[mod] move language recognition to get_search_query_from_webapp

To set the language from language recognition and hold the value selected by the
client, the previous implementation creates a copy of the SearchQuery object and
manipulates the SearchQuery object by calling function replace_auto_language().

This patch tries to implement a similar functionality in a more central place,
in function get_search_query_from_webapp() when the SearchQuery object is build
up.

Additional this patch uses the language preferred by the client, if language
recognition does not have a match / the existing implementation does not care
about client preferences and uses 'all' in case of no match.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

1 files changed, 30 insertions, 2 deletions

diff --git a/searx/webadapter.py b/searx/webadapter.py
index dbcf25058..121319eeb 100644
--- a/searx/webadapter.py
+++ b/searx/webadapter.py
@@ -6,6 +6,7 @@ from searx.query import RawTextQuery
 from searx.engines import categories, engines
 from searx.search import SearchQuery, EngineRef
 from searx.preferences import Preferences, is_locked
+from searx.utils import detect_language
 
 
 # remove duplicate queries.
@@ -214,7 +215,27 @@ def parse_engine_data(form):
 
 def get_search_query_from_webapp(
     preferences: Preferences, form: Dict[str, str]
-) -> Tuple[SearchQuery, RawTextQuery, List[EngineRef], List[EngineRef]]:
+) -> Tuple[SearchQuery, RawTextQuery, List[EngineRef], List[EngineRef], str]:
+    """Assemble data from preferences and request.form (from the HTML form) needed
+    in a search query.
+
+    The returned tuple consits of:
+
+    1. instance of :py:obj:`searx.search.SearchQuery`
+    2. instance of :py:obj:`searx.query.RawTextQuery`
+    3. list of :py:obj:`searx.search.EngineRef` instances
+    4. string with the *selected locale* of the query
+
+    About language/locale: if the client selects the alias ``auto`` the
+    ``SearchQuery`` object is build up by the :py:obj:`detected language
+    <searx.utils.detect_language>`.  If language recognition does not have a
+    match the language preferred by the :py:obj:`Preferences.client` is used.
+    If client does not have a preference, the default ``all`` is used.
+
+    The *selected locale* in the tuple always represents the selected
+    language/locale and might differ from the language recognition.
+
+    """
     # no text for the query ?
     if not form.get('q'):
         raise SearxParameterException('q', '')
@@ -229,13 +250,19 @@ def get_search_query_from_webapp(
     # set query
     query = raw_text_query.getQuery()
     query_pageno = parse_pageno(form)
-    query_lang = parse_lang(preferences, form, raw_text_query)
     query_safesearch = parse_safesearch(preferences, form)
     query_time_range = parse_time_range(form)
     query_timeout = parse_timeout(form, raw_text_query)
     external_bang = raw_text_query.external_bang
     engine_data = parse_engine_data(form)
 
+    query_lang = parse_lang(preferences, form, raw_text_query)
+    selected_locale = query_lang
+
+    if query_lang == 'auto':
+        query_lang = detect_language(query, threshold=0.8, only_search_languages=True)
+        query_lang = query_lang or preferences.client.locale_tag or 'all'
+
     if not is_locked('categories') and raw_text_query.specific:
         # if engines are calculated from query,
         # set categories by using that information
@@ -265,4 +292,5 @@ def get_search_query_from_webapp(
         raw_text_query,
         query_engineref_list_unknown,
         query_engineref_list_notoken,
+        selected_locale,
     )