[mod] reduce memory footprint by not calling babel.Locale.parse at runtime

babel.Locale.parse loads more than 60MB in RAM.  The only purpose is to get:

    LOCALE_NAMES   - searx.data.LOCALES["LOCALE_NAMES"]
    RTL_LOCALES    - searx.data.LOCALES["RTL_LOCALES"]

This commit calls babel.Locale.parse when the translations are update from
weblate and stored in::

    searx/data/locales.json

This file can be build by::

    ./manage data.locales

By store these variables in searx.data when the translations are updated we save
round about 65MB (usually 4 worker = 260MB of RAM saved.

Suggested-by: https://github.com/searxng/searxng/discussions/2633#discussioncomment-8490494
Co-authored-by: Markus Heiser <markus.heiser@darmarit.de>

2 files changed, 107 insertions, 2 deletions

diff --git a/searxng_extra/update/update_engine_traits.py b/searxng_extra/update/update_engine_traits.py
index 46892cc2b..faab198d2 100755
--- a/searxng_extra/update/update_engine_traits.py
+++ b/searxng_extra/update/update_engine_traits.py
@@ -31,9 +31,11 @@ languages_file_header = """\
 # -*- coding: utf-8 -*-
 '''List of SearXNG's locale codes.
 
-This file is generated automatically by::
+.. hint::
 
-   ./manage pyenv.cmd searxng_extra/update/update_engine_traits.py
+   Don't modify this file, this file is generated by::
+
+     ./manage data.traits
 '''
 
 sxng_locales = (
diff --git a/searxng_extra/update/update_locales.py b/searxng_extra/update/update_locales.py
new file mode 100644
index 000000000..e823ebaf1
--- /dev/null
+++ b/searxng_extra/update/update_locales.py
@@ -0,0 +1,103 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Update locale names in :origin:`searx/data/locales.json` used by
+:ref:`searx.locales`
+
+- :py:obj:`searx.locales.RTL_LOCALES`
+- :py:obj:`searx.locales.LOCALE_NAMES`
+"""
+from __future__ import annotations
+
+from typing import Set
+import json
+from pathlib import Path
+import os
+
+import babel
+import babel.languages
+import babel.core
+
+from searx import searx_dir
+from searx.locales import (
+    ADDITIONAL_TRANSLATIONS,
+    LOCALE_BEST_MATCH,
+    get_translation_locales,
+)
+
+LOCALE_DATA_FILE = Path(searx_dir) / 'data' / 'locales.json'
+TRANSLATOINS_FOLDER = Path(searx_dir) / 'translations'
+
+
+def main():
+
+    LOCALE_NAMES = {}
+    RTL_LOCALES: Set[str] = set()
+
+    for tag, descr in ADDITIONAL_TRANSLATIONS.items():
+        locale = babel.Locale.parse(LOCALE_BEST_MATCH[tag], sep='-')
+        LOCALE_NAMES[tag] = descr
+        if locale.text_direction == 'rtl':
+            RTL_LOCALES.add(tag)
+
+    for tag in LOCALE_BEST_MATCH:
+        descr = LOCALE_NAMES.get(tag)
+        if not descr:
+            locale = babel.Locale.parse(tag, sep='-')
+            LOCALE_NAMES[tag] = get_locale_descr(locale, tag.replace('-', '_'))
+            if locale.text_direction == 'rtl':
+                RTL_LOCALES.add(tag)
+
+    for tr_locale in get_translation_locales():
+        sxng_tag = tr_locale.replace('_', '-')
+        descr = LOCALE_NAMES.get(sxng_tag)
+        if not descr:
+            locale = babel.Locale.parse(tr_locale)
+            LOCALE_NAMES[sxng_tag] = get_locale_descr(locale, tr_locale)
+            if locale.text_direction == 'rtl':
+                RTL_LOCALES.add(sxng_tag)
+
+    content = {
+        "LOCALE_NAMES": LOCALE_NAMES,
+        "RTL_LOCALES": list(RTL_LOCALES),
+    }
+
+    with open(LOCALE_DATA_FILE, 'w', encoding='utf-8') as f:
+        json.dump(content, f, indent=2, sort_keys=True, ensure_ascii=False)
+
+
+def get_locale_descr(locale: babel.Locale, tr_locale):
+    """Get locale name e.g. 'Français - fr' or 'Português (Brasil) - pt-BR'
+
+    :param locale: instance of :py:class:`Locale`
+    :param tr_locale: name e.g. 'fr'  or 'pt_BR' (delimiter is *underscore*)
+    """
+
+    native_language, native_territory = _get_locale_descr(locale, tr_locale)
+    english_language, english_territory = _get_locale_descr(locale, 'en')
+
+    if native_territory == english_territory:
+        english_territory = None
+
+    if not native_territory and not english_territory:
+        # none territory name
+        if native_language == english_language:
+            return native_language
+        return native_language + ' (' + english_language + ')'
+
+    else:
+        result = native_language + ', ' + native_territory + ' (' + english_language
+        if english_territory:
+            return result + ', ' + english_territory + ')'
+        return result + ')'
+
+
+def _get_locale_descr(locale: babel.Locale, tr_locale: str) -> tuple[str, str]:
+    language_name = locale.get_language_name(tr_locale).capitalize()  # type: ignore
+    if language_name and ('a' <= language_name[0] <= 'z'):
+        language_name = language_name.capitalize()
+    territory_name: str = locale.get_territory_name(tr_locale)  # type: ignore
+    return language_name, territory_name
+
+
+if __name__ == "__main__":
+    main()