forked from Ponysearch/Ponysearch
[mod] add flags to the languages filter
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser
parent
7625da9fa0
commit
2841abaf55
6 changed files with 139 additions and 78 deletions
|
|
@ -2,70 +2,61 @@
|
|||
# list of language codes
|
||||
# this file is generated automatically by utils/fetch_languages.py
|
||||
language_codes = (
|
||||
('af-ZA', 'Afrikaans', '', 'Afrikaans'),
|
||||
('ar-EG', 'العربية', '', 'Arabic'),
|
||||
('be-BY', 'Беларуская', '', 'Belarusian'),
|
||||
('bg-BG', 'Български', '', 'Bulgarian'),
|
||||
('ca-ES', 'Català', '', 'Catalan'),
|
||||
('cs-CZ', 'Čeština', '', 'Czech'),
|
||||
('da-DK', 'Dansk', '', 'Danish'),
|
||||
('de', 'Deutsch', '', 'German'),
|
||||
('de-AT', 'Deutsch', 'Österreich', 'German'),
|
||||
('de-CH', 'Deutsch', 'Schweiz', 'German'),
|
||||
('de-DE', 'Deutsch', 'Deutschland', 'German'),
|
||||
('el-GR', 'Ελληνικά', '', 'Greek'),
|
||||
('en', 'English', '', 'English'),
|
||||
('en-AU', 'English', 'Australia', 'English'),
|
||||
('en-CA', 'English', 'Canada', 'English'),
|
||||
('en-GB', 'English', 'United Kingdom', 'English'),
|
||||
('en-IE', 'English', 'Ireland', 'English'),
|
||||
('en-MY', 'English', 'Malaysia', 'English'),
|
||||
('en-NZ', 'English', 'New Zealand', 'English'),
|
||||
('en-US', 'English', 'United States', 'English'),
|
||||
('es', 'Español', '', 'Spanish'),
|
||||
('es-AR', 'Español', 'Argentina', 'Spanish'),
|
||||
('es-CL', 'Español', 'Chile', 'Spanish'),
|
||||
('es-ES', 'Español', 'España', 'Spanish'),
|
||||
('es-MX', 'Español', 'México', 'Spanish'),
|
||||
('et-EE', 'Eesti', '', 'Estonian'),
|
||||
('fa-IR', 'فارسی', '', 'Persian'),
|
||||
('fi-FI', 'Suomi', '', 'Finnish'),
|
||||
('fr', 'Français', '', 'French'),
|
||||
('fr-BE', 'Français', 'Belgique', 'French'),
|
||||
('fr-CA', 'Français', 'Canada', 'French'),
|
||||
('fr-CH', 'Français', 'Suisse', 'French'),
|
||||
('fr-FR', 'Français', 'France', 'French'),
|
||||
('he-IL', 'עברית', '', 'Hebrew'),
|
||||
('hi-IN', 'हिन्दी', '', 'Hindi'),
|
||||
('hr-HR', 'Hrvatski', '', 'Croatian'),
|
||||
('hu-HU', 'Magyar', '', 'Hungarian'),
|
||||
('id-ID', 'Indonesia', '', 'Indonesian'),
|
||||
('is-IS', 'Íslenska', '', 'Icelandic'),
|
||||
('it-IT', 'Italiano', '', 'Italian'),
|
||||
('ja-JP', '日本語', '', 'Japanese'),
|
||||
('ko-KR', '한국어', '', 'Korean'),
|
||||
('lt-LT', 'Lietuvių', '', 'Lithuanian'),
|
||||
('lv-LV', 'Latviešu', '', 'Latvian'),
|
||||
('nl', 'Nederlands', '', 'Dutch'),
|
||||
('nl-BE', 'Nederlands', 'België', 'Dutch'),
|
||||
('nl-NL', 'Nederlands', 'Nederland', 'Dutch'),
|
||||
('pl-PL', 'Polski', '', 'Polish'),
|
||||
('pt', 'Português', '', 'Portuguese'),
|
||||
('pt-BR', 'Português', 'Brasil', 'Portuguese'),
|
||||
('pt-PT', 'Português', 'Portugal', 'Portuguese'),
|
||||
('ro-RO', 'Română', '', 'Romanian'),
|
||||
('ru-RU', 'Русский', '', 'Russian'),
|
||||
('sk-SK', 'Slovenčina', '', 'Slovak'),
|
||||
('sl-SI', 'Slovenščina', '', 'Slovenian'),
|
||||
('sr-RS', 'Српски', '', 'Serbian'),
|
||||
('sv-SE', 'Svenska', '', 'Swedish'),
|
||||
('sw-TZ', 'Kiswahili', '', 'Swahili'),
|
||||
('th-TH', 'ไทย', '', 'Thai'),
|
||||
('tr-TR', 'Türkçe', '', 'Turkish'),
|
||||
('uk-UA', 'Українська', '', 'Ukrainian'),
|
||||
('vi-VN', 'Tiếng Việt', '', 'Vietnamese'),
|
||||
('zh', '中文', '', 'Chinese'),
|
||||
('zh-CN', '中文', '中国', 'Chinese'),
|
||||
('zh-HK', '中文', '中國香港特別行政區', 'Chinese'),
|
||||
('zh-TW', '中文', '台灣', 'Chinese'),
|
||||
('ar-EG', 'العربية', '', 'Arabic', '\U0001f1ea\U0001f1ec'),
|
||||
('bg-BG', 'Български', '', 'Bulgarian', '\U0001f1e7\U0001f1ec'),
|
||||
('ca-ES', 'Català', '', 'Catalan', '\U0001f1ea\U0001f1f8'),
|
||||
('cs-CZ', 'Čeština', '', 'Czech', '\U0001f1e8\U0001f1ff'),
|
||||
('da-DK', 'Dansk', '', 'Danish', '\U0001f1e9\U0001f1f0'),
|
||||
('de', 'Deutsch', '', 'German', '\U0001f1e9\U0001f1ea'),
|
||||
('de-AT', 'Deutsch', 'Österreich', 'German', '\U0001f1e6\U0001f1f9'),
|
||||
('de-CH', 'Deutsch', 'Schweiz', 'German', '\U0001f1e8\U0001f1ed'),
|
||||
('de-DE', 'Deutsch', 'Deutschland', 'German', '\U0001f1e9\U0001f1ea'),
|
||||
('el-GR', 'Ελληνικά', '', 'Greek', '\U0001f1ec\U0001f1f7'),
|
||||
('en', 'English', '', 'English', '\U0001f1ec\U0001f1e7'),
|
||||
('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-NZ', 'English', 'New Zealand', 'English', '\U0001f1f3\U0001f1ff'),
|
||||
('en-US', 'English', 'United States', 'English', '\U0001f1fa\U0001f1f8'),
|
||||
('es', 'Español', '', 'Spanish', '\U0001f1ea\U0001f1f8'),
|
||||
('es-AR', 'Español', 'Argentina', 'Spanish', '\U0001f1e6\U0001f1f7'),
|
||||
('es-CL', 'Español', 'Chile', 'Spanish', '\U0001f1e8\U0001f1f1'),
|
||||
('es-ES', 'Español', 'España', 'Spanish', '\U0001f1ea\U0001f1f8'),
|
||||
('es-MX', 'Español', 'México', 'Spanish', '\U0001f1f2\U0001f1fd'),
|
||||
('et-EE', 'Eesti', '', 'Estonian', '\U0001f1ea\U0001f1ea'),
|
||||
('fi-FI', 'Suomi', '', 'Finnish', '\U0001f1eb\U0001f1ee'),
|
||||
('fr', 'Français', '', 'French', '\U0001f1eb\U0001f1f7'),
|
||||
('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', '', 'Hebrew', '\U0001f1ee\U0001f1f1'),
|
||||
('hr-HR', 'Hrvatski', '', 'Croatian', '\U0001f1ed\U0001f1f7'),
|
||||
('hu-HU', 'Magyar', '', 'Hungarian', '\U0001f1ed\U0001f1fa'),
|
||||
('it-IT', 'Italiano', '', 'Italian', '\U0001f1ee\U0001f1f9'),
|
||||
('ja-JP', '日本語', '', 'Japanese', '\U0001f1ef\U0001f1f5'),
|
||||
('ko-KR', '한국어', '', 'Korean', '\U0001f1f0\U0001f1f7'),
|
||||
('lt-LT', 'Lietuvių', '', 'Lithuanian', '\U0001f1f1\U0001f1f9'),
|
||||
('lv-LV', 'Latviešu', '', 'Latvian', '\U0001f1f1\U0001f1fb'),
|
||||
('nl', 'Nederlands', '', 'Dutch', '\U0001f1f3\U0001f1f1'),
|
||||
('nl-BE', 'Nederlands', 'België', 'Dutch', '\U0001f1e7\U0001f1ea'),
|
||||
('nl-NL', 'Nederlands', 'Nederland', 'Dutch', '\U0001f1f3\U0001f1f1'),
|
||||
('pl-PL', 'Polski', '', 'Polish', '\U0001f1f5\U0001f1f1'),
|
||||
('pt', 'Português', '', 'Portuguese', '\U0001f1f5\U0001f1f9'),
|
||||
('pt-BR', 'Português', 'Brasil', 'Portuguese', '\U0001f1e7\U0001f1f7'),
|
||||
('pt-PT', 'Português', 'Portugal', 'Portuguese', '\U0001f1f5\U0001f1f9'),
|
||||
('ro-RO', 'Română', '', 'Romanian', '\U0001f1f7\U0001f1f4'),
|
||||
('ru-RU', 'Русский', '', 'Russian', '\U0001f1f7\U0001f1fa'),
|
||||
('sk-SK', 'Slovenčina', '', 'Slovak', '\U0001f1f8\U0001f1f0'),
|
||||
('sl-SI', 'Slovenščina', '', 'Slovenian', '\U0001f1f8\U0001f1ee'),
|
||||
('sv-SE', 'Svenska', '', 'Swedish', '\U0001f1f8\U0001f1ea'),
|
||||
('th-TH', 'ไทย', '', 'Thai', '\U0001f1f9\U0001f1ed'),
|
||||
('tr-TR', 'Türkçe', '', 'Turkish', '\U0001f1f9\U0001f1f7'),
|
||||
('uk-UA', 'Українська', '', 'Ukrainian', '\U0001f1fa\U0001f1e6'),
|
||||
('zh', '中文', '', 'Chinese', '\U0001f1e8\U0001f1f3'),
|
||||
('zh-CN', '中文', '中国', 'Chinese', '\U0001f1e8\U0001f1f3'),
|
||||
('zh-HK', '中文', '中國香港特別行政區', 'Chinese', '\U0001f1ed\U0001f1f0'),
|
||||
('zh-TW', '中文', '台灣', 'Chinese', '\U0001f1f9\U0001f1fc'),
|
||||
)
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ class LanguageParser(QueryPartParser):
|
|||
# check if any language-code is equal with
|
||||
# declared language-codes
|
||||
for lc in language_codes:
|
||||
lang_id, lang_name, country, english_name = map(str.lower, lc)
|
||||
lang_id, lang_name, country, english_name, _flag = map(str.lower, lc)
|
||||
|
||||
# if correct language-code is found
|
||||
# set it as new search-language
|
||||
|
|
@ -128,7 +128,7 @@ class LanguageParser(QueryPartParser):
|
|||
for lc in language_codes:
|
||||
if lc[0] not in settings['search']['languages']:
|
||||
continue
|
||||
lang_id, lang_name, country, english_name = map(str.lower, lc)
|
||||
lang_id, lang_name, country, english_name, _flag = map(str.lower, lc)
|
||||
|
||||
# check if query starts with language-id
|
||||
if lang_id.startswith(value):
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
<label class="visually-hidden" for="language">{{ _('Language') }}</label>
|
||||
<select class="language form-control {{ custom_select_class(rtl) }}" id="language" name="language" accesskey="l">
|
||||
<option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option>
|
||||
{%- for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) -%}
|
||||
{%- 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 %}>
|
||||
{{- lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id -}}
|
||||
</option>
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
<select class="language" id="language" name="language" aria-label="{{ _('Search language') }}">{{- '' -}}
|
||||
<option value="all" {% if current_language == 'all' %}selected="selected"{% endif %}>{{ _('Default language') }}</option>
|
||||
{%- for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) -%}
|
||||
{%- 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 %}>
|
||||
{{- lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id -}}
|
||||
{% if flag %}{{ flag }} {% endif%} {{- lang_name }} {% if country_name %}({{ country_name }}) {% endif %}
|
||||
</option>
|
||||
{%- endfor -%}
|
||||
</select>
|
||||
|
|
|
|||
|
|
@ -116,8 +116,8 @@
|
|||
<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>
|
||||
{%- for lang_id,lang_name,country_name,english_name in language_codes | sort(attribute=1) -%}
|
||||
<option value="{{ lang_id }}" {% if lang_id == current_language %}selected="selected"{% endif %}>{{ lang_name }} {% if country_name %}({{ country_name }}) {% endif %}- {{ lang_id }}</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>
|
||||
{%- endfor -%}
|
||||
</select>{{- '' -}}
|
||||
</p>
|
||||
|
|
|
|||
|
|
@ -12,12 +12,13 @@ Output files: :origin:`searx/data/engines_languages.json` and
|
|||
"""
|
||||
|
||||
# pylint: disable=invalid-name
|
||||
|
||||
from unicodedata import lookup
|
||||
import json
|
||||
from pathlib import Path
|
||||
from pprint import pformat
|
||||
from babel import Locale, UnknownLocaleError
|
||||
from babel.languages import get_global
|
||||
from babel.core import parse_locale
|
||||
|
||||
from searx import settings, searx_dir
|
||||
from searx.engines import load_engines, engines
|
||||
|
|
@ -61,6 +62,62 @@ def get_locale(lang_code):
|
|||
return None
|
||||
|
||||
|
||||
lang2emoji = {
|
||||
'ha': '\U0001F1F3\U0001F1EA', # Hausa / Niger
|
||||
'bs': '\U0001F1E7\U0001F1E6', # Bosnian / Bosnia & Herzegovina
|
||||
'jp': '\U0001F1EF\U0001F1F5', # Japanese
|
||||
'ua': '\U0001F1FA\U0001F1E6', # Ukrainian
|
||||
'he': '\U0001F1EE\U0001F1F7', # Hebrew
|
||||
'zh': '\U0001F1E8\U0001F1F3', # China (zh)
|
||||
}
|
||||
|
||||
|
||||
def get_unicode_flag(lang_code):
|
||||
"""Determine a unicode flag (emoji) that fits to the ``lang_code``"""
|
||||
|
||||
emoji = lang2emoji.get(lang_code.lower())
|
||||
if emoji:
|
||||
return emoji
|
||||
|
||||
if len(lang_code) == 2:
|
||||
l_code = lang_code.lower()
|
||||
c_code = lang_code.upper()
|
||||
if c_code == 'EN':
|
||||
c_code = 'GB'
|
||||
lang_code = "%s-%s" % (l_code, c_code)
|
||||
|
||||
language = territory = script = variant = ''
|
||||
try:
|
||||
language, territory, script, variant = parse_locale(lang_code, '-')
|
||||
except ValueError as exc:
|
||||
print(exc)
|
||||
|
||||
# https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2
|
||||
if not territory:
|
||||
# https://www.unicode.org/emoji/charts/emoji-list.html#country-flag
|
||||
emoji = lang2emoji.get(language)
|
||||
if not emoji:
|
||||
print(
|
||||
"%s --> language: %s / territory: %s / script: %s / variant: %s"
|
||||
% (lang_code, language, territory, script, variant)
|
||||
)
|
||||
return emoji
|
||||
|
||||
emoji = lang2emoji.get(territory.lower())
|
||||
if emoji:
|
||||
return emoji
|
||||
|
||||
try:
|
||||
c1 = lookup('REGIONAL INDICATOR SYMBOL LETTER ' + territory[0])
|
||||
c2 = lookup('REGIONAL INDICATOR SYMBOL LETTER ' + territory[1])
|
||||
# print("%s --> territory: %s --> %s%s" %(lang_code, territory, c1, c2 ))
|
||||
except KeyError as exc:
|
||||
print("%s --> territory: %s --> %s" % (lang_code, territory, exc))
|
||||
return None
|
||||
|
||||
return c1 + c2
|
||||
|
||||
|
||||
# Join all language lists.
|
||||
def join_language_lists(engines_languages):
|
||||
language_list = {}
|
||||
|
|
@ -113,7 +170,10 @@ def join_language_lists(engines_languages):
|
|||
print("ERROR: %s --> %s" % (locale, exc))
|
||||
locale = None
|
||||
|
||||
language_list[short_code]['countries'][lang_code] = {'country_name': country_name, 'counter': set()}
|
||||
language_list[short_code]['countries'][lang_code] = {
|
||||
'country_name': country_name,
|
||||
'counter': set(),
|
||||
}
|
||||
|
||||
# count engine for both language_country combination and language alone
|
||||
language_list[short_code]['counter'].add(engine_name)
|
||||
|
|
@ -167,7 +227,7 @@ def filter_language_list(all_languages):
|
|||
|
||||
# add language without countries too if there's more than one country to choose from
|
||||
if len(filtered_countries) > 1:
|
||||
filtered_countries[lang] = _copy_lang_data(lang)
|
||||
filtered_countries[lang] = _copy_lang_data(lang, None)
|
||||
elif len(filtered_countries) == 1:
|
||||
# if there's only one country per language, it's not necessary to show country name
|
||||
lang_country = next(iter(filtered_countries))
|
||||
|
|
@ -183,15 +243,22 @@ def filter_language_list(all_languages):
|
|||
lang_country = "{lang}-{country}".format(lang=lang, country=country_code)
|
||||
|
||||
if lang_country:
|
||||
filtered_countries[lang_country] = _copy_lang_data(lang)
|
||||
filtered_countries[lang_country] = _copy_lang_data(lang, None)
|
||||
else:
|
||||
filtered_countries[lang] = _copy_lang_data(lang)
|
||||
filtered_countries[lang] = _copy_lang_data(lang, None)
|
||||
|
||||
filtered_languages_with_countries.update(filtered_countries)
|
||||
|
||||
return filtered_languages_with_countries
|
||||
|
||||
|
||||
class UnicodeEscape(str):
|
||||
"""Escape unicode string in :py:obj:`pprint.pformat`"""
|
||||
|
||||
def __repr__(self):
|
||||
return "'" + "".join([chr(c) for c in self.encode('unicode-escape')]) + "'"
|
||||
|
||||
|
||||
# Write languages.py.
|
||||
def write_languages_file(languages):
|
||||
file_headers = (
|
||||
|
|
@ -209,11 +276,14 @@ def write_languages_file(languages):
|
|||
if name is None:
|
||||
print("ERROR: languages['%s'] --> %s" % (code, languages[code]))
|
||||
continue
|
||||
|
||||
flag = get_unicode_flag(code) or ''
|
||||
item = (
|
||||
code,
|
||||
languages[code]['name'].split(' (')[0],
|
||||
languages[code].get('country_name') or '',
|
||||
languages[code].get('english_name') or '',
|
||||
UnicodeEscape(flag),
|
||||
)
|
||||
|
||||
language_codes.append(item)
|
||||
|
|
|
|||
Loading…
Reference in a new issue