Created
March 11, 2022 08:14
-
-
Save innermond/de0c11e09d67ccc0bc2b21505130b4ee to your computer and use it in GitHub Desktop.
elastic 8.1 search map corespondence between language codes and long names (from https://www.elastic.co/guide/en/machine-learning/8.1/ml-nlp-classify-text.html)
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
| $lang = [ | |
| 'af' => 'afrikaans', | |
| 'hr' => 'croatian', | |
| 'pa' => 'punjabi', | |
| 'am' => 'amharic', | |
| 'ht' => 'haitian', | |
| 'pl' => 'polish', | |
| 'ar' => 'arabic', | |
| 'hu' => 'hungarian', | |
| 'ps' => 'pashto', | |
| 'az' => 'azerbaijani', | |
| 'hy' => 'armenian', | |
| 'pt' => 'portuguese', | |
| 'be' => 'belarusian', | |
| 'id' => 'indonesian', | |
| 'ro' => 'romanian', | |
| 'bg' => 'bulgarian', | |
| 'ig' => 'igbo', | |
| 'ru' => 'russian', | |
| 'bg-latn' => 'bulgarian', | |
| 'is' => 'icelandic', | |
| 'ru-latn' => 'russian', | |
| 'bn' => 'bengali', | |
| 'it' => 'italian', | |
| 'sd' => 'sindhi', | |
| 'bs' => 'bosnian', | |
| 'iw' => 'hebrew', | |
| 'si' => 'sinhala', | |
| 'ca' => 'catalan', | |
| 'ja' => 'japanese', | |
| 'sk' => 'slovak', | |
| 'ceb' => 'cebuano', | |
| 'ja-latn' => 'japanese', | |
| 'sl' => 'slovenian', | |
| 'co' => 'corsican', | |
| 'jv' => 'javanese', | |
| 'sm' => 'samoan', | |
| 'cs' => 'czech', | |
| 'ka' => 'georgian', | |
| 'sn' => 'shona', | |
| 'cy' => 'welsh', | |
| 'kk' => 'kazakh', | |
| 'so' => 'somali', | |
| 'da' => 'danish', | |
| 'km' => 'central khmer', | |
| 'sq' => 'albanian', | |
| 'de' => 'german', | |
| 'kn' => 'kannada', | |
| 'sr' => 'serbian', | |
| 'el' => 'greek, modern', | |
| 'ko' => 'korean', | |
| 'st' => 'southern sotho', | |
| 'el-latn' => 'greek, modern', | |
| 'ku' => 'kurdish', | |
| 'su' => 'sundanese', | |
| 'en' => 'english', | |
| 'ky' => 'kirghiz', | |
| 'sv' => 'swedish', | |
| 'eo' => 'esperanto', | |
| 'la' => 'latin', | |
| 'sw' => 'swahili', | |
| 'es' => 'spanish, castilian', | |
| 'lb' => 'luxembourgish', | |
| 'ta' => 'tamil', | |
| 'et' => 'estonian', | |
| 'lo' => 'lao', | |
| 'te' => 'telugu', | |
| 'eu' => 'basque', | |
| 'lt' => 'lithuanian', | |
| 'tg' => 'tajik', | |
| 'fa' => 'persian', | |
| 'lv' => 'latvian', | |
| 'th' => 'thai', | |
| 'fi' => 'finnish', | |
| 'mg' => 'malagasy', | |
| 'tr' => 'turkish', | |
| 'fil' => 'filipino', | |
| 'mi' => 'maori', | |
| 'uk' => 'ukrainian', | |
| 'fr' => 'french', | |
| 'mk' => 'macedonian', | |
| 'ur' => 'urdu', | |
| 'fy' => 'western frisian', | |
| 'ml' => 'malayalam', | |
| 'uz' => 'uzbek', | |
| 'ga' => 'irish', | |
| 'mn' => 'mongolian', | |
| 'vi' => 'vietnamese', | |
| 'gd' => 'gaelic', | |
| 'mr' => 'marathi', | |
| 'xh' => 'xhosa', | |
| 'gl' => 'galician', | |
| 'ms' => 'malay', | |
| 'yi' => 'yiddish', | |
| 'gu' => 'gujarati', | |
| 'mt' => 'maltese', | |
| 'yo' => 'yoruba', | |
| 'ha' => 'hausa', | |
| 'my' => 'burmese', | |
| 'zh' => 'chinese', | |
| 'haw' => 'hawaiian', | |
| 'ne' => 'nepali', | |
| 'zh-latn' => 'chinese', | |
| 'hi' => 'hindi', | |
| 'nl' => 'dutch, flemish', | |
| 'zu' => 'zulu', | |
| 'hi-latn' => 'hindi', | |
| 'no' => 'norwegian', | |
| 'hmn' => 'hmong', | |
| 'ny' => 'chichewa', | |
| ]; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment