[mod] replace searx.languages by searx.sxng_locales

With the language and region tags from the EngineTraitsMap the handling of
SearXNG's tags of languages and regions has been normalized and is no longer
a *mystery*.  The "languages" became "locales" that are supported by babel and
by this, the update_engine_traits.py can be simplified a lot.

Other code places can be simplified as well, but these simplifications
should (respectively can) only be done when none of the engines work with the
deprecated EngineTraits.supported_languages interface anymore.

This commit replaces searx.languages by searx.sxng_locales and fix the naming of
some names from "language" to "locale" (e.g. language_codes --> sxng_locales).

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

7 files changed, 91 insertions, 36 deletions

diff --git a/searx/query.py b/searx/query.py
index dbc52ec75..751308baa 100644
--- a/searx/query.py
+++ b/searx/query.py
@@ -4,7 +4,7 @@ from abc import abstractmethod, ABC
 import re
 
 from searx import settings
-from searx.languages import language_codes
+from searx.sxng_locales import sxng_locales
 from searx.engines import categories, engines, engine_shortcuts
 from searx.external_bang import get_bang_definition_and_autocomplete
 from searx.search import EngineRef
@@ -84,7 +84,7 @@ class LanguageParser(QueryPartParser):
         found = False
         # check if any language-code is equal with
         # declared language-codes
-        for lc in language_codes:
+        for lc in sxng_locales:
             lang_id, lang_name, country, english_name, _flag = map(str.lower, lc)
 
             # if correct language-code is found
@@ -125,7 +125,7 @@ class LanguageParser(QueryPartParser):
                     self.raw_text_query.autocomplete_list.append(lang)
             return
 
-        for lc in language_codes:
+        for lc in sxng_locales:
             if lc[0] not in settings['search']['languages']:
                 continue
             lang_id, lang_name, country, english_name, _flag = map(str.lower, lc)
diff --git a/searx/settings_defaults.py b/searx/settings_defaults.py
index 6e98076ff..7f657aa54 100644
--- a/searx/settings_defaults.py
+++ b/searx/settings_defaults.py
@@ -12,13 +12,13 @@ import logging
 from base64 import b64decode
 from os.path import dirname, abspath
 
-from searx.languages import language_codes as languages
+from .sxng_locales import sxng_locales
 
 searx_dir = abspath(dirname(__file__))
 
 logger = logging.getLogger('searx')
 OUTPUT_FORMATS = ['html', 'csv', 'json', 'rss']
-LANGUAGE_CODES = ['all', 'auto'] + list(l[0] for l in languages)
+SXNG_LOCALE_TAGS = ['all', 'auto'] + list(l[0] for l in sxng_locales)
 SIMPLE_STYLE = ('auto', 'light', 'dark')
 CATEGORIES_AS_TABS = {
     'general': {},
@@ -156,8 +156,8 @@ SCHEMA = {
         'safe_search': SettingsValue((0, 1, 2), 0),
         'autocomplete': SettingsValue(str, ''),
         'autocomplete_min': SettingsValue(int, 4),
-        'default_lang': SettingsValue(tuple(LANGUAGE_CODES + ['']), ''),
-        'languages': SettingSublistValue(LANGUAGE_CODES, LANGUAGE_CODES),
+        'default_lang': SettingsValue(tuple(SXNG_LOCALE_TAGS + ['']), ''),
+        'languages': SettingSublistValue(SXNG_LOCALE_TAGS, SXNG_LOCALE_TAGS),
         'ban_time_on_fail': SettingsValue(numbers.Real, 5),
         'max_ban_time_on_fail': SettingsValue(numbers.Real, 120),
         'suspended_times': {
diff --git a/searx/languages.py b/searx/sxng_locales.py
index 377e7495b..110c4f17a 100644
--- a/searx/languages.py
+++ b/searx/sxng_locales.py
@@ -1,73 +1,128 @@
 # -*- coding: utf-8 -*-
-# list of language codes
-# this file is generated automatically by utils/fetch_languages.py
-language_codes = (
-    ('af-ZA', 'Afrikaans', 'Suid-Afrika', 'Afrikaans', '\U0001f1ff\U0001f1e6'),
+'''List of SearXNG's locale codes.
+
+This file is generated automatically by::
+
+   ./manage pyenv.cmd searxng_extra/update/update_engine_traits.py
+'''
+
+sxng_locales = (
+    ('ar', 'العربية', '', 'Arabic', '\U0001f310'),
     ('ar-EG', 'العربية', 'مصر', 'Arabic', '\U0001f1ea\U0001f1ec'),
-    ('be-BY', 'Беларуская', 'Беларусь', 'Belarusian', '\U0001f1e7\U0001f1fe'),
+    ('ar-SA', 'العربية', 'المملكة العربية السعودية', 'Arabic', '\U0001f1f8\U0001f1e6'),
+    ('bg', 'Български', '', 'Bulgarian', '\U0001f310'),
     ('bg-BG', 'Български', 'България', 'Bulgarian', '\U0001f1e7\U0001f1ec'),
+    ('ca', 'Català', '', 'Catalan', '\U0001f310'),
     ('ca-ES', 'Català', 'Espanya', 'Catalan', '\U0001f1ea\U0001f1f8'),
+    ('cs', 'Čeština', '', 'Czech', '\U0001f310'),
     ('cs-CZ', 'Čeština', 'Česko', 'Czech', '\U0001f1e8\U0001f1ff'),
+    ('da', 'Dansk', '', 'Danish', '\U0001f310'),
     ('da-DK', 'Dansk', 'Danmark', 'Danish', '\U0001f1e9\U0001f1f0'),
     ('de', 'Deutsch', '', 'German', '\U0001f310'),
     ('de-AT', 'Deutsch', 'Österreich', 'German', '\U0001f1e6\U0001f1f9'),
     ('de-CH', 'Deutsch', 'Schweiz', 'German', '\U0001f1e8\U0001f1ed'),
     ('de-DE', 'Deutsch', 'Deutschland', 'German', '\U0001f1e9\U0001f1ea'),
+    ('el', 'Ελληνικά', '', 'Greek', '\U0001f310'),
     ('el-GR', 'Ελληνικά', 'Ελλάδα', 'Greek', '\U0001f1ec\U0001f1f7'),
     ('en', 'English', '', 'English', '\U0001f310'),
     ('en-AU', 'English', 'Australia', 'English', '\U0001f1e6\U0001f1fa'),
     ('en-CA', 'English', 'Canada', 'English', '\U0001f1e8\U0001f1e6'),
     ('en-GB', 'English', 'United Kingdom', 'English', '\U0001f1ec\U0001f1e7'),
     ('en-IE', 'English', 'Ireland', 'English', '\U0001f1ee\U0001f1ea'),
-    ('en-MY', 'English', 'Malaysia', 'English', '\U0001f1f2\U0001f1fe'),
+    ('en-IN', 'English', 'India', 'English', '\U0001f1ee\U0001f1f3'),
     ('en-NZ', 'English', 'New Zealand', 'English', '\U0001f1f3\U0001f1ff'),
+    ('en-PH', 'English', 'Philippines', 'English', '\U0001f1f5\U0001f1ed'),
+    ('en-PK', 'English', 'Pakistan', 'English', '\U0001f1f5\U0001f1f0'),
+    ('en-SG', 'English', 'Singapore', 'English', '\U0001f1f8\U0001f1ec'),
     ('en-US', 'English', 'United States', 'English', '\U0001f1fa\U0001f1f8'),
+    ('en-ZA', 'English', 'South Africa', 'English', '\U0001f1ff\U0001f1e6'),
     ('es', 'Español', '', 'Spanish', '\U0001f310'),
     ('es-AR', 'Español', 'Argentina', 'Spanish', '\U0001f1e6\U0001f1f7'),
     ('es-CL', 'Español', 'Chile', 'Spanish', '\U0001f1e8\U0001f1f1'),
+    ('es-CO', 'Español', 'Colombia', 'Spanish', '\U0001f1e8\U0001f1f4'),
     ('es-ES', 'Español', 'España', 'Spanish', '\U0001f1ea\U0001f1f8'),
     ('es-MX', 'Español', 'México', 'Spanish', '\U0001f1f2\U0001f1fd'),
+    ('es-PE', 'Español', 'Perú', 'Spanish', '\U0001f1f5\U0001f1ea'),
+    ('et', 'Eesti', '', 'Estonian', '\U0001f310'),
     ('et-EE', 'Eesti', 'Eesti', 'Estonian', '\U0001f1ea\U0001f1ea'),
-    ('fa-IR', 'فارسی', 'ایران', 'Persian', '\U0001f1ee\U0001f1f7'),
+    ('fi', 'Suomi', '', 'Finnish', '\U0001f310'),
     ('fi-FI', 'Suomi', 'Suomi', 'Finnish', '\U0001f1eb\U0001f1ee'),
-    ('fil-PH', 'Filipino', 'Pilipinas', 'Filipino', '\U0001f1f5\U0001f1ed'),
     ('fr', 'Français', '', 'French', '\U0001f310'),
     ('fr-BE', 'Français', 'Belgique', 'French', '\U0001f1e7\U0001f1ea'),
     ('fr-CA', 'Français', 'Canada', 'French', '\U0001f1e8\U0001f1e6'),
     ('fr-CH', 'Français', 'Suisse', 'French', '\U0001f1e8\U0001f1ed'),
     ('fr-FR', 'Français', 'France', 'French', '\U0001f1eb\U0001f1f7'),
-    ('he-IL', 'עברית', 'ישראל', 'Hebrew', '\U0001f1ee\U0001f1f1'),
-    ('hi-IN', 'हिन्दी', 'भारत', 'Hindi', '\U0001f1ee\U0001f1f3'),
+    ('he', 'עברית', '', 'Hebrew', '\U0001f1ee\U0001f1f7'),
+    ('hr', 'Hrvatski', '', 'Croatian', '\U0001f310'),
     ('hr-HR', 'Hrvatski', 'Hrvatska', 'Croatian', '\U0001f1ed\U0001f1f7'),
+    ('hu', 'Magyar', '', 'Hungarian', '\U0001f310'),
     ('hu-HU', 'Magyar', 'Magyarország', 'Hungarian', '\U0001f1ed\U0001f1fa'),
+    ('id', 'Indonesia', '', 'Indonesian', '\U0001f310'),
     ('id-ID', 'Indonesia', 'Indonesia', 'Indonesian', '\U0001f1ee\U0001f1e9'),
-    ('is-IS', 'Íslenska', 'Ísland', 'Icelandic', '\U0001f1ee\U0001f1f8'),
+    ('it', 'Italiano', '', 'Italian', '\U0001f310'),
+    ('it-CH', 'Italiano', 'Svizzera', 'Italian', '\U0001f1e8\U0001f1ed'),
     ('it-IT', 'Italiano', 'Italia', 'Italian', '\U0001f1ee\U0001f1f9'),
+    ('ja', '日本語', '', 'Japanese', '\U0001f310'),
     ('ja-JP', '日本語', '日本', 'Japanese', '\U0001f1ef\U0001f1f5'),
+    ('ko', '한국어', '', 'Korean', '\U0001f310'),
     ('ko-KR', '한국어', '대한민국', 'Korean', '\U0001f1f0\U0001f1f7'),
+    ('lt', 'Lietuvių', '', 'Lithuanian', '\U0001f310'),
     ('lt-LT', 'Lietuvių', 'Lietuva', 'Lithuanian', '\U0001f1f1\U0001f1f9'),
+    ('lv', 'Latviešu', '', 'Latvian', '\U0001f310'),
     ('lv-LV', 'Latviešu', 'Latvija', 'Latvian', '\U0001f1f1\U0001f1fb'),
+    ('nb', 'Norsk Bokmål', '', 'Norwegian Bokmål', '\U0001f310'),
+    ('nb-NO', 'Norsk Bokmål', 'Norge', 'Norwegian Bokmål', '\U0001f1f3\U0001f1f4'),
     ('nl', 'Nederlands', '', 'Dutch', '\U0001f310'),
     ('nl-BE', 'Nederlands', 'België', 'Dutch', '\U0001f1e7\U0001f1ea'),
     ('nl-NL', 'Nederlands', 'Nederland', 'Dutch', '\U0001f1f3\U0001f1f1'),
-    ('no-NO', 'Norsk', '', 'Norwegian (Bokmål)', '\U0001f1f3\U0001f1f4'),
+    ('pl', 'Polski', '', 'Polish', '\U0001f310'),
     ('pl-PL', 'Polski', 'Polska', 'Polish', '\U0001f1f5\U0001f1f1'),
     ('pt', 'Português', '', 'Portuguese', '\U0001f310'),
     ('pt-BR', 'Português', 'Brasil', 'Portuguese', '\U0001f1e7\U0001f1f7'),
     ('pt-PT', 'Português', 'Portugal', 'Portuguese', '\U0001f1f5\U0001f1f9'),
+    ('ro', 'Română', '', 'Romanian', '\U0001f310'),
     ('ro-RO', 'Română', 'România', 'Romanian', '\U0001f1f7\U0001f1f4'),
+    ('ru', 'Русский', '', 'Russian', '\U0001f310'),
     ('ru-RU', 'Русский', 'Россия', 'Russian', '\U0001f1f7\U0001f1fa'),
+    ('sk', 'Slovenčina', '', 'Slovak', '\U0001f310'),
     ('sk-SK', 'Slovenčina', 'Slovensko', 'Slovak', '\U0001f1f8\U0001f1f0'),
+    ('sl', 'Slovenščina', '', 'Slovenian', '\U0001f310'),
     ('sl-SI', 'Slovenščina', 'Slovenija', 'Slovenian', '\U0001f1f8\U0001f1ee'),
-    ('sr-RS', 'Српски', 'Србија', 'Serbian', '\U0001f1f7\U0001f1f8'),
+    ('sv', 'Svenska', '', 'Swedish', '\U0001f310'),
     ('sv-SE', 'Svenska', 'Sverige', 'Swedish', '\U0001f1f8\U0001f1ea'),
-    ('sw-TZ', 'Kiswahili', 'Tanzania', 'Swahili', '\U0001f1f9\U0001f1ff'),
+    ('th', 'ไทย', '', 'Thai', '\U0001f310'),
     ('th-TH', 'ไทย', 'ไทย', 'Thai', '\U0001f1f9\U0001f1ed'),
+    ('tr', 'Türkçe', '', 'Turkish', '\U0001f310'),
     ('tr-TR', 'Türkçe', 'Türkiye', 'Turkish', '\U0001f1f9\U0001f1f7'),
+    ('uk', 'Українська', '', 'Ukrainian', '\U0001f310'),
     ('uk-UA', 'Українська', 'Україна', 'Ukrainian', '\U0001f1fa\U0001f1e6'),
+    ('vi', 'Tiếng Việt', '', 'Vietnamese', '\U0001f310'),
     ('vi-VN', 'Tiếng Việt', 'Việt Nam', 'Vietnamese', '\U0001f1fb\U0001f1f3'),
     ('zh', '中文', '', 'Chinese', '\U0001f310'),
     ('zh-CN', '中文', '中国', 'Chinese', '\U0001f1e8\U0001f1f3'),
     ('zh-HK', '中文', '中國香港', 'Chinese', '\U0001f1ed\U0001f1f0'),
     ('zh-TW', '中文', '台灣', 'Chinese', '\U0001f1f9\U0001f1fc'),
 )
+'''
+A list of five-digit tuples:
+
+0. SearXNG's internal locale tag (a language or region tag)
+1. Name of the language (:py:obj:`babel.core.Locale.get_language_name`)
+2. For region tags the name of the region (:py:obj:`babel.core.Locale.get_territory_name`).
+   Empty string for language tags.
+3. English language name (from :py:obj:`babel.core.Locale.english_name`)
+4. Unicode flag (emoji) that fits to SearXNG's internal region tag. Languages
+   are represented by a globe (🌐)
+
+.. code:: python
+
+   ('en',    'English', '',              'English', '🌐'),
+   ('en-CA', 'English', 'Canada',        'English', '🇨🇦'),
+   ('en-US', 'English', 'United States', 'English', '🇺🇸'),
+   ..
+   ('fr',    'Français', '',             'French',  '🌐'),
+   ('fr-BE', 'Français', 'Belgique',     'French',  '🇧🇪'),
+   ('fr-CA', 'Français', 'Canada',       'French',  '🇨🇦'),
+
+:meta hide-value:
+'''
diff --git a/searx/templates/simple/filters/languages.html b/searx/templates/simple/filters/languages.html
index 54e07e209..a42a304a5 100644
--- a/searx/templates/simple/filters/languages.html
+++ b/searx/templates/simple/filters/languages.html
@@ -1,12 +1,12 @@
 <select class="language" id="language" name="language" aria-label="{{ _('Search language') }}">{{- '' -}}
-	<option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option>
+	<option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }} [all]</option>
 	<option value="auto" {% if current_language == 'auto' %}selected="selected"{% endif %}>
 		{{- _('Auto-detect') -}}
 		{%- if current_language == 'auto' %} ({{ search_language }}){%- endif -%}
 	</option>
-	{%- for lang_id,lang_name,country_name,english_name,flag in language_codes | sort(attribute=1) -%}
-	<option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>
-		{% if flag %}{{ flag }} {% endif%} {{- lang_name }} {% if country_name %}({{ country_name }}) {% endif %}
+	{%- for sxng_tag,lang_name,country_name,english_name,flag in sxng_locales | sort(attribute=1) -%}
+	<option value="{{ sxng_tag }}" {% if sxng_tag == current_language %}selected="selected"{% endif %}>
+		{% if flag %}{{ flag }} {% endif%} {{- lang_name }} {% if country_name %} - {{ country_name }} {% endif %} [{{sxng_tag}}]
 	</option>
 	{%- endfor -%}
 </select>
diff --git a/searx/templates/simple/preferences.html b/searx/templates/simple/preferences.html
index 9626b04d4..a0cc8efc2 100644
--- a/searx/templates/simple/preferences.html
+++ b/searx/templates/simple/preferences.html
@@ -115,10 +115,10 @@
       <legend id="pref_language">{{ _('Search language') }}</legend>
       <p class="value">{{- '' -}}
         <select name='language' aria-labelledby="pref_language" aria-describedby="desc_language">{{- '' -}}
-          <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option>
-          <option value="auto" {% if current_language == 'auto' %}selected="selected"{% endif %}>{{ _('Auto-detect') }}</option>
-          {%- for lang_id,lang_name,country_name,english_name,flag in language_codes | sort(attribute=1) -%}
-          <option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{% if flag %}{{ flag }} {% endif%} {{- lang_name }} {% if country_name %}({{ country_name }}) {% endif %}</option>
+          <option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }} [all]</option>
+          <option value="auto" {% if current_language == 'auto' %}selected="selected"{% endif %}>{{ _('Auto-detect') }} [auto]</option>
+          {%- for sxng_tag,lang_name,country_name,english_name,flag in sxng_locales | sort(attribute=1) -%}
+          <option value="{{ sxng_tag }}" {% if sxng_tag == current_language %}selected="selected"{% endif %}>{% if flag %}{{ flag }} {% endif%} {{- lang_name }} {% if country_name %} - {{ country_name }} {% endif %} [{{sxng_tag}}]</option>
           {%- endfor -%}
         </select>{{- '' -}}
       </p>
diff --git a/searx/utils.py b/searx/utils.py
index e6180906b..f7a71b649 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -24,7 +24,7 @@ from babel.core import get_global
 from searx import settings
 from searx.data import USER_AGENTS, data_dir
 from searx.version import VERSION_TAG
-from searx.languages import language_codes
+from searx.sxng_locales import sxng_locales
 from searx.exceptions import SearxXPathSyntaxException, SearxEngineXPathException
 from searx import logger
 
@@ -53,8 +53,8 @@ _LANG_TO_LC_CACHE: Dict[str, Dict[str, str]] = {}
 _FASTTEXT_MODEL: Optional["fasttext.FastText._FastText"] = None
 """fasttext model to predict laguage of a search term"""
 
-SEARCH_LANGUAGE_CODES = frozenset([searxng_locale[0].split('-')[0] for searxng_locale in language_codes])
-"""Languages supported by most searxng engines (:py:obj:`searx.languages.language_codes`)."""
+SEARCH_LANGUAGE_CODES = frozenset([searxng_locale[0].split('-')[0] for searxng_locale in sxng_locales])
+"""Languages supported by most searxng engines (:py:obj:`searx.sxng_locales.sxng_locales`)."""
 
 
 class _NotSetClass:  # pylint: disable=too-few-public-methods
@@ -355,11 +355,11 @@ def is_valid_lang(lang) -> Optional[Tuple[bool, str, str]]:
     is_abbr = len(lang) == 2
     lang = lang.lower()
     if is_abbr:
-        for l in language_codes:
+        for l in sxng_locales:
             if l[0][:2] == lang:
                 return (True, l[0][:2], l[3].lower())
         return None
-    for l in language_codes:
+    for l in sxng_locales:
         if l[1].lower() == lang or l[3].lower() == lang:
             return (True, l[0][:2], l[3].lower())
     return None
diff --git a/searx/webapp.py b/searx/webapp.py
index e62badaf7..fdd119128 100755
--- a/searx/webapp.py
+++ b/searx/webapp.py
@@ -121,8 +121,8 @@ from searx.locales import (
 
 # renaming names from searx imports ...
 from searx.autocomplete import search_autocomplete, backends as autocomplete_backends
-from searx.languages import language_codes as languages
 from searx.redisdb import initialize as redis_initialize
+from searx.sxng_locales import sxng_locales
 from searx.search import SearchWithPlugins, initialize as search_initialize
 from searx.network import stream as http_stream, set_context_network_name
 from searx.search.checker import get_result as checker_get_result
@@ -438,7 +438,7 @@ def render(template_name: str, **kwargs):
     kwargs['OTHER_CATEGORY'] = OTHER_CATEGORY
 
     # i18n
-    kwargs['language_codes'] = [l for l in languages if l[0] in settings['search']['languages']]
+    kwargs['sxng_locales'] = [l for l in sxng_locales if l[0] in settings['search']['languages']]
 
     locale = request.preferences.get_value('locale')
     kwargs['locale_rfc5646'] = _get_locale_rfc5646(locale)