Skip to content

Instantly share code, notes, and snippets.

@phayes

phayes/alphabets_and_scripts.json

Last active May 17, 2024 18:33
Show Gist options
  • Save phayes/99e52dc1d32bb2db6b331a674d3dcefe to your computer and use it in GitHub Desktop.
Save phayes/99e52dc1d32bb2db6b331a674d3dcefe to your computer and use it in GitHub Desktop.
Download ZIP
A JSON list of common alphabets and scripts and some of their properties
Raw
alphabets_and_scripts.json
{
"Latn": {
"iso_code": "Latn",
"iso_number": 215,
"name": "Latin",
"unicode_ranges": ["U+0000–U+007F", "U+0080–U+00FF", "U+0100–U+017F", "U+0180–U+024F", "U+1E00–U+1EFF", "U+2C60–U+2C7F", "U+A720–U+A7FF"],
"languages": ["en", "fr", "de", "es", "pt", "it", "nl", "pl", "sv", "da", "no", "fi", "hu", "ro", "cs", "sk", "hr", "bs", "sl", "is"],
"direction": "ltr",
"casing": true,
"family": "Latin",
"script_type": "alphabet"
},
"Arab": {
"iso_code": "Arab",
"iso_number": 160,
"name": "Arabic",
"unicode_ranges": ["U+0600–U+06FF", "U+0750–U+077F", "U+08A0–U+08FF", "U+FB50–U+FDFF", "U+FE70–U+FEFF"],
"languages": ["ar", "fa", "ur", "ps", "ku"],
"direction": "rtl",
"casing": false,
"family": "Semitic",
"script_type": "abjad"
},
"Cyrl": {
"iso_code": "Cyrl",
"iso_number": 220,
"name": "Cyrillic",
"unicode_ranges": ["U+0400–U+04FF", "U+0500–U+052F", "U+2DE0–U+2DFF", "U+A640–U+A69F"],
"languages": ["ru", "uk", "bg", "sr", "mk", "be", "kk", "uz", "mn", "ky", "tg"],
"direction": "ltr",
"casing": true,
"family": "Cyrillic",
"script_type": "alphabet"
},
"Grek": {
"iso_code": "Grek",
"iso_number": 200,
"name": "Greek",
"unicode_ranges": ["U+0370–U+03FF", "U+1F00–U+1FFF"],
"languages": ["el"],
"direction": "ltr",
"casing": true,
"family": "Greek",
"script_type": "alphabet"
},
"Hebr": {
"iso_code": "Hebr",
"iso_number": 125,
"name": "Hebrew",
"unicode_ranges": ["U+0590–U+05FF", "U+FB1D–U+FB4F"],
"languages": ["he", "yi"],
"direction": "rtl",
"casing": false,
"family": "Semitic",
"script_type": "abjad"
},
"Deva": {
"iso_code": "Deva",
"iso_number": 315,
"name": "Devanagari",
"unicode_ranges": ["U+0900–U+097F", "U+A8E0–U+A8FF"],
"languages": ["hi", "mr", "ne", "sa"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Hani": {
"iso_code": "Hani",
"iso_number": 500,
"name": "Han",
"unicode_ranges": ["U+4E00–U+9FFF", "U+3400–U+4DBF", "U+20000–U+2A6DF", "U+2A700–U+2B73F", "U+2B740–U+2B81F", "U+2B820–U+2CEAF", "U+F900–U+FAFF", "U+2F800–U+2FA1F"],
"languages": ["zh", "ja", "ko"],
"direction": "ltr",
"casing": false,
"family": "Han",
"script_type": "logographic"
},
"Hira": {
"iso_code": "Hira",
"iso_number": 410,
"name": "Hiragana",
"unicode_ranges": ["U+3040–U+309F", "U+1B001–U+1B11F"],
"languages": ["ja"],
"direction": "ltr",
"casing": false,
"family": "Kana",
"script_type": "syllabary"
},
"Kana": {
"iso_code": "Kana",
"iso_number": 411,
"name": "Katakana",
"unicode_ranges": ["U+30A0–U+30FF", "U+31F0–U+31FF", "U+32D0–U+32FF", "U+3300–U+3357"],
"languages": ["ja"],
"direction": "ltr",
"casing": false,
"family": "Kana",
"script_type": "syllabary"
},
"Hebr": {
"iso_code": "Hebr",
"iso_number": 125,
"name": "Hebrew",
"unicode_ranges": ["U+0590–U+05FF", "U+FB1D–U+FB4F"],
"languages": ["he", "yi"],
"direction": "rtl",
"casing": false,
"family": "Semitic",
"script_type": "abjad"
},
"Deva": {
"iso_code": "Deva",
"iso_number": 315,
"name": "Devanagari",
"unicode_ranges": ["U+0900–U+097F", "U+A8E0–U+A8FF"],
"languages": ["hi", "mr", "ne", "sa"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Ethi": {
"iso_code": "Ethi",
"iso_number": 430,
"name": "Ethiopic",
"unicode_ranges": ["U+1200–U+137F", "U+1380–U+139F", "U+2D80–U+2DDF", "U+AB00–U+AB2F"],
"languages": ["am", "gez"],
"direction": "ltr",
"casing": false,
"family": "Ethiopic",
"script_type": "abugida"
},
"Beng": {
"iso_code": "Beng",
"iso_number": 325,
"name": "Bengali",
"unicode_ranges": ["U+0980–U+09FF"],
"languages": ["bn", "as"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Thai": {
"iso_code": "Thai",
"iso_number": 352,
"name": "Thai",
"unicode_ranges": ["U+0E00–U+0E7F"],
"languages": ["th"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Taml": {
"iso_code": "Taml",
"iso_number": 346,
"name": "Tamil",
"unicode_ranges": ["U+0B80–U+0BFF"],
"languages": ["ta"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Knda": {
"iso_code": "Knda",
"iso_number": 345,
"name": "Kannada",
"unicode_ranges": ["U+0C80–U+0CFF"],
"languages": ["kn"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Mlym": {
"iso_code": "Mlym",
"iso_number": 347,
"name": "Malayalam",
"unicode_ranges": ["U+0D00–U+0D7F"],
"languages": ["ml"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Sinh": {
"iso_code": "Sinh",
"iso_number":
348,
"name": "Sinhala",
"unicode_ranges": ["U+0D80–U+0DFF"],
"languages": ["si"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Mymr": {
"iso_code": "Mymr",
"iso_number": 350,
"name": "Myanmar",
"unicode_ranges": ["U+1000–U+109F"],
"languages": ["my", "shn"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Laoo": {
"iso_code": "Laoo",
"iso_number": 356,
"name": "Lao",
"unicode_ranges": ["U+0E80–U+0EFF"],
"languages": ["lo"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Telu": {
"iso_code": "Telu",
"iso_number": 340,
"name": "Telugu",
"unicode_ranges": ["U+0C00–U+0C7F"],
"languages": ["te"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Khmr": {
"iso_code": "Khmr",
"iso_number": 355,
"name": "Khmer",
"unicode_ranges": ["U+1780–U+17FF", "U+19E0–U+19FF"],
"languages": ["km"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Hang": {
"iso_code": "Hang",
"iso_number": 286,
"name": "Hangul",
"unicode_ranges": ["U+1100–U+11FF", "U+3130–U+318F", "U+AC00–U+D7AF", "U+D7B0–U+D7FF"],
"languages": ["ko"],
"direction": "ltr",
"casing": false,
"family": "Koreanic",
"script_type": "alphabet"
},
"Thai": {
"iso_code": "Thai",
"iso_number": 352,
"name": "Thai",
"unicode_ranges": ["U+0E00–U+0E7F"],
"languages": ["th"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Geor": {
"iso_code": "Geor",
"iso_number": 240,
"name": "Georgian",
"unicode_ranges": ["U+10A0–U+10FF", "U+2D00–U+2D2F"],
"languages": ["ka"],
"direction": "ltr",
"casing": false,
"family": "Kartvelian",
"script_type": "alphabet"
},
"Armn": {
"iso_code": "Armn",
"iso_number": 230,
"name": "Armenian",
"unicode_ranges": ["U+0530–U+058F"],
"languages": ["hy"],
"direction": "ltr",
"casing": false,
"family": "Indo-European",
"script_type": "alphabet"
},
"Tfng": {
"iso_code": "Tfng",
"iso_number": 120,
"name": "Tifinagh",
"unicode_ranges": ["U+2D30–U+2D7F"],
"languages": ["ber"],
"direction": "ltr",
"casing": false,
"family": "Afro-Asiatic",
"script_type": "abjad"
},
"Orya": {
"iso_code": "Orya",
"iso_number": 327,
"name": "Oriya",
"unicode_ranges": ["U+0B00–U+0B7F"],
"languages": ["or"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Tale": {
"iso_code": "Tale",
"iso_number": 353,
"name": "Tai Le",
"unicode_ranges": ["U+1950–U+197F"],
"languages": ["tdd"],
"direction": "ltr",
"casing": false,
"family": "Tai-Kadai",
"script_type": "syllabary"
},
"Lisu": {
"iso_code": "Lisu",
"iso_number": 399,
"name": "Lisu",
"unicode_ranges": ["U+A4D0–U+A4FF"],
"languages": ["lis"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "alphabet"
},
"Yiii": {
"iso_code": "Yiii",
"iso_number": 460,
"name": "Yi",
"unicode_ranges": ["U+A000–U+A48F", "U+A490–U+A4CF"],
"languages": ["ii"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "syllabary"
},
"Lana": {
"iso_code": "Lana",
"iso_number": 351,
"name": "Lanna",
"unicode_ranges": ["U+1A20–U+1AAF"],
"languages": ["nod"],
"direction": "ltr",
"casing": false,
"family": "Tai-Kadai",
"script_type": "syllabary"
},
"Bopo": {
"iso_code": "Bopo",
"iso_number": 285,
"name": "Bopomofo",
"unicode_ranges": ["U+3100–U+312F", "U+31A0–U+31BF"],
"languages": ["zh"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "syllabary"
},
"Cher": {
"iso_code": "Cher",
"iso_number": 445,
"name": "Cherokee",
"unicode_ranges": ["U+13A0–U+13FF", "U+AB70–U+ABBF"],
"languages": ["chr"],
"direction": "ltr",
"casing": false,
"family": "Iroquoian",
"script_type": "syllabary"
},
"Runr": {
"iso_code": "Runr",
"iso_number": 211,
"name": "Runic",
"unicode_ranges": ["U+16A0–U+16FF"],
"languages": ["non"],
"direction": "ltr",
"casing": false,
"family": "Indo-European",
"script_type": "alphabet"
},
"Sund": {
"iso_code": "Sund",
"iso_number": 362,
"name": "Sundanese",
"unicode_ranges": ["U+1B80–U+1BBF"],
"languages": ["su"],
"direction": "ltr",
"casing": false,
"family": "Austronesian",
"script_type": "abugida"
},
"Guru": {
"iso_code": "Guru",
"iso_number": 310,
"name": "Gurmukhi",
"unicode_ranges": ["U+0A00–U+0A7F"],
"languages": ["pa"],
"direction": "ltr",
"casing": false,
"family": "Brahmic",
"script_type": "abugida"
},
"Tibt": {
"iso_code": "Tibt",
"iso_number": 330,
"name": "Tibetan",
"unicode_ranges": ["U+0F00–U+0FFF"],
"languages": ["bo", "dz"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "abugida"
},
"Tglg": {
"iso_code": "Tglg",
"iso_number": 370,
"name": "Tagalog",
"unicode_ranges": ["U+1700–U+171F"],
"languages": ["tl"],
"direction": "ltr",
"casing": false,
"family": "Austronesian",
"script_type": "abugida"
},
"Glag": {
"iso_code": "Glag",
"iso_number": 225,
"name": "Glagolitic",
"unicode_ranges": ["U+2C00–U+2C5F"],
"languages": ["cu"],
"direction": "ltr",
"casing": true,
"family": "Indo-European",
"script_type": "alphabet"
},
"Copt": {
"iso_code": "Copt",
"iso_number": 204,
"name": "Coptic",
"unicode_ranges": ["U+2C80–U+2CFF"],
"languages": ["cop"],
"direction": "ltr",
"casing": true,
"family": "Afro-Asiatic",
"script_type": "alphabet"
},
"Goth": {
"iso_code": "Goth",
"iso_number": 206,
"name": "Gothic",
"unicode_ranges": ["U+10330–U+1034F"],
"languages": ["got"],
"direction": "ltr",
"casing": true,
"family": "Indo-European",
"script_type": "alphabet"
},
"Osge": {
"iso_code": "Osge",
"iso_number": 219,
"name": "Osage",
"unicode_ranges": ["U+104B0–U+104FF"],
"languages": ["osa"],
"direction": "ltr",
"casing": false,
"family": "Siouan",
"script_type": "alphabet"
},
"Cans": {
"iso_code": "Cans",
"iso_number": 440,
"name": "Canadian Aboriginal Syllabics",
"unicode_ranges": ["U+1400–U+167F", "U+18B0–U+18FF"],
"languages": ["cr", "iu", "oj"],
"direction": "ltr",
"casing": false,
"family": "Algonquian",
"script_type": "syllabary"
},
"Limb": {
"iso_code": "Limb",
"iso_number": 336,
"name": "Limbu",
"unicode_ranges": ["U+1900–U+194F"],
"languages": ["lif"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "abugida"
},
"Bali": {
"iso_code": "Bali",
"iso_number": 360,
"name": "Balinese",
"unicode_ranges": ["U+1B00–U+1B7F"],
"languages": ["ban"],
"direction": "ltr",
"casing": false,
"family": "Austronesian",
"script_type": "abugida"
},
"Lepc": {
"iso_code": "Lepc",
"iso_number": 335,
"name": "Lepcha",
"unicode_ranges": ["U+1C00–U+1C4F"],
"languages": ["lep"],
"direction": "ltr",
"casing": false,
"family": "Sino-Tibetan",
"script_type": "abugida"
},
"Vaii": {
"iso_code": "Vaii",
"iso_number": 470,
"name": "Vai",
"unicode_ranges": ["U+A500–U+A63F"],
"languages": ["vai"],
"direction": "ltr",
"casing": false,
"family": "Mande",
"script_type": "syllabary"
},
"Sora": {
"iso_code": "Sora",
"iso_number": 398,
"name": "Sora Sompeng",
"unicode_ranges": ["U+110D0–U+110FF"],
"languages": ["srb"],
"direction": "ltr",
"casing": false,
"family": "Austroasiatic",
"script_type": "alphabet"
},
"Bugi": {
"iso_code": "Bugi",
"iso_number": 367,
"name": "Buginese",
"unicode_ranges": ["U+1A00–U+1A1F"],
"languages": ["bug"],
"direction": "ltr",
"casing": false,
"family": "Austronesian",
"script_type": "abugida"
},
"Tagb": {
"iso_code": "Tagb",
"iso_number": 373,
"name": "Tagbanwa",
"unicode_ranges": ["U+1760–U+177F"],
"languages": ["tbw"],
"direction": "ltr",
"casing": false,
"family": "Austronesian",
"script_type": "abugida"
},
"Lana": {
"iso_code": "Lana",
"iso_number": 351,
"name": "Lanna",
"unicode_ranges": ["U+1A20–U+1AAF"],
"languages": ["nod"],
"direction": "ltr",
"casing": false,
"family": "Tai-Kadai",
"script_type": "syllabary"
},
"Tale": {
"iso_code": "Tale",
"iso_number": 353,
"name": "Tai Le",
"unicode_ranges": ["U+1950–U+197F"],
"languages": ["tdd"],
"direction": "ltr",
"casing": false,
"family": "Tai-Kadai",
"script_type": "syllabary"
},
"Cprt": {
"iso_code": "Cprt",
"iso_number": 403,
"name": "Cypriot",
"unicode_ranges": ["U+10800–U+1083F"],
"languages": ["grc"],
"direction": "rtl",
"casing": false,
"family": "Indo-European",
"script_type": "syllabary"
},
"Xsux": {
"iso_code": "Xsux",
"iso_number": 101,
"name": "Cuneiform",
"unicode_ranges": ["U+12000–U+123FF", "U+12400–U+1247F"],
"languages": ["akk"],
"direction": "ltr",
"casing": false,
"family": "Afro-Asiatic",
"script_type": "logographic"
},
"Ugar": {
"iso_code": "Ugar",
"iso_number": 40,
"name": "Ugaritic",
"unicode_ranges": ["U+10380–U+1039F"],
"languages": ["uga"],
"direction": "ltr",
"casing": false,
"family": "Afro-Asiatic",
"script_type": "alphabet"
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment