| ## |
| # Licensed to the Apache Software Foundation (ASF) under one |
| # or more contributor license agreements. See the NOTICE file |
| # distributed with this work for additional information |
| # regarding copyright ownership. The ASF licenses this file |
| # to you under the Apache License, Version 2.0 (the "License"); |
| # you may not use this file except in compliance with the License. |
| # You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, software |
| # distributed under the License is distributed on an "AS IS" BASIS, |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| # See the License for the specific language governing permissions and |
| # limitations under the License. |
| ## |
| # |
| # $Id: Encodings.properties 468654 2006-10-28 07:09:23Z minchau $ |
| # |
| # Each entry in this properties file is: |
| # 1) The Java name for the encoding |
| # 2) A comma separated list of the MIME names for the encoding, |
| # with the first one being the preferred MIME name. |
| # 3) An optional high char. Characters at or below this value are |
| # definately in the encoding, but characters above it may or may not be. |
| # This value is given only for performance reasons. |
| # A value of zero is the same as no value at all. |
| # |
| # For example this line in this file: |
| # ASCII ASCII,US-ASCII 0x007F |
| # Means the Java name for the encoding is "ASCII". The MIME names for this |
| # encoding which may appear in a stylesheet are "ASCII" or "US-ASCII" |
| # and the optional high code point value is given, and it is 0X007F |
| # which means that the contiguous block of chars from |
| # 0x0001 to 0x007F ( 127 in base 10) are all in the encoding. |
| # Higher values above this char might be in the encoding, although in the |
| # case of this particular encoding there are no higher chars. |
| # |
| # |
| # <JAVA name encoding>, <PREFERRED name MIME> |
| # |
| # |
| ASCII ASCII,US-ASCII 0x007F |
| # |
| # Big5, Traditional Chinese |
| Big5 BIG5,csBig5 0x007F |
| #Big5 with Hong Kong extensions, Traditional Chinese (incorporating 2001 revision) |
| Big5_HKSCS BIG5-HKSCS 0x007F |
| # USA, Canada (Bilingual, French), Netherlands, Portugal, Brazil, Australia |
| Cp037 EBCDIC-CP-US,EBCDIC-CP-CA,EBCDIC-CP-WT,EBCDIC-CP-NL,IBM037 0x0019 |
| # IBM Austria, Germany |
| Cp273 IBM273,csIBM273 0x0019 |
| Cp274 csIBM274,EBCDIC-BE |
| Cp275 csIBM275,EBCDIC-BR |
| # IBM Denmark, Norway |
| Cp277 EBCDIC-CP-DK,EBCDIC-CP-NO,IBM277,csIBM277 0x0019 |
| # IBM Finland, Sweden |
| Cp278 EBCDIC-CP-FI,EBCDIC-CP-SE,IBM278,csIBM278 0x0019 |
| # IBM Italy |
| Cp280 EBCDIC-CP-IT,IBM280,csIBM280 0x0019 |
| Cp281 EBCDIC-JP-E,csIBM281 |
| # IBM Catalan/Spain, Spanish Latin America |
| Cp284 EBCDIC-CP-ES,IBM284,csIBM284 0x0019 |
| # IBM United Kingdom, Ireland |
| Cp285 EBCDIC-CP-GB,IBM284,csIBM285 0x0019 |
| Cp290 EBCDIC-JP-kana,IBM290,csIBM290 0x0019 |
| # IBM France |
| Cp297 EBCDIC-CP-FR,IBM297,csIBM297 0x0019 |
| # IBM Arabic |
| Cp420 EBCDIC-CP-AR1,IBM420,csIBM420 0x0019 |
| Cp423 EBCDIC-CP-GR,IBM423,csIBM423 |
| # IBM Hebrew |
| Cp424 EBCDIC-CP-HE,IBM424,csIBM424 0x0019 |
| Cp437 437,IBM437,csPC8CodePage437 0x007F |
| # EBCDIC 500V1 |
| Cp500 EBCDIC-CP-CH,EBCDIC-CP-BE,IBM500,csIBM500 0x0019 |
| # PC Baltic |
| Cp775 IBM775,csPC775Baltic 0x007F |
| # IBM Thailand extended SBCS |
| Cp838 IBM-Thai,838,csIBMThai 0x0019 |
| # MS-DOS Latin-1 |
| Cp850 850,csPC850Multilingual,IBM850 0x007F |
| Cp851 851,IBM851,csIBM851 |
| # MS-DOS Latin-2 |
| Cp852 IBM852,852,csPCp852 0x007F |
| # IBM Cyrillic |
| Cp855 IBM855,855,csIBM855 0x007F |
| # IBM Turkish |
| Cp857 IBM857,857,csIBM857 0x007F |
| # Variant of Cp850 with Euro character |
| Cp858 IBM00858 0x007F |
| # MS-DOS Portuguese |
| Cp860 860,csIBM860,IBM860 0x007F |
| # MS-DOS Icelandic |
| Cp861 IBM861,861,csIBM861,cp-is 0x007F |
| # |
| Cp862 IBM862,862,csPCi62LatinHebrew 0x007F |
| # MS-DOS Canadian French |
| Cp863 IBM863,863,csIBM863 0x007F |
| # PC Arabic |
| Cp864 IBM864,864,csIBM864 0x007F |
| # MS-DOS Nordic |
| Cp865 IBM865,865,csIBM865 0x007F |
| # MS-DOS Russian |
| Cp866 IBM866,866,csIBM866 0x007F |
| # MS-DOS Pakistan |
| Cp868 IBM868,cp-ar,csIBM868 0x007F |
| # IBM Modern Greek |
| Cp869 IBM869,869,cp-gr,csIBM869 0x007F |
| # IBM Multilingual Latin-2 |
| Cp870 EBCDIC-CP-ROECE,EBCDIC-CP-YU,IBM870,csIBM870 0x0019 |
| # IBM Iceland |
| Cp871 EBCDIC-CP-IS,IBM871,csIBM871 0x0019 |
| Cp880 EBCDIC-Cyrillic,IBM880,csIBM880 |
| Cp891 IBM891,csIBM891 |
| Cp903 IBM903,csIBM903 |
| Cp904 IBM904,csIBM904 |
| Cp905 IBM905,csIBM905,EBCDIC-CP-TR |
| # IBM Pakistan (Urdu) |
| Cp918 EBCDIC-CP-AR2,IBM918,csIBM918 0x0019 |
| # GBK, Simplified Chinese |
| Cp936 GBK,MS936,WINDOWS-936 |
| # IBM Latin-5, Turkey |
| Cp1026 IBM1026,csIBM1026 0x0019 |
| # Latin-1 character set for EBCDIC hosts |
| Cp1047 IBM1047,IBM-1047 0x0019 |
| # Variant of Cp037 with Euro character |
| Cp1140 IBM01140 0x0019 |
| # Variant of Cp273 with Euro character |
| Cp1141 IBM01141 0x0019 |
| # Variant of Cp277 with Euro character |
| Cp1142 IBM01142 0x0019 |
| # Variant of Cp278 with Euro character |
| Cp1143 IBM01143 0x0019 |
| # Variant of Cp280 with Euro character |
| Cp1144 IBM01144 0x0019 |
| # Variant of Cp284 with Euro character |
| Cp1145 IBM01145 0x0019 |
| # Variant of Cp285 with Euro character |
| Cp1146 IBM01146 0x0019 |
| # Variant of Cp297 with Euro character |
| Cp1147 IBM01147 0x0019 |
| # Variant of Cp500 with Euro character |
| Cp1148 IBM01148 0x0019 |
| # Variant of Cp871 with Euro character |
| Cp1149 IBM01149 0x0019 |
| Cp1250 WINDOWS-1250 0x007F |
| Cp1251 WINDOWS-1251 0x007F |
| Cp1252 WINDOWS-1252 0x007F |
| Cp1253 WINDOWS-1253 0x007F |
| Cp1254 WINDOWS-1254 0x007F |
| # Windows Hebrew |
| Cp1255 WINDOWS-1255 0x007F |
| # Windows Arabic |
| Cp1256 WINDOWS-1256 0x007F |
| Cp1257 WINDOWS-1257 0x007F |
| # Windows Vietnamese |
| Cp1258 WINDOWS-1258 0x007F |
| EUC-CN EUC-CN 0x007F |
| EUC_CN EUC-CN 0x007F |
| # |
| #JISX 0201, 0208 and 0212, EUC encoding Japanese |
| EUC-JP EUC-JP 0x007F |
| EUC_JP EUC-JP 0x007F |
| # KS C 5601, EUC encoding, Korean |
| EUC-KR EUC-KR 0x007F |
| EUC_KR EUC-KR 0x007F |
| # CNS11643 (Plane 1-7,15), EUC encoding, Traditional Chinese |
| EUC-TW EUC-TW 0x007F |
| EUC_TW EUC-TW,x-EUC-TW 0x007F |
| EUCJIS EUC-JP 0x007F |
| # |
| # GB2312, EUC encoding, Simplified Chinese |
| GB2312 GB2312 0x007F |
| |
| # GB2312 and CNS11643 in ISO 2022 CN form, Simplified and Traditional Chinese (conversion to Unicode only) |
| ISO2022CN ISO-2022-CN |
| # JIS X 0201, 0208, in ISO 2022 form, Japanese |
| ISO2022JP ISO-2022-JP |
| # ISO 2022 KR, Korean |
| ISO2022KR ISO-2022-KR 0x007F |
| # |
| # |
| ISO8859-1 ISO-8859-1 0x00FF |
| ISO8859_1 ISO-8859-1 0x00FF |
| 8859-1 ISO-8859-1 0x00FF |
| 8859_1 ISO-8859-1 0x00FF |
| # |
| ISO8859-2 ISO-8859-2 0x00A0 |
| ISO8859_2 ISO-8859-2 0x00A0 |
| 8859-2 ISO-8859-2 0x00A0 |
| 8859_2 ISO-8859-2 0x00A0 |
| # |
| # Latin Alphabet No. 3 |
| ISO8859-3 ISO-8859-3 0x00A0 |
| ISO8859_3 ISO-8859-3 0x00A0 |
| 8859-3 ISO-8859-3 0x00A0 |
| 8859_3 ISO-8859-3 0x00A0 |
| # |
| ISO8859-4 ISO-8859-4 0x00A0 |
| ISO8859_4 ISO-8859-4 0x00A0 |
| 8859-4 ISO-8859-4 0x00A0 |
| 8859_4 ISO-8859-4 0x00A0 |
| # |
| ISO8859-5 ISO-8859-5 0x00A0 |
| ISO8859_5 ISO-8859-5 0x00A0 |
| 8859-5 ISO-8859-5 0x00A0 |
| 8859_5 ISO-8859-5 0x00A0 |
| # |
| # Latin/Arabic Alphabet |
| ISO8859-6 ISO-8859-6 0x00A0 |
| ISO8859_6 ISO-8859-6 0x00A0 |
| 8859-6 ISO-8859-6 0x00A0 |
| 8859_6 ISO-8859-6 0x00A0 |
| # |
| ISO8859-7 ISO-8859-7 0x00A0 |
| ISO8859_7 ISO-8859-7 0x00A0 |
| 8859-7 ISO-8859-7 0x00A0 |
| 8859_7 ISO-8859-7 0x00A0 |
| # |
| ISO8859-8 ISO-8859-8 0x00A0 |
| ISO8859_8 ISO-8859-8 0x00A0 |
| 8859-8 ISO-8859-8 0x00A0 |
| 8859_8 ISO-8859-8 0x00A0 |
| # |
| ISO8859-9 ISO-8859-9 0x00CF |
| ISO8859_9 ISO-8859-9 0x00CF |
| 8859-9 ISO-8859-9 0x00CF |
| 8859_9 ISO-8859-9 0x00CF |
| # |
| ISO8859-10 ISO-8859-10 0x007E |
| ISO8859_10 ISO-8859-10 0x007E |
| ISO8859-11 ISO-8859-11 0x007E |
| ISO8859_11 ISO-8859-11 0x007E |
| ISO8859-12 ISO-8859-12 0x007F |
| ISO8859_12 ISO-8859-12 0x007F |
| ISO8859-13 ISO-8859-13 0x00A0 |
| ISO8859_13 ISO-8859-13 0x00A0 |
| ISO8859-14 ISO-8859-14 0x007E |
| ISO8859_14 ISO-8859-14 0x007E |
| ISO8859-15 ISO-8859-15 0x00A3 |
| ISO8859_15 ISO-8859-15 0x00A3 |
| JIS ISO-2022-JP 0x007F |
| KOI8_R KOI8-R 0x007F |
| KSC5601 EUC-KR 0x007F |
| KS_C_5601-1987 KS_C_5601-1987,iso-ir-149,KS_C_5601-1989,KSC_5601,csKSC56011987 0x007F |
| MacTEC MacRoman |
| # Windows Japanese |
| MS932 windows-31j |
| # Shift-JIS, Japanese |
| SJIS SHIFT_JIS 0x007F |
| # TIS620, Thai |
| TIS620 TIS-620 |
| UTF8 UTF-8 0xFFFF |
| Unicode UNICODE,UTF-16 0xFFFF |
| |
| # note that more character set names and their aliases |
| # can be found at http://www.iana.org/assignments/character-sets |
| |