2021-08-03 18:17:23 +02:00
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
|
|
# lint: pylint
|
2021-10-06 10:26:40 +02:00
|
|
|
"""Initialize :py:obj:`LOCALE_NAMES`, :py:obj:`RTL_LOCALES`.
|
|
|
|
"""
|
2021-08-03 18:17:23 +02:00
|
|
|
|
2023-02-07 14:11:58 +01:00
|
|
|
from typing import Set, Optional, List
|
2021-08-03 15:13:00 +02:00
|
|
|
import os
|
|
|
|
import pathlib
|
|
|
|
|
2022-09-29 20:54:46 +02:00
|
|
|
import babel
|
2022-06-10 17:01:12 +02:00
|
|
|
from babel.support import Translations
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
import babel.languages
|
|
|
|
import babel.core
|
2022-06-10 17:01:12 +02:00
|
|
|
import flask_babel
|
|
|
|
import flask
|
|
|
|
from flask.ctx import has_request_context
|
|
|
|
from searx import logger
|
2021-08-03 15:13:00 +02:00
|
|
|
|
2022-06-10 17:01:12 +02:00
|
|
|
logger = logger.getChild('locales')
|
|
|
|
|
|
|
|
|
|
|
|
# safe before monkey patching flask_babel.get_translations
|
|
|
|
_flask_babel_get_translations = flask_babel.get_translations
|
|
|
|
|
|
|
|
LOCALE_NAMES = {}
|
|
|
|
"""Mapping of locales and their description. Locales e.g. 'fr' or 'pt-BR' (see
|
2022-09-18 12:44:12 +02:00
|
|
|
:py:obj:`locales_initialize`).
|
|
|
|
|
|
|
|
:meta hide-value:
|
|
|
|
"""
|
2022-06-10 17:01:12 +02:00
|
|
|
|
|
|
|
RTL_LOCALES: Set[str] = set()
|
|
|
|
"""List of *Right-To-Left* locales e.g. 'he' or 'fa-IR' (see
|
|
|
|
:py:obj:`locales_initialize`)."""
|
|
|
|
|
|
|
|
ADDITIONAL_TRANSLATIONS = {
|
2022-11-04 17:49:43 +01:00
|
|
|
"dv": "ދިވެހި (Dhivehi)",
|
2021-08-04 09:50:34 +02:00
|
|
|
"oc": "Occitan",
|
2022-05-06 11:40:45 +02:00
|
|
|
"szl": "Ślōnski (Silesian)",
|
2022-07-08 10:00:20 +02:00
|
|
|
"pap": "Papiamento",
|
2021-08-03 15:13:00 +02:00
|
|
|
}
|
2022-06-10 17:01:12 +02:00
|
|
|
"""Additional languages SearXNG has translations for but not supported by
|
|
|
|
python-babel (see :py:obj:`locales_initialize`)."""
|
2021-08-03 18:17:23 +02:00
|
|
|
|
2022-06-10 17:01:12 +02:00
|
|
|
LOCALE_BEST_MATCH = {
|
2022-11-04 17:49:43 +01:00
|
|
|
"dv": "si",
|
2022-06-10 17:01:12 +02:00
|
|
|
"oc": 'fr-FR',
|
|
|
|
"szl": "pl",
|
|
|
|
"nl-BE": "nl",
|
|
|
|
"zh-HK": "zh-Hant-TW",
|
2022-07-08 10:00:20 +02:00
|
|
|
"pap": "pt-BR",
|
2022-06-10 17:01:12 +02:00
|
|
|
}
|
|
|
|
"""Map a locale we do not have a translations for to a locale we have a
|
|
|
|
translation for. By example: use Taiwan version of the translation for Hong
|
|
|
|
Kong."""
|
2021-08-03 15:13:00 +02:00
|
|
|
|
|
|
|
|
2022-06-10 17:01:12 +02:00
|
|
|
def localeselector():
|
|
|
|
locale = 'en'
|
|
|
|
if has_request_context():
|
|
|
|
value = flask.request.preferences.get_value('locale')
|
|
|
|
if value:
|
|
|
|
locale = value
|
|
|
|
|
|
|
|
# first, set the language that is not supported by babel
|
|
|
|
if locale in ADDITIONAL_TRANSLATIONS:
|
|
|
|
flask.request.form['use-translation'] = locale
|
|
|
|
|
|
|
|
# second, map locale to a value python-babel supports
|
|
|
|
locale = LOCALE_BEST_MATCH.get(locale, locale)
|
|
|
|
|
|
|
|
if locale == '':
|
|
|
|
# if there is an error loading the preferences
|
|
|
|
# the locale is going to be ''
|
|
|
|
locale = 'en'
|
|
|
|
|
|
|
|
# babel uses underscore instead of hyphen.
|
|
|
|
locale = locale.replace('-', '_')
|
|
|
|
return locale
|
|
|
|
|
|
|
|
|
|
|
|
def get_translations():
|
2022-06-14 16:31:41 +02:00
|
|
|
"""Monkey patch of :py:obj:`flask_babel.get_translations`"""
|
2022-11-04 17:47:02 +01:00
|
|
|
if has_request_context():
|
|
|
|
use_translation = flask.request.form.get('use-translation')
|
|
|
|
if use_translation in ADDITIONAL_TRANSLATIONS:
|
|
|
|
babel_ext = flask_babel.current_app.extensions['babel']
|
2023-01-20 10:19:18 +01:00
|
|
|
return Translations.load(babel_ext.translation_directories[0], use_translation)
|
2022-06-10 17:01:12 +02:00
|
|
|
return _flask_babel_get_translations()
|
2021-08-03 15:13:00 +02:00
|
|
|
|
|
|
|
|
2022-06-10 17:01:12 +02:00
|
|
|
def get_locale_descr(locale, locale_name):
|
2021-08-03 18:17:23 +02:00
|
|
|
"""Get locale name e.g. 'Français - fr' or 'Português (Brasil) - pt-BR'
|
|
|
|
|
|
|
|
:param locale: instance of :py:class:`Locale`
|
2021-10-06 10:26:40 +02:00
|
|
|
:param locale_name: name e.g. 'fr' or 'pt_BR' (delimiter is *underscore*)
|
2021-08-03 18:17:23 +02:00
|
|
|
"""
|
2022-06-10 17:01:12 +02:00
|
|
|
|
|
|
|
native_language, native_territory = _get_locale_descr(locale, locale_name)
|
|
|
|
english_language, english_territory = _get_locale_descr(locale, 'en')
|
|
|
|
|
2021-08-03 15:13:00 +02:00
|
|
|
if native_territory == english_territory:
|
|
|
|
english_territory = None
|
2022-06-10 17:01:12 +02:00
|
|
|
|
2021-08-03 15:13:00 +02:00
|
|
|
if not native_territory and not english_territory:
|
|
|
|
if native_language == english_language:
|
|
|
|
return native_language
|
|
|
|
return native_language + ' (' + english_language + ')'
|
2022-06-10 17:01:12 +02:00
|
|
|
|
2021-08-03 15:13:00 +02:00
|
|
|
result = native_language + ', ' + native_territory + ' (' + english_language
|
|
|
|
if english_territory:
|
|
|
|
return result + ', ' + english_territory + ')'
|
|
|
|
return result + ')'
|
|
|
|
|
|
|
|
|
2022-06-10 17:01:12 +02:00
|
|
|
def _get_locale_descr(locale, language_code):
|
|
|
|
language_name = locale.get_language_name(language_code).capitalize()
|
|
|
|
if language_name and ('a' <= language_name[0] <= 'z'):
|
|
|
|
language_name = language_name.capitalize()
|
|
|
|
terrirtory_name = locale.get_territory_name(language_code)
|
|
|
|
return language_name, terrirtory_name
|
|
|
|
|
|
|
|
|
|
|
|
def locales_initialize(directory=None):
|
|
|
|
"""Initialize locales environment of the SearXNG session.
|
|
|
|
|
2022-06-14 16:31:41 +02:00
|
|
|
- monkey patch :py:obj:`flask_babel.get_translations` by :py:obj:`get_translations`
|
2022-06-10 17:01:12 +02:00
|
|
|
- init global names :py:obj:`LOCALE_NAMES`, :py:obj:`RTL_LOCALES`
|
|
|
|
"""
|
|
|
|
|
|
|
|
directory = directory or pathlib.Path(__file__).parent / 'translations'
|
|
|
|
logger.debug("locales_initialize: %s", directory)
|
|
|
|
flask_babel.get_translations = get_translations
|
|
|
|
|
|
|
|
for tag, descr in ADDITIONAL_TRANSLATIONS.items():
|
2022-09-29 20:54:46 +02:00
|
|
|
locale = babel.Locale.parse(LOCALE_BEST_MATCH[tag], sep='-')
|
2022-06-10 17:01:12 +02:00
|
|
|
LOCALE_NAMES[tag] = descr
|
2022-11-04 17:47:02 +01:00
|
|
|
if locale.text_direction == 'rtl':
|
|
|
|
RTL_LOCALES.add(tag)
|
2022-06-10 17:01:12 +02:00
|
|
|
|
|
|
|
for tag in LOCALE_BEST_MATCH:
|
|
|
|
descr = LOCALE_NAMES.get(tag)
|
|
|
|
if not descr:
|
2022-09-29 20:54:46 +02:00
|
|
|
locale = babel.Locale.parse(tag, sep='-')
|
2022-06-10 17:01:12 +02:00
|
|
|
LOCALE_NAMES[tag] = get_locale_descr(locale, tag.replace('-', '_'))
|
2022-11-04 17:47:02 +01:00
|
|
|
if locale.text_direction == 'rtl':
|
|
|
|
RTL_LOCALES.add(tag)
|
2022-06-10 17:01:12 +02:00
|
|
|
|
2021-08-03 15:13:00 +02:00
|
|
|
for dirname in sorted(os.listdir(directory)):
|
|
|
|
# Based on https://flask-babel.tkte.ch/_modules/flask_babel.html#Babel.list_translations
|
2021-12-27 09:26:22 +01:00
|
|
|
if not os.path.isdir(os.path.join(directory, dirname, 'LC_MESSAGES')):
|
2021-08-03 15:13:00 +02:00
|
|
|
continue
|
2022-06-10 17:01:12 +02:00
|
|
|
tag = dirname.replace('_', '-')
|
|
|
|
descr = LOCALE_NAMES.get(tag)
|
|
|
|
if not descr:
|
2022-09-29 20:54:46 +02:00
|
|
|
locale = babel.Locale.parse(dirname)
|
2022-06-10 17:01:12 +02:00
|
|
|
LOCALE_NAMES[tag] = get_locale_descr(locale, dirname)
|
2021-08-03 15:13:00 +02:00
|
|
|
if locale.text_direction == 'rtl':
|
2022-06-10 17:01:12 +02:00
|
|
|
RTL_LOCALES.add(tag)
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
|
|
|
|
|
2022-09-29 20:54:46 +02:00
|
|
|
def region_tag(locale: babel.Locale) -> str:
|
|
|
|
"""Returns SearXNG's region tag from the locale (e.g. zh-TW , en-US)."""
|
|
|
|
if not locale.territory:
|
|
|
|
raise ValueError('%s missed a territory')
|
|
|
|
return locale.language + '-' + locale.territory
|
|
|
|
|
|
|
|
|
|
|
|
def language_tag(locale: babel.Locale) -> str:
|
|
|
|
"""Returns SearXNG's language tag from the locale and if exits, the tag
|
|
|
|
includes the script name (e.g. en, zh_Hant).
|
|
|
|
"""
|
|
|
|
sxng_lang = locale.language
|
|
|
|
if locale.script:
|
|
|
|
sxng_lang += '_' + locale.script
|
|
|
|
return sxng_lang
|
|
|
|
|
|
|
|
|
2023-02-07 14:11:58 +01:00
|
|
|
def get_locale(locale_tag: str) -> Optional[babel.Locale]:
|
|
|
|
"""Returns a :py:obj:`babel.Locale` object parsed from argument
|
|
|
|
``locale_tag``"""
|
|
|
|
try:
|
|
|
|
locale = babel.Locale.parse(locale_tag, sep='-')
|
|
|
|
return locale
|
|
|
|
|
|
|
|
except babel.core.UnknownLocaleError:
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
2022-09-29 20:54:46 +02:00
|
|
|
def get_offical_locales(
|
|
|
|
territory: str, languages=None, regional: bool = False, de_facto: bool = True
|
|
|
|
) -> Set[babel.Locale]:
|
|
|
|
"""Returns a list of :py:obj:`babel.Locale` with languages from
|
|
|
|
:py:obj:`babel.languages.get_official_languages`.
|
|
|
|
|
|
|
|
:param territory: The territory (country or region) code.
|
|
|
|
|
|
|
|
:param languages: A list of language codes the languages from
|
|
|
|
:py:obj:`babel.languages.get_official_languages` should be in
|
|
|
|
(intersection). If this argument is ``None``, all official languages in
|
|
|
|
this territory are used.
|
|
|
|
|
|
|
|
:param regional: If the regional flag is set, then languages which are
|
|
|
|
regionally official are also returned.
|
|
|
|
|
|
|
|
:param de_facto: If the de_facto flag is set to `False`, then languages
|
|
|
|
which are “de facto” official are not returned.
|
|
|
|
|
|
|
|
"""
|
|
|
|
ret_val = set()
|
|
|
|
o_languages = babel.languages.get_official_languages(territory, regional=regional, de_facto=de_facto)
|
|
|
|
|
|
|
|
if languages:
|
|
|
|
languages = [l.lower() for l in languages]
|
|
|
|
o_languages = set(l for l in o_languages if l.lower() in languages)
|
|
|
|
|
|
|
|
for lang in o_languages:
|
|
|
|
try:
|
|
|
|
locale = babel.Locale.parse(lang + '_' + territory)
|
|
|
|
ret_val.add(locale)
|
|
|
|
except babel.UnknownLocaleError:
|
|
|
|
continue
|
|
|
|
|
|
|
|
return ret_val
|
|
|
|
|
|
|
|
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
def get_engine_locale(searxng_locale, engine_locales, default=None):
|
|
|
|
"""Return engine's language (aka locale) string that best fits to argument
|
|
|
|
``searxng_locale``.
|
|
|
|
|
|
|
|
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
|
2022-09-18 12:44:12 +02:00
|
|
|
corresponding *engine locales*::
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
|
|
|
|
<engine>: {
|
|
|
|
# SearXNG string : engine-string
|
|
|
|
'ca-ES' : 'ca_ES',
|
|
|
|
'fr-BE' : 'fr_BE',
|
|
|
|
'fr-CA' : 'fr_CA',
|
|
|
|
'fr-CH' : 'fr_CH',
|
|
|
|
'fr' : 'fr_FR',
|
|
|
|
...
|
|
|
|
'pl-PL' : 'pl_PL',
|
|
|
|
'pt-PT' : 'pt_PT'
|
2022-09-29 20:54:46 +02:00
|
|
|
..
|
|
|
|
'zh' : 'zh'
|
|
|
|
'zh_Hans' : 'zh'
|
2023-04-17 08:40:44 +02:00
|
|
|
'zh_Hant' : 'zh_TW'
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
.. hint::
|
|
|
|
|
|
|
|
The *SearXNG locale* string has to be known by babel!
|
|
|
|
|
|
|
|
If there is no direct 1:1 mapping, this functions tries to narrow down
|
|
|
|
engine's language (locale). If no value can be determined by these
|
|
|
|
approximation attempts the ``default`` value is returned.
|
|
|
|
|
|
|
|
Assumptions:
|
|
|
|
|
|
|
|
A. When user select a language the results should be optimized according to
|
|
|
|
the selected language.
|
|
|
|
|
|
|
|
B. When user select a language and a territory the results should be
|
|
|
|
optimized with first priority on terrirtory and second on language.
|
|
|
|
|
|
|
|
First approximation rule (*by territory*):
|
|
|
|
|
|
|
|
When the user selects a locale with terrirtory (and a language), the
|
|
|
|
territory has priority over the language. If any of the offical languages
|
|
|
|
in the terrirtory is supported by the engine (``engine_locales``) it will
|
|
|
|
be used.
|
|
|
|
|
|
|
|
Second approximation rule (*by language*):
|
|
|
|
|
|
|
|
If "First approximation rule" brings no result or the user selects only a
|
|
|
|
language without a terrirtory. Check in which territories the language
|
|
|
|
has an offical status and if one of these territories is supported by the
|
|
|
|
engine.
|
|
|
|
|
|
|
|
"""
|
2022-09-29 20:54:46 +02:00
|
|
|
# pylint: disable=too-many-branches, too-many-return-statements
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
|
|
|
|
engine_locale = engine_locales.get(searxng_locale)
|
|
|
|
|
|
|
|
if engine_locale is not None:
|
2022-09-29 20:54:46 +02:00
|
|
|
# There was a 1:1 mapping (e.g. a region "fr-BE --> fr_BE" or a language
|
|
|
|
# "zh --> zh"), no need to narrow language-script nor territory.
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
return engine_locale
|
|
|
|
|
[fix] harden get_engine_locale: handle UnknownLocaleError exceptions
When a user selects an unknown or invalid locale by using the search syntax:
!qw siemens :de-TW
Before this patch a UnknownLocaleError exception will be rasied:
```
Traceback (most recent call last):
File "SearXNG/searx/search/processors/online.py", line 154, in search
search_results = self._search_basic(query, params)
File "SearXNG/searx/search/processors/online.py", line 128, in _search_basic
self.engine.request(query, params)
File "SearXNG/searx/engines/qwant.py", line 98, in request
q_locale = get_engine_locale(params['language'], supported_languages, default='en_US')
File "SearXNG/searx/locales.py", line 216, in get_engine_locale
locale = babel.Locale.parse(searxng_locale, sep='-')
File "SearXNG/local/py3/lib/python3.8/site-packages/babel/core.py", line 330, in parse
raise UnknownLocaleError(input_id)
```
This patch implements a simple exception handling, since e.g. `de-TW` does not
exists `de` will be used to get engines locale. On invalid terms like `xy-XY`
the default will be returned.
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-14 13:38:50 +02:00
|
|
|
try:
|
|
|
|
locale = babel.Locale.parse(searxng_locale, sep='-')
|
|
|
|
except babel.core.UnknownLocaleError:
|
|
|
|
try:
|
2022-08-14 14:35:09 +02:00
|
|
|
locale = babel.Locale.parse(searxng_locale.split('-')[0])
|
[fix] harden get_engine_locale: handle UnknownLocaleError exceptions
When a user selects an unknown or invalid locale by using the search syntax:
!qw siemens :de-TW
Before this patch a UnknownLocaleError exception will be rasied:
```
Traceback (most recent call last):
File "SearXNG/searx/search/processors/online.py", line 154, in search
search_results = self._search_basic(query, params)
File "SearXNG/searx/search/processors/online.py", line 128, in _search_basic
self.engine.request(query, params)
File "SearXNG/searx/engines/qwant.py", line 98, in request
q_locale = get_engine_locale(params['language'], supported_languages, default='en_US')
File "SearXNG/searx/locales.py", line 216, in get_engine_locale
locale = babel.Locale.parse(searxng_locale, sep='-')
File "SearXNG/local/py3/lib/python3.8/site-packages/babel/core.py", line 330, in parse
raise UnknownLocaleError(input_id)
```
This patch implements a simple exception handling, since e.g. `de-TW` does not
exists `de` will be used to get engines locale. On invalid terms like `xy-XY`
the default will be returned.
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-14 13:38:50 +02:00
|
|
|
except babel.core.UnknownLocaleError:
|
|
|
|
return default
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
|
2022-09-29 20:54:46 +02:00
|
|
|
searxng_lang = language_tag(locale)
|
|
|
|
engine_locale = engine_locales.get(searxng_lang)
|
|
|
|
if engine_locale is not None:
|
|
|
|
# There was a 1:1 mapping (e.g. "zh-HK --> zh_Hant" or "zh-CN --> zh_Hans")
|
|
|
|
return engine_locale
|
|
|
|
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
# SearXNG's selected locale is not supported by the engine ..
|
|
|
|
|
|
|
|
if locale.territory:
|
|
|
|
# Try to narrow by *offical* languages in the territory (??-XX).
|
|
|
|
|
|
|
|
for official_language in babel.languages.get_official_languages(locale.territory, de_facto=True):
|
|
|
|
searxng_locale = official_language + '-' + locale.territory
|
|
|
|
engine_locale = engine_locales.get(searxng_locale)
|
|
|
|
if engine_locale is not None:
|
|
|
|
return engine_locale
|
|
|
|
|
|
|
|
# Engine does not support one of the offical languages in the territory or
|
|
|
|
# there is only a language selected without a territory.
|
|
|
|
|
|
|
|
# Now lets have a look if the searxng_lang (the language selected by the
|
|
|
|
# user) is a offical language in other territories. If so, check if
|
|
|
|
# engine does support the searxng_lang in this other territory.
|
|
|
|
|
|
|
|
if locale.language:
|
|
|
|
|
|
|
|
terr_lang_dict = {}
|
|
|
|
for territory, langs in babel.core.get_global("territory_languages").items():
|
|
|
|
if not langs.get(searxng_lang, {}).get('official_status'):
|
|
|
|
continue
|
|
|
|
terr_lang_dict[territory] = langs.get(searxng_lang)
|
|
|
|
|
|
|
|
# first: check fr-FR, de-DE .. is supported by the engine
|
2022-08-14 15:45:07 +02:00
|
|
|
# exception: 'en' --> 'en-US'
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
|
|
|
|
territory = locale.language.upper()
|
2022-08-14 15:45:07 +02:00
|
|
|
if territory == 'EN':
|
|
|
|
territory = 'US'
|
|
|
|
|
[mod] add locale.get_engine_locale to get predictable results
The match_language function sometimes returns incorrect results which is why a
new function get_engine_locale is required.
A bugfix of the match_language is not easily possible, because there is almost
no documentation for it and already the call parameters are undefined. E.g. the
function processes values like the ones from yahoo::
"yahoo": [
"ar",
...
"zh_chs",
"zh_cht"
]
The get_engine_locale has been documented in detail, there is a clear
description of the assumptions as well as the requirements and approximation
rules (read doc-string for more details)::
Argument ``engine_locales`` is a python dict that maps *SearXNG locales* to
corresponding *engine locales*:
<engine>: {
# SearXNG string : engine-string
'ca-ES' : 'ca_ES',
'fr-BE' : 'fr_BE',
'fr-CA' : 'fr_CA',
'fr-CH' : 'fr_CH',
'fr' : 'fr_FR',
...
'pl-PL' : 'pl_PL',
'pt-PT' : 'pt_PT'
}
.. hint::
The *SearXNG locale* string has to be known by babel!
In the following you will find a comparison:
>>> import babel.languages
>>> from searx.utils import match_language
>>> from searx.locales import get_engine_locale
Assume we have an engine that supports the follwoing locales:
>>> lang_list = {
... "zh-CN": "zh_CN",
... "zh-HK": "zh_HK",
... "nl-BE": "nl_BE",
... "fr-CA": "fr_CA",
... }
Assumption:
A. When a user selects a language the results should be optimized according to
the selected language.
B. When user selects a language and a territory the results should be
optimized with first priority on territory and second on language.
----
Example: (Assumption A.)
A user selects region 'zh-TW' which should end in zh_HK
hint:
CN is 'Hans' and HK ('Hant') fits better to TW ('Hant')
>>> get_engine_locale('zh-TW', lang_list)
'zh_HK'
>>> lang_list[match_language('zh-TW', lang_list)]
'zh_CN'
----
Example: (Assumption A.)
A user selects only the language 'zh' which should end in CN
>>> get_engine_locale('zh', lang_list)
'zh_CN'
>>> lang_list[match_language('zh', lang_list)]
'zh_CN'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
hint:
priority should be on the territory the user selected. If the user
prefers 'fr' he will select 'fr' without a region tag.
>>> get_engine_locale('fr-BE', lang_list, default='unknown')
'nl_BE'
>>> match_language('fr-BE', lang_list, fallback='unknown')
'fr-CA'
----
Example: (Assumption A.)
A user selects only the language 'fr' which should end in fr_CA
>>> get_engine_locale('fr', lang_list)
'fr_CA'
>>> lang_list[match_language('fr', lang_list)]
'fr_CA'
----
The difference in priority on the territory is best shown with a engine that
supports the following locales:
>>> lang_list = {
... "fr-FR": "fr_FR",
... "fr-CA": "fr_CA",
... "en-GB": "en_GB",
... "nl-BE": "nl_BE",
... }
----
Example: (Assumption A.)
A user selects only a language
>>> get_engine_locale('en', lang_list)
'en_GB'
>>> match_language('en', lang_list)
'en-GB'
hint: the engine supports fr_FR and fr_CA since no territory is given, fr_FR
takes priority ..
>>> get_engine_locale('fr', lang_list)
'fr_FR'
>>> lang_list[match_language('fr', lang_list)]
'fr_FR'
----
Example: (Assumption B.)
A user selects region 'fr-BE' which should end in nl-BE
>>> get_engine_locale('fr-BE', lang_list)
'nl_BE'
>>> lang_list[match_language('fr-BE', lang_list)]
'fr_FR'
----
If the user selects a language and there are two locales like the following:
>>> lang_list = {
... "fr-BE": "fr_BE",
... "fr-CH": "fr_CH",
... }
>>>
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_BE'
Looks like both functions return the same value, but match_language depends on the
order of the dictionary (which is not predictable):
>>> lang_list = {
... "fr-CH": "fr_CH",
... "fr-BE": "fr_BE",
... }
>>> get_engine_locale('fr', lang_list)
'fr_BE'
>>> lang_list[match_language('fr', lang_list)]
'fr_CH'
>>>
The get_engine_locale selects the locale by looking at the "population percent"
and this percentage has an higher amount in BE (68.%) compared to CH (21%)
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2022-08-12 17:46:20 +02:00
|
|
|
if terr_lang_dict.get(territory):
|
|
|
|
searxng_locale = locale.language + '-' + territory
|
|
|
|
engine_locale = engine_locales.get(searxng_locale)
|
|
|
|
if engine_locale is not None:
|
|
|
|
return engine_locale
|
|
|
|
|
|
|
|
# second: sort by population_percent and take first match
|
|
|
|
|
|
|
|
# drawback of "population percent": if there is a terrirtory with a
|
|
|
|
# small number of people (e.g 100) but the majority speaks the
|
|
|
|
# language, then the percentage migth be 100% (--> 100 people) but in
|
|
|
|
# a different terrirtory with more people (e.g. 10.000) where only 10%
|
|
|
|
# speak the language the total amount of speaker is higher (--> 200
|
|
|
|
# people).
|
|
|
|
#
|
|
|
|
# By example: The population of Saint-Martin is 33.000, of which 100%
|
|
|
|
# speak French, but this is less than the 30% of the approximately 2.5
|
|
|
|
# million Belgian citizens
|
|
|
|
#
|
|
|
|
# - 'fr-MF', 'population_percent': 100.0, 'official_status': 'official'
|
|
|
|
# - 'fr-BE', 'population_percent': 38.0, 'official_status': 'official'
|
|
|
|
|
|
|
|
terr_lang_list = []
|
|
|
|
for k, v in terr_lang_dict.items():
|
|
|
|
terr_lang_list.append((k, v))
|
|
|
|
|
|
|
|
for territory, _lang in sorted(terr_lang_list, key=lambda item: item[1]['population_percent'], reverse=True):
|
|
|
|
searxng_locale = locale.language + '-' + territory
|
|
|
|
engine_locale = engine_locales.get(searxng_locale)
|
|
|
|
if engine_locale is not None:
|
|
|
|
return engine_locale
|
|
|
|
|
|
|
|
# No luck: narrow by "language from territory" and "territory from language"
|
|
|
|
# does not fit to a locale supported by the engine.
|
|
|
|
|
|
|
|
if engine_locale is None:
|
|
|
|
engine_locale = default
|
|
|
|
|
|
|
|
return default
|
2023-02-07 14:11:58 +01:00
|
|
|
|
|
|
|
|
|
|
|
def match_locale(searxng_locale: str, locale_tag_list: List[str], fallback: Optional[str] = None) -> Optional[str]:
|
|
|
|
"""Return tag from ``locale_tag_list`` that best fits to ``searxng_locale``.
|
|
|
|
|
|
|
|
:param str searxng_locale: SearXNG's internal representation of locale (de,
|
|
|
|
de-DE, fr-BE, zh, zh-CN, zh-TW ..).
|
|
|
|
|
|
|
|
:param list locale_tag_list: The list of locale tags to select from
|
|
|
|
|
|
|
|
:param str fallback: fallback locale tag (if unset --> ``None``)
|
|
|
|
|
|
|
|
The rules to find a match are implemented in :py:obj:`get_engine_locale`,
|
|
|
|
the ``engine_locales`` is build up by :py:obj:`build_engine_locales`.
|
|
|
|
|
|
|
|
.. hint::
|
|
|
|
|
|
|
|
The *SearXNG locale* string and the members of ``locale_tag_list`` has to
|
|
|
|
be known by babel! The :py:obj:`ADDITIONAL_TRANSLATIONS` are used in the
|
|
|
|
UI and are not known by babel --> will be ignored.
|
|
|
|
"""
|
|
|
|
|
|
|
|
# searxng_locale = 'es'
|
|
|
|
# locale_tag_list = ['es-AR', 'es-ES', 'es-MX']
|
|
|
|
|
|
|
|
if not searxng_locale:
|
|
|
|
return fallback
|
|
|
|
|
|
|
|
locale = get_locale(searxng_locale)
|
|
|
|
if locale is None:
|
|
|
|
return fallback
|
|
|
|
|
|
|
|
# normalize to a SearXNG locale that can be passed to get_engine_locale
|
|
|
|
|
|
|
|
searxng_locale = language_tag(locale)
|
|
|
|
if locale.territory:
|
|
|
|
searxng_locale = region_tag(locale)
|
|
|
|
|
|
|
|
# clean up locale_tag_list
|
|
|
|
|
|
|
|
tag_list = []
|
|
|
|
for tag in locale_tag_list:
|
|
|
|
if tag in ('all', 'auto') or tag in ADDITIONAL_TRANSLATIONS:
|
|
|
|
continue
|
|
|
|
tag_list.append(tag)
|
|
|
|
|
|
|
|
# emulate fetch_traits
|
|
|
|
engine_locales = build_engine_locales(tag_list)
|
|
|
|
return get_engine_locale(searxng_locale, engine_locales, default=fallback)
|
|
|
|
|
|
|
|
|
|
|
|
def build_engine_locales(tag_list: List[str]):
|
|
|
|
"""From a list of locale tags a dictionary is build that can be passed by
|
|
|
|
argument ``engine_locales`` to :py:obj:`get_engine_locale`. This function
|
|
|
|
is mainly used by :py:obj:`match_locale` and is similar to what the
|
|
|
|
``fetch_traits(..)`` function of engines do.
|
|
|
|
|
|
|
|
If there are territory codes in the ``tag_list`` that have a *script code*
|
|
|
|
additional keys are added to the returned dictionary.
|
|
|
|
|
|
|
|
.. code:: python
|
|
|
|
|
|
|
|
>>> import locales
|
|
|
|
>>> engine_locales = locales.build_engine_locales(['en', 'en-US', 'zh', 'zh-CN', 'zh-TW'])
|
|
|
|
>>> engine_locales
|
|
|
|
{
|
|
|
|
'en': 'en', 'en-US': 'en-US',
|
|
|
|
'zh': 'zh', 'zh-CN': 'zh-CN', 'zh_Hans': 'zh-CN',
|
|
|
|
'zh-TW': 'zh-TW', 'zh_Hant': 'zh-TW'
|
|
|
|
}
|
|
|
|
>>> get_engine_locale('zh-Hans', engine_locales)
|
|
|
|
'zh-CN'
|
|
|
|
|
|
|
|
This function is a good example to understand the language/region model
|
|
|
|
of SearXNG:
|
|
|
|
|
|
|
|
SearXNG only distinguishes between **search languages** and **search
|
|
|
|
regions**, by adding the *script-tags*, languages with *script-tags* can
|
|
|
|
be assigned to the **regions** that SearXNG supports.
|
|
|
|
|
|
|
|
"""
|
|
|
|
engine_locales = {}
|
|
|
|
|
|
|
|
for tag in tag_list:
|
|
|
|
locale = get_locale(tag)
|
|
|
|
if locale is None:
|
2023-05-19 16:05:29 +02:00
|
|
|
logger.warning("build_engine_locales: skip locale tag %s / unknown by babel", tag)
|
2023-02-07 14:11:58 +01:00
|
|
|
continue
|
|
|
|
if locale.territory:
|
|
|
|
engine_locales[region_tag(locale)] = tag
|
|
|
|
if locale.script:
|
|
|
|
engine_locales[language_tag(locale)] = tag
|
|
|
|
else:
|
|
|
|
engine_locales[language_tag(locale)] = tag
|
|
|
|
return engine_locales
|