SickGear/lib/hachoir/core/iso639.py

557 lines
18 KiB
Python
Raw Permalink Normal View History

"""
ISO639-2 standart: the module only contains the dictionary ISO639_2
which maps a language code in three letters (eg. "fre") to a language
name in english (eg. "French").
"""
# ISO-639, the list comes from:
# http://www.loc.gov/standards/iso639-2/php/English_list.php
_ISO639 = (
("Abkhazian", "abk", "ab"),
("Achinese", "ace", None),
("Acoli", "ach", None),
("Adangme", "ada", None),
("Adygei", "ady", None),
("Adyghe", "ady", None),
("Afar", "aar", "aa"),
("Afrihili", "afh", None),
("Afrikaans", "afr", "af"),
("Afro-Asiatic (Other)", "afa", None),
("Ainu", "ain", None),
("Akan", "aka", "ak"),
("Akkadian", "akk", None),
("Albanian", "alb/sqi", "sq"),
("Alemani", "gsw", None),
("Aleut", "ale", None),
("Algonquian languages", "alg", None),
("Altaic (Other)", "tut", None),
("Amharic", "amh", "am"),
("Angika", "anp", None),
("Apache languages", "apa", None),
("Arabic", "ara", "ar"),
("Aragonese", "arg", "an"),
("Aramaic", "arc", None),
("Arapaho", "arp", None),
("Araucanian", "arn", None),
("Arawak", "arw", None),
("Armenian", "arm/hye", "hy"),
("Aromanian", "rup", None),
("Artificial (Other)", "art", None),
("Arumanian", "rup", None),
("Assamese", "asm", "as"),
("Asturian", "ast", None),
("Athapascan languages", "ath", None),
("Australian languages", "aus", None),
("Austronesian (Other)", "map", None),
("Avaric", "ava", "av"),
("Avestan", "ave", "ae"),
("Awadhi", "awa", None),
("Aymara", "aym", "ay"),
("Azerbaijani", "aze", "az"),
("Bable", "ast", None),
("Balinese", "ban", None),
("Baltic (Other)", "bat", None),
("Baluchi", "bal", None),
("Bambara", "bam", "bm"),
("Bamileke languages", "bai", None),
("Banda", "bad", None),
("Bantu (Other)", "bnt", None),
("Basa", "bas", None),
("Bashkir", "bak", "ba"),
("Basque", "baq/eus", "eu"),
("Batak (Indonesia)", "btk", None),
("Beja", "bej", None),
("Belarusian", "bel", "be"),
("Bemba", "bem", None),
("Bengali", "ben", "bn"),
("Berber (Other)", "ber", None),
("Bhojpuri", "bho", None),
("Bihari", "bih", "bh"),
("Bikol", "bik", None),
("Bilin", "byn", None),
("Bini", "bin", None),
("Bislama", "bis", "bi"),
("Blin", "byn", None),
("Bokmål, Norwegian", "nob", "nb"),
("Bosnian", "bos", "bs"),
("Braj", "bra", None),
("Breton", "bre", "br"),
("Buginese", "bug", None),
("Bulgarian", "bul", "bg"),
("Buriat", "bua", None),
("Burmese", "bur/mya", "my"),
("Caddo", "cad", None),
("Carib", "car", None),
("Castilian", "spa", "es"),
("Catalan", "cat", "ca"),
("Caucasian (Other)", "cau", None),
("Cebuano", "ceb", None),
("Celtic (Other)", "cel", None),
("Central American Indian (Other)", "cai", None),
("Chagatai", "chg", None),
("Chamic languages", "cmc", None),
("Chamorro", "cha", "ch"),
("Chechen", "che", "ce"),
("Cherokee", "chr", None),
("Chewa", "nya", "ny"),
("Cheyenne", "chy", None),
("Chibcha", "chb", None),
("Chichewa", "nya", "ny"),
("Chinese", "chi/zho", "zh"),
("Chinook jargon", "chn", None),
("Chipewyan", "chp", None),
("Choctaw", "cho", None),
("Chuang", "zha", "za"),
("Church Slavic", "chu", "cu"),
("Church Slavonic", "chu", "cu"),
("Chuukese", "chk", None),
("Chuvash", "chv", "cv"),
("Classical Nepal Bhasa", "nwc", None),
("Classical Newari", "nwc", None),
("Coptic", "cop", None),
("Cornish", "cor", "kw"),
("Corsican", "cos", "co"),
("Cree", "cre", "cr"),
("Creek", "mus", None),
("Creoles and pidgins (Other)", "crp", None),
("Creoles and pidgins, English based (Other)", "cpe", None),
("Creoles and pidgins, French-based (Other)", "cpf", None),
("Creoles and pidgins, Portuguese-based (Other)", "cpp", None),
("Crimean Tatar", "crh", None),
("Crimean Turkish", "crh", None),
("Croatian", "scr/hrv", "hr"),
("Cushitic (Other)", "cus", None),
("Czech", "cze/ces", "cs"),
("Dakota", "dak", None),
("Danish", "dan", "da"),
("Dargwa", "dar", None),
("Dayak", "day", None),
("Delaware", "del", None),
("Dhivehi", "div", "dv"),
("Dimili", "zza", None),
("Dimli", "zza", None),
("Dinka", "din", None),
("Divehi", "div", "dv"),
("Dogri", "doi", None),
("Dogrib", "dgr", None),
("Dravidian (Other)", "dra", None),
("Duala", "dua", None),
("Dutch", "dut/nld", "nl"),
("Dutch, Middle (ca.1050-1350)", "dum", None),
("Dyula", "dyu", None),
("Dzongkha", "dzo", "dz"),
("Eastern Frisian", "frs", None),
("Efik", "efi", None),
("Egyptian (Ancient)", "egy", None),
("Ekajuk", "eka", None),
("Elamite", "elx", None),
("English", "eng", "en"),
("English, Middle (1100-1500)", "enm", None),
("English, Old (ca.450-1100)", "ang", None),
("Erzya", "myv", None),
("Esperanto", "epo", "eo"),
("Estonian", "est", "et"),
("Ewe", "ewe", "ee"),
("Ewondo", "ewo", None),
("Fang", "fan", None),
("Fanti", "fat", None),
("Faroese", "fao", "fo"),
("Fijian", "fij", "fj"),
("Filipino", "fil", None),
("Finnish", "fin", "fi"),
("Finno-Ugrian (Other)", "fiu", None),
("Flemish", "dut/nld", "nl"),
("Fon", "fon", None),
("French", "fre/fra", "fr"),
("French, Middle (ca.1400-1600)", "frm", None),
("French, Old (842-ca.1400)", "fro", None),
("Friulian", "fur", None),
("Fulah", "ful", "ff"),
("Ga", "gaa", None),
("Gaelic", "gla", "gd"),
("Galician", "glg", "gl"),
("Ganda", "lug", "lg"),
("Gayo", "gay", None),
("Gbaya", "gba", None),
("Geez", "gez", None),
("Georgian", "geo/kat", "ka"),
("German", "ger/deu", "de"),
("German, Low", "nds", None),
("German, Middle High (ca.1050-1500)", "gmh", None),
("German, Old High (ca.750-1050)", "goh", None),
("Germanic (Other)", "gem", None),
("Gikuyu", "kik", "ki"),
("Gilbertese", "gil", None),
("Gondi", "gon", None),
("Gorontalo", "gor", None),
("Gothic", "got", None),
("Grebo", "grb", None),
("Greek, Ancient (to 1453)", "grc", None),
("Greek, Modern (1453-)", "gre/ell", "el"),
("Greenlandic", "kal", "kl"),
("Guarani", "grn", "gn"),
("Gujarati", "guj", "gu"),
("Gwich´in", "gwi", None),
("Haida", "hai", None),
("Haitian", "hat", "ht"),
("Haitian Creole", "hat", "ht"),
("Hausa", "hau", "ha"),
("Hawaiian", "haw", None),
("Hebrew", "heb", "he"),
("Herero", "her", "hz"),
("Hiligaynon", "hil", None),
("Himachali", "him", None),
("Hindi", "hin", "hi"),
("Hiri Motu", "hmo", "ho"),
("Hittite", "hit", None),
("Hmong", "hmn", None),
("Hungarian", "hun", "hu"),
("Hupa", "hup", None),
("Iban", "iba", None),
("Icelandic", "ice/isl", "is"),
("Ido", "ido", "io"),
("Igbo", "ibo", "ig"),
("Ijo", "ijo", None),
("Iloko", "ilo", None),
("Inari Sami", "smn", None),
("Indic (Other)", "inc", None),
("Indo-European (Other)", "ine", None),
("Indonesian", "ind", "id"),
("Ingush", "inh", None),
("Interlingua", "ina", "ia"),
("Interlingue", "ile", "ie"),
("Inuktitut", "iku", "iu"),
("Inupiaq", "ipk", "ik"),
("Iranian (Other)", "ira", None),
("Irish", "gle", "ga"),
("Irish, Middle (900-1200)", "mga", None),
("Irish, Old (to 900)", "sga", None),
("Iroquoian languages", "iro", None),
("Italian", "ita", "it"),
("Japanese", "jpn", "ja"),
("Javanese", "jav", "jv"),
("Judeo-Arabic", "jrb", None),
("Judeo-Persian", "jpr", None),
("Kabardian", "kbd", None),
("Kabyle", "kab", None),
("Kachin", "kac", None),
("Kalaallisut", "kal", "kl"),
("Kalmyk", "xal", None),
("Kamba", "kam", None),
("Kannada", "kan", "kn"),
("Kanuri", "kau", "kr"),
("Kara-Kalpak", "kaa", None),
("Karachay-Balkar", "krc", None),
("Karelian", "krl", None),
("Karen", "kar", None),
("Kashmiri", "kas", "ks"),
("Kashubian", "csb", None),
("Kawi", "kaw", None),
("Kazakh", "kaz", "kk"),
("Khasi", "kha", None),
("Khmer", "khm", "km"),
("Khoisan (Other)", "khi", None),
("Khotanese", "kho", None),
("Kikuyu", "kik", "ki"),
("Kimbundu", "kmb", None),
("Kinyarwanda", "kin", "rw"),
("Kirdki", "zza", None),
("Kirghiz", "kir", "ky"),
("Kirmanjki", "zza", None),
("Klingon", "tlh", None),
("Komi", "kom", "kv"),
("Kongo", "kon", "kg"),
("Konkani", "kok", None),
("Korean", "kor", "ko"),
("Kosraean", "kos", None),
("Kpelle", "kpe", None),
("Kru", "kro", None),
("Kuanyama", "kua", "kj"),
("Kumyk", "kum", None),
("Kurdish", "kur", "ku"),
("Kurukh", "kru", None),
("Kutenai", "kut", None),
("Kwanyama", "kua", "kj"),
("Ladino", "lad", None),
("Lahnda", "lah", None),
("Lamba", "lam", None),
("Lao", "lao", "lo"),
("Latin", "lat", "la"),
("Latvian", "lav", "lv"),
("Letzeburgesch", "ltz", "lb"),
("Lezghian", "lez", None),
("Limburgan", "lim", "li"),
("Limburger", "lim", "li"),
("Limburgish", "lim", "li"),
("Lingala", "lin", "ln"),
("Lithuanian", "lit", "lt"),
("Lojban", "jbo", None),
("Low German", "nds", None),
("Low Saxon", "nds", None),
("Lower Sorbian", "dsb", None),
("Lozi", "loz", None),
("Luba-Katanga", "lub", "lu"),
("Luba-Lulua", "lua", None),
("Luiseno", "lui", None),
("Lule Sami", "smj", None),
("Lunda", "lun", None),
("Luo (Kenya and Tanzania)", "luo", None),
("Lushai", "lus", None),
("Luxembourgish", "ltz", "lb"),
("Macedo-Romanian", "rup", None),
("Macedonian", "mac/mkd", "mk"),
("Madurese", "mad", None),
("Magahi", "mag", None),
("Maithili", "mai", None),
("Makasar", "mak", None),
("Malagasy", "mlg", "mg"),
("Malay", "may/msa", "ms"),
("Malayalam", "mal", "ml"),
("Maldivian", "div", "dv"),
("Maltese", "mlt", "mt"),
("Manchu", "mnc", None),
("Mandar", "mdr", None),
("Mandingo", "man", None),
("Manipuri", "mni", None),
("Manobo languages", "mno", None),
("Manx", "glv", "gv"),
("Maori", "mao/mri", "mi"),
("Marathi", "mar", "mr"),
("Mari", "chm", None),
("Marshallese", "mah", "mh"),
("Marwari", "mwr", None),
("Masai", "mas", None),
("Mayan languages", "myn", None),
("Mende", "men", None),
("Mi'kmaq", "mic", None),
("Micmac", "mic", None),
("Minangkabau", "min", None),
("Mirandese", "mwl", None),
("Mohawk", "moh", None),
("Moksha", "mdf", None),
("Moldavian", "mol", "mo"),
("Mon-Khmer (Other)", "mkh", None),
("Mongo", "lol", None),
("Mongolian", "mon", "mn"),
("Mossi", "mos", None),
("Multiple languages", "mul", None),
("Munda languages", "mun", None),
("N'Ko", "nqo", None),
("Nahuatl", "nah", None),
("Nauru", "nau", "na"),
("Navaho", "nav", "nv"),
("Navajo", "nav", "nv"),
("Ndebele, North", "nde", "nd"),
("Ndebele, South", "nbl", "nr"),
("Ndonga", "ndo", "ng"),
("Neapolitan", "nap", None),
("Nepal Bhasa", "new", None),
("Nepali", "nep", "ne"),
("Newari", "new", None),
("Nias", "nia", None),
("Niger-Kordofanian (Other)", "nic", None),
("Nilo-Saharan (Other)", "ssa", None),
("Niuean", "niu", None),
("No linguistic content", "zxx", None),
("Nogai", "nog", None),
("Norse, Old", "non", None),
("North American Indian", "nai", None),
("North Ndebele", "nde", "nd"),
("Northern Frisian", "frr", None),
("Northern Sami", "sme", "se"),
("Northern Sotho", "nso", None),
("Norwegian", "nor", "no"),
("Norwegian Bokmål", "nob", "nb"),
("Norwegian Nynorsk", "nno", "nn"),
("Nubian languages", "nub", None),
("Nyamwezi", "nym", None),
("Nyanja", "nya", "ny"),
("Nyankole", "nyn", None),
("Nynorsk, Norwegian", "nno", "nn"),
("Nyoro", "nyo", None),
("Nzima", "nzi", None),
("Occitan (post 1500)", "oci", "oc"),
("Oirat", "xal", None),
("Ojibwa", "oji", "oj"),
("Old Bulgarian", "chu", "cu"),
("Old Church Slavonic", "chu", "cu"),
("Old Newari", "nwc", None),
("Old Slavonic", "chu", "cu"),
("Oriya", "ori", "or"),
("Oromo", "orm", "om"),
("Osage", "osa", None),
("Ossetian", "oss", "os"),
("Ossetic", "oss", "os"),
("Otomian languages", "oto", None),
("Pahlavi", "pal", None),
("Palauan", "pau", None),
("Pali", "pli", "pi"),
("Pampanga", "pam", None),
("Pangasinan", "pag", None),
("Panjabi", "pan", "pa"),
("Papiamento", "pap", None),
("Papuan (Other)", "paa", None),
("Pedi", "nso", None),
("Persian", "per/fas", "fa"),
("Persian, Old (ca.600-400 B.C.)", "peo", None),
("Philippine (Other)", "phi", None),
("Phoenician", "phn", None),
("Pilipino", "fil", None),
("Pohnpeian", "pon", None),
("Polish", "pol", "pl"),
("Portuguese", "por", "pt"),
("Prakrit languages", "pra", None),
("Provençal", "oci", "oc"),
("Provençal, Old (to 1500)", "pro", None),
("Punjabi", "pan", "pa"),
("Pushto", "pus", "ps"),
("Quechua", "que", "qu"),
("Raeto-Romance", "roh", "rm"),
("Rajasthani", "raj", None),
("Rapanui", "rap", None),
("Rarotongan", "rar", None),
("Reserved for local use", "qaa/qtz", None),
("Romance (Other)", "roa", None),
("Romanian", "rum/ron", "ro"),
("Romany", "rom", None),
("Rundi", "run", "rn"),
("Russian", "rus", "ru"),
("Salishan languages", "sal", None),
("Samaritan Aramaic", "sam", None),
("Sami languages (Other)", "smi", None),
("Samoan", "smo", "sm"),
("Sandawe", "sad", None),
("Sango", "sag", "sg"),
("Sanskrit", "san", "sa"),
("Santali", "sat", None),
("Sardinian", "srd", "sc"),
("Sasak", "sas", None),
("Saxon, Low", "nds", None),
("Scots", "sco", None),
("Scottish Gaelic", "gla", "gd"),
("Selkup", "sel", None),
("Semitic (Other)", "sem", None),
("Sepedi", "nso", None),
("Serbian", "scc/srp", "sr"),
("Serer", "srr", None),
("Shan", "shn", None),
("Shona", "sna", "sn"),
("Sichuan Yi", "iii", "ii"),
("Sicilian", "scn", None),
("Sidamo", "sid", None),
("Sign Languages", "sgn", None),
("Siksika", "bla", None),
("Sindhi", "snd", "sd"),
("Sinhala", "sin", "si"),
("Sinhalese", "sin", "si"),
("Sino-Tibetan (Other)", "sit", None),
("Siouan languages", "sio", None),
("Skolt Sami", "sms", None),
("Slave (Athapascan)", "den", None),
("Slavic (Other)", "sla", None),
("Slovak", "slo/slk", "sk"),
("Slovenian", "slv", "sl"),
("Sogdian", "sog", None),
("Somali", "som", "so"),
("Songhai", "son", None),
("Soninke", "snk", None),
("Sorbian languages", "wen", None),
("Sotho, Northern", "nso", None),
("Sotho, Southern", "sot", "st"),
("South American Indian (Other)", "sai", None),
("South Ndebele", "nbl", "nr"),
("Southern Altai", "alt", None),
("Southern Sami", "sma", None),
("Spanish", "spa", "es"),
("Sranan Togo", "srn", None),
("Sukuma", "suk", None),
("Sumerian", "sux", None),
("Sundanese", "sun", "su"),
("Susu", "sus", None),
("Swahili", "swa", "sw"),
("Swati", "ssw", "ss"),
("Swedish", "swe", "sv"),
("Swiss German", "gsw", None),
("Syriac", "syr", None),
("Tagalog", "tgl", "tl"),
("Tahitian", "tah", "ty"),
("Tai (Other)", "tai", None),
("Tajik", "tgk", "tg"),
("Tamashek", "tmh", None),
("Tamil", "tam", "ta"),
("Tatar", "tat", "tt"),
("Telugu", "tel", "te"),
("Tereno", "ter", None),
("Tetum", "tet", None),
("Thai", "tha", "th"),
("Tibetan", "tib/bod", "bo"),
("Tigre", "tig", None),
("Tigrinya", "tir", "ti"),
("Timne", "tem", None),
("Tiv", "tiv", None),
("tlhIngan-Hol", "tlh", None),
("Tlingit", "tli", None),
("Tok Pisin", "tpi", None),
("Tokelau", "tkl", None),
("Tonga (Nyasa)", "tog", None),
("Tonga (Tonga Islands)", "ton", "to"),
("Tsimshian", "tsi", None),
("Tsonga", "tso", "ts"),
("Tswana", "tsn", "tn"),
("Tumbuka", "tum", None),
("Tupi languages", "tup", None),
("Turkish", "tur", "tr"),
("Turkish, Ottoman (1500-1928)", "ota", None),
("Turkmen", "tuk", "tk"),
("Tuvalu", "tvl", None),
("Tuvinian", "tyv", None),
("Twi", "twi", "tw"),
("Udmurt", "udm", None),
("Ugaritic", "uga", None),
("Uighur", "uig", "ug"),
("Ukrainian", "ukr", "uk"),
("Umbundu", "umb", None),
("Uncoded languages", "mis", None),
("Undetermined", "und", None),
("Upper Sorbian", "hsb", None),
("Urdu", "urd", "ur"),
("Uyghur", "uig", "ug"),
("Uzbek", "uzb", "uz"),
("Vai", "vai", None),
("Valencian", "cat", "ca"),
("Venda", "ven", "ve"),
("Vietnamese", "vie", "vi"),
("Volapük", "vol", "vo"),
("Votic", "vot", None),
("Wakashan languages", "wak", None),
("Walamo", "wal", None),
("Walloon", "wln", "wa"),
("Waray", "war", None),
("Washo", "was", None),
("Welsh", "wel/cym", "cy"),
("Western Frisian", "fry", "fy"),
("Wolof", "wol", "wo"),
("Xhosa", "xho", "xh"),
("Yakut", "sah", None),
("Yao", "yao", None),
("Yapese", "yap", None),
("Yiddish", "yid", "yi"),
("Yoruba", "yor", "yo"),
("Yupik languages", "ypk", None),
("Zande", "znd", None),
("Zapotec", "zap", None),
("Zaza", "zza", None),
("Zazaki", "zza", None),
("Zenaga", "zen", None),
("Zhuang", "zha", "za"),
("Zulu", "zul", "zu"),
("Zuni", "zun", None),
)
# Bibliographic ISO-639-2 form (eg. "fre" => "French")
ISO639_2 = {}
for line in _ISO639:
for key in line[1].split("/"):
ISO639_2[key] = line[0]
del _ISO639