mirror/ghidra
1
0
Fork 0
mirror of https://github.com/NationalSecurityAgency/ghidra.git synced 2026-10-22 18:22:23 -09:00
Code Issues Packages Projects Releases Wiki Activity
Files
5259f4b7ae2aa4d7aaf44511057fc66fa56d09d4
ghidra/Ghidra/Framework/SoftwareModeling/data/charset_info.json
dev747368 84641bff03 GP-5689 Add ByteViewer 'Chars' column 
Convert the Ascii format to Chars, which supports decoding bytes using
any available charset.
Reworked the memory alignment option of the ByteViewer to allow the user
to bump the displayed bytes left/right using an action.
Add option to control how widely spaced the chars are displayed, to
allow for wider non-Latin characters to be displayed correctly.
Refactor the CharsetInfo class to better support the information needed
by the new chars column.
Fixed HexLongLong format to not mix BE / LE longs when constructing its
final 16 byte value.
Fixed handling of ByteViewer's background color to use its theme value.
2026-01-05 22:54:40 +00:00

3213 lines
80 KiB
JSON
Raw Blame History

{
"comments": [
"Information about character encodings used by Ghidra.",
"Generated on Thu Dec 18 21:18:49 UTC 2025 by CharsetInfoManagerTest.generateCharsetInfoFile"
],
"charsets": [
{
"name": "Big5",
"comment": "A traditional Chinese encoding used mainly in Taiwan and Hong Kong for Traditional Chinese characters. It supports a large repertoire but does not cover all Unicode characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 13830,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "Big5-HKSCS",
"comment": "An extension of Big5 used in Hong Kong that adds Cantonese-specific and government-required characters. It improves compatibility with local applications and legacy data.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 18578,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"Big5",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-Big5-HKSCS-2001",
"comment": "An older version of the Hong Kong Supplementary Character Set based on Big5. It includes Cantonese-specific and government-required characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 18384,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"Big5",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-Big5-Solaris",
"comment": "A Solaris-specific variant of Big5. It includes vendor extensions used on Sun systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 13837,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"Big5",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "CESU-8",
"comment": "A variant of UTF-8 designed for internal processing that preserves UTF-16 surrogate pairs. It is not intended for data interchange and is rarely used outside specific systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 6,
"alignment": 1,
"codePointCount": 149249,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"ARMENIAN",
"HEBREW",
"ARABIC",
"SYRIAC",
"THAANA",
"DEVANAGARI",
"BENGALI",
"GURMUKHI",
"GUJARATI",
"ORIYA",
"TAMIL",
"TELUGU",
"KANNADA",
"MALAYALAM",
"SINHALA",
"THAI",
"LAO",
"TIBETAN",
"MYANMAR",
"GEORGIAN",
"HANGUL",
"ETHIOPIC",
"CHEROKEE",
"CANADIAN_ABORIGINAL",
"OGHAM",
"RUNIC",
"KHMER",
"MONGOLIAN",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN",
"YI",
"OLD_ITALIC",
"GOTHIC",
"DESERET",
"INHERITED",
"TAGALOG",
"HANUNOO",
"BUHID",
"TAGBANWA",
"LIMBU",
"TAI_LE",
"LINEAR_B",
"UGARITIC",
"SHAVIAN",
"OSMANYA",
"CYPRIOT",
"BRAILLE",
"BUGINESE",
"COPTIC",
"NEW_TAI_LUE",
"GLAGOLITIC",
"TIFINAGH",
"SYLOTI_NAGRI",
"OLD_PERSIAN",
"KHAROSHTHI",
"BALINESE",
"CUNEIFORM",
"PHOENICIAN",
"PHAGS_PA",
"NKO",
"SUNDANESE",
"BATAK",
"LEPCHA",
"OL_CHIKI",
"VAI",
"SAURASHTRA",
"KAYAH_LI",
"REJANG",
"LYCIAN",
"CARIAN",
"LYDIAN",
"CHAM",
"TAI_THAM",
"TAI_VIET",
"AVESTAN",
"EGYPTIAN_HIEROGLYPHS",
"SAMARITAN",
"MANDAIC",
"LISU",
"BAMUM",
"JAVANESE",
"MEETEI_MAYEK",
"IMPERIAL_ARAMAIC",
"OLD_SOUTH_ARABIAN",
"INSCRIPTIONAL_PARTHIAN",
"INSCRIPTIONAL_PAHLAVI",
"OLD_TURKIC",
"BRAHMI",
"KAITHI",
"MEROITIC_HIEROGLYPHS",
"MEROITIC_CURSIVE",
"SORA_SOMPENG",
"CHAKMA",
"SHARADA",
"TAKRI",
"MIAO",
"CAUCASIAN_ALBANIAN",
"BASSA_VAH",
"DUPLOYAN",
"ELBASAN",
"GRANTHA",
"PAHAWH_HMONG",
"KHOJKI",
"LINEAR_A",
"MAHAJANI",
"MANICHAEAN",
"MENDE_KIKAKUI",
"MODI",
"MRO",
"OLD_NORTH_ARABIAN",
"NABATAEAN",
"PALMYRENE",
"PAU_CIN_HAU",
"OLD_PERMIC",
"PSALTER_PAHLAVI",
"SIDDHAM",
"KHUDAWADI",
"TIRHUTA",
"WARANG_CITI",
"AHOM",
"ANATOLIAN_HIEROGLYPHS",
"HATRAN",
"MULTANI",
"OLD_HUNGARIAN",
"SIGNWRITING",
"ADLAM",
"BHAIKSUKI",
"MARCHEN",
"NEWA",
"OSAGE",
"TANGUT",
"MASARAM_GONDI",
"NUSHU",
"SOYOMBO",
"ZANABAZAR_SQUARE",
"HANIFI_ROHINGYA",
"OLD_SOGDIAN",
"SOGDIAN",
"DOGRA",
"GUNJALA_GONDI",
"MAKASAR",
"MEDEFAIDRIN",
"ELYMAIC",
"NANDINAGARI",
"NYIAKENG_PUACHUE_HMONG",
"WANCHO",
"YEZIDI",
"CHORASMIAN",
"DIVES_AKURU",
"KHITAN_SMALL_SCRIPT",
"VITHKUQI",
"OLD_UYGHUR",
"CYPRO_MINOAN",
"TANGSA",
"TOTO",
"KAWI",
"NAG_MUNDARI"
],
"contains": [
"Big5-HKSCS",
"x-ISO-2022-CN-CNS",
"KOI8-R",
"JIS_X0212-1990",
"x-Johab",
"windows-31j",
"GB2312",
"Shift_JIS",
"x-ISO-2022-CN-GB",
"windows-1251",
"UTF-8",
"ISO-8859-13",
"windows-1253",
"windows-1252",
"windows-1255",
"windows-1254",
"windows-1257",
"ISO-8859-16",
"windows-1256",
"ISO-8859-15",
"US-ASCII",
"windows-1258",
"x-UTF-16LE-BOM",
"UTF-16LE",
"x-MS950-HKSCS",
"Big5",
"x-windows-950",
"EUC-JP",
"x-mswin-936",
"GB18030",
"x-euc-jp-linux",
"GBK",
"x-JIS0208",
"ISO-2022-KR",
"ISO-8859-4",
"x-windows-949",
"ISO-8859-3",
"TIS-620",
"ISO-8859-2",
"x-EUC-TW",
"ISO-8859-1",
"ISO-8859-8",
"ISO-8859-7",
"ISO-8859-6",
"ISO-8859-5",
"UTF-16",
"EUC-KR",
"ISO-8859-9",
"x-ISCII91",
"ISO-2022-JP",
"UTF-16BE",
"JIS_X0201"
],
"canProduceError": true
},
{
"name": "EUC-JP",
"comment": "A multibyte encoding for Japanese that includes ASCII, JIS X 0208, and half-width kana. It was widely used on Unix systems before UTF-8 became dominant.",
"minBytesPerChar": 1,
"maxBytesPerChar": 3,
"alignment": 1,
"codePointCount": 13138,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-JIS0208",
"JIS_X0201",
"JIS_X0212-1990",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-euc-jp-linux",
"comment": "A Linux-specific variant of EUC-JP. It includes additional mappings used by Japanese Linux distributions.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7071,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"JIS_X0201",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "EUC-KR",
"comment": "A Korean encoding based on KS X 1001 combined with ASCII. It supports modern Hangul syllables and was common on Unix platforms.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 8354,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-EUC-TW",
"comment": "A Taiwanese encoding supporting Traditional Chinese and additional plane mappings. It includes characters from CNS 11643.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 55567,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-eucJP-Open",
"comment": "An extended EUC-JP variant used in some open-source systems. It includes additional Kanji beyond standard EUC-JP.",
"minBytesPerChar": 1,
"maxBytesPerChar": 3,
"alignment": 1,
"codePointCount": 13304,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"EUC-JP",
"JIS_X0201",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "GB18030",
"comment": "China\u0027s mandatory national encoding standard that covers all Unicode characters using 1, 2, or 4 bytes. It supersedes GBK and GB2312 and ensures compatibility with rare and historical characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 149249,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"ARMENIAN",
"HEBREW",
"ARABIC",
"SYRIAC",
"THAANA",
"DEVANAGARI",
"BENGALI",
"GURMUKHI",
"GUJARATI",
"ORIYA",
"TAMIL",
"TELUGU",
"KANNADA",
"MALAYALAM",
"SINHALA",
"THAI",
"LAO",
"TIBETAN",
"MYANMAR",
"GEORGIAN",
"HANGUL",
"ETHIOPIC",
"CHEROKEE",
"CANADIAN_ABORIGINAL",
"OGHAM",
"RUNIC",
"KHMER",
"MONGOLIAN",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN",
"YI",
"OLD_ITALIC",
"GOTHIC",
"DESERET",
"INHERITED",
"TAGALOG",
"HANUNOO",
"BUHID",
"TAGBANWA",
"LIMBU",
"TAI_LE",
"LINEAR_B",
"UGARITIC",
"SHAVIAN",
"OSMANYA",
"CYPRIOT",
"BRAILLE",
"BUGINESE",
"COPTIC",
"NEW_TAI_LUE",
"GLAGOLITIC",
"TIFINAGH",
"SYLOTI_NAGRI",
"OLD_PERSIAN",
"KHAROSHTHI",
"BALINESE",
"CUNEIFORM",
"PHOENICIAN",
"PHAGS_PA",
"NKO",
"SUNDANESE",
"BATAK",
"LEPCHA",
"OL_CHIKI",
"VAI",
"SAURASHTRA",
"KAYAH_LI",
"REJANG",
"LYCIAN",
"CARIAN",
"LYDIAN",
"CHAM",
"TAI_THAM",
"TAI_VIET",
"AVESTAN",
"EGYPTIAN_HIEROGLYPHS",
"SAMARITAN",
"MANDAIC",
"LISU",
"BAMUM",
"JAVANESE",
"MEETEI_MAYEK",
"IMPERIAL_ARAMAIC",
"OLD_SOUTH_ARABIAN",
"INSCRIPTIONAL_PARTHIAN",
"INSCRIPTIONAL_PAHLAVI",
"OLD_TURKIC",
"BRAHMI",
"KAITHI",
"MEROITIC_HIEROGLYPHS",
"MEROITIC_CURSIVE",
"SORA_SOMPENG",
"CHAKMA",
"SHARADA",
"TAKRI",
"MIAO",
"CAUCASIAN_ALBANIAN",
"BASSA_VAH",
"DUPLOYAN",
"ELBASAN",
"GRANTHA",
"PAHAWH_HMONG",
"KHOJKI",
"LINEAR_A",
"MAHAJANI",
"MANICHAEAN",
"MENDE_KIKAKUI",
"MODI",
"MRO",
"OLD_NORTH_ARABIAN",
"NABATAEAN",
"PALMYRENE",
"PAU_CIN_HAU",
"OLD_PERMIC",
"PSALTER_PAHLAVI",
"SIDDHAM",
"KHUDAWADI",
"TIRHUTA",
"WARANG_CITI",
"AHOM",
"ANATOLIAN_HIEROGLYPHS",
"HATRAN",
"MULTANI",
"OLD_HUNGARIAN",
"SIGNWRITING",
"ADLAM",
"BHAIKSUKI",
"MARCHEN",
"NEWA",
"OSAGE",
"TANGUT",
"MASARAM_GONDI",
"NUSHU",
"SOYOMBO",
"ZANABAZAR_SQUARE",
"HANIFI_ROHINGYA",
"OLD_SOGDIAN",
"SOGDIAN",
"DOGRA",
"GUNJALA_GONDI",
"MAKASAR",
"MEDEFAIDRIN",
"ELYMAIC",
"NANDINAGARI",
"NYIAKENG_PUACHUE_HMONG",
"WANCHO",
"YEZIDI",
"CHORASMIAN",
"DIVES_AKURU",
"KHITAN_SMALL_SCRIPT",
"VITHKUQI",
"OLD_UYGHUR",
"CYPRO_MINOAN",
"TANGSA",
"TOTO",
"KAWI",
"NAG_MUNDARI"
],
"contains": [
"Big5-HKSCS",
"x-MS950-HKSCS",
"x-ISO-2022-CN-CNS",
"Big5",
"x-windows-950",
"EUC-JP",
"x-mswin-936",
"KOI8-R",
"GBK",
"x-Johab",
"windows-31j",
"GB2312",
"ISO-2022-KR",
"ISO-8859-4",
"x-windows-949",
"ISO-8859-3",
"TIS-620",
"ISO-8859-2",
"Shift_JIS",
"x-EUC-TW",
"ISO-8859-1",
"ISO-8859-8",
"ISO-8859-7",
"x-ISO-2022-CN-GB",
"ISO-8859-6",
"windows-1251",
"ISO-8859-5",
"UTF-16",
"UTF-8",
"ISO-8859-13",
"windows-1253",
"windows-1252",
"EUC-KR",
"windows-1255",
"ISO-8859-9",
"windows-1254",
"windows-1257",
"ISO-8859-16",
"windows-1256",
"ISO-8859-15",
"US-ASCII",
"windows-1258",
"UTF-16LE",
"x-ISCII91",
"ISO-2022-JP",
"UTF-16BE",
"JIS_X0201"
],
"canProduceError": true
},
{
"name": "GB2312",
"comment": "An early Simplified Chinese encoding standard covering the most common characters used in mainland China. It served as the foundation for GBK and GB18030.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7572,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "GBK",
"comment": "An extension of GB2312 that adds thousands of Simplified and Traditional Chinese characters. It is widely used in Windows systems and is backward-compatible with GB2312.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 21919,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "IBM-Thai",
"comment": "An IBM code page for Thai script based on TIS-620. It supports Thai characters and punctuation for legacy IBM systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 250,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM00858",
"comment": "A DOS-era IBM code page similar to CP850 but with the Euro symbol added. It supports Western European languages in legacy environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01140",
"comment": "An EBCDIC code page based on IBM037 with Euro support. It is used on IBM mainframes for Western European languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01141",
"comment": "An EBCDIC code page similar to IBM273 with Euro support. It supports German-language environments on IBM systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01142",
"comment": "An EBCDIC code page derived from IBM277 with Euro support. It is used for Danish and Norwegian text on IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01143",
"comment": "An EBCDIC code page based on IBM278 with Euro support. It is designed for Finnish and Swedish environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01144",
"comment": "An EBCDIC code page derived from IBM280 with Euro support. It supports Italian-language mainframe systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01145",
"comment": "An EBCDIC code page based on IBM284 with Euro support. It is used for Spanish-language environments on IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01146",
"comment": "An EBCDIC code page derived from IBM285 with Euro support. It supports UK English on IBM systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01147",
"comment": "An EBCDIC code page based on IBM297 with Euro support. It is used for French-language mainframe environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01148",
"comment": "An EBCDIC code page derived from IBM500 with Euro support. It supports multiple Western European languages on IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM01149",
"comment": "An EBCDIC code page based on IBM871 with Euro support. It is used for Icelandic-language environments on IBM systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM037",
"comment": "A core EBCDIC code page used in the United States and some Western countries. It supports basic Latin characters and control codes for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1006",
"comment": "An IBM code page for Urdu written in Arabic script (IBM EBCDIC). It supports contextual shaping for proper display.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"ARABIC"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM1025",
"comment": "An IBM Cyrillic code page used in Eastern Europe (IBM EBCDIC). It supports Russian, Bulgarian, and Serbian Cyrillic.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM1026",
"comment": "An EBCDIC code page used for Turkish language support. It includes Latin characters with Turkish-specific letters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1046",
"comment": "An IBM Arabic code page supporting contextual shaping (IBM EBCDIC). It is used in Middle Eastern IBM environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 245,
"scripts": [
"COMMON",
"LATIN",
"ARABIC"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM1047",
"comment": "An EBCDIC code page designed to better align with ASCII for easier interoperability. It is used in Unix-like environments on IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1097",
"comment": "An IBM Farsi code page (IBM EBCDIC). It supports Arabic-derived Persian script with contextual shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 252,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM1098",
"comment": "An IBM code page for Farsi with alternative mappings (IBM EBCDIC). It supports Persian letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 249,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM1112",
"comment": "An IBM code page for Estonian (IBM EBCDIC). It includes diacritics and letters used in Estonian orthography.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1122",
"comment": "An IBM code page for Latvian (IBM EBCDIC). It supports Latvian diacritics and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1123",
"comment": "An IBM code page for Ukrainian (IBM EBCDIC). It includes Ukrainian Cyrillic letters not found in KOI8-R.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1124",
"comment": "An IBM code page for Lithuanian (IBM EBCDIC). It supports Lithuanian diacritics and special characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1129",
"comment": "An IBM code page for Vietnamese (IBM EBCDIC). It uses combining diacritics to represent Vietnamese tones.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 349,
"scripts": [
"COMMON",
"LATIN",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM1166",
"comment": "An IBM code page for Belarusian (IBM EBCDIC). It includes Belarusian Cyrillic letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM1364",
"comment": "An IBM code page for Korean (IBM EBCDIC). It supports Hangul syllables and Hanja characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 17847,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM1381",
"comment": "An IBM code page for Simplified Chinese (IBM EBCDIC). It includes GB2312 characters and IBM extensions.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7609,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM1383",
"comment": "An IBM code page for Traditional Chinese (IBM EBCDIC). It includes Big5 characters and IBM-specific additions.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7634,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "IBM273",
"comment": "An EBCDIC code page used for German-language systems. It includes German umlauts and standard Latin characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM277",
"comment": "An EBCDIC code page for Danish and Norwegian languages. It supports regional letters and punctuation used in Scandinavia.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM278",
"comment": "An EBCDIC code page used for Finnish and Swedish languages. It includes Nordic characters and standard Latin letters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM280",
"comment": "An EBCDIC code page for Italian-language environments. It supports accented Italian characters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM284",
"comment": "An EBCDIC code page used for Spanish-language systems. It includes Spanish accented letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM285",
"comment": "An EBCDIC code page for UK English. It supports British punctuation and currency symbols.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM290",
"comment": "An EBCDIC code page for Japanese Katakana. It was used on IBM mainframes before multibyte encodings became common.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 321,
"scripts": [
"COMMON",
"LATIN",
"KATAKANA"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM29626C",
"comment": "An IBM code page for Chinese used in AIX systems (IBM EBCDIC). It supports CNS 11643 planes and extended characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 3,
"alignment": 1,
"codePointCount": 7595,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "IBM297",
"comment": "An EBCDIC code page for French-language systems. It includes accented French characters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM300",
"comment": "A double-byte IBM code page for Japanese (IBM EBCDIC). It supports Kanji, Hiragana, Katakana, and symbols.",
"minBytesPerChar": 2,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7309,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM33722",
"comment": "An IBM code page for Korean used in AIX (IBM EBCDIC). It supports KS X 1001 and extended Hangul.",
"minBytesPerChar": 1,
"maxBytesPerChar": 3,
"alignment": 1,
"codePointCount": 7540,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM420",
"comment": "An EBCDIC code page for Arabic script. It supports contextual shaping required for Arabic text.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 427,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM424",
"comment": "An EBCDIC code page for Hebrew script. It supports Hebrew letters and right-to-left text direction.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 217,
"scripts": [
"COMMON",
"LATIN",
"HEBREW"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM437",
"comment": "The original IBM PC code page used in DOS. It includes box-drawing characters and basic Latin letters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM500",
"comment": "An EBCDIC code page supporting multiple Western European languages. It includes accented characters and punctuation for multilingual environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM737",
"comment": "A DOS code page for Greek. It includes Greek letters and basic punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM775",
"comment": "A code page used for Baltic languages such as Latvian and Lithuanian. It supports diacritics and regional characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM833",
"comment": "An IBM code page for Korean (IBM EBCDIC). It supports early Hangul encodings and Hanja.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 310,
"scripts": [
"COMMON",
"LATIN",
"HANGUL"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM834",
"comment": "An IBM code page for Korean similar to x-IBM833 but with additional characters (IBM EBCDIC). It supports extended Hangul and Hanja.",
"minBytesPerChar": 2,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 8839,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM850",
"comment": "A DOS code page for Western European languages. It expands on CP437 by adding more accented characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM852",
"comment": "A DOS code page for Central and Eastern European languages. It supports diacritics used in Polish, Czech, Slovak, and related languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM855",
"comment": "A DOS code page for Cyrillic languages. It includes Russian, Bulgarian, and Serbian Cyrillic characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM856",
"comment": "A DOS code page for Hebrew. It supports Hebrew letters but lacks right-to-left control characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 214,
"scripts": [
"COMMON",
"LATIN",
"HEBREW"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM857",
"comment": "A DOS code page for Turkish. It includes Turkish-specific letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 252,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM860",
"comment": "A DOS code page for Portuguese as used in Portugal. It includes accented characters and symbols.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM861",
"comment": "A DOS code page for Icelandic. It includes Icelandic letters and diacritics.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM862",
"comment": "A DOS code page for Hebrew. It supports Hebrew letters and right-to-left text.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"HEBREW"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM863",
"comment": "A DOS code page for Canadian French. It includes accented French characters used in Canada.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM864",
"comment": "A DOS code page for Arabic. It supports Arabic letters and contextual forms.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 250,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"ARABIC",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM865",
"comment": "A DOS code page for Nordic languages. It includes characters used in Danish, Norwegian, and Icelandic.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM866",
"comment": "A DOS code page for Russian and other Cyrillic languages. It became widely used in Eastern Europe and the former Soviet Union.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM868",
"comment": "A DOS code page for Arabic used in some regions. It supports Arabic letters and basic punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 253,
"scripts": [
"COMMON",
"LATIN",
"ARABIC"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM869",
"comment": "A DOS code page for Greek. It includes Greek letters and diacritics.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 246,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM870",
"comment": "An EBCDIC code page for multilingual Latin scripts including Eastern European languages. It supports accented characters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "IBM871",
"comment": "An EBCDIC code page for Icelandic. It includes Icelandic letters and special characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM874",
"comment": "A Windows and DOS code page for Thai. It supports Thai script without contextual shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 219,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM875",
"comment": "An EBCDIC code page for Greek. It includes Greek letters and punctuation for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 249,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "IBM918",
"comment": "An EBCDIC code page for Urdu. It supports Arabic-derived Urdu script with contextual shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"ARABIC"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM921",
"comment": "A Baltic code page supporting Latvian, Lithuanian, and Estonian. It includes regional diacritics and symbols.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM922",
"comment": "A Baltic code page similar to x-IBM921 but with alternative mappings. It supports additional regional characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-IBM930",
"comment": "A Japanese EBCDIC mixed single-byte and double-byte code page. It supports Kanji and Katakana for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 7541,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM933",
"comment": "A Korean EBCDIC mixed-byte code page. It supports Hangul and Hanja for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 9047,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM935",
"comment": "A Simplified Chinese EBCDIC mixed-byte code page. It supports GB2312 characters for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 7636,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM937",
"comment": "A Traditional Chinese EBCDIC mixed-byte code page. It supports Big5 characters for IBM mainframes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 14026,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM939",
"comment": "A Japanese EBCDIC mixed-byte code page similar to x-IBM930 but with extended characters. It supports Kanji and Katakana.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 7542,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM942",
"comment": "A Shift_JIS-based IBM code page for Japanese. It includes IBM extensions and vendor-specific characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7511,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM942C",
"comment": "A variant of x-IBM942 with corrected mappings. It improves compatibility with standard Shift_JIS.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7511,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM943",
"comment": "An IBM code page combining Shift_JIS with additional Kanji. It supports a wide range of Japanese characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7560,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM943C",
"comment": "A corrected version of x-IBM943 with improved character mappings. It enhances compatibility with Windows-31J.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7562,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM948",
"comment": "An IBM code page for Simplified Chinese based on GBK. It includes IBM extensions for additional characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 13996,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM949",
"comment": "An IBM code page for Korean based on EUC-KR. It includes extended Hangul syllables.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 8965,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM949C",
"comment": "A corrected version of x-IBM949 with improved mappings. It enhances compatibility with Windows Korean encodings.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 8965,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM950",
"comment": "An IBM code page for Traditional Chinese based on Big5. It includes IBM extensions for additional characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 13993,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-IBM964",
"comment": "An IBM code page for Traditional Chinese used in Taiwan. It supports CNS 11643 plane mappings.",
"minBytesPerChar": 1,
"maxBytesPerChar": 4,
"alignment": 1,
"codePointCount": 14023,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-IBM970",
"comment": "An IBM code page for Korean supporting Hangul and Hanja. It is used in IBM mainframe environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 8388,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-ISCII91",
"comment": "An Indian encoding standard supporting multiple Indic scripts through a shared code structure. It uses shift codes to switch between scripts.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 233,
"scripts": [
"COMMON",
"LATIN",
"DEVANAGARI",
"INHERITED"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-ISO-2022-CN-CNS",
"comment": "A variant of ISO-2022-CN supporting CNS 11643 character planes. It enables Traditional Chinese encoding in 7-bit environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 8,
"alignment": 1,
"codePointCount": 19966,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"BOPOMOFO",
"HAN"
],
"contains": [
"x-EUC-TW",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-ISO-2022-CN-GB",
"comment": "A variant of ISO-2022-CN supporting GB2312. It enables Simplified Chinese encoding in 7-bit environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 7,
"alignment": 1,
"codePointCount": 7572,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"GB2312",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-2022-JP",
"comment": "A Japanese encoding that switches between ASCII, JIS X 0201, and JIS X 0208 using escape sequences. It was widely used for email and early web content in Japan.",
"minBytesPerChar": 1,
"maxBytesPerChar": 8,
"alignment": 1,
"codePointCount": 7071,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-windows-iso2022jp",
"x-windows-50220",
"x-windows-50221",
"x-JIS0208",
"ISO-2022-JP-2",
"JIS_X0201",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-2022-JP-2",
"comment": "An extension of ISO-2022-JP that adds additional character sets including Chinese and Korean. It was intended for multilingual communication but saw limited adoption.",
"minBytesPerChar": 1,
"maxBytesPerChar": 9,
"alignment": 1,
"codePointCount": 13138,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-windows-iso2022jp",
"x-windows-50220",
"x-windows-50221",
"x-JIS0208",
"ISO-2022-JP",
"JIS_X0201",
"JIS_X0212-1990",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-2022-KR",
"comment": "A Korean encoding that switches between ASCII and KS X 1001 using escape sequences. It was used in email systems that required 7-bit compatibility.",
"minBytesPerChar": 1,
"maxBytesPerChar": 7,
"alignment": 1,
"codePointCount": 8354,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"EUC-KR",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-1",
"comment": "A widely used Western European encoding also known as Latin-1. It supports major Western European languages but lacks the Euro symbol.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "x-iso-8859-11",
"comment": "A Thai encoding similar to TIS-620 but with additional control characters. It supports Thai script without shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 247,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-13",
"comment": "A Baltic language encoding supporting Latvian, Lithuanian, and Estonian. It includes diacritics needed for regional languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-15",
"comment": "A revision of Latin-1 that adds the Euro symbol and replaces some rarely used characters. It was intended as a modernized Western European encoding.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-16",
"comment": "A South-Eastern European encoding supporting Romanian, Albanian, and related languages. It includes characters missing from earlier ISO-8859 sets.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-2",
"comment": "A Central European encoding supporting Polish, Czech, Slovak, and Hungarian. It includes diacritics used in Slavic and Finno-Ugric languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-3",
"comment": "A South European encoding supporting Maltese, Esperanto, and Turkish. It was less widely adopted than other ISO-8859 variants.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 248,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-4",
"comment": "A Baltic encoding supporting Estonian, Latvian, and Lithuanian. It was later superseded by ISO-8859-13.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-5",
"comment": "A Cyrillic encoding supporting Russian, Bulgarian, and Serbian. It was used before Unicode and Windows-1251 became dominant.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "ISO-8859-6",
"comment": "An Arabic encoding supporting basic Arabic letters. It does not include contextual shaping, making it unsuitable for display without additional processing.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 210,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-7",
"comment": "A Greek encoding supporting modern Greek characters. It was widely used before Unicode adoption.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 252,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-8",
"comment": "A Hebrew encoding supporting Hebrew letters. It does not include vowel points or right-to-left control characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 219,
"scripts": [
"COMMON",
"LATIN",
"HEBREW"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "ISO-8859-9",
"comment": "A Turkish encoding based on Latin-1 but replacing Icelandic letters with Turkish ones. It supports modern Turkish orthography.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "x-JIS0208",
"comment": "A Japanese character set containing thousands of Kanji and kana. It forms the basis of many Japanese encodings including Shift_JIS and EUC-JP.",
"minBytesPerChar": 2,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 6879,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "JIS_X0201",
"comment": "A Japanese encoding containing ASCII and half-width Katakana. It is often used as part of larger Japanese encoding schemes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 192,
"scripts": [
"COMMON",
"LATIN",
"KATAKANA"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "JIS_X0212-1990",
"comment": "A supplementary Japanese character set containing additional Kanji. It is used in extended Japanese encodings such as ISO-2022-JP-2.",
"minBytesPerChar": 2,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 6067,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HAN"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-Johab",
"comment": "A Korean encoding supporting full Hangul composition. It provides complete coverage of modern Hangul syllables.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 17175,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "KOI8-R",
"comment": "A Cyrillic encoding widely used in Russia and the former Soviet Union. It supports Russian, Bulgarian, and other Cyrillic languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "KOI8-U",
"comment": "A Cyrillic encoding designed for Ukrainian. It extends KOI8-R with additional Ukrainian letters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "x-MacArabic",
"comment": "A legacy Mac OS encoding for Arabic. It includes contextual forms for proper Arabic rendering.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 229,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacCentralEurope",
"comment": "A Mac OS encoding for Central European languages. It supports diacritics used in Polish, Czech, Slovak, and Hungarian.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-MacCroatian",
"comment": "A Mac OS encoding for Croatian. It includes accented characters used in Croatian orthography.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacCyrillic",
"comment": "A Mac OS encoding for Cyrillic languages. It supports Russian, Bulgarian, and Serbian Cyrillic.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-MacDingbat",
"comment": "A Mac OS symbol encoding containing decorative and typographic symbols. It includes ornaments, arrows, and shapes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 220,
"scripts": [
"COMMON"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacGreek",
"comment": "A Mac OS encoding for Greek. It includes Greek letters and diacritics used in modern Greek.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacHebrew",
"comment": "A Mac OS encoding for Hebrew. It supports Hebrew letters and right-to-left text.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 213,
"scripts": [
"COMMON",
"LATIN",
"HEBREW"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacIceland",
"comment": "A Mac OS encoding for Icelandic. It includes Icelandic letters and diacritics.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacRoman",
"comment": "The primary Mac OS Roman encoding for Western European languages. It includes accented letters and typographic symbols.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacRomania",
"comment": "A Mac OS encoding for Romanian. It includes Romanian diacritics and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacSymbol",
"comment": "A Mac OS symbol encoding containing mathematical and typographic symbols. It includes arrows, operators, and Greek letters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 195,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacThai",
"comment": "A Mac OS encoding for Thai. It supports Thai script without contextual shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 227,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacTurkish",
"comment": "A Mac OS encoding for Turkish. It includes Turkish-specific letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 253,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [],
"canProduceError": true
},
{
"name": "x-MacUkraine",
"comment": "A Mac OS encoding for Ukrainian. It includes Ukrainian Cyrillic letters and diacritics.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [],
"canProduceError": false
},
{
"name": "x-MS932_0213",
"comment": "A Microsoft variant of Shift_JIS that includes JIS X 0213 characters. It expands the available Kanji set beyond standard Shift_JIS.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 11491,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN",
"INHERITED"
],
"contains": [
"windows-31j",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-MS950-HKSCS",
"comment": "A Microsoft Big5 variant including Hong Kong Supplementary Character Set mappings. It supports Cantonese-specific and government-required characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 18585,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"x-windows-950",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-MS950-HKSCS-XP",
"comment": "A Windows XP version of the HKSCS Big5 extension. It includes older mappings that differ from later HKSCS releases.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 16633,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"x-windows-950",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-mswin-936",
"comment": "A Microsoft implementation of GBK for Simplified Chinese. It supports a wide range of Chinese characters used on Windows systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 21919,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-PCK",
"comment": "A variant of Shift_JIS used on Solaris systems. It includes vendor-specific extensions for Japanese text.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7518,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "Shift_JIS",
"comment": "A major Japanese encoding combining single-byte and double-byte sequences. It supports Kanji, Hiragana, Katakana, and ASCII.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7071,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-SJIS_0213",
"comment": "A Shift_JIS variant supporting JIS X 0213 characters. It expands the Kanji repertoire for modern Japanese usage.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 11398,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN",
"INHERITED"
],
"contains": [
"Shift_JIS",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "TIS-620",
"comment": "The standard Thai character encoding used in Thailand. It supports Thai script without contextual shaping.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 215,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1250",
"comment": "A Central European Windows encoding supporting Polish, Czech, Slovak, and Hungarian. It includes diacritics used in Slavic languages.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 250,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1251",
"comment": "A Cyrillic Windows encoding supporting Russian, Bulgarian, and Serbian. It became the de facto standard for Cyrillic text on Windows.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 254,
"scripts": [
"COMMON",
"LATIN",
"CYRILLIC"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1252",
"comment": "A Western European Windows encoding often mistaken for ISO-8859-1. It includes additional printable characters such as smart quotes.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 250,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1253",
"comment": "A Greek Windows encoding supporting modern Greek. It includes accented Greek letters and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 238,
"scripts": [
"COMMON",
"LATIN",
"GREEK"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1254",
"comment": "A Turkish Windows encoding similar to ISO-8859-9. It supports Turkish-specific letters and symbols.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 248,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1255",
"comment": "A Hebrew Windows encoding supporting Hebrew letters and vowel points. It includes right-to-left control characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 232,
"scripts": [
"COMMON",
"LATIN",
"HEBREW"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1256",
"comment": "An Arabic Windows encoding supporting Arabic letters and contextual forms. It includes characters for Persian and Urdu as well.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 255,
"scripts": [
"COMMON",
"LATIN",
"ARABIC",
"INHERITED"
],
"contains": [
"US-ASCII"
],
"canProduceError": false
},
{
"name": "windows-1257",
"comment": "A Baltic Windows encoding supporting Latvian, Lithuanian, and Estonian. It includes regional diacritics and punctuation.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 243,
"scripts": [
"COMMON",
"LATIN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-1258",
"comment": "A Vietnamese Windows encoding supporting tone marks and diacritics. It uses combining characters to represent Vietnamese vowels.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 246,
"scripts": [
"COMMON",
"LATIN",
"INHERITED"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "windows-31j",
"comment": "A Microsoft extension of Shift_JIS adding vendor-specific characters. It is widely used in Japanese Windows environments.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 7528,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"JIS_X0201",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-50220",
"comment": "A Windows variant of ISO-2022-JP using escape sequences for Japanese text. It supports 7-bit transport environments such as email.",
"minBytesPerChar": 1,
"maxBytesPerChar": 9,
"alignment": 1,
"codePointCount": 13308,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-windows-iso2022jp",
"x-windows-50221",
"x-JIS0208",
"ISO-2022-JP",
"ISO-2022-JP-2",
"JIS_X0201",
"JIS_X0212-1990",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-50221",
"comment": "A Windows version of ISO-2022-JP that allows 8-bit bytes. It improves compatibility with applications that do not enforce strict 7-bit paths.",
"minBytesPerChar": 1,
"maxBytesPerChar": 9,
"alignment": 1,
"codePointCount": 13308,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-windows-iso2022jp",
"x-windows-50220",
"x-JIS0208",
"ISO-2022-JP",
"ISO-2022-JP-2",
"JIS_X0201",
"JIS_X0212-1990",
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-874",
"comment": "A Windows encoding for Thai similar to TIS-620. It includes additional symbols used in Windows applications.",
"minBytesPerChar": 1,
"maxBytesPerChar": 1,
"alignment": 1,
"codePointCount": 224,
"scripts": [
"COMMON",
"LATIN",
"THAI"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-949",
"comment": "A Windows encoding for Korean based on EUC-KR. It includes extended Hangul syllables and vendor-specific characters.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 17175,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HANGUL",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-950",
"comment": "A Windows encoding for Traditional Chinese based on Big5. It includes additional characters used in Taiwanese and Hong Kong systems.",
"minBytesPerChar": 1,
"maxBytesPerChar": 2,
"alignment": 1,
"codePointCount": 13620,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"BOPOMOFO",
"HAN"
],
"contains": [
"US-ASCII"
],
"canProduceError": true
},
{
"name": "x-windows-iso2022jp",
"comment": "A Windows variant of ISO-2022-JP with modified escape sequences. It improves compatibility with Japanese email and legacy applications.",
"minBytesPerChar": 1,
"maxBytesPerChar": 8,
"alignment": 1,
"codePointCount": 7525,
"scripts": [
"COMMON",
"LATIN",
"GREEK",
"CYRILLIC",
"HIRAGANA",
"KATAKANA",
"HAN"
],
"contains": [
"x-windows-50220",
"x-windows-50221",
"x-JIS0208",
"ISO-2022-JP",
"ISO-2022-JP-2",
"JIS_X0201",
"US-ASCII"
],
"canProduceError": true
}
]
}
Reference in New Issue View Git Blame Copy Permalink