[refactor] introduce searx.utils.find_language_aliases

searx/engines/__init__.py

@@ -16,19 +16,14 @@ import copy
 from typing import Dict, List, Optional
 
 from os.path import realpath, dirname
-from babel.localedata import locale_identifiers
 from searx import logger, settings
 from searx.data import ENGINES_LANGUAGES
 from searx.network import get
-from searx.utils import load_module, match_language, gen_useragent
+from searx.utils import load_module, gen_useragent, find_language_aliases
 
 
 logger = logger.getChild('engines')
 ENGINE_DIR = dirname(realpath(__file__))
-BABEL_LANGS = [
-    lang_parts[0] + '-' + lang_parts[-1] if len(lang_parts) > 1 else lang_parts[0]
-    for lang_parts in (lang_code.split('_') for lang_code in locale_identifiers())
-]
 ENGINE_DEFAULT_ARGS = {
     "engine_type": "online",
     "inactive": False,
@@ -206,15 +201,7 @@ def set_language_attributes(engine: ConfiguredEngine):
             engine.supported_languages = [engine.language]
 
     # find custom aliases for non standard language codes
-    for engine_lang in engine.supported_languages:
+    engine.language_aliases.update(find_language_aliases(engine.supported_languages))
-        iso_lang = match_language(engine_lang, BABEL_LANGS, fallback=None)
-        if (
-            iso_lang
-            and iso_lang != engine_lang
-            and not engine_lang.startswith(iso_lang)
-            and iso_lang not in engine.supported_languages
-        ):
-            engine.language_aliases[iso_lang] = engine_lang
 
     # language_support
     engine.language_support = len(engine.supported_languages) > 0

searx/utils.py

@@ -6,11 +6,13 @@ from numbers import Number
 from os.path import splitext, join
 from random import choice
 from html.parser import HTMLParser
+from typing import Collection, Dict
 from urllib.parse import urljoin, urlparse
 
 from lxml import html
 from lxml.etree import ElementBase, XPath, XPathError, XPathSyntaxError, _ElementStringResult, _ElementUnicodeResult
 from babel.core import get_global
+from babel.localedata import locale_identifiers
 
 
 from searx import settings
@@ -438,6 +440,26 @@ def match_language(locale_code, lang_list=[], custom_aliases={}, fallback='en-US
     return language or fallback
 
 
+_BABEL_LANGS = [
+    lang_parts[0] + '-' + lang_parts[-1] if len(lang_parts) > 1 else lang_parts[0]
+    for lang_parts in (lang_code.split('_') for lang_code in locale_identifiers())
+]
+
+
+def find_language_aliases(supported_languages: Collection[str]) -> Dict[str, str]:
+    aliases = {}
+    for engine_lang in supported_languages:
+        iso_lang = match_language(engine_lang, _BABEL_LANGS, fallback=None)
+        if (
+            iso_lang
+            and iso_lang != engine_lang
+            and not engine_lang.startswith(iso_lang)
+            and iso_lang not in supported_languages
+        ):
+            aliases[iso_lang] = engine_lang
+    return aliases
+
+
 def load_module(filename, module_dir):
     modname = splitext(filename)[0]
     filepath = join(module_dir, filename)