Merge pull request #1475 from kvch/add-all-language-option-again

Revert "remove 'all' option from search languages"

searx/engines/archlinux.py

@@ -36,7 +36,7 @@ def locale_to_lang_code(locale):
 # wikis for some languages were moved off from the main site, we need to make
 # requests to correct URLs to be able to get results in those languages
 lang_urls = {
-    'en': {
+    'all': {
         'base': 'https://wiki.archlinux.org',
         'search': '/index.php?title=Special:Search&offset={offset}&{query}'
     },
@@ -67,7 +67,7 @@ lang_urls = {
 def get_lang_urls(language):
     if language in lang_urls:
         return lang_urls[language]
-    return lang_urls['en']
+    return lang_urls['all']
 
 
 # Language names to build search requests for

searx/engines/bing.py

@@ -34,6 +34,9 @@ search_string = 'search?{query}&first={offset}'
 def request(query, params):
     offset = (params['pageno'] - 1) * 10 + 1
 
+    if params['language'] == 'all':
+        lang = 'EN'
+    else:
         lang = match_language(params['language'], supported_languages, language_aliases)
 
     query = u'language:{} {}'.format(lang.split('-')[0].upper(), query.decode('utf-8')).encode('utf-8')

searx/engines/bing_news.py

@@ -71,6 +71,9 @@ def request(query, params):
 
     offset = (params['pageno'] - 1) * 10 + 1
 
+    if params['language'] == 'all':
+        language = 'en-US'
+    else:
         language = match_language(params['language'], supported_languages, language_aliases)
 
     params['url'] = _get_url(query, language, offset, params['time_range'])

searx/engines/dailymotion.py

@@ -33,6 +33,9 @@ supported_languages_url = 'https://api.dailymotion.com/languages'
 
 # do search-request
 def request(query, params):
+    if params['language'] == 'all':
+        locale = 'en-US'
+    else:
         locale = match_language(params['language'], supported_languages)
 
     params['url'] = search_url.format(

searx/engines/duckduckgo.py

@@ -54,6 +54,9 @@ content_xpath = './/a[@class="result__snippet"]'
 
 # match query's language to a region code that duckduckgo will accept
 def get_region_code(lang, lang_list=[]):
+    if lang == 'all':
+        return None
+
     lang_code = match_language(lang, lang_list, language_aliases, 'wt-WT')
     lang_parts = lang_code.split('-')
 
@@ -61,7 +64,6 @@ def get_region_code(lang, lang_list=[]):
     return lang_parts[1].lower() + '-' + lang_parts[0].lower()
 
 
-# do search-request
 def request(query, params):
     if params['time_range'] and params['time_range'] not in time_range_dict:
         return params
@@ -69,8 +71,12 @@ def request(query, params):
     offset = (params['pageno'] - 1) * 30
 
     region_code = get_region_code(params['language'], supported_languages)
+    if region_code:
         params['url'] = url.format(
             query=urlencode({'q': query, 'kl': region_code}), offset=offset, dc_param=offset)
+    else:
+        params['url'] = url.format(
+            query=urlencode({'q': query}), offset=offset, dc_param=offset)
 
     if params['time_range'] in time_range_dict:
         params['url'] += time_range_url.format(range=time_range_dict[params['time_range']])

searx/engines/duckduckgo_images.py

@@ -56,8 +56,12 @@ def request(query, params):
     safesearch = params['safesearch'] - 1
 
     region_code = get_region_code(params['language'], lang_list=supported_languages)
+    if region_code:
         params['url'] = images_url.format(
             query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd)
+    else:
+        params['url'] = images_url.format(
+            query=urlencode({'q': query}), offset=offset, safesearch=safesearch, vqd=vqd)
 
     return params
 

searx/engines/faroo.py

@@ -40,6 +40,9 @@ def request(query, params):
     offset = (params['pageno'] - 1) * number_of_results + 1
     categorie = search_category.get(params['category'], 'web')
 
+    if params['language'] == 'all':
+        language = 'en'
+    else:
         language = params['language'].split('-')[0]
 
     # if language is not supported, put it in english

searx/engines/gigablast.py

@@ -50,6 +50,9 @@ supported_languages_url = 'https://gigablast.com/search?&rxikd=1'
 def request(query, params):
     offset = (params['pageno'] - 1) * number_of_results
 
+    if params['language'] == 'all':
+        language = 'xx'
+    else:
         language = params['language'].replace('-', '_').lower()
         if language.split('-')[0] != 'zh':
             language = language.split('-')[0]

searx/engines/google.py

@@ -166,7 +166,11 @@ def extract_text_from_dom(result, xpath):
 def request(query, params):
     offset = (params['pageno'] - 1) * 10
 
+    if params['language'] == 'all' or params['language'] == 'en-US':
+        language = 'en-GB'
+    else:
         language = match_language(params['language'], supported_languages, language_aliases)
+
     language_array = language.split('-')
     if params['language'].find('-') > 0:
         country = params['language'].split('-')[1]

searx/engines/google_news.py

@@ -51,6 +51,7 @@ def request(query, params):
     params['url'] = search_url.format(query=urlencode({'q': query}),
                                       search_options=urlencode(search_options))
 
+    if params['language'] != 'all':
         language = match_language(params['language'], supported_languages, language_aliases).split('-')[0]
         if language:
             params['url'] += '&lr=lang_' + language

searx/engines/mediawiki.py

@@ -45,6 +45,9 @@ def request(query, params):
 
     format_strings = list(Formatter().parse(base_url))
 
+    if params['language'] == 'all':
+        language = 'en'
+    else:
         language = params['language'].split('-')[0]
 
     # format_string [('https://', 'language', '', None), ('.wikipedia.org/', None, None, None)]

searx/engines/photon.py

@@ -35,7 +35,8 @@ def request(query, params):
         search_string.format(query=urlencode({'q': query}),
                              limit=number_of_results)
 
-    language = params['language'].split('-')[0]
+    if params['language'] != 'all':
+        language = params['language'].split('_')[0]
         if language in supported_languages:
             params['url'] = params['url'] + "&lang=" + language
 

searx/engines/qwant.py

@@ -46,6 +46,7 @@ def request(query, params):
                                    offset=offset)
 
     # add language tag
+    if params['language'] != 'all':
         language = match_language(params['language'], supported_languages, language_aliases)
         params['url'] += '&locale=' + language.replace('-', '_').lower()
 

searx/engines/startpage.py

@@ -46,7 +46,8 @@ def request(query, params):
     params['data'] = {'query': query,
                       'startat': offset}
 
-    # set language
+    # set language if specified
+    if params['language'] != 'all':
         params['data']['with_language'] = ('lang_' + params['language'].split('-')[0])
 
     return params

searx/engines/subtitleseeker.py

@@ -48,7 +48,7 @@ def response(resp):
         search_lang = 'Farsi'
     elif resp.search_params['language'] == 'pt-BR':
         search_lang = 'Brazilian'
-    else:
+    elif resp.search_params['language'] != 'all':
         search_lang = [lc[3]
                        for lc in language_codes
                        if lc[0].split('-')[0] == resp.search_params['language'].split('-')[0]]

searx/engines/swisscows.py

@@ -36,6 +36,10 @@ regex_img_url_remove_start = re.compile(b'^https?://i\.swisscows\.ch/\?link=')
 
 # do search-request
 def request(query, params):
+    if params['language'] == 'all':
+        ui_language = 'browser'
+        region = 'browser'
+    else:
         region = match_language(params['language'], supported_languages, language_aliases)
         ui_language = region.split('-')[0]
 

searx/engines/twitter.py

@@ -37,7 +37,12 @@ timestamp_xpath = './/span[contains(@class,"_timestamp")]'
 # do search-request
 def request(query, params):
     params['url'] = search_url + urlencode({'q': query})
+
+    # set language if specified
+    if params['language'] != 'all':
         params['cookies']['lang'] = params['language'].split('-')[0]
+    else:
+        params['cookies']['lang'] = 'en'
 
     return params
 

searx/engines/wikidata.py

@@ -68,6 +68,9 @@ def response(resp):
     html = fromstring(resp.text)
     search_results = html.xpath(wikidata_ids_xpath)
 
+    if resp.search_params['language'].split('-')[0] == 'all':
+        language = 'en'
+    else:
         language = match_language(resp.search_params['language'], supported_languages, language_aliases).split('-')[0]
 
     # TODO: make requests asynchronous to avoid timeout when result_count > 1

searx/engines/wikipedia.py

@@ -31,6 +31,9 @@ supported_languages_url = 'https://meta.wikimedia.org/wiki/List_of_Wikipedias'
 
 # set language in base_url
 def url_lang(lang):
+    lang_pre = lang.split('-')[0]
+    if lang_pre == 'all' or lang_pre not in supported_languages and lang_pre not in language_aliases:
+        return 'en'
     return match_language(lang, supported_languages, language_aliases).split('-')[0]
 
 

searx/engines/yacy.py

@@ -51,6 +51,8 @@ def request(query, params):
                           limit=number_of_results,
                           search_type=search_type)
 
+    # add language tag if specified
+    if params['language'] != 'all':
         params['url'] += '&lr=lang_' + params['language'].split('-')[0]
 
     return params