commit: 149802c56926bf48520c98932c4c36b8152b3d2d parent e58949b76fac7aa93341523ff0e2f35e0a03e057 Author: marc <a01200356@itesm.mx> Date: Fri, 5 Aug 2016 23:34:56 -0500 [enh] add supported_languages on engines and auto-generate languages.pyDiffstat:
34 files changed, 666 insertions(+), 128 deletions(-)diff --git a/searx/autocomplete.py b/searx/autocomplete.py@@ -81,17 +81,17 @@ def searx_bang(full_query): engine_query = full_query.getSearchQuery()[1:] for lc in language_codes: - lang_id, lang_name, country = map(str.lower, lc) + lang_id, lang_name, country, english_name = map(str.lower, lc) # check if query starts with language-id if lang_id.startswith(engine_query): if len(engine_query) <= 2: - results.append(':{lang_id}'.format(lang_id=lang_id.split('_')[0])) + results.append(':{lang_id}'.format(lang_id=lang_id.split('-')[0])) else: results.append(':{lang_id}'.format(lang_id=lang_id)) # check if query starts with language name - if lang_name.startswith(engine_query): + if lang_name.startswith(engine_query) or english_name.startswith(engine_query): results.append(':{lang_name}'.format(lang_name=lang_name)) # check if query starts with countrydiff --git a/searx/engines/__init__.py b/searx/engines/__init__.py@@ -38,6 +38,7 @@ engine_shortcuts = {} engine_default_args = {'paging': False, 'categories': ['general'], 'language_support': True, + 'supported_languages': [], 'safesearch': False, 'timeout': settings['outgoing']['request_timeout'], 'shortcut': '-',diff --git a/searx/engines/archlinux.py b/searx/engines/archlinux.py@@ -29,8 +29,8 @@ xpath_link = './/div[@class="mw-search-result-heading"]/a' # cut 'en' from 'en_US', 'de' from 'de_CH', and so on def locale_to_lang_code(locale): - if locale.find('_') >= 0: - locale = locale.split('_')[0] + if locale.find('-') >= 0: + locale = locale.split('-')[0] return locale @@ -95,6 +95,7 @@ main_langs = { 'uk': 'Українська', 'zh': '简体中文' } +supported_languages = dict(lang_urls, **main_langs) # do search-requestdiff --git a/searx/engines/bing.py b/searx/engines/bing.py@@ -32,7 +32,7 @@ def request(query, params): offset = (params['pageno'] - 1) * 10 + 1 if params['language'] != 'all': - query = u'language:{} {}'.format(params['language'].split('_')[0].upper(), + query = u'language:{} {}'.format(params['language'].split('-')[0].upper(), query.decode('utf-8')).encode('utf-8') search_path = search_string.format(diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py@@ -19,6 +19,7 @@ from urllib import urlencode from lxml import html from json import loads import re +from searx.engines.bing import supported_languages # engine dependent config categories = ['images'] @@ -53,7 +54,7 @@ def request(query, params): if params['language'] == 'all': language = 'en-US' else: - language = params['language'].replace('_', '-') + language = params['language'] search_path = search_string.format( query=urlencode({'q': query}),diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py@@ -17,6 +17,7 @@ from datetime import datetime from dateutil import parser from lxml import etree from searx.utils import list_get +from searx.engines.bing import supported_languages # engine dependent config categories = ['news'] @@ -74,7 +75,7 @@ def request(query, params): if params['language'] == 'all': language = 'en-US' else: - language = params['language'].replace('_', '-') + language = params['language'] params['url'] = _get_url(query, language, offset, params['time_range'])diff --git a/searx/engines/duckduckgo.py b/searx/engines/duckduckgo.py@@ -22,6 +22,13 @@ from searx.languages import language_codes categories = ['general'] paging = True language_support = True +supported_languages = ["es-AR", "en-AU", "de-AT", "fr-BE", "nl-BE", "pt-BR", "bg-BG", "en-CA", "fr-CA", "ca-CT", + "es-CL", "zh-CN", "es-CO", "hr-HR", "cs-CZ", "da-DK", "et-EE", "fi-FI", "fr-FR", "de-DE", + "el-GR", "tzh-HK", "hu-HU", "en-IN", "id-ID", "en-ID", "en-IE", "he-IL", "it-IT", "jp-JP", + "kr-KR", "es-XL", "lv-LV", "lt-LT", "ms-MY", "en-MY", "es-MX", "nl-NL", "en-NZ", "no-NO", + "es-PE", "en-PH", "tl-PH", "pl-PL", "pt-PT", "ro-RO", "ru-RU", "ar-XA", "en-XA", "en-SG", + "sk-SK", "sl-SL", "en-ZA", "es-ES", "ca-ES", "sv-SE", "de-CH", "fr-CH", "it-CH", "tzh-TW", + "th-TH", "tr-TR", "uk-UA", "en-UK", "en-US", "es-US", "vi-VN"] time_range_support = True # search-url @@ -46,10 +53,23 @@ def request(query, params): offset = (params['pageno'] - 1) * 30 + # custom fixes for languages if params['language'] == 'all': locale = None + elif params['language'][:2] == 'ja': + locale = 'jp-jp' + elif params['language'] == 'zh-TW': + locale = 'tw-tzh' + elif params['language'] == 'zh-HK': + locale = 'hk-tzh' + elif params['language'][-2:] == 'SA': + locale = 'xa' + params['language'].split('-')[0] + elif params['language'][-2:] == 'GB': + locale = 'uk' + params['language'].split('-')[0] + elif params['language'] == 'es-419': + locale = 'xl-es' else: - locale = params['language'].split('_') + locale = params['language'].split('-') if len(locale) == 2: # country code goes first locale = locale[1].lower() + '-' + locale[0].lower() @@ -58,7 +78,25 @@ def request(query, params): locale = locale[0].lower() lang_codes = [x[0] for x in language_codes] for lc in lang_codes: - lc = lc.split('_') + lc = lc.split('-') + if locale == lc[0] and len(lc) == 2: + locale = lc[1].lower() + '-' + lc[0].lower() + break + + if locale: + params['url'] = url.format( + query=urlencode({'q': query, 'kl': locale}), offset=offset) + else: + locale = params['language'].split('-') + if len(locale) == 2: + # country code goes first + locale = locale[1].lower() + '-' + locale[0].lower() + else: + # tries to get a country code from language + locale = locale[0].lower() + lang_codes = [x[0] for x in language_codes] + for lc in lang_codes: + lc = lc.split('-') if locale == lc[0]: locale = lc[1].lower() + '-' + lc[0].lower() breakdiff --git a/searx/engines/duckduckgo_definitions.py b/searx/engines/duckduckgo_definitions.py@@ -4,6 +4,7 @@ from re import compile, sub from lxml import html from searx.utils import html_to_text from searx.engines.xpath import extract_text +from searx.engines.duckduckgo import supported_languages url = 'https://api.duckduckgo.com/'\ + '?{query}&format=json&pretty=0&no_redirect=1&d=1' @@ -23,7 +24,7 @@ def result_to_text(url, text, htmlResult): def request(query, params): params['url'] = url.format(query=urlencode({'q': query})) - params['headers']['Accept-Language'] = params['language'] + params['headers']['Accept-Language'] = params['language'].split('-')[0] return paramsdiff --git a/searx/engines/gigablast.py b/searx/engines/gigablast.py@@ -48,7 +48,7 @@ def request(query, params): if params['language'] == 'all': language = 'xx' else: - language = params['language'][0:2] + language = params['language'].split('-')[0] if params['safesearch'] >= 1: safesearch = 1diff --git a/searx/engines/google.py b/searx/engines/google.py@@ -23,6 +23,20 @@ categories = ['general'] paging = True language_support = True use_locale_domain = True +supported_languages = ['de', 'en', 'es', 'es_419', 'fr', 'hr', 'it', 'nl', 'pl', 'pt-BR', + 'pt-PT', 'vi', 'tr', 'ru', 'ar', 'th', 'ko', 'zh-CN', 'zh-TW', 'ja', + 'ach', 'af', 'ak', 'az', 'ms', 'ban', 'xx_bork', 'bs', 'br', 'ca', + 'ceb', 'ckb', 'cs', 'sn', 'co', 'cy', 'da', 'yo', 'et', 'xx_elmer', + 'eo', 'eu', 'ee', 'tl', 'fo', 'gaa', 'ga', 'gd', 'gl', 'gn', 'xx_hacker', + 'ht', 'ha', 'haw', 'bem', 'ig', 'rn', 'id', 'ia', 'zu', 'is', 'jw', 'rw', + 'sw', 'tlh', 'kg', 'mfe', 'kri', 'la', 'lv', 'to', 'lt', 'ln', 'loz', + 'lua', 'lg', 'hu', 'mg', 'mt', 'mi', 'pcm', 'no', 'nso', 'ny', 'nn', + 'uz', 'oc', 'om', 'xx_pirate', 'pt', 'ro', 'mo', 'rm', 'qu', 'nyn', 'crs', + 'sq', 'sd', 'sk', 'sl', 'so', 'st', 'sr_ME', 'sr_Latn', 'su', 'fi', 'sv', + 'tg', 'tt', 'tn', 'tum', 'tk', 'tw', 'fy', 'wo', 'xh', 'el', 'be', 'bg', + 'ky', 'kk', 'mk', 'mn', 'sr', 'uk', 'ka', 'hy', 'yi', 'iw', 'ug', 'ur', + 'ps', 'fa', 'ti', 'am', 'ne', 'mr', 'hi', 'bn', 'pa', 'gu', 'or', 'ta', + 'te', 'kn', 'ml', 'si', 'lo', 'my', 'km', 'chr'] time_range_support = True # based on https://en.wikipedia.org/wiki/List_of_Google_domains and testsdiff --git a/searx/engines/google_news.py b/searx/engines/google_news.py@@ -12,6 +12,8 @@ from lxml import html from urllib import urlencode +from json import loads +from searx.engines.google import supported_languages # search-url categories = ['news'] @@ -50,7 +52,7 @@ def request(query, params): search_options=urlencode(search_options)) if params['language'] != 'all': - language_array = params['language'].lower().split('_') + language_array = params['language'].lower().split('-') params['url'] += '&lr=lang_' + language_array[0] return paramsdiff --git a/searx/engines/mediawiki.py b/searx/engines/mediawiki.py@@ -15,6 +15,7 @@ from json import loads from string import Formatter from urllib import urlencode, quote +from searx.engines.wikipedia import supported_engines # engine dependent config categories = ['general'] @@ -46,7 +47,7 @@ def request(query, params): if params['language'] == 'all': language = 'en' else: - language = params['language'].split('_')[0] + language = params['language'].split('-')[0] # format_string [('https://', 'language', '', None), ('.wikipedia.org/', None, None, None)] if any(x[1] == 'language' for x in format_strings):diff --git a/searx/engines/photon.py b/searx/engines/photon.py@@ -26,7 +26,7 @@ search_string = 'api/?{query}&limit={limit}' result_base_url = 'https://openstreetmap.org/{osm_type}/{osm_id}' # list of supported languages -allowed_languages = ['de', 'en', 'fr', 'it'] +supported_languages = ['de', 'en', 'fr', 'it'] # do search-request @@ -37,7 +37,7 @@ def request(query, params): if params['language'] != 'all': language = params['language'].split('_')[0] - if language in allowed_languages: + if language in supported_languages: params['url'] = params['url'] + "&lang=" + language # using searx User-Agentdiff --git a/searx/engines/startpage.py b/searx/engines/startpage.py@@ -47,7 +47,7 @@ def request(query, params): # set language if specified if params['language'] != 'all': - params['data']['with_language'] = ('lang_' + params['language'].split('_')[0]) + params['data']['with_language'] = ('lang_' + params['language'].split('-')[0]) return paramsdiff --git a/searx/engines/subtitleseeker.py b/searx/engines/subtitleseeker.py@@ -43,8 +43,13 @@ def response(resp): search_lang = "" - if resp.search_params['language'] != 'all': - search_lang = [lc[1] + # dirty fix for languages named differenly in their site + if resp.search_params['language'][:2] == 'fa': + search_lang = 'Farsi' + elif resp.search_params['language'] == 'pt_BR': + search_lang = 'Brazilian' + elif resp.search_params['language'] != 'all': + search_lang = [lc[3] for lc in language_codes if lc[0][:2] == resp.search_params['language'].split('_')[0]][0]diff --git a/searx/engines/swisscows.py b/searx/engines/swisscows.py@@ -36,8 +36,8 @@ def request(query, params): ui_language = 'browser' region = 'browser' else: - region = params['language'].replace('_', '-') - ui_language = params['language'].split('_')[0] + region = params['language'] + ui_language = params['language'].split('-')[0] search_path = search_string.format( query=urlencode({'query': query,diff --git a/searx/engines/twitter.py b/searx/engines/twitter.py@@ -40,7 +40,7 @@ def request(query, params): # set language if specified if params['language'] != 'all': - params['cookies']['lang'] = params['language'].split('_')[0] + params['cookies']['lang'] = params['language'].split('-')[0] else: params['cookies']['lang'] = 'en'diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py@@ -14,6 +14,8 @@ from searx import logger from searx.poolrequests import get from searx.engines.xpath import extract_text +from searx.utils import format_date_by_locale +from searx.engines.wikipedia import supported_languages from json import loads from lxml.html import fromstringdiff --git a/searx/engines/wikipedia.py b/searx/engines/wikipedia.py@@ -13,6 +13,36 @@ from json import loads from urllib import urlencode, quote +supported_languages = ["en", "sv", "ceb", "de", "nl", "fr", "ru", "it", "es", "war", + "pl", "vi", "ja", "pt", "zh", "uk", "ca", "fa", "no", "sh", + "ar", "fi", "hu", "id", "ro", "cs", "ko", "sr", "ms", "tr", + "eu", "eo", "min", "bg", "da", "kk", "sk", "hy", "he", "zh-min-nan", + "lt", "hr", "sl", "et", "ce", "gl", "nn", "uz", "la", "vo", + "el", "simple", "be", "az", "th", "ur", "ka", "hi", "oc", "ta", + "mk", "mg", "new", "lv", "cy", "bs", "tt", "tl", "te", "pms", + "be-tarask", "br", "sq", "ky", "ht", "jv", "tg", "ast", "zh-yue", "lb", + "mr", "ml", "bn", "pnb", "is", "af", "sco", "ga", "ba", "fy", + "cv", "lmo", "sw", "my", "an", "yo", "ne", "io", "gu", "nds", + "scn", "bpy", "pa", "ku", "als", "kn", "bar", "ia", "qu", "su", + "ckb", "bat-smg", "mn", "arz", "nap", "wa", "bug", "gd", "yi", "map-bms", + "am", "mzn", "fo", "si", "nah", "li", "sah", "vec", "hsb", "or", + "os", "mrj", "sa", "hif", "mhr", "roa-tara", "azb", "pam", "ilo", + "sd", "ps", "se", "mi", "bh", "eml", "bcl", "xmf", "diq", "hak", + "gan", "glk", "vls", "nds-nl", "rue", "bo", "fiu-vro", "co", "sc", + "tk", "csb", "lrc", "vep", "wuu", "km", "szl", "gv", "crh", "kv", + "zh-classical", "frr", "zea", "as", "so", "kw", "nso", "ay", "stq", + "udm", "cdo", "nrm", "ie", "koi", "rm", "pcd", "myv", "mt", "fur", + "ace", "lad", "gn", "lij", "dsb", "dv", "cbk-zam", "ext", "gom", + "kab", "ksh", "ang", "mai", "mwl", "lez", "gag", "ln", "ug", "pi", + "pag", "frp", "sn", "nv", "av", "pfl", "haw", "xal", "krc", "kaa", + "rw", "bxr", "pdc", "to", "kl", "nov", "arc", "kbd", "lo", "bjn", + "pap", "ha", "tet", "ki", "tyv", "tpi", "na", "lbe", "ig", "jbo", + "roa-rup", "ty", "jam", "za", "kg", "mdf", "lg", "wo", "srn", "ab", + "ltg", "zu", "sm", "chr", "om", "tn", "chy", "rmy", "cu", "tw", "tum", + "xh", "bi", "rn", "pih", "got", "ss", "pnt", "bm", "ch", "mo", "ts", + "ady", "iu", "st", "ee", "ny", "fj", "ks", "ak", "ik", "sg", "ve", + "dz", "ff", "ti", "cr", "ng", "cho", "kj", "mh", "ho", "ii", "aa", "mus", "hz", "kr"] + # search-url base_url = 'https://{language}.wikipedia.org/' search_postfix = 'w/api.php?'\ @@ -28,10 +58,11 @@ search_postfix = 'w/api.php?'\ # set language in base_url def url_lang(lang): - if lang == 'all': + lang = lang.split('-')[0] + if lang == 'all' or lang not in supported_languages: language = 'en' else: - language = lang.split('_')[0] + language = lang return base_url.format(language=language)diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py@@ -53,7 +53,7 @@ def request(query, params): # add language tag if specified if params['language'] != 'all': - params['url'] += '&lr=lang_' + params['language'].split('_')[0] + params['url'] += '&lr=lang_' + params['language'].split('-')[0] return paramsdiff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py@@ -20,6 +20,10 @@ from searx.engines.xpath import extract_text, extract_url categories = ['general'] paging = True language_support = True +supported_languages = ["ar", "bg", "ca", "szh", "tzh", "hr", "cs", "da", "nl", "en", + "et", "fi", "fr", "de", "el", "he", "hu", "is", "id", "it", "ja", + "ko", "lv", "lt", "no", "fa", "pl", "pt", "ro", "ru", "sk", "sr", + "sl", "es", "sv", "th", "tr"] time_range_support = True # search-url @@ -72,7 +76,13 @@ def _get_url(query, offset, language, time_range): def _get_language(params): if params['language'] == 'all': return 'en' - return params['language'].split('_')[0] + elif params['language'][:2] == 'zh': + if params['language'] == 'zh' or params['language'] == 'zh-CH': + return 'szh' + else: + return 'tzh' + else: + return params['language'].split('-')[0] # do search-requestdiff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py@@ -12,7 +12,7 @@ from urllib import urlencode from lxml import html from searx.engines.xpath import extract_text, extract_url -from searx.engines.yahoo import parse_url +from searx.engines.yahoo import parse_url, supported_languages from datetime import datetime, timedelta import re from dateutil import parserdiff --git a/searx/engines/yandex.py b/searx/engines/yandex.py@@ -36,7 +36,7 @@ content_xpath = './/div[@class="text-container typo typo_text_m typo_line_m orga def request(query, params): - lang = params['language'].split('_')[0] + lang = params['language'].split('-')[0] host = base_url.format(tld=language_map.get(lang) or default_tld) params['url'] = host + search_url.format(page=params['pageno'] - 1, query=urlencode({'text': query}))diff --git a/searx/engines/youtube_api.py b/searx/engines/youtube_api.py@@ -36,7 +36,7 @@ def request(query, params): # add language tag if specified if params['language'] != 'all': - params['url'] += '&relevanceLanguage=' + params['language'].split('_')[0] + params['url'] += '&relevanceLanguage=' + params['language'].split('-')[0] return paramsdiff --git a/searx/languages.py b/searx/languages.py@@ -1,78 +1,390 @@ -''' -searx is free software: you can redistribute it and/or modify -it under the terms of the GNU Affero General Public License as published by -the Free Software Foundation, either version 3 of the License, or -(at your option) any later version. - -searx is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU Affero General Public License for more details. - -You should have received a copy of the GNU Affero General Public License -along with searx. If not, see < http://www.gnu.org/licenses/ >. - -(C) 2013- by Adam Tauber, <asciimoo@gmail.com> -''' - +# -*- coding: utf-8 -*- # list of language codes +# this file is generated automatically by utils/update_search_languages.py + language_codes = ( - ("ar_XA", "Arabic", "Arabia"), - ("bg_BG", "Bulgarian", "Bulgaria"), - ("cs_CZ", "Czech", "Czech Republic"), - ("da_DK", "Danish", "Denmark"), - ("de_AT", "German", "Austria"), - ("de_CH", "German", "Switzerland"), - ("de_DE", "German", "Germany"), - ("el_GR", "Greek", "Greece"), - ("en_AU", "English", "Australia"), - ("en_CA", "English", "Canada"), - ("en_GB", "English", "United Kingdom"), - ("en_ID", "English", "Indonesia"), - ("en_IE", "English", "Ireland"), - ("en_IN", "English", "India"), - ("en_MY", "English", "Malaysia"), - ("en_NZ", "English", "New Zealand"), - ("en_PH", "English", "Philippines"), - ("en_SG", "English", "Singapore"), - ("en_US", "English", "United States"), - ("en_XA", "English", "Arabia"), - ("en_ZA", "English", "South Africa"), - ("es_AR", "Spanish", "Argentina"), - ("es_CL", "Spanish", "Chile"), - ("es_ES", "Spanish", "Spain"), - ("es_MX", "Spanish", "Mexico"), - ("es_US", "Spanish", "United States"), - ("es_XL", "Spanish", "Latin America"), - ("et_EE", "Estonian", "Estonia"), - ("fi_FI", "Finnish", "Finland"), - ("fr_BE", "French", "Belgium"), - ("fr_CA", "French", "Canada"), - ("fr_CH", "French", "Switzerland"), - ("fr_FR", "French", "France"), - ("he_IL", "Hebrew", "Israel"), - ("hr_HR", "Croatian", "Croatia"), - ("hu_HU", "Hungarian", "Hungary"), - ("it_IT", "Italian", "Italy"), - ("ja_JP", "Japanese", "Japan"), - ("ko_KR", "Korean", "Korea"), - ("lt_LT", "Lithuanian", "Lithuania"), - ("lv_LV", "Latvian", "Latvia"), - ("nb_NO", "Norwegian", "Norway"), - ("nl_BE", "Dutch", "Belgium"), - ("nl_NL", "Dutch", "Netherlands"), - ("oc_OC", "Occitan", "Occitan"), - ("pl_PL", "Polish", "Poland"), - ("pt_BR", "Portuguese", "Brazil"), - ("pt_PT", "Portuguese", "Portugal"), - ("ro_RO", "Romanian", "Romania"), - ("ru_RU", "Russian", "Russia"), - ("sk_SK", "Slovak", "Slovak Republic"), - ("sl_SL", "Slovenian", "Slovenia"), - ("sv_SE", "Swedish", "Sweden"), - ("th_TH", "Thai", "Thailand"), - ("tr_TR", "Turkish", "Turkey"), - ("uk_UA", "Ukrainian", "Ukraine"), - ("zh_CN", "Chinese", "China"), - ("zh_HK", "Chinese", "Hong Kong SAR"), - ("zh_TW", "Chinese", "Taiwan")) + (u"gv", u"Gaelg", u"", u"Manx"), + (u"sco", u"Scots", u"", u"Scots"), + (u"scn", u"Sicilianu", u"", u"Sicilian"), + (u"gu", u"ગુજરાતી", u"", u"Gujarati"), + (u"gd", u"Gàidhlig", u"", u"Scottish Gaelic"), + (u"ga", u"Gaeilge", u"", u"Irish"), + (u"gn", u"Avañe'ẽ", u"", u"Guarani"), + (u"gl", u"Galego", u"", u"Galician"), + (u"als", u"Alemannisch", u"", u"Alemannic"), + (u"lt-LT", u"Lietuvių", u"", u"Lithuanian"), + (u"vep", u"Vepsän", u"", u"Vepsian"), + (u"ty", u"Reo Mā`ohi", u"", u"Tahitian"), + (u"tw", u"Twi", u"", u"Twi"), + (u"tt", u"Tatarça / Татарча", u"", u"Tatar"), + (u"tr", u"Türkçe", u"", u"Turkish"), + (u"ts", u"Xitsonga", u"", u"Tsonga"), + (u"tn", u"Setswana", u"", u"Tswana"), + (u"to", u"faka Tonga", u"", u"Tongan"), + (u"tl", u"Tagalog", u"", u"Tagalog"), + (u"vec", u"Vèneto", u"", u"Venetian"), + (u"th", u"ไทย", u"", u"Thai"), + (u"ti", u"ትግርኛ", u"", u"Tigrinya"), + (u"tg", u"Тоҷикӣ", u"", u"Tajik"), + (u"te", u"తెలుగు", u"", u"Telugu"), + (u"ta", u"தமிழ்", u"", u"Tamil"), + (u"lrc", u"لۊری شومالی", u"", u"Northern Luri"), + (u"en-NZ", u"English", u"", u"English"), + (u"got", u"𐌲𐌿𐍄𐌹𐍃𐌺", u"", u"Gothic"), + (u"vls", u"West-Vlams", u"", u"West Flemish"), + (u"ro", u"Română", u"", u"Romanian"), + (u"bxr", u"Буряад", u"", u"Buryat"), + (u"fiu-vro", u"Võro", u"", u"Võro"), + (u"diq", u"Zazaki", u"", u"Zazaki"), + (u"zh", u"中文", u"", u"Chinese"), + (u"pms", u"Piemontèis", u"", u"Piedmontese"), + (u"za", u"Cuengh", u"", u"Zhuang"), + (u"zh-HK", u"中文", u"", u"Chinese"), + (u"zu", u"isiZulu", u"", u"Zulu"), + (u"tet", u"Tetun", u"", u"Tetum"), + (u"es-PE", u"Español", u"", u"Spanish"), + (u"new", u"नेपाल भाषा", u"", u"Newar"), + (u"lez", u"Лезги чІал (Lezgi č’al)", u"", u"Lezgian"), + (u"glk", u"گیلکی", u"", u"Gilaki"), + (u"ko-KR", u"한국어", u"", u"Korean"), + (u"id-ID", u"Bahasa Indonesia", u"", u"Indonesian"), + (u"cho", u"Choctaw", u"", u"Choctaw"), + (u"chr", u"ᏣᎳᎩ", u"", u"Cherokee"), + (u"vi", u"Tiếng Việt", u"", u"Vietnamese"), + (u"chy", u"Tsetsêhestâhese", u"", u"Cheyenne"), + (u"is", u"Íslenska", u"", u"Icelandic"), + (u"tk", u"تركمن / Туркмен", u"", u"Turkmen"), + (u"da-DK", u"Dansk", u"", u"Danish"), + (u"pfl", u"Pälzisch", u"", u"Palatinate German"), + (u"hu-HU", u"Magyar", u"", u"Hungarian"), + (u"he-IL", u"עברית", u"", u"Hebrew"), + (u"mg", u"Malagasy", u"", u"Malagasy"), + (u"ml", u"മലയാളം", u"", u"Malayalam"), + (u"mo", u"Молдовеняскэ", u"", u"Moldovan"), + (u"mn", u"Монгол", u"", u"Mongolian"), + (u"mi", u"Māori", u"", u"Maori"), + (u"mh", u"Ebon", u"", u"Marshallese"), + (u"mk", u"Македонски", u"", u"Macedonian"), + (u"mt", u"Malti", u"", u"Maltese"), + (u"ms", u"Bahasa Melayu", u"", u"Malay"), + (u"mr", u"मराठी", u"", u"Marathi"), + (u"mwl", u"Mirandés", u"", u"Mirandese"), + (u"my", u"မြန်မာဘာသာ", u"", u"Burmese"), + (u"en-PH", u"English", u"", u"English"), + (u"srn", u"Sranantongo", u"", u"Sranan"), + (u"pl-PL", u"Polski", u"", u"Polish"), + (u"sl-SL", u"Slovenščina", u"", u"Slovenian"), + (u"csb", u"Kaszëbsczi", u"", u"Kashubian"), + (u"cbk-zam", u"Chavacano de Zamboanga", u"", u"Zamboanga Chavacano"), + (u"nyn", u"Runyankore", u"", u""), + (u"ig", u"Igbo", u"", u"Igbo"), + (u"fr", u"Français", u"", u"French"), + (u"lad", u"Dzhudezmo", u"", u"Ladino"), + (u"fy", u"Frysk", u"", u"West Frisian"), + (u"fa", u"فارسی", u"", u"Persian"), + (u"ff", u"Fulfulde", u"", u"Fula"), + (u"mai", u"मैथिली", u"", u"Maithili"), + (u"fi", u"Suomi", u"", u"Finnish"), + (u"fj", u"Na Vosa Vakaviti", u"", u"Fijian"), + (u"fo", u"Føroyskt", u"", u"Faroese"), + (u"ss", u"SiSwati", u"", u"Swati"), + (u"roa-tara", u"Tarandíne", u"", u"Tarantino"), + (u"sq", u"Shqip", u"", u"Albanian"), + (u"sw", u"Kiswahili", u"", u"Swahili"), + (u"sv", u"Svenska", u"", u"Swedish"), + (u"su", u"Basa Sunda", u"", u"Sundanese"), + (u"st", u"Sesotho", u"", u"Sesotho"), + (u"sk", u"Slovenčina", u"", u"Slovak"), + (u"si", u"සිංහල", u"", u"Sinhalese"), + (u"sh", u"Srpskohrvatski / Српскохрватски", u"", u"Serbo-Croatian"), + (u"so", u"Soomaali", u"", u"Somali"), + (u"sn", u"chiShona", u"", u"Shona"), + (u"sm", u"Gagana Samoa", u"", u"Samoan"), + (u"sl", u"Slovenščina", u"", u"Slovenian"), + (u"sc", u"Sardu", u"", u"Sardinian"), + (u"pt-BR", u"português (Brasil)", u"", u""), + (u"sa", u"संस्कृतम्", u"", u"Sanskrit"), + (u"sg", u"Sängö", u"", u"Sango"), + (u"se", u"Sámegiella", u"", u"Northern Sami"), + (u"sd", u"سنڌي، سندھی ، सिन्ध", u"", u"Sindhi"), + (u"fr-CH", u"Français", u"", u"French"), + (u"zea", u"Zeêuws", u"", u"Zeelandic"), + (u"it-CH", u"Italiano", u"", u"Italian"), + (u"wuu", u"吴语", u"", u"Wu"), + (u"fr-CA", u"Français", u"", u"French"), + (u"ar-XA", u"العربية", u"", u"Arabic"), + (u"kbd", u"Адыгэбзэ (Adighabze)", u"", u"Kabardian Circassian"), + (u"no-NO", u"Norsk (Bokmål)", u"", u"Norwegian (Bokmål)"), + (u"ca-ES", u"Català", u"", u"Catalan"), + (u"lg", u"Luganda", u"", u"Luganda"), + (u"lb", u"Lëtzebuergesch", u"", u"Luxembourgish"), + (u"la", u"Latina", u"", u"Latin"), + (u"ln", u"Lingala", u"", u"Lingala"), + (u"lo", u"ລາວ", u"", u"Lao"), + (u"de-CH", u"Deutsch", u"", u"German"), + (u"li", u"Limburgs", u"", u"Limburgish"), + (u"lv", u"Latviešu", u"", u"Latvian"), + (u"lt", u"Lietuvių", u"", u"Lithuanian"), + (u"pcm", u"Nigerian Pidgin", u"", u""), + (u"pcd", u"Picard", u"", u"Picard"), + (u"yi", u"ייִדיש", u"", u"Yiddish"), + (u"ceb", u"Sinugboanong Binisaya", u"", u"Cebuano"), + (u"yo", u"Yorùbá", u"", u"Yoruba"), + (u"ro-RO", u"Română", u"", u"Romanian"), + (u"bar", u"Boarisch", u"", u"Bavarian"), + (u"nov", u"Novial", u"", u"Novial"), + (u"sr-ME", u"srpski (Crna Gora)", u"", u""), + (u"es-CL", u"Español", u"", u"Spanish"), + (u"es-CO", u"Español", u"", u"Spanish"), + (u"nl-NL", u"Nederlands", u"", u"Dutch"), + (u"map-bms", u"Basa Banyumasan", u"", u"Banyumasan"), + (u"el", u"Ελληνικά", u"", u"Greek"), + (u"eo", u"Esperanto", u"", u"Esperanto"), + (u"en", u"English", u"", u"English"), + (u"ee", u"Eʋegbe", u"", u"Ewe"), + (u"mdf", u"Мокшень (Mokshanj Kälj)", u"", u"Moksha"), + (u"eu", u"Euskara", u"", u"Basque"), + (u"et", u"Eesti", u"", u"Estonian"), + (u"es", u"Español", u"", u"Spanish"), + (u"gom", u"गोवा कोंकणी / Gova Konknni", u"", u"Goan Konkani"), + (u"ru", u"Русский", u"", u"Russian"), + (u"rw", u"Ikinyarwanda", u"", u"Kinyarwanda"), + (u"rm", u"Rumantsch", u"", u"Romansh"), + (u"rn", u"Kirundi", u"", u"Kirundi"), + (u"es-419", u"español (Latinoamérica)", u"", u""), + (u"dsb", u"Dolnoserbski", u"", u"Lower Sorbian"), + (u"ast", u"Asturianu", u"", u"Asturian"), + (u"lmo", u"Lumbaart", u"", u"Lombard"), + (u"ltg", u"Latgaļu", u"", u"Latgalian"), + (u"xh", u"isiXhosa", u"", u"Xhosa"), + (u"en-CA", u"English", u"", u"English"), + (u"koi", u"Перем Коми (Perem Komi)", u"", u"Komi-Permyak"), + (u"tr-TR", u"Türkçe", u"", u"Turkish"), + (u"pnt", u"Ποντιακά", u"", u"Pontic"), + (u"es-XL", u"Español", u"", u"Spanish"), + (u"fi-FI", u"Suomi", u"", u"Finnish"), + (u"pnb", u"شاہ مکھی پنجابی (Shāhmukhī Pañjābī)", u"", u"Western Punjabi"), + (u"udm", u"Удмурт кыл", u"", u"Udmurt"), + (u"bem", u"Ichibemba", u"", u""), + (u"roa-rup", u"Armãneashce", u"", u"Aromanian"), + (u"sr-Latn", u"srpski (latinica)", u"", u""), + (u"stq", u"Seeltersk", u"", u"Saterland Frisian"), + (u"sr", u"Српски / Srpski", u"", u"Serbian"), + (u"ang", u"Englisc", u"", u"Anglo-Saxon"), + (u"ru-RU", u"Русский", u"", u"Russian"), + (u"lbe", u"Лакку", u"", u"Lak"), + (u"min", u"Minangkabau", u"", u"Minangkabau"), + (u"es-US", u"Español", u"", u"Spanish"), + (u"lij", u"Líguru", u"", u"Ligurian"), + (u"kab", u"Taqbaylit", u"", u"Kabyle"), + (u"kaa", u"Qaraqalpaqsha", u"", u"Karakalpak"), + (u"fr-FR", u"Français", u"", u"French"), + (u"tyv", u"Тыва", u"", u"Tuvan"), + (u"ka", u"ქართული", u"", u"Georgian"), + (u"kg", u"KiKongo", u"", u"Kongo"), + (u"ckb", u"Soranî / کوردی", u"", u"Sorani"), + (u"kk", u"Қазақша", u"", u"Kazakh"), + (u"kj", u"Kuanyama", u"", u"Kuanyama"), + (u"ki", u"Gĩkũyũ", u"", u"Kikuyu"), + (u"ko", u"한국어", u"", u"Korean"), + (u"kn", u"ಕನ್ನಡ", u"", u"Kannada"), + (u"tpi", u"Tok Pisin", u"", u"Tok Pisin"), + (u"kl", u"Kalaallisut", u"", u"Greenlandic"), + (u"ks", u"कश्मीरी / كشميري", u"", u"Kashmiri"), + (u"kr", u"Kanuri", u"", u"Kanuri"), + (u"ext", u"Estremeñu", u"", u"Extremaduran"), + (u"kw", u"Kernewek/Karnuack", u"", u"Cornish"), + (u"kv", u"Коми", u"", u"Komi"), + (u"mrj", u"Кырык Мары (Kyryk Mary)", u"", u"Hill Mari"), + (u"ky", u"Кыргызча", u"", u"Kirghiz"), + (u"szl", u"Ślůnski", u"", u"Silesian"), + (u"cdo", u"Mìng-dĕ̤ng-ngṳ̄", u"", u"Min Dong"), + (u"en-GB", u"English", u"", u"English"), + (u"xmf", u"მარგალური (Margaluri)", u"", u"Mingrelian"), + (u"jam", u"Jamaican Creole English", u"", u"Patois"), + (u"ar-SA", u"العربية", u"", u"Arabic"), + (u"ksh", u"Ripoarisch", u"", u"Ripuarian"), + (u"ms-MY", u"Bahasa Melayu", u"", u"Malay"), + (u"de", u"Deutsch", u"", u"German"), + (u"da", u"Dansk", u"", u"Danish"), + (u"dz", u"ཇོང་ཁ", u"", u"Dzongkha"), + (u"hif", u"Fiji Hindi", u"", u"Fiji Hindi"), + (u"dv", u"ދިވެހިބަސް", u"", u"Divehi"), + (u"crs", u"Seychellois Creole", u"", u""), + (u"qu", u"Runa Simi", u"", u"Quechua"), + (u"eml", u"Emiliàn e rumagnòl", u"", u"Emilian-Romagnol"), + (u"ban", u"Balinese", u"", u""), + (u"crh", u"Qırımtatarca", u"", u"Crimean Tatar"), + (u"arz", u"مصرى (Maṣri)", u"", u"Egyptian Arabic"), + (u"rmy", u"romani - रोमानी", u"", u"Romani"), + (u"arc", u"ܐܪܡܝܐ", u"", u"Aramaic"), + (u"th-TH", u"ไทย", u"", u"Thai"), + (u"mus", u"Muskogee", u"", u"Muscogee"), + (u"lua", u"Luba-Lulua", u"", u""), + (u"en-ZA", u"English", u"", u"English"), + (u"wa", u"Walon", u"", u"Walloon"), + (u"wo", u"Wolof", u"", u"Wolof"), + (u"jv", u"Basa Jawa", u"", u"Javanese"), + (u"jw", u"Javanese", u"", u""), + (u"fr-BE", u"Français", u"", u"French"), + (u"tum", u"chiTumbuka", u"", u"Tumbuka"), + (u"ja", u"日本語", u"", u"Japanese"), + (u"pt-PT", u"português (Portugal)", u"", u""), + (u"ilo", u"Ilokano", u"", u"Ilokano"), + (u"tlh", u"Klingon", u"", u""), + (u"pdc", u"Deitsch", u"", u"Pennsylvania German"), + (u"aa", u"Afar", u"", u"Afar"), + (u"ch", u"Chamoru", u"", u"Chamorro"), + (u"co", u"Corsu", u"", u"Corsican"), + (u"simple", u"Simple English", u"", u"Simple English"), + (u"ca", u"Català", u"", u"Catalan"), + (u"xx-pirate", u"Pirate", u"", u""), + (u"ce", u"Нохчийн", u"", u"Chechen"), + (u"cy", u"Cymraeg", u"", u"Welsh"), + (u"sah", u"Саха тыла (Saxa Tyla)", u"", u"Sakha"), + (u"cs", u"Čeština", u"", u"Czech"), + (u"cr", u"Nehiyaw", u"", u"Cree"), + (u"bg-BG", u"Български", u"", u"Bulgarian"), + (u"cv", u"Чăваш", u"", u"Chuvash"), + (u"cu", u"Словѣньскъ", u"", u"Old Church Slavonic"), + (u"ps", u"پښتو", u"", u"Pashto"), + (u"pt", u"Português", u"", u"Portuguese"), + (u"vi-VN", u"Tiếng Việt", u"", u"Vietnamese"), + (u"frr", u"Nordfriisk", u"", u"North Frisian"), + (u"frp", u"Arpitan", u"", u"Franco-Provençal"), + (u"xal", u"Хальмг", u"", u"Kalmyk"), + (u"pi", u"पाऴि", u"", u"Pali"), + (u"it-IT", u"Italiano", u"", u"Italian"), + (u"pl", u"Polski", u"", u"Polish"), + (u"nrm", u"Nouormand/Normaund", u"", u"Norman"), + (u"en-US", u"English", u"", u"English"), + (u"gan", u"贛語", u"", u"Gan"), + (u"bat-smg", u"Žemaitėška", u"", u"Samogitian"), + (u"en-UK", u"English", u"", u"English"), + (u"gag", u"Gagauz", u"", u"Gagauz"), + (u"an", u"Aragonés", u"", u"Aragonese"), + (u"gaa", u"Ga", u"", u""), + (u"fur", u"Furlan", u"", u"Friulian"), + (u"kr-KR", u"Kanuri", u"", u"Kanuri"), + (u"zh-CN", u"中文 (简体)", u"", u""), + (u"tl-PH", u"Tagalog", u"", u"Tagalog"), + (u"en-IN", u"English", u"", u"English"), + (u"ve", u"Tshivenda", u"", u"Venda"), + (u"en-ID", u"English", u"", u"English"), + (u"en-IE", u"English", u"", u"English"), + (u"xx-bork", u"Bork, bork, bork!", u"", u""), + (u"iu", u"ᐃᓄᒃᑎᑐᑦ", u"", u"Inuktitut"), + (u"it", u"Italiano", u"", u"Italian"), + (u"iw", u"עברית", u"", u""), + (u"vo", u"Volapük", u"", u"Volapük"), + (u"ii", u"ꆇꉙ", u"", u"Sichuan Yi"), + (u"ik", u"Iñupiak", u"", u"Inupiak"), + (u"io", u"Ido", u"", u"Ido"), + (u"ia", u"Interlingua", u"", u"Interlingua"), + (u"ja-JP", u"日本語", u"", u"Japanese"), + (u"ie", u"Interlingue", u"", u"Interlingue"), + (u"id", u"Bahasa Indonesia", u"", u"Indonesian"), + (u"nds-nl", u"Nedersaksisch", u"", u"Dutch Low Saxon"), + (u"pap", u"Papiamentu", u"", u"Papiamentu"), + (u"pag", u"Pangasinan", u"", u"Pangasinan"), + (u"pam", u"Kapampangan", u"", u"Kapampangan"), + (u"lv-LV", u"Latviešu", u"", u"Latvian"), + (u"mzn", u"مَزِروني", u"", u"Mazandarani"), + (u"nl-BE", u"Nederlands", u"", u"Dutch"), + (u"sk-SK", u"Slovenčina", u"", u"Slovak"), + (u"zh-TW", u"中文 (繁體)", u"", u""), + (u"es-MX", u"Español", u"", u"Spanish"), + (u"de-DE", u"Deutsch", u"", u"German"), + (u"jbo", u"Lojban", u"", u"Lojban"), + (u"mfe", u"kreol morisien", u"", u""), + (u"hak", u"Hak-kâ-fa / 客家話", u"", u"Hakka"), + (u"ny", u"Chichewa", u"", u"Chichewa"), + (u"ady", u"Адыгэбзэ", u"", u"Adyghe"), + (u"haw", u"Hawai`i", u"", u"Hawaiian"), + (u"el-GR", u"Ελληνικά", u"", u"Greek"), + (u"bpy", u"ইমার ঠার/বিষ্ণুপ্রিয়া মণিপুরী", u"", u"Bishnupriya Manipuri"), + (u"mhr", u"Олык Марий (Olyk Marij)", u"", u"Meadow Mari"), + (u"ca-CT", u"Català", u"", u"Catalan"), + (u"en-MY", u"English", u"", u"English"), + (u"sv-SE", u"Svenska", u"", u"Swedish"), + (u"de-AT", u"Deutsch", u"", u"German"), + (u"xx-elmer", u"Elmer Fudd", u"", u""), + (u"hsb", u"Hornjoserbsce", u"", u"Upper Sorbian"), + (u"be", u"Беларуская", u"", u"Belarusian"), + (u"bg", u"Български", u"", u"Bulgarian"), + (u"ba", u"Башҡорт", u"", u"Bashkir"), + (u"bm", u"Bamanankan", u"", u"Bambara"), + (u"bn", u"বাংলা", u"", u"Bengali"), + (u"bo", u"བོད་སྐད", u"", u"Tibetan"), + (u"bh", u"भोजपुरी", u"", u"Bihari"), + (u"bi", u"Bislama", u"", u"Bislama"), + (u"rue", u"Русиньскый", u"", u"Rusyn"), + (u"et-EE", u"Eesti", u"", u"Estonian"), + (u"br", u"Brezhoneg", u"", u"Breton"), + (u"bs", u"Bosanski", u"", u"Bosnian"), + (u"om", u"Oromoo", u"", u"Oromo"), + (u"ace", u"Bahsa Acèh", u"", u"Acehnese"), + (u"es-AR", u"Español", u"", u"Spanish"), + (u"ach", u"Acoli", u"", u""), + (u"oc", u"Occitan", u"", u"Occitan"), + (u"kri", u"Krio (Sierra Leone)", u"", u""), + (u"be-tarask", u"Беларуская (тарашкевіца)", u"", u"Belarusian (Taraškievica)"), + (u"krc", u"Къарачай-Малкъар (Qarachay-Malqar)", u"", u"Karachay-Balkar"), + (u"nds", u"Plattdüütsch", u"", u"Low Saxon"), + (u"os", u"Иронау", u"", u"Ossetian"), + (u"or", u"ଓଡ଼ିଆ", u"", u"Oriya"), + (u"nso", u"Sepedi", u"", u"Northern Sotho"), + (u"bjn", u"Bahasa Banjar", u"", u"Banjar"), + (u"xx-hacker", u"Hacker", u"", u""), + (u"zh-min-nan", u"Bân-lâm-gú", u"", u"Min Nan"), + (u"pa", u"ਪੰਜਾਬੀ", u"", u"Punjabi"), + (u"loz", u"Lozi", u"", u""), + (u"war", u"Winaray", u"", u"Waray-Waray"), + (u"hz", u"Otsiherero", u"", u"Herero"), + (u"hy", u"Հայերեն", u"", u"Armenian"), + (u"hr", u"Hrvatski", u"", u"Croatian"), + (u"ht", u"Krèyol ayisyen", u"", u"Haitian"), + (u"hu", u"Magyar", u"", u"Hungarian"), + (u"hi", u"हिन्दी", u"", u"Hindi"), + (u"ho", u"Hiri Motu", u"", u"Hiri Motu"), + (u"ha", u"هَوُسَ", u"", u"Hausa"), + (u"bug", u"Basa Ugi", u"", u"Buginese"), + (u"he", u"עברית", u"", u"Hebrew"), + (u"hr-HR", u"Hrvatski", u"", u"Croatian"), + (u"uz", u"O‘zbek", u"", u"Uzbek"), + (u"azb", u"تۆرکجه", u"", u"South Azerbaijani"), + (u"ur", u"اردو", u"", u"Urdu"), + (u"uk", u"Українська", u"", u"Ukrainian"), + (u"ug", u"ئۇيغۇر تىلى", u"", u"Uyghur"), + (u"pih", u"Norfuk", u"", u"Norfolk"), + (u"ab", u"Аҧсуа", u"", u"Abkhazian"), + (u"af", u"Afrikaans", u"", u"Afrikaans"), + (u"ak", u"Akana", u"", u"Akan"), + (u"am", u"አማርኛ", u"", u"Amharic"), + (u"myv", u"Эрзянь (Erzjanj Kelj)", u"", u"Erzya"), + (u"as", u"অসমীয়া", u"", u"Assamese"), + (u"ar", u"العربية", u"", u"Arabic"), + (u"km", u"ភាសាខ្មែរ", u"", u"Khmer"), + (u"uk-UA", u"Українська", u"", u"Ukrainian"), + (u"av", u"Авар", u"", u"Avar"), + (u"ay", u"Aymar", u"", u"Aymara"), + (u"az", u"Azərbaycanca", u"", u"Azerbaijani"), + (u"es-ES", u"Español", u"", u"Spanish"), + (u"nl", u"Nederlands", u"", u"Dutch"), + (u"nn", u"Nynorsk", u"", u"Norwegian (Nynorsk)"), + (u"no", u"Norsk (Bokmål)", u"", u"Norwegian (Bokmål)"), + (u"na", u"dorerin Naoero", u"", u"Nauruan"), + (u"nah", u"Nāhuatl", u"", u"Nahuatl"), + (u"ne", u"नेपाली", u"", u"Nepali"), + (u"ng", u"Oshiwambo", u"", u"Ndonga"), + (u"en-AU", u"English", u"", u"English"), + (u"nap", u"Nnapulitano", u"", u"Neapolitan"), + (u"nv", u"Diné bizaad", u"", u"Navajo"), + (u"ku", u"Kurdî / كوردی", u"", u"Kurdish"), + (u"cs-CZ", u"Čeština", u"", u"Czech"), + (u"zh-yue", u"粵語", u"", u"Cantonese"), + (u"en-SG", u"English", u"", u"English"), + (u"zh-classical", u"古文 / 文言文", u"", u"Classical Chinese"), + (u"bcl", u"Bikol", u"", u"Central Bicolano"), + (u"en-XA", u"English", u"", u"English") +)diff --git a/searx/query.py b/searx/query.py@@ -71,21 +71,24 @@ class RawTextQuery(object): # check if any language-code is equal with # declared language-codes for lc in language_codes: - lang_id, lang_name, country = map(str.lower, lc) + lang_id, lang_name, country, english_name = map(unicode.lower, lc) # if correct language-code is found # set it as new search-language if lang == lang_id\ or lang_id.startswith(lang)\ or lang == lang_name\ + or lang == english_name\ or lang.replace('_', ' ') == country: parse_next = True - self.languages.append(lang) - break + self.languages.append(lang_id) + # to ensure best match (first match is not necessarily the best one) + if lang == lang_id: + break # this force a engine or category if query_part[0] == '!' or query_part[0] == '?': - prefix = query_part[1:].replace('_', ' ') + prefix = query_part[1:].replace('-', ' ') # check if prefix is equal with engine shortcut if prefix in engine_shortcuts:diff --git a/searx/templates/courgette/preferences.html b/searx/templates/courgette/preferences.html@@ -13,9 +13,9 @@ <legend>{{ _('Search language') }}</legend> <p> <select name='language'> - <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Automatic') }}</option> - {% for lang_id,lang_name,country_name in language_codes | sort(attribute=1) %} - <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} ({{ country_name }}) - {{ lang_id }}</option> + <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option> + {% for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) %} + <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id }}</option> {% endfor %} </select> </p>diff --git a/searx/templates/legacy/preferences.html b/searx/templates/legacy/preferences.html@@ -14,9 +14,9 @@ <legend>{{ _('Search language') }}</legend> <p> <select name='language'> - <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Automatic') }}</option> - {% for lang_id,lang_name,country_name in language_codes | sort(attribute=1) %} - <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} ({{ country_name }}) - {{ lang_id }}</option> + <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option> + {% for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) %} + <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id }}</option> {% endfor %} </select> </p>diff --git a/searx/templates/oscar/advanced.html b/searx/templates/oscar/advanced.html@@ -6,4 +6,5 @@ <div id="advanced-search-container"> {% include 'oscar/categories.html' %} {% include 'oscar/time-range.html' %} + {% include 'oscar/languages.html' %} </div>diff --git a/searx/templates/oscar/languages.html b/searx/templates/oscar/languages.html@@ -0,0 +1,12 @@ +{% if preferences %} +<select class="form-control" name='language'> +{% else %} +<select class="time_range" name='language'> +{% endif %} + <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option> + {% for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) %} + <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}> + {{ lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id }} + </option> + {% endfor %} +</select>diff --git a/searx/templates/oscar/preferences.html b/searx/templates/oscar/preferences.html@@ -40,12 +40,7 @@ {% set language_label = _('Search language') %} {% set language_info = _('What language do you prefer for search?') %} {{ preferences_item_header(language_info, language_label, rtl) }} - <select class="form-control" name='language'> - <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Automatic') }}</option> - {% for lang_id,lang_name,country_name in language_codes | sort(attribute=1) %} - <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} ({{ country_name }}) - {{ lang_id }}</option> - {% endfor %} - </select> + {% include 'oscar/languages.html' %} {{ preferences_item_footer(language_info, language_label, rtl) }} {% set locale_label = _('Interface language') %} @@ -153,6 +148,7 @@ <th>{{ _("Allow") }}</th> <th>{{ _("Engine name") }}</th> <th>{{ _("Shortcut") }}</th> + <th>{{ _("Language support") }}</th> <th>{{ _("SafeSearch") }}</th> <th>{{ _("Time range") }}</th> <th>{{ _("Avg. time") }}</th> @@ -161,6 +157,7 @@ <th>{{ _("Max time") }}</th> <th>{{ _("Avg. time") }}</th> <th>{{ _("SafeSearch") }}</th> + <th>{{ _("Language support") }}</th> <th>{{ _("Shortcut") }}</th> <th>{{ _("Engine name") }}</th> <th>{{ _("Allow") }}</th> @@ -175,6 +172,7 @@ </td> <th>{{ search_engine.name }}</th> <td>{{ shortcuts[search_engine.name] }}</td> + <td><input type="checkbox" {{ "checked" if current_language in search_engine.supported_languages or current_language.split('-')[0] in search_engine.supported_languages else ""}} readonly="readonly" disabled="disabled"></td> <td><input type="checkbox" {{ "checked" if search_engine.safesearch==True else ""}} readonly="readonly" disabled="disabled"></td> <td><input type="checkbox" {{ "checked" if search_engine.time_range_support==True else ""}} readonly="readonly" disabled="disabled"></td> <td class="{{ 'danger' if stats[search_engine.name]['warn_time'] else '' }}">{{ 'N/A' if stats[search_engine.name].time==None else stats[search_engine.name].time }}</td> @@ -183,6 +181,7 @@ <td class="{{ 'danger' if stats[search_engine.name]['warn_timeout'] else '' }}">{{ search_engine.timeout }}</td> <td class="{{ 'danger' if stats[search_engine.name]['warn_time'] else '' }}">{{ 'N/A' if stats[search_engine.name].time==None else stats[search_engine.name].time }}</td> <td><input type="checkbox" {{ "checked" if search_engine.safesearch==True else ""}} readonly="readonly" disabled="disabled"></td> + <td><input type="checkbox" {{ "checked" if current_language in search_engine.supported_languages or current_language.split('-')[0] in search_engine.supported_languages else ""}} readonly="readonly" disabled="disabled"></td> <td>{{ shortcuts[search_engine.name] }}</td> <th>{{ search_engine.name }}</th> <td class="onoff-checkbox">diff --git a/searx/templates/pix-art/preferences.html b/searx/templates/pix-art/preferences.html@@ -9,9 +9,9 @@ <legend>{{ _('Search language') }}</legend> <p> <select name='language'> - <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Automatic') }}</option> - {% for lang_id,lang_name,country_name in language_codes | sort(attribute=1) %} - <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} ({{ country_name }}) - {{ lang_id }}</option> + <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option> + {% for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) %} + <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id }}</option> {% endfor %} </select> </p>diff --git a/searx/webapp.py b/searx/webapp.py@@ -330,6 +330,10 @@ def render(template_name, override_theme=None, **kwargs): kwargs['safesearch'] = str(request.preferences.get_value('safesearch')) + kwargs['language_codes'] = language_codes + if 'current_language' not in kwargs: + kwargs['current_language'] = request.preferences.get_value('language') + # override url_for function in templates kwargs['url_for'] = url_for_theme @@ -510,6 +514,7 @@ def index(): answers=result_container.answers, infoboxes=result_container.infoboxes, paging=result_container.paging, + current_language=search.lang, base_url=get_base_url(), theme=get_current_theme_name(), favicons=global_favicons[themes.index(get_current_theme_name())] @@ -552,7 +557,7 @@ def autocompleter(): if not language or language == 'all': language = 'en' else: - language = language.split('_')[0] + language = language.split('-')[0] # run autocompletion raw_results.extend(completer(raw_text_query.getSearchQuery(), language)) @@ -615,9 +620,7 @@ def preferences(): return render('preferences.html', locales=settings['locales'], current_locale=get_locale(), - current_language=lang, image_proxy=image_proxy, - language_codes=language_codes, engines_by_category=categories, stats=stats, answerers=[{'info': a.self_info(), 'keywords': a.keywords} for a in answerers], @@ -627,7 +630,8 @@ def preferences(): themes=themes, plugins=plugins, allowed_plugins=allowed_plugins, - theme=get_current_theme_name()) + theme=get_current_theme_name(), + preferences=True) @app.route('/image_proxy', methods=['GET'])diff --git a/utils/update_languages.py b/utils/update_languages.py@@ -0,0 +1,99 @@ +# -*- coding: utf-8 -*- + +# This script generates languages.py from +# intersecting each engine's supported languages. +# +# The language's native names are obtained from +# Wikipedia's supported languages. +# +# Output file (languages.py) is written in current directory +# to avoid overwriting in case something goes wrong. + +from requests import get +from re import sub +from lxml.html import fromstring +from json import loads +from sys import path +path.append('../searx') +from searx.engines import engines + +# list of language names +wiki_languages_url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias' +google_languages_url = 'https://www.google.com/preferences?#languages' + +google_json_name = 'google.preferences.langMap' + +languages = {} + +# Get language names from Wikipedia. +def get_wikipedia_languages(): + response = get(wiki_languages_url) + dom = fromstring(response.text) + tables = dom.xpath('//table[contains(@class,"sortable")]') + for table in tables: + # exclude header row + trs = table.xpath('.//tr')[1:] + for tr in trs: + td = tr.xpath('./td') + code = td[3].xpath('./a')[0].text + name = td[2].xpath('./a')[0].text + english_name = td[1].xpath('./a')[0].text + + if code not in languages: + languages[code] = (name, '', english_name) + +# Get language names from Google. +def get_google_languages(): + response = get(google_languages_url) + dom = fromstring(response.text) + options = dom.xpath('//select[@name="hl"]/option') + for option in options: + code = option.xpath('./@value')[0] + name = option.text[:-1] + + if code not in languages: + languages[code] = (name, '', '') + +# Join all language lists. +# iterate all languages supported by each engine +def join_language_lists(): + for engine_name in engines: + for locale in engines[engine_name].supported_languages: + locale = locale.replace('_', '-') + if locale not in languages: + # try to get language name + language = languages.get(locale.split('-')[0], None) + if language == None: + print engine_name + ": " + locale + continue + + (name, country, english) = language + languages[locale] = (name, country, english) + +# Write languages.py. +def write_languages_file(): + new_file = open('languages.py', 'w') + file_content = '# -*- coding: utf-8 -*-\n' + file_content += '# list of language codes\n' + file_content += '# this file is generated automatically by utils/update_search_languages.py\n' + file_content += '\nlanguage_codes = (' + for code in languages: + (name, country, english) = languages[code] + file_content += '\n (u"' + code + '"'\ + + ', u"' + name + '"'\ + + ', u"' + country[1:-1] + '"'\ + + ', u"' + english + '"),' + # remove last comma + file_content = file_content[:-1] + file_content += '\n)\n' + new_file.write(file_content.encode('utf8')) + new_file.close() + +def main(): + get_wikipedia_languages() + get_google_languages() + join_language_lists() + write_languages_file() + +if __name__ == "__main__": + main()