-
-
Save carlopires/1262033 to your computer and use it in GitHub Desktop.
Python dict with ISO-639-2 language codes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -o- coding: utf-8 -o- | |
# ISO639 python dict | |
# oficial list in http://www.loc.gov/standards/iso639-2/php/code_list.php | |
ISO639_2 = { | |
'ab': 'Abkhaz', | |
'aa': 'Afar', | |
'af': 'Afrikaans', | |
'ak': 'Akan', | |
'sq': 'Albanian', | |
'am': 'Amharic', | |
'ar': 'Arabic', | |
'an': 'Aragonese', | |
'hy': 'Armenian', | |
'as': 'Assamese', | |
'av': 'Avaric', | |
'ae': 'Avestan', | |
'ay': 'Aymara', | |
'az': 'Azerbaijani', | |
'bm': 'Bambara', | |
'ba': 'Bashkir', | |
'eu': 'Basque', | |
'be': 'Belarusian', | |
'bn': 'Bengali', | |
'bh': 'Bihari', | |
'bi': 'Bislama', | |
'bs': 'Bosnian', | |
'br': 'Breton', | |
'bg': 'Bulgarian', | |
'my': 'Burmese', | |
'ca': 'Catalan; Valencian', | |
'ch': 'Chamorro', | |
'ce': 'Chechen', | |
'ny': 'Chichewa; Chewa; Nyanja', | |
'zh': 'Chinese', | |
'cv': 'Chuvash', | |
'kw': 'Cornish', | |
'co': 'Corsican', | |
'cr': 'Cree', | |
'hr': 'Croatian', | |
'cs': 'Czech', | |
'da': 'Danish', | |
'dv': 'Divehi; Maldivian;', | |
'nl': 'Dutch', | |
'dz': 'Dzongkha', | |
'en': 'English', | |
'eo': 'Esperanto', | |
'et': 'Estonian', | |
'ee': 'Ewe', | |
'fo': 'Faroese', | |
'fj': 'Fijian', | |
'fi': 'Finnish', | |
'fr': 'French', | |
'ff': 'Fula', | |
'gl': 'Galician', | |
'ka': 'Georgian', | |
'de': 'German', | |
'el': 'Greek, Modern', | |
'gn': 'Guaraní', | |
'gu': 'Gujarati', | |
'ht': 'Haitian', | |
'ha': 'Hausa', | |
'he': 'Hebrew (modern)', | |
'hz': 'Herero', | |
'hi': 'Hindi', | |
'ho': 'Hiri Motu', | |
'hu': 'Hungarian', | |
'ia': 'Interlingua', | |
'id': 'Indonesian', | |
'ie': 'Interlingue', | |
'ga': 'Irish', | |
'ig': 'Igbo', | |
'ik': 'Inupiaq', | |
'io': 'Ido', | |
'is': 'Icelandic', | |
'it': 'Italian', | |
'iu': 'Inuktitut', | |
'ja': 'Japanese', | |
'jv': 'Javanese', | |
'kl': 'Kalaallisut', | |
'kn': 'Kannada', | |
'kr': 'Kanuri', | |
'ks': 'Kashmiri', | |
'kk': 'Kazakh', | |
'km': 'Khmer', | |
'ki': 'Kikuyu, Gikuyu', | |
'rw': 'Kinyarwanda', | |
'ky': 'Kirghiz, Kyrgyz', | |
'kv': 'Komi', | |
'kg': 'Kongo', | |
'ko': 'Korean', | |
'ku': 'Kurdish', | |
'kj': 'Kwanyama, Kuanyama', | |
'la': 'Latin', | |
'lb': 'Luxembourgish', | |
'lg': 'Luganda', | |
'li': 'Limburgish', | |
'ln': 'Lingala', | |
'lo': 'Lao', | |
'lt': 'Lithuanian', | |
'lu': 'Luba-Katanga', | |
'lv': 'Latvian', | |
'gv': 'Manx', | |
'mk': 'Macedonian', | |
'mg': 'Malagasy', | |
'ms': 'Malay', | |
'ml': 'Malayalam', | |
'mt': 'Maltese', | |
'mi': 'Māori', | |
'mr': 'Marathi (Marāṭhī)', | |
'mh': 'Marshallese', | |
'mn': 'Mongolian', | |
'na': 'Nauru', | |
'nv': 'Navajo, Navaho', | |
'nb': 'Norwegian Bokmål', | |
'nd': 'North Ndebele', | |
'ne': 'Nepali', | |
'ng': 'Ndonga', | |
'nn': 'Norwegian Nynorsk', | |
'no': 'Norwegian', | |
'ii': 'Nuosu', | |
'nr': 'South Ndebele', | |
'oc': 'Occitan', | |
'oj': 'Ojibwe, Ojibwa', | |
'cu': 'Old Church Slavonic', | |
'om': 'Oromo', | |
'or': 'Oriya', | |
'os': 'Ossetian, Ossetic', | |
'pa': 'Panjabi, Punjabi', | |
'pi': 'Pāli', | |
'fa': 'Persian', | |
'pl': 'Polish', | |
'ps': 'Pashto, Pushto', | |
'pt': 'Portuguese', | |
'qu': 'Quechua', | |
'rm': 'Romansh', | |
'rn': 'Kirundi', | |
'ro': 'Romanian, Moldavan', | |
'ru': 'Russian', | |
'sa': 'Sanskrit (Saṁskṛta)', | |
'sc': 'Sardinian', | |
'sd': 'Sindhi', | |
'se': 'Northern Sami', | |
'sm': 'Samoan', | |
'sg': 'Sango', | |
'sr': 'Serbian', | |
'gd': 'Scottish Gaelic', | |
'sn': 'Shona', | |
'si': 'Sinhala, Sinhalese', | |
'sk': 'Slovak', | |
'sl': 'Slovene', | |
'so': 'Somali', | |
'st': 'Southern Sotho', | |
'es': 'Spanish; Castilian', | |
'su': 'Sundanese', | |
'sw': 'Swahili', | |
'ss': 'Swati', | |
'sv': 'Swedish', | |
'ta': 'Tamil', | |
'te': 'Telugu', | |
'tg': 'Tajik', | |
'th': 'Thai', | |
'ti': 'Tigrinya', | |
'bo': 'Tibetan', | |
'tk': 'Turkmen', | |
'tl': 'Tagalog', | |
'tn': 'Tswana', | |
'to': 'Tonga', | |
'tr': 'Turkish', | |
'ts': 'Tsonga', | |
'tt': 'Tatar', | |
'tw': 'Twi', | |
'ty': 'Tahitian', | |
'ug': 'Uighur, Uyghur', | |
'uk': 'Ukrainian', | |
'ur': 'Urdu', | |
'uz': 'Uzbek', | |
've': 'Venda', | |
'vi': 'Vietnamese', | |
'vo': 'Volapük', | |
'wa': 'Walloon', | |
'cy': 'Welsh', | |
'wo': 'Wolof', | |
'fy': 'Western Frisian', | |
'xh': 'Xhosa', | |
'yi': 'Yiddish', | |
'yo': 'Yoruba', | |
'za': 'Zhuang, Chuang', | |
'zu': 'Zulu', | |
} |
est is correct. 639-1 is two characters and 639-2 is three characters.
I tried to generalize a bit: https://pypi.python.org/pypi/iso639/
How to generate this dictionary using the iso639 package in python?
I don't know what the version of this is. But this just helped me alot.
This is a list, not a dictionary.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is looks like ISO639_1 not ISO639_2