swaplfnl ibm-16804-s390 # This is a special version of ibm-1140 that the XML4C (Xerces) parser team # requested in 2000. # It maps both EBCDIC LF and NL controls to Unicode LF U+000A. ebcdic-xml-us # These were removed due to age, and they are rarely used. # ibm-274 IBM274 { IANA* } cp274 csIBM274 ebcdic-be # ibm-870 IBM870 { IANA* } ebcdic-cp-roece ebcdic-cp-yu csIBM870 cp870 870 #ibm-942_P120-1999 { UTR22* } # #ibm-942 { IBM* } # ibm-942_VASCII_VSUB_VPUA # #ibm-932 { IBM } # ibm-932_VASCII_VSUB_VPUA # Old s_jis #ibm-859 { IBM* } cp859 { MIME* } # PC Latin 9 (w/ euro update) #ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } cp1008 # 8-bit Arabic (w/ euro update) #ibm-9238 { IBM* } cp1046 # PC Arabic Extended (w/ euro update) #ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864 #ibm-941 jis-208 jisx-208 # Pure DBCS jisx-208 # ibm-941 is not JISX 208 code page #ibm-955 jis-208 jisx-208 # Pure DBCS jisx-208