# The items on the left are names of CFStringEncoding values (without the leading kCFStringEncoding). # The items on the right are IANA character set names. Names listed in character-sets.txt are not # repeated here; mentioning any one character set from a group in there pulls in all the aliases in # that group. MacRoman: macintosh, xmacroman WindowsLatin1: windows-1252, winlatin1, xansi ISOLatin1: ISO-8859-1, 88591 NextStepLatin: x-nextstep ASCII: US-ASCII, isoir6us Unicode: ISO-10646-UCS-2, ucs2, unicode, utf16 Unicode, BigEndian: UTF-16BE, unicodefffe Unicode, LittleEndian: UTF-16LE, unicodefeff UTF8: UTF-8, unicode11utf8, unicode20utf8, xunicode20utf8 NonLossyASCII MacJapanese, IsJapanese: x-mac-japanese MacChineseTrad: x-mac-chinesetrad, xmactradchinese MacKorean: x-mac-korean MacArabic: x-mac-arabic MacHebrew: x-mac-hebrew MacGreek: x-mac-greek MacCyrillic: x-mac-cyrillic, xmacukrainian MacDevanagari: x-mac-devanagari MacGurmukhi: x-mac-gurmukhi MacGujarati: x-mac-gujarati MacOriya MacBengali MacTamil MacTelugu MacKannada MacMalayalam MacSinhalese MacBurmese MacKhmer MacThai: x-mac-thai MacLaotian MacGeorgian MacArmenian MacChineseSimp: x-mac-chinesesimp, xmacsimpchinese MacTibetan: x-mac-tibetan MacMongolian MacEthiopic MacCentralEurRoman: x-mac-centraleurroman, xmacce MacVietnamese MacExtArabic MacSymbol: x-mac-symbol MacDingbats: x-mac-dingbats MacTurkish: x-mac-turkish MacCroatian: x-mac-croatian MacIcelandic: x-mac-icelandic MacRomanian: x-mac-romanian MacCeltic MacGaelic MacFarsi: x-mac-farsi MacUkrainian MacInuit MacVT100: x-mac-vt100 ISOLatin2: ISO-8859-2 ISOLatin3: ISO-8859-3 ISOLatin4: ISO-8859-4 ISOLatinCyrillic: ISO-8859-5 ISOLatinArabic: ISO-8859-6 ISOLatinGreek: ISO-8859-7 ISOLatinHebrew: ISO-8859-8-I, logical ISOLatinHebrew, VisualOrdering: ISO-8859-8, dos862, visual ISOLatin5: ISO-8859-9 ISOLatin6: ISO-8859-10 ISOLatinThai: ISO-8859-11 ISOLatin7: ISO-8859-13 ISOLatin8: ISO-8859-14 ISOLatin9: ISO-8859-15, csisolatin9, l9 ISOLatin10: ISO-8859-16 DOSLatinUS: cp437 DOSGreek: cp737, ibm737 DOSBalticRim: cp500, cp775 DOSLatin1: cp850 DOSGreek1 DOSLatin2: cp852 DOSCyrillic DOSTurkish: cp857 DOSPortuguese DOSIcelandic: cp861 DOSHebrew DOSCanadianFrench DOSArabic: cp864, dos720 DOSNordic DOSRussian: cp866 DOSGreek2: cp869 DOSThai: cp874, dos874, tis620, windows874 DOSJapanese, IsJapanese: cp932, cswindows31j, xmscp932 DOSChineseSimplif DOSKorean DOSChineseTrad: cp950 WindowsLatin2: windows-1250, winlatin2, xcp1250 WindowsCyrillic: windows-1251, wincyrillic, xcp1251 WindowsGreek: windows-1253, wingreek WindowsLatin5: windows-1254, winturkish WindowsHebrew: windows-1255, winhebrew WindowsArabic: windows-1256, cp1256, winarabic WindowsBalticRim: windows-1257, winbaltic WindowsKoreanJohab: johab WindowsVietnamese: windows-1258, winvietnamese JIS_X0201_76, IsJapanese: JIS_X0201 JIS_X0208_83, IsJapanese: JIS_X0208-1983 JIS_X0208_90, IsJapanese: JIS_X0208-1990 JIS_X0212_90, IsJapanese: JIS_X0212-1990 JIS_C6226_78, IsJapanese: JIS_C6226-1978 ShiftJIS_X0213_00, IsJapanese: Shift_JIS_X0213-2000 GB_2312_80 GBK_95 GB_18030_2000: GB18030 KSC_5601_87 KSC_5601_92_Johab CNS_11643_92_P1 CNS_11643_92_P2 CNS_11643_92_P3 ISO_2022_JP, IsJapanese: ISO-2022-JP, jis7 ISO_2022_JP_2, IsJapanese: ISO-2022-JP-2 ISO_2022_JP_1, IsJapanese: ISO-2022-JP-1 ISO_2022_JP_3, IsJapanese: ISO-2022-JP-3 ISO_2022_CN: ISO-2022-CN ISO_2022_CN_EXT: ISO-2022-CN-EXT ISO_2022_KR: ISO-2022-KR EUC_JP, IsJapanese: EUC-JP, xeuc, xeucjp EUC_CN_DOSVariant: EUC-CN, cngb, csgb231280, gb2312, gb231280, gbk, xeuccn, xgbk EUC_TW: EUC-TW EUC_KR_DOSVariant: EUC-KR, cp949, ksc5601 ShiftJIS_DOSVariant, IsJapanese: Shift_JIS, sjis, xsjis KOI8_R: KOI8-R, koi, koi8 Big5_DOSVariant: Big5, cnbig5, xxbig5 MacRomanLatin1: x-mac-roman-latin1 HZ_GB_2312: HZ-GB-2312 Big5_HKSCS_1999: Big5-HKSCS KOI8_U: KOI8-U EBCDIC_US EBCDIC_CP037: cp037 # I got these additional items from the Perl module I18N-Charset-1.17, # but could not figure out what to do with them. # # Adobe-Standard-Encoding === adobe-standard # Adobe-Symbol-Encoding === adobe-symbol # EBCDIC-ES === ebcdic-cp-es # EBCDIC-FR === ebcdic-cp-fr # EBCDIC-IT === ebcdic-cp-it # EBCDIC-UK === ebcdic-cp-gb # EBCDIC-US === ebcdic-cp-us # EBCDIC-FI-SE === ebcdic-cp-fi # UTF-7 === Unicode-2-0-utf-7 # ISO-10646-UCS-4 === ucs4