| # ******************************************************************************* |
| # * |
| # * Copyright (C) 1995-2000, International Business Machines |
| # * Corporation and others. All Rights Reserved. |
| # * |
| # ******************************************************************************* |
| |
| #This is an alias file used by the character set converter |
| #format: |
| #Actual File Name || Algorithm name alias1 alias2 ... |
| #except for column1(file names) case insensitive |
| |
| # 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.isi.edu/in-notes/iana/assignments/character-sets |
| |
| # Name matching is case-insensitive. |
| # 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. |
| |
| # Algorithmic |
| UTF8 utf-8 utf8 ibm-1208 utf_8 ibm1208 cp1208 |
| UTF16_BigEndian utf-16be |
| UTF16_LittleEndian utf-16le |
| UTF16_PlatformEndian iso-10646-ucs-2 csUnicode utf16 utf-16 ibm-1200 ibm1200 cp1200 ucs-2 |
| UTF16_OppositeEndian |
| LATIN_1 iso-8859-1 iso_8859-1 ibm-819 ibm819 cp819 latin1 latin-1 ascii ascii-7 us-ascii 8859-1 csisolatin1 iso-ir-100 iso_8859-1:1978 ansi_x3.4-1968 ansi_x3.4-1986 iso_646.irv:1991 iso646-us us cp367 csASCII ibm367 iso-8859-1:1987 l1 iso_8859_1 ansi_x3.110-1983 iso8859-1 #!!!!! There's whole lot of names for this - cp367 csASCII etc. |
| ISO_2022 iso-2022 2022 cp2022 iso2022 iso_2022 |
| 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 |
| |
| # Special mapping for S/390 new line characters |
| ebcdic-xml-us |
| |
| # Interchange codepages |
| ibm-912 iso-8859-2 iso_8859-2 iso8859-2 ibm912 cp912 latin2 8859-2 csisolatin2 iso-ir-101 iso_8859-2:1987 l2 # Central Europe |
| ibm-913 iso-8859-3 iso_8859-3 iso8859-3 latin3 cp913 ibm913 8859-3 csisolatin3 iso-ir-109 iso_8859-3:1988 l3 # Maltese Esperanto |
| ibm-914 iso-8859-4 iso_8859-4 iso8859-4 latin4 cp914 ibm914 8859-4 csisolatin4 iso-ir-110 iso_8859-4:1988 l4 # Baltic |
| ibm-915 iso-8859-5 iso_8859-5 iso8859-5 cyrillic cp915 ibm915 8859-5 csisolatincyrillic iso-ir-144 iso_8859-5:1988 # Cyrillic |
| ibm-1089 iso-8859-6 iso_8859-6 iso8859-6 arabic cp1089 ibm1089 8859-6 csisolatinarabic iso-ir-127 iso_8859-6:1987 ecma-114 asmo-708 # Arabic |
| ibm-4909 cp813 iso-8859-7 iso_8859-7 iso8859-7 ibm813 cp813 greek greek8 elot_928 ecma-118 8859-7 csisolatingreek iso-ir-126 iso_8859-7:1987 # ISO Greek (w/ euro update) |
| ibm-813 # same as 4909 (w/o euro update) |
| ibm-916 iso-8859-8 iso_8859-8 iso8859-8 hebrew cp916 ibm916 8859-8 csisolatinhebrew iso-ir-138 iso_8859-8:1988 # hebrew iso-8859-8i - typo? |
| ibm-920 iso-8859-9 iso_8859-9 iso8859-9 ECMA-128 latin5 cp920 ibm920 8859-9 csisolatin5 iso-ir-148 l5 # Turkish |
| ibm-923 iso-8859-15 iso_8859-15 iso8859-15 latin9 cp923 ibm923 8859-15 latin0 csisolatin0 csisolatin9 # Latin 9 |
| ibm-1252 windows-1252 cp1252 ibm-1004 cp1004 # Windows Latin 1 We don't have an ibm-5348, so this is a best possible match |
| ibm-943 shift_jis csWindows31J sjis shiftjis shift-jis ibm943 cp943 cp932 ms_kanji csshiftjis windows-31j x-sjis # japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe Iana says that Windows-31J is an extension to csshiftjis ibm-932 removed |
| ibm-949 KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 csKSC56011987 korean ibm949 ksc-5601 ksc_5601 johab ks_x_1001:1992 # KSC-5601-1992, korean |
| ibm-1370 Big5 csBig5 big-5 x-big5 cp950 # Taiwan Big-5 (w/ euro update) |
| ibm-950 # Taiwan Big-5 |
| ibm-1386 gb_2312-80 iso-ir-58 csISO58GB231280 gb2312-80 gbk chinese gb ibm1386 gb2312 gb2312-1980 cp936 zh_cn # Chinese GBK removed |
| #ibm-954 euc-jp eucJP ibm-eucJP eucjis extended_unix_code_packed_format_for_japanese cseuckdfmtjapanese x-euc-jp x-eucjp # Japan EUC Why is this one commented!!! |
| ibm-970 euc-kr euckr ibm-eucKR csEUCKR # Korean EUC |
| #ibm-964 euc-tw euctw ibm-eucTW cns11643 # Taiwan EUC |
| ibm-1361 cp949 ksc korean # Korean KSC |
| ibm-1383 euc-cn euccn ibm-eucCN # China EUC |
| #ibm-1162 tis-620 cp874 windows-874 ms874 # Thai (w/ euro support) #what is the connection between this and the one below!!! |
| ibm-874 ibm-1161 #same as 1162 (w/o euro update) ***This is commented out in Helena's |
| |
| lmb-excp # special exceptions list for LMBCS algorithm |
| |
| # Platform codepages |
| ibm-437 ibm437 cp437 csPC8CodePage437 437 # PC US |
| # HSYS: |
| ibm-850 IBM850 cp850 850 csPC850Multilingual # PC latin1 |
| ibm-851 IBM851 cp851 851 csPC851 # PC DOS Greek (no euro) |
| ibm-858 ibm858 cp858 # PC latin1 with Euro cp850 removed |
| ibm-9044 IBM852 852 csPCp852 cp852 # PC latin2 (w/ euro update) #where should the names go here or below - inconsistency!!! |
| ibm-852 # PC latin2 (w/o euro update) |
| ibm-872 IBM855 855 csIBM855 cp855 # PC cyrillic (w/ euro update) #where should the names go here or below - inconsistency!!! |
| ibm-855 # PC cyrillic (w/o euro update) |
| ibm-856 ibm856 cp856 # PC Hebrew (old) |
| ibm-9049 IBM857 857 csIBM857 cp857 # PC Latin 5 (Turkish) (w/ euro update) #where should the names go here or below - inconsistency!!! |
| ibm-857 # PC Latin 5 (w/o euro update) |
| ibm-859 ibm859 cp859 # PC Latin 9 (w/ euro update) |
| ibm-860 ibm860 cp860 860 csIBM860 # PC Portugal |
| ibm-861 ibm861 cp861 861 cp-is csIBM861 # PC Iceland |
| ibm-867 ibm867 cp867 862 cp862 cspc862latinhebrew # PC Hebrew (w/ euro update) #where should the names go here or below - inconsistency!!! |
| ibm-862 IBM862 # PC Hebrew (w/o euro update) |
| ibm-863 ibm863 cp863 863 csIBM863 # PC Canadian French |
| ibm-17248 IBM864 cp864 csIBM864 # PC Arabic (w/ euro update) #where should the names go here or below - inconsistency!!! |
| ibm-864 # PC Arabic (w/o euro update) |
| ibm-865 ibm865 cp865 865 csIBM865 # PC Nordic |
| ibm-808 cp866 866 csIBM866 # PC Russian (w/ euro update) #where should the names go here or below - inconsistency!!! put IBM866 cp866 866 csIBM866 down |
| ibm-866 IBM866 # PC Russian (w/o euro update) added IBM866 cp866 866 csIBM866 |
| ibm-868 ibm868 cp868 cp-ar csIBM868 # PC Urdu |
| ibm-9061 IBM869 869 cp-gr csIBM869 cp869 # PC Greek (w/ euro update) |
| ibm-869 # PC Greek (w/o euro update) |
| ibm-878 koi8-r ibm878 cp878 koi8 cskoi8r # Russian internet |
| ibm-901 cp921 # PC Baltic (w/ euro update) moved cp921 down |
| ibm-921 # PC Baltic (w/o euro update) from above |
| ibm-902 cp922 # PC Estonian (w/ euro update) moved cp922 down |
| ibm-922 # PC Estonian (w/o euro update) from above |
| ibm-942 shift_jis78 sjis78 ibm-932 ibm932 # Old s_jis ibm-932 added! |
| ibm-1038 Adobe-Symbol-Encoding csHPPSMath symbol |
| ibm-5346 windows-1250 cp1250 # Windows Latin2 (w/ euro update) |
| ibm-5347 windows-1251 cp1251 # Windows Cyrillic (w/ euro update) |
| ibm-5349 windows-1253 cp1253 # Windows Greek (w/ euro update) |
| ibm-5350 windows-1254 cp1254 # Windows Turkish (w/ euro update) |
| ibm-5351 windows-1255 cp1255 # Windows Hebrew (w/ euro update) |
| ibm-5352 windows-1256 cp1256 # Windows Arabic (w/ euro update) |
| ibm-5353 windows-1257 cp1257 # Windows Baltic (w/ euro update) |
| ibm-5354 windows-1258 cp1258 # Windows Vietnamese (w/ euro update) |
| ibm-1250 # Windows Latin2 (w/o euro update) |
| ibm-1251 # Windows Cyrillic (w/o euro update) |
| ibm-1253 # Windows Greek (w/o euro update) |
| ibm-1254 # Windows Turkish (w/o euro update) |
| ibm-1255 # Windows Hebrew (w/o euro update) |
| ibm-1256 # Windows Arabic (w/o euro update) |
| ibm-1257 # Windows Baltic (w/o euro update) |
| ibm-1258 # Windows Vietnamese (w/o euro update) |
| |
| ibm-1275 macintosh mac csMacintosh # Apple latin 1 |
| ibm-1276 Adobe-Standard-Encoding csAdobeStandardEncoding |
| ibm-1277 Adobe-Latin1-Encoding |
| ibm-1280 macgr # Apple Greek |
| ibm-1281 mactr # Apple Turkish |
| ibm-1282 macce # Apple Central Europe |
| ibm-1283 maccy # Apple Cyrillic |
| |
| ibm-1051 hp-roman8 roman8 r8 csHPRoman8 # HP Latin1 |
| |
| # Added for more euro support |
| |
| ibm-849 cp1131 # PC Belarus (w/ euro update) |
| ibm-848 cp1125 # PC Ukraine (w/ euro update) |
| ibm-5104 cp1008 # 8-bit Arabic (w/ euro update) |
| ibm-9238 cp1046 # PC Arabic Extended (w/ euro update) |
| #ibm-1161 cp9066 # PC Thailand (IBM "version) (w/ euro update) |
| ibm-1362 cp1362 # Korean Windows DBCS (w/ euro update) |
| ibm-1363 cp1363 # Korean Windows MBCS (w/ euro update) |
| ibm-5210 cp1114 # PC SBCS Big-5 (w/ euro update) |
| ibm-21427 cp947 # PC DBCS Big-5 (w/ euro update) |
| |
| # EBCDIC codepages according to the CDRA |
| |
| # without Euro |
| ibm-37 IBM037 ibm-037 cpibm37 ebcdic-cp-ca ebcdic-cp-wt ebcdic-cp-nl csIBM037 cp37 ebcdic-cp-us cp037 # EBCDIC US |
| ibm-273 IBM273 csIBM273 ebcdic-de cp273 cpibm273 # EBCDIC Germanay, Austria... |
| ibm-277 IBM277 EBCDIC-CP-DK EBCDIC-CP-NO csIBM277 ebcdic-dk cp277 cpibm277 # EBCDIC Denmark... |
| ibm-278 IBM278 ebcdic-cp-fi ebcdic-cp-se csIBM278 ebcdic-sv cp278 cpibm278 # EBCDIC Sweden |
| ibm-280 IBM280 ebcdic-cp-it csIBM280 cp280 cpibm280 # EBCDIC Italy |
| ibm-284 IBM284 ebcdic-cp-es csIBM284 cp284 cpibm284 # EBCDIC Spain |
| ibm-285 IBM285 ebcdic-cp-gb csIBM285 ebcdic-gb cp285 cpibm285 # EBCDIC UK Ireland |
| ibm-290 IBM290 EBCDIC-JP-kana csIBM290 cp290 # host SBCS (Katakana) |
| ibm-297 IBM297 ebcdic-cp-fr csIBM297 cp297 cpibm297 # EBCDIC France |
| ibm-420 IBM420 ebcdic-cp-ar1 csIBM420 ibm-420 cp420 |
| ibm-424 IBM424 ebcdic-cp-he csIBM424 cp424 ibm-424 |
| ibm-500 IBM500 cpibm500 csIBM500 cp500 ebcdic-cp-be ebcdic-cp-ch # EBCDIC International Latin1 |
| ibm-803 cp803 # Old EBCDIC Hebrew |
| ibm-834 cp834 # Korean DBCS Host |
| ibm-835 cp835 # DBCS T-Ch Host |
| ibm-871 IBM871 ebcdic-cp-is csIBM871 cpibm871 cp871 # EBCDIC Iceland |
| ibm-930 cp930 cpibm930 # Japan EBCDIC MIXED |
| ibm-933 ibm933 cp933 cpibm933 # Korea EBCDIC MIXED |
| ibm-935 ibm935 cp935 cpibm935 # China EBCDIC MIXED |
| ibm-937 cp937 cpibm937 # Taiwan EBCDIC MIXED |
| ibm-939 cp939 # Host MBCS (Latin-Kanji) |
| #ibm-1046 # PC Arabic without EURO |
| # with Euro |
| ibm-1390 cpibm1390 # Japan EBCDIC MIXED |
| ibm-1371 cpibm1371 # Taiwan EBCDIC MIXED |
| ibm-1047 cpibm1047 # EBCDIC Open systems Latin1 |
| ibm-1123 cpibm1123 # Cyrillic Ukraine EBCDIC |
| ibm-1140 cpibm1140 ibm1140 # EBCDIC US... |
| ibm-1141 cpibm1141 ibm1141 # EBCDIC Germanay, Austria... |
| ibm-1142 cpibm1142 ibm1142 # EBCDIC Denmark... |
| ibm-1143 cpibm1143 ibm1143 # EBCDIC Sweden |
| ibm-1144 cpibm1144 ibm1144 # EBCDIC Italy |
| ibm-1145 cpibm1145 ibm1145 # EBCDIC Spain |
| ibm-1146 cpibm1146 ibm1146 # EBCDIC UK Ireland |
| ibm-1147 cpibm1147 ibm1147 # EBCDIC France |
| ibm-1148 cpibm1148 ibm1148 # EBCDIC International Latin1 |
| ibm-1149 cpibm1149 ibm1149 ebcdic-is # EBCDIC Iceland |
| ibm-1153 cpibm1153 ibm1153 # EBCDIC latin 2 |
| ibm-1154 cp1025 cpibm1154 # EBCDIC Cyrillic Multilingual |
| ibm-1155 IBM1026 csIBM1026 cp1026 cpibm1155 # EBCDIC Turkey |
| ibm-1156 cp1112 cpibm1156 # EBCDIC Baltic Multilingual |
| ibm-1157 cp1122 cpibm1157 # EBCDIC Estonia |
| ibm-1158 cp1123 cpibm1158 # Cyrillic Ukraine EBCDIC |
| ibm-1159 cp28709 # SBCS T-Ch Host |
| ibm-1160 cp9030 cpibm1160 # EBCDIC Thailand |
| ibm-1164 cp1130 cpibm1164 # EBCDIC Viet Nam |
| |
| ibm-1399 # Host MBCS (Latin-Kanji) |
| ibm-4930 cp4930 # Korean DBCS Host |
| ibm-1364 cp1364 # Korean Host Mixed |
| ibm-8482 # host SBCS (Katakana) |
| ibm-4899 cpibm4899 # Old EBCDIC Hebrew |
| ibm-4971 cp875 cpibm4971 # EBCDIC Greek |
| ibm-1159 cp28709 # SBCS T-Ch Host |
| ibm-9027 # DBCS T-Ch Host |
| ibm-5123 cp1027 # Host Roman Jis |
| ibm-12712 cpibm12712 ibm12712 ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update) |
| ibm-16684 cp300 # Jis + Roman Jis Host |
| ibm-16804 cpibm16804 ibm16804 ebcdic-ar # EBCDIC Arabic |
| |
| # unsupported IANA names |
| # ebcdic-us |
| # ebcdic-it csEBCDICIT |
| # ebcdic-es csEBCDICES |
| # csEBCDICFR ebcdic-fr |
| # ibm-274 IBM274 cp274 csIBM274 ebcdic-be |
| # IBM870 ebcdic-cp-roece ebcdic-cp-yu csIBM870 cp870 |
| |
| # EBCDIC codepages for S/390, with LF and NL codes swapped |
| |
| # without Euro |
| ibm-37-s390 ibm037-s390 # EBCDIC US |
| ibm-1047-s390 ibm1047-s390 # EBCDIC for S/390 Open Edition |
| |
| # with Euro |
| ibm-1140-s390 ibm1140-s390 # EBCDIC US |
| ibm-1142-s390 ibm1142-s390 # EBCDIC Denmark |
| ibm-1143-s390 ibm1143-s390 # EBCDIC Sweden |
| ibm-1144-s390 ibm1144-s390 # EBCDIC Italy |
| ibm-1145-s390 ibm1145-s390 # EBCDIC Spain |
| ibm-1146-s390 ibm1146-s390 # EBCDIC UK Ireland |
| ibm-1147-s390 ibm1147-s390 # EBCDIC France |
| ibm-1148-s390 ibm1148-s390 # EBCDIC International Latin1 |
| ibm-1149-s390 ibm1149-s390 # EBCDIC Iceland |
| ibm-1153-s390 ibm1153-s390 # EBCDIC latin 2 |
| ibm-12712-s390 ibm12712-s390 # EBCDIC Hebrew |
| ibm-16804-s390 ibm16804-s390 # EBCDIC Arabic |