3 Commits

Author SHA1 Message Date
Markus Heiser
1d16b94279 [fix] wikidata: increase wikidata queries timeout
The big queries for initializing and updating the currencies take longer than
the default of the wikidata engine, which is only 3sec.

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2025-03-01 12:21:29 +01:00
return42
30a820437d [data] update searx.data - update_engine_traits.py 2025-03-01 09:43:06 +01:00
Markus Heiser
03419078ef [fix] bing fetch engine traits - adjusted XPath selectors
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2025-03-01 09:43:06 +01:00
9 changed files with 409 additions and 195 deletions

View File

@@ -75,7 +75,7 @@ test.shell:
# wrap ./manage script
MANAGE += weblate.translations.commit weblate.push.translations
MANAGE += data.all data.traits data.useragents data.locales
MANAGE += data.all data.traits data.useragents data.locales data.currencies
MANAGE += docs.html docs.live docs.gh-pages docs.prebuild docs.clean
MANAGE += docker.build docker.push docker.buildx
MANAGE += gecko.driver

View File

@@ -1557,7 +1557,7 @@
"ar": "بيزو دومنيكاني",
"bg": "Доминиканско песо",
"ca": "peso dominicà",
"cs": "Dominikánské peso",
"cs": "dominikánské peso",
"cy": "Peso Dominica",
"de": "dominikanischer Peso",
"en": "Dominican peso",
@@ -1582,7 +1582,7 @@
"pt": "peso dominicano",
"ro": "peso dominican",
"ru": "доминиканское песо",
"sk": "Dominikánske peso",
"sk": "dominikánske peso",
"sl": "dominikanski peso",
"sr": "доминикански пезос",
"sv": "Dominikansk peso",
@@ -1809,7 +1809,7 @@
"fi": "Fidžin dollari",
"fr": "dollar des Fidji",
"ga": "dollar Fhidsí",
"gl": "Dólar fidxiano",
"gl": "Dólar fijiano",
"he": "דולר פיג'י",
"hr": "Fidžijski dolar",
"hu": "fidzsi dollár",
@@ -1921,7 +1921,7 @@
"ar": "لاري جورجي",
"bg": "Грузинско лари",
"ca": "lari",
"cs": "gruzínské lari",
"cs": "gruzínský lari",
"da": "Lari",
"de": "georgischer Lari",
"en": "Georgian lari",
@@ -3308,7 +3308,7 @@
"ar": "درهم مغربي",
"bg": "Марокански дирхам",
"ca": "dírham marroquí",
"cs": "Marocký dirham",
"cs": "marocký dirham",
"cy": "Dirham Moroco",
"de": "Marokkanischer Dirham",
"en": "Moroccan dirham",
@@ -3776,6 +3776,7 @@
"en": "Malaysian ringgit",
"eo": "malajzia ringito",
"es": "ringgit",
"et": "Ringgit",
"eu": "Ringgit",
"fi": "Malesian ringgit",
"fr": "ringgit",
@@ -3885,12 +3886,13 @@
"bg": "Нигерийска найра",
"ca": "naira",
"cs": "nigerijská naira",
"cy": "naira",
"de": "Naira",
"en": "naira",
"eo": "niĝeria najro",
"es": "naira",
"fi": "Nigerian naira",
"fr": "Naira",
"fr": "naira",
"ga": "naira",
"gl": "Naira",
"he": "נאירה",
@@ -4412,7 +4414,7 @@
"ar": "غواراني باراغواي",
"ca": "guaraní",
"cs": "paraguayský guaraní",
"cy": "Gwarani Paragwâi",
"cy": "Gwarani Paragwái",
"de": "Paraguayischer Guaraní",
"en": "Paraguayan guaraní",
"eo": "paragvaja gvaranio",
@@ -6284,6 +6286,7 @@
"es": "Oro de Zimbabue",
"fi": "Zimbabwen kulta",
"fr": "or du Zimbabwe",
"hr": "zimbabveanski gold",
"id": "Zimbabwe Gold",
"it": "Zimbabwe Gold",
"ja": "ジンバブエ・ゴールド",
@@ -6459,7 +6462,6 @@
"NT$": "TWD",
"NZ$": "NZD",
"Nfk": "ERN",
"Noha heinen krasss": "EUR",
"Nu": "BTN",
"N₨": "NPR",
"P": "BWP",
@@ -8146,7 +8148,6 @@
"dólar dos barbados": "BBD",
"dólar dos estados unidos": "USD",
"dólar estadounidense": "USD",
"dólar fidxiano": "FJD",
"dólar fijiano": "FJD",
"dólar fixiano": "FJD",
"dólar fiyiano": "FJD",
@@ -8832,7 +8833,7 @@
"gvinejski franak": "GNF",
"gvinejski frank": "GNF",
"gvinėjos frankas": "GNF",
"gwarani paragwâi": "PYG",
"gwarani paragwái": "PYG",
"gy$": "GYD",
"gyd": "GYD",
"ĝibraltara pundo": "GIP",
@@ -10186,6 +10187,8 @@
"naira nigeriana": "NGN",
"naira nigeriano": "NGN",
"naira nigérian": "NGN",
"naïra": "NGN",
"naïra nigérian": "NGN",
"najro": "NGN",
"nakfa": "ERN",
"nakfa eritrea": "ERN",
@@ -12442,6 +12445,7 @@
"zimbabva dolaro": "ZWL",
"zimbabva oro": "ZWG",
"zimbabve altını": "ZWG",
"zimbabveanski gold": "ZWG",
"zimbabvejski dolar": "ZWL",
"zimbabvejski gold": "ZWG",
"zimbabwaanse dollar": "ZWL",
@@ -13060,6 +13064,7 @@
"джибутийский франк": "DJF",
"джибутски франк": "DJF",
"дин": "RSD",
"дин.": "RSD",
"динар": [
"TND",
"RSD",
@@ -14304,7 +14309,9 @@
"الروبل": "RUB",
"الروبل الروسي": "RUB",
"الروبية الهندية": "INR",
"الريال السعودي": "SAR",
"الشيكل الإسرائيلي الجديد": "ILS",
"العملة السعودية": "SAR",
"العملة الموريتانية": "MRU",
"الفرنك الجيبوتي": "DJF",
"الفرنك السويسري": "CHF",
@@ -14465,6 +14472,8 @@
"روفيه": "MVR",
"روفيه مالديفية": "MVR",
"ريال": "YER",
"ريال السعودية": "SAR",
"ريال المملكة العربية السعودية": "SAR",
"ريال إيراني": "IRR",
"ريال برازيلي": "BRL",
"ريال سعودي": "SAR",
@@ -14473,6 +14482,7 @@
"ريال قطري": "QAR",
"ريال كمبودي": "KHR",
"ريال يمني": "YER",
"ريالات": "SAR",
"رينغيت": "MYR",
"رينغيت ماليزي": "MYR",
"ریال": [
@@ -14525,6 +14535,8 @@
"شيلينغ تنزاني": "TZS",
"شيلينغ كيني": "KES",
"شيلينغ كينيي": "KES",
"عملة السعودية": "SAR",
"عملة المملكة العربية السعودية": "SAR",
"غواراني": "PYG",
"غواراني باراغواي": "PYG",
"غيلدر الأنتيل الهولندية": "ANG",
@@ -15778,7 +15790,6 @@
"香港元": "HKD",
"﷼": [
"YER",
"SAR",
"IRR"
],
"﷼'": "YER"

File diff suppressed because it is too large Load Diff

View File

@@ -223,7 +223,7 @@ def fetch_traits(engine_traits: EngineTraits):
'da': 'dk', # da --> da-dk
}
for href in eval_xpath(dom, '//div[@id="language-section"]//li/a/@href'):
for href in eval_xpath(dom, '//div[@id="language-section-content"]//div[@class="languageItem"]/a/@href'):
eng_lang = parse_qs(urlparse(href).query)['setlang'][0]
babel_lang = map_lang.get(eng_lang, eng_lang)
try:
@@ -253,7 +253,7 @@ def fetch_traits(engine_traits: EngineTraits):
map_market_codes = {
'zh-hk': 'en-hk', # not sure why, but at M$ this is the market code for Hongkong
}
for href in eval_xpath(dom, '//div[@id="region-section"]//li/a/@href'):
for href in eval_xpath(dom, '//div[@id="region-section-content"]//div[@class="regionItem"]/a/@href'):
cc_tag = parse_qs(urlparse(href).query)['cc'][0]
if cc_tag == 'clear':
engine_traits.all_locale = cc_tag

View File

@@ -158,13 +158,13 @@ def get_label_for_entity(entity_id, language):
return name
def send_wikidata_query(query, method='GET'):
def send_wikidata_query(query, method='GET', **kwargs):
if method == 'GET':
# query will be cached by wikidata
http_response = get(SPARQL_ENDPOINT_URL + '?' + urlencode({'query': query}), headers=get_headers())
http_response = get(SPARQL_ENDPOINT_URL + '?' + urlencode({'query': query}), headers=get_headers(), **kwargs)
else:
# query won't be cached by wikidata
http_response = post(SPARQL_ENDPOINT_URL, data={'query': query}, headers=get_headers())
http_response = post(SPARQL_ENDPOINT_URL, data={'query': query}, headers=get_headers(), **kwargs)
if http_response.status_code != 200:
logger.debug('SPARQL endpoint error %s', http_response.content.decode())
logger.debug('request time %s', str(http_response.elapsed))
@@ -808,7 +808,7 @@ def init(engine_settings=None): # pylint: disable=unused-argument
if attribute.name not in WIKIDATA_PROPERTIES:
wikidata_property_names.append("wd:" + attribute.name)
query = QUERY_PROPERTY_NAMES.replace('%ATTRIBUTES%', " ".join(wikidata_property_names))
jsonresponse = send_wikidata_query(query)
jsonresponse = send_wikidata_query(query, timeout=20)
for result in jsonresponse.get('results', {}).get('bindings', {}):
name = result['name']['value']
lang = result['name']['xml:lang']

View File

@@ -1,5 +1,5 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
'''List of SearXNG's locale codes.
'''List of SearXNG's locale codes used for the search language/region.
.. hint::
@@ -11,14 +11,9 @@
sxng_locales = (
('af', 'Afrikaans', '', 'Afrikaans', '\U0001f310'),
('ar', 'العربية', '', 'Arabic', '\U0001f310'),
('ar-SA', 'العربية', 'المملكة العربية السعودية', 'Arabic', '\U0001f1f8\U0001f1e6'),
('be', 'Беларуская', '', 'Belarusian', '\U0001f310'),
('bg', 'Български', '', 'Bulgarian', '\U0001f310'),
('bg-BG', 'Български', 'България', 'Bulgarian', '\U0001f1e7\U0001f1ec'),
('ca', 'Català', '', 'Catalan', '\U0001f310'),
('cs', 'Čeština', '', 'Czech', '\U0001f310'),
('cs-CZ', 'Čeština', 'Česko', 'Czech', '\U0001f1e8\U0001f1ff'),
('cy', 'Cymraeg', '', 'Welsh', '\U0001f310'),
('da', 'Dansk', '', 'Danish', '\U0001f310'),
('da-DK', 'Dansk', 'Danmark', 'Danish', '\U0001f1e9\U0001f1f0'),
('de', 'Deutsch', '', 'German', '\U0001f310'),
@@ -26,7 +21,6 @@ sxng_locales = (
('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'),
@@ -35,20 +29,13 @@ sxng_locales = (
('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', 'فارسی', '', 'Persian', '\U0001f310'),
('fi', 'Suomi', '', 'Finnish', '\U0001f310'),
('fi-FI', 'Suomi', 'Suomi', 'Finnish', '\U0001f1eb\U0001f1ee'),
('fr', 'Français', '', 'French', '\U0001f310'),
@@ -56,14 +43,10 @@ sxng_locales = (
('fr-CA', 'Français', 'Canada', 'French', '\U0001f1e8\U0001f1e6'),
('fr-CH', 'Français', 'Suisse', 'French', '\U0001f1e8\U0001f1ed'),
('fr-FR', 'Français', 'France', 'French', '\U0001f1eb\U0001f1f7'),
('ga', 'Gaeilge', '', 'Irish', '\U0001f310'),
('gd', 'Gàidhlig', '', 'Scottish Gaelic', '\U0001f310'),
('gl', 'Galego', '', 'Galician', '\U0001f310'),
('he', 'עברית', '', 'Hebrew', '\U0001f1ee\U0001f1f1'),
('hi', 'हिन्दी', '', 'Hindi', '\U0001f310'),
('hr', 'Hrvatski', '', 'Croatian', '\U0001f310'),
('hu', 'Magyar', '', 'Hungarian', '\U0001f310'),
('hu-HU', 'Magyar', 'Magyarország', 'Hungarian', '\U0001f1ed\U0001f1fa'),
('id', 'Indonesia', '', 'Indonesian', '\U0001f310'),
('id-ID', 'Indonesia', 'Indonesia', 'Indonesian', '\U0001f1ee\U0001f1e9'),
('it', 'Italiano', '', 'Italian', '\U0001f310'),
@@ -71,13 +54,9 @@ sxng_locales = (
('it-IT', 'Italiano', 'Italia', 'Italian', '\U0001f1ee\U0001f1f9'),
('ja', '日本語', '', 'Japanese', '\U0001f310'),
('ja-JP', '日本語', '日本', 'Japanese', '\U0001f1ef\U0001f1f5'),
('kn', 'ಕನ್ನಡ', '', 'Kannada', '\U0001f310'),
('ko', '한국어', '', 'Korean', '\U0001f310'),
('ko-KR', '한국어', '대한민국', 'Korean', '\U0001f1f0\U0001f1f7'),
('lt', 'Lietuvių', '', 'Lithuanian', '\U0001f310'),
('lv', 'Latviešu', '', 'Latvian', '\U0001f310'),
('ml', 'മലയാളം', '', 'Malayalam', '\U0001f310'),
('mr', 'मराठी', '', 'Marathi', '\U0001f310'),
('nb', 'Norsk Bokmål', '', 'Norwegian Bokmål', '\U0001f310'),
('nb-NO', 'Norsk Bokmål', 'Norge', 'Norwegian Bokmål', '\U0001f1f3\U0001f1f4'),
('nl', 'Nederlands', '', 'Dutch', '\U0001f310'),
@@ -89,22 +68,16 @@ sxng_locales = (
('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'),
('sl', 'Slovenščina', '', 'Slovenian', '\U0001f310'),
('sq', 'Shqip', '', 'Albanian', '\U0001f310'),
('sv', 'Svenska', '', 'Swedish', '\U0001f310'),
('sv-SE', 'Svenska', 'Sverige', 'Swedish', '\U0001f1f8\U0001f1ea'),
('ta', 'தமிழ்', '', 'Tamil', '\U0001f310'),
('te', 'తెలుగు', '', 'Telugu', '\U0001f310'),
('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'),
('ur', 'اردو', '', 'Urdu', '\U0001f310'),
('vi', 'Tiếng Việt', '', 'Vietnamese', '\U0001f310'),
('zh', '中文', '', 'Chinese', '\U0001f310'),
('zh-CN', '中文', '中国', 'Chinese', '\U0001f1e8\U0001f1f3'),

View File

@@ -92,8 +92,7 @@ def add_currency_label(db, label, iso4217, language):
def wikidata_request_result_iterator(request):
wikidata.timeout = 30 # github CI has longer timeouts
result = wikidata.send_wikidata_query(request.replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL))
result = wikidata.send_wikidata_query(request.replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL), timeout=20)
if result is not None:
yield from result['results']['bindings']

View File

@@ -28,7 +28,7 @@ from searx.enginelib.traits import EngineTraitsMap
languages_file = Path(searx_dir) / 'sxng_locales.py'
languages_file_header = """\
# SPDX-License-Identifier: AGPL-3.0-or-later
'''List of SearXNG's locale codes.
'''List of SearXNG's locale codes used for the search language/region.
.. hint::
@@ -101,8 +101,8 @@ def fetch_traits_map():
def filter_locales(traits_map: EngineTraitsMap):
"""Filter language & region tags by a threshold."""
min_eng_per_region = 18
min_eng_per_lang = 20
min_eng_per_region = 22
min_eng_per_lang = 24
_ = {}
for eng in traits_map.values():

View File

@@ -8,6 +8,7 @@ data.:
traits : update searx/data/engine_traits.json & searx/sxng_locales.py
useragents: update searx/data/useragents.json with the most recent versions of Firefox
locales : update searx/data/locales.json from babel
currencies: update searx/data/currencies.json from wikidata
EOF
}
@@ -59,3 +60,12 @@ data.locales() {
)
dump_return $?
}
data.currencies(){
( set -e
pyenv.activate
build_msg DATA "update searx/data/currencies.json"
python searxng_extra/update/update_currencies.py
)
dump_return $?
}