fmt

Bumps [black](https://github.com/psf/black) from 25.9.0 to 26.5.1.
- [Release notes](https://github.com/psf/black/releases)
- [Changelog](https://github.com/psf/black/blob/main/CHANGES.md)
- [Commits](https://github.com/psf/black/compare/25.9.0...26.5.1)

---
updated-dependencies:
- dependency-name: black
  dependency-version: 26.5.1
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/workflows/data-update.yml

@@ -31,7 +31,7 @@ jobs:
           - update_external_bangs.py
           - update_firefox_version.py
           - update_engine_traits.py
-          - update_wikidata_units.py
+          - update_wikidata.py
           - update_engine_descriptions.py
 
     permissions:

docs/dev/quickstart.rst

@@ -80,8 +80,8 @@ same environment, here are a few examples::
     # to test one of the update scripts
     (dev.env)$ searxng_extra/update/update_engine_traits.py --help
 
-    # to test the update of the wikidata units
-    (dev.env)$ searxng_extra/update/update_wikidata_units.py
+    # to test the update of the wikidata units and property names
+    (dev.env)$ searxng_extra/update/update_wikidata.py
 
 
 .. sidebar:: further read

docs/dev/searxng_extra/update.rst

@@ -90,10 +90,10 @@ Scripts to update static data in :origin:`searx/data/`
   :members:
 
 
-``update_wikidata_units.py``
+``update_wikidata.py``
 ============================
 
-:origin:`[source] <searxng_extra/update/update_wikidata_units.py>`
+:origin:`[source] <searxng_extra/update/update_wikidata.py>`
 
-.. automodule:: searxng_extra.update.update_wikidata_units
+.. automodule:: searxng_extra.update.update_wikidata
   :members:

requirements-dev.txt

@@ -1,7 +1,7 @@
 mock==5.2.0
 nose2[coverage_plugin]==0.16.0
 cov-core==1.15.0
-black==25.9.0
+black==26.5.1
 pylint==4.0.7
 splinter==0.21.0
 selenium==4.47.0

searx/_settings.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of the :py:obj:`preference <searx.preference>` settings."""
+
 # pylint: disable = too-few-public-methods
 
 import typing as t

searx/answerers/__init__.py

@@ -38,7 +38,6 @@ area:
 
 """
 
-
 __all__ = ["AnswererInfo", "Answerer", "AnswerStorage"]
 
 

searx/answerers/_core.py

@@ -13,7 +13,6 @@ from dataclasses import dataclass
 from searx.utils import load_module
 from searx.result_types.answer import BaseAnswer
 
-
 _default = pathlib.Path(__file__).parent
 log: logging.Logger = logging.getLogger("searx.answerers")
 

searx/botdetection/__init__.py

@@ -5,7 +5,6 @@ Implementations used for bot detection.
 
 """
 
-
 __all__ = ["init", "dump_request", "get_network", "too_many_requests", "ProxyFix"]
 
 

searx/botdetection/config.py

@@ -182,7 +182,7 @@ class Config:
             if default is UNSET:
                 raise KeyError(name)
             return default
-        (modulename, name) = str(fqn).rsplit('.', 1)
+        modulename, name = str(fqn).rsplit('.', 1)
         m = __import__(modulename, {}, {}, [name], 0)
         return getattr(m, name)
 

searx/botdetection/http_accept.py

@@ -13,7 +13,6 @@ Accept_ header ..
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_accept_encoding.py

@@ -14,7 +14,6 @@ bot if the Accept-Encoding_ header ..
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_accept_language.py

@@ -11,7 +11,6 @@ if the Accept-Language_ header is unset.
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_connection.py

@@ -11,7 +11,6 @@ the Connection_ header is set to ``close``.
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_sec_fetch.py

@@ -20,6 +20,7 @@ Metadata`_.  A request is filtered out in case of:
 
 
 """
+
 # pylint: disable=unused-argument
 
 

searx/botdetection/http_user_agent.py

@@ -12,7 +12,6 @@ the User-Agent_ header is unset or matches the regular expression
 
 """
 
-
 import re
 from ipaddress import (
     IPv4Network,
@@ -25,7 +24,6 @@ import flask
 from . import config
 from ._helpers import too_many_requests
 
-
 USER_AGENT = (
     r'('
     + r'unknown'

searx/botdetection/ip_limit.py

@@ -55,7 +55,6 @@ from ._helpers import (
     logger,
 )
 
-
 logger = logger.getChild('ip_limit')
 
 BURST_WINDOW = 20

searx/botdetection/ip_lists.py

@@ -23,6 +23,7 @@ The ``ip_lists`` method implements :py:obj:`block-list <block_ip>` and
    ]
 
 """
+
 # pylint: disable=unused-argument
 
 

searx/botdetection/trusted_proxies.py

@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of a middleware to determine the real IP of an HTTP request
 (:py:obj:`flask.request.remote_addr`) behind a proxy chain."""
+
 # pylint: disable=too-many-branches
 
 

searx/botdetection/valkeydb.py

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Providing a Valkey database for the botdetection methods."""
 
-
 import valkey
 
 __all__ = ["set_valkey_client", "get_valkey_client"]

searx/brand.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations needed for a branding of SearXNG."""
+
 # pylint: disable=too-few-public-methods
 
 # Struct fields aren't discovered in Python 3.14

searx/cache.py

@@ -465,7 +465,7 @@ class ExpireCacheSQLite(sqlitedb.SQLiteAppl, ExpireCache):
 
         # Check if value is expired. It's possible that it's expired but has not
         # yet been automatically deleted by the periodic maintenance
-        (value, expire) = row
+        value, expire = row
         now = time.time()
         if expire < now:
             # The record is deleted during the maintenance interval. Deleting

searx/compat.py

@@ -3,7 +3,6 @@
 
 import warnings
 
-
 # limiter backward compatibility
 # ------------------------------
 

searx/data/__init__.py

@@ -4,6 +4,7 @@
 make data.all
 
 """
+
 # pylint: disable=invalid-name
 
 __all__ = ["ahmia_blacklist_loader", "data_dir", "get_cache"]
@@ -32,6 +33,13 @@ class WikiDataUnitType(t.TypedDict):
     to_si_factor: float
 
 
+WikiDataPropertyNameType = str | dict[str, str]
+"""Name of a Wikidata property. Can be either the plain name or a dictionary of
+language code to property name, e.g. ``{"en": "Date of birth"}``."""
+WikiDataPropertiesType = dict[str, WikiDataPropertyNameType]
+"""Dictionary from wikidata property ID to property name."""
+
+
 class LocalesType(t.TypedDict):
     """Data structure of an item in ``locales.json``"""
 
@@ -41,6 +49,7 @@ class LocalesType(t.TypedDict):
 
 USER_AGENTS: UserAgentType
 WIKIDATA_UNITS: dict[str, WikiDataUnitType]
+WIKIDATA_PROPERTIES: WikiDataPropertiesType
 TRACKER_PATTERNS: TrackerPatternsDB
 LOCALES: LocalesType
 CURRENCIES: CurrenciesDB
@@ -52,11 +61,12 @@ ENGINE_DESCRIPTIONS: dict[str, dict[str, t.Any]]
 ENGINE_TRAITS: dict[str, dict[str, t.Any]]
 
 
-lazy_globals = {
+lazy_globals: dict[str, t.Any] = {
     "CURRENCIES": CurrenciesDB(),
     "USER_AGENTS": None,
     "EXTERNAL_URLS": None,
     "WIKIDATA_UNITS": None,
+    "WIKIDATA_PROPERTIES": None,
     "EXTERNAL_BANGS": None,
     "OSM_KEYS_TAGS": None,
     "ENGINE_DESCRIPTIONS": None,
@@ -69,6 +79,7 @@ data_json_files = {
     "USER_AGENTS": "useragents.json",
     "EXTERNAL_URLS": "external_urls.json",
     "WIKIDATA_UNITS": "wikidata_units.json",
+    "WIKIDATA_PROPERTIES": "wikidata_properties.json",
     "EXTERNAL_BANGS": "external_bangs.json",
     "OSM_KEYS_TAGS": "osm_keys_tags.json",
     "ENGINE_DESCRIPTIONS": "engine_descriptions.json",

searx/data/tracker_patterns.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Simple implementation to store TrackerPatterns data in a SQL database."""
+
 # pylint: disable=too-many-branches
 
 import typing as t

searx/data/wikidata_units.json

@@ -3474,11 +3474,6 @@
         "symbol": "mm⁻²",
         "to_si_factor": 1e-06
     },
-    "Q136039973": {
-        "si_name": "Q6137407",
-        "symbol": "FPS",
-        "to_si_factor": 1.0
-    },
     "Q1361854": {
         "si_name": "Q11570",
         "symbol": "dwt",
@@ -5254,6 +5249,11 @@
         "symbol": "μA",
         "to_si_factor": 1e-06
     },
+    "Q31274648": {
+        "si_name": "Q6137407",
+        "symbol": "FPS",
+        "to_si_factor": 1.0
+    },
     "Q3186734": {
         "si_name": "Q3186734",
         "symbol": "J/(m³ K)",

searx/engines/azure.py

@@ -25,6 +25,7 @@ To use this engine, add an entry similar to the following to your engine list in
     https://learn.microsoft.com/en-us/entra/identity-platform/quickstart-register-app
 
 """
+
 import typing as t
 
 from searx.enginelib import EngineCache

searx/engines/base.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """BASE (Scholar publications)"""
+
 from datetime import datetime
 import re
 

searx/engines/command.py

@@ -83,7 +83,6 @@ from threading import Thread
 from searx import logger
 from searx.result_types import EngineResults
 
-
 engine_type = 'offline'
 paging = True
 command = []

searx/engines/docker_hub.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Docker Hub (IT)"""
+
 # pylint: disable=use-dict-literal
 
 from urllib.parse import urlencode

searx/engines/duckduckgo.py

@@ -164,6 +164,7 @@ Terms / phrases that you keep coming across:
    https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers/Accept-Language
 
 """
+
 # pylint: disable=global-statement
 
 import json

searx/engines/duckduckgo_definitions.py

@@ -12,6 +12,7 @@ least we could not find out how language support should work.  It seems that
 most of the features are based on English terms.
 
 """
+
 import typing as t
 
 from urllib.parse import urlencode, urlparse, urljoin

searx/engines/duckduckgo_weather.py

@@ -17,7 +17,6 @@ from searx.result_types import EngineResults
 from searx.extended_types import SXNG_Response
 from searx import weather
 
-
 about = {
     "website": 'https://duckduckgo.com/',
     "wikidata_id": 'Q12805',

searx/engines/dummy-offline.py

@@ -2,7 +2,6 @@
 # pylint: disable=invalid-name
 """Dummy Offline"""
 
-
 # about
 about = {
     "wikidata_id": None,

searx/engines/github_code.py

@@ -65,7 +65,6 @@ code lines are just relabeled (starting from 1) and appended (a disjoint set of
 code blocks in a single file might be returned from the API).
 """
 
-
 import typing as t
 from urllib.parse import urlencode
 

searx/engines/hex.py

@@ -4,7 +4,6 @@
 from urllib.parse import urlencode
 from dateutil import parser
 
-
 about = {
     # pylint: disable=line-too-long
     "website": "https://hex.pm/",

searx/engines/jisho.py

@@ -108,14 +108,12 @@ def get_infobox(alt_forms, result_url, definitions):
         infobox_content.append(f'<p><i>Other forms:</i> {", ".join(alt_forms[1:])}</p>')
 
     # definitions
-    infobox_content.append(
-        '''
+    infobox_content.append('''
         <small><a href="https://www.edrdg.org/wiki/index.php/JMdict-EDICT_Dictionary_Project">JMdict</a>
         and <a href="https://www.edrdg.org/enamdict/enamdict_doc.html">JMnedict</a>
         by <a href="https://www.edrdg.org/edrdg/licence.html">EDRDG</a>, CC BY-SA 3.0.</small>
         <ul>
-    '''
-    )
+    ''')
     for pos, engdef, extra in definitions:
         if pos == 'Wikipedia definition':
             infobox_content.append('</ul><small>Wikipedia, CC BY-SA 3.0.</small><ul>')

searx/engines/mongodb.py

@@ -49,7 +49,6 @@ except ImportError:
 
 from searx.result_types import EngineResults
 
-
 engine_type = 'offline'
 
 # mongodb connection variables

searx/engines/npm.py

@@ -4,7 +4,6 @@
 from urllib.parse import urlencode
 from dateutil import parser
 
-
 about = {
     "website": "https://npms.io/",
     "wikidata_id": "Q7067518",

searx/engines/open_meteo.py

@@ -9,7 +9,6 @@ from datetime import datetime
 from searx.result_types import EngineResults, WeatherAnswer
 from searx import weather
 
-
 about = {
     "website": "https://open-meteo.com",
     "wikidata_id": None,

searx/engines/openstreetmap.py

@@ -10,7 +10,8 @@ from flask_babel import gettext
 
 from searx.data import OSM_KEYS_TAGS, CURRENCIES
 from searx.external_urls import get_external_url
-from searx.engines.wikidata import send_wikidata_query, sparql_string_escape, get_thumbnail
+from searx.wikidata import send_wikidata_query
+from searx.engines.wikidata import sparql_string_escape, get_thumbnail
 from searx.result_types import EngineResults
 
 # about
@@ -290,7 +291,8 @@ def get_title_address(result):
                 'house_number': address_raw.get('house_number'),
                 'road': address_raw.get('road'),
                 'locality': address_raw.get(
-                    'city', address_raw.get('town', address_raw.get('village'))  # noqa
+                    'city',
+                    address_raw.get('town', address_raw.get('village')),  # noqa
                 ),  # noqa
                 'postcode': address_raw.get('postcode'),
                 'country': address_raw.get('country'),

searx/engines/openverse.py

@@ -8,7 +8,6 @@ Openverse (formerly known as: Creative Commons search engine) [Images]
 from json import loads
 from urllib.parse import urlencode
 
-
 about = {
     "website": 'https://openverse.org/',
     "wikidata_id": None,

searx/engines/pexels.py

@@ -12,7 +12,6 @@ from searx.enginelib import EngineCache
 from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
 from searx.network import get
 
-
 # about
 about = {
     "website": 'https://www.pexels.com',

searx/engines/piped.py

@@ -48,7 +48,6 @@ Implementations
 
 """
 
-
 import time
 import random
 from urllib.parse import urlencode

searx/engines/privacywall.py

@@ -18,7 +18,6 @@ from searx.utils import eval_xpath_list, eval_xpath, extract_text, get_embeded_s
 from searx.locales import region_tag
 from searx.result_types import EngineResults
 
-
 if t.TYPE_CHECKING:
     from lxml.etree import ElementBase
     from searx.extended_types import SXNG_Response

searx/engines/recoll.py

@@ -35,6 +35,7 @@ Implementations
 ===============
 
 """
+
 import typing as t
 
 from datetime import date, timedelta

searx/engines/solr.py

@@ -34,7 +34,6 @@ from searx.exceptions import SearxEngineAPIException
 from searx.result_types import EngineResults
 from searx.extended_types import SXNG_Response
 
-
 base_url = 'http://localhost:8983'
 collection = ''
 rows = 10

searx/engines/soundcloud.py

@@ -117,7 +117,7 @@ def response(resp):
 
 def init(engine_settings):  # pylint: disable=unused-argument
     global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type:ignore
+    CACHE = EngineCache(engine_settings["name"])  # type: ignore
 
 
 def get_client_id() -> str | None:

searx/engines/sqlite.py

@@ -44,6 +44,7 @@ Implementations
 ===============
 
 """
+
 import typing as t
 import sqlite3
 import contextlib

searx/engines/startpage.py

@@ -82,6 +82,7 @@ Startpage's category (for Web-search, News, Videos, ..) is set by
   Supported categories are ``web``, ``news`` and ``images``.
 
 """
+
 # pylint: disable=too-many-statements
 
 import re

searx/engines/tubearchivist.py

@@ -74,7 +74,6 @@ Implementations
 ===============
 """
 
-
 from urllib.parse import urlencode
 from dateutil.parser import parse
 from searx.utils import html_to_text, humanize_number

searx/engines/vuhuv.py

@@ -12,7 +12,6 @@ from lxml import html
 from searx.result_types import EngineResults
 from searx.utils import eval_xpath_list, eval_xpath, extract_text
 
-
 if t.TYPE_CHECKING:
     from lxml.etree import ElementBase
     from searx.extended_types import SXNG_Response

searx/engines/wikidata.py

@@ -3,28 +3,34 @@
 
 Some implementations are shared from :ref:`wikipedia engine`.
 """
+
 # pylint: disable=missing-class-docstring
 
 import typing as t
 
-import os
 from hashlib import md5
 from urllib.parse import urlencode, unquote
 from json import loads
 
-from dateutil.parser import isoparse
-from babel.dates import format_datetime, format_date, format_time, get_datetime_format
 
-from searx.enginelib import EngineCache
-from searx.data import WIKIDATA_UNITS
 from searx.network import post, get
-from searx.utils import searxng_useragent, get_string_replaces_function
-from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom
+from searx.utils import get_string_replaces_function
+from searx.external_urls import area_to_osm_zoom
 from searx.engines.wikipedia import (
     fetch_wikimedia_traits,
     get_wiki_params,
 )
 from searx.enginelib.traits import EngineTraits
+from searx.wikidata_properties import (
+    QUERY_TEMPLATE,
+    WDArticle,
+    WDAttrList,
+    WDGeoAttribute,
+    WDImageAttribute,
+    WDURLAttribute,
+    get_attributes,
+)
+from searx.wikidata import SPARQL_ENDPOINT_URL, SPARQL_EXPLAIN_URL, get_wikidata_headers
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
@@ -47,78 +53,6 @@ display_type = ["infobox"]
 one will add a hit to the result list.  The first one will show a hit in the
 info box.  Both values can be set, or one of the two can be set."""
 
-CACHE: EngineCache
-"""Persistent (SQLite) key/value cache that deletes its values after ``expire``
-seconds."""
-
-# SPARQL
-SPARQL_ENDPOINT_URL = "https://query.wikidata.org/sparql"
-SPARQL_EXPLAIN_URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql?explain"
-WDPType = dict[str | tuple[str, str], str]
-WIKIDATA_PROPERTIES: WDPType = {
-    "P434": "MusicBrainz",
-    "P435": "MusicBrainz",
-    "P436": "MusicBrainz",
-    "P966": "MusicBrainz",
-    "P345": "IMDb",
-    "P2397": "YouTube",
-    "P1651": "YouTube",
-    "P2002": "Twitter",
-    "P2013": "Facebook",
-    "P2003": "Instagram",
-    "P4033": "Mastodon",
-    "P11947": "Lemmy",
-    "P12622": "PeerTube",
-}
-
-# SERVICE wikibase:mwapi : https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual/MWAPI
-# SERVICE wikibase:label: https://en.wikibooks.org/wiki/SPARQL/SERVICE_-_Label#Manual_Label_SERVICE
-# https://en.wikibooks.org/wiki/SPARQL/WIKIDATA_Precision,_Units_and_Coordinates
-# https://www.mediawiki.org/wiki/Wikibase/Indexing/RDF_Dump_Format#Data_model
-# optimization:
-# * https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service/query_optimization
-# * https://github.com/blazegraph/database/wiki/QueryHints
-QUERY_TEMPLATE = """
-SELECT ?item ?itemLabel ?itemDescription ?lat ?long %SELECT%
-WHERE
-{
-  SERVICE wikibase:mwapi {
-        bd:serviceParam wikibase:endpoint "www.wikidata.org";
-        wikibase:api "EntitySearch";
-        wikibase:limit 1;
-        mwapi:search "%QUERY%";
-        mwapi:language "%LANGUAGE%".
-        ?item wikibase:apiOutputItem mwapi:item.
-  }
-  hint:Prior hint:runFirst "true".
-
-  %WHERE%
-
-  SERVICE wikibase:label {
-      bd:serviceParam wikibase:language "%LANGUAGE%,en".
-      ?item rdfs:label ?itemLabel .
-      ?item schema:description ?itemDescription .
-      %WIKIBASE_LABELS%
-  }
-
-}
-GROUP BY ?item ?itemLabel ?itemDescription ?lat ?long %GROUP_BY%
-"""
-
-# Get the calendar names and the property names
-QUERY_PROPERTY_NAMES = """
-SELECT ?item ?name
-WHERE {
-    {
-      SELECT ?item
-      WHERE { ?item wdt:P279* wd:Q12132 }
-    } UNION {
-      VALUES ?item { %ATTRIBUTES% }
-    }
-    OPTIONAL { ?item rdfs:label ?name. }
-}
-"""
-
 # see the property "dummy value" of https://www.wikidata.org/wiki/Q2013 (Wikidata)
 # hard coded here to avoid to an additional SPARQL request when the server starts
 DUMMY_ENTITY_URLS = set(
@@ -130,357 +64,13 @@ DUMMY_ENTITY_URLS = set(
 # https://lists.w3.org/Archives/Public/public-rdf-dawg/2011OctDec/0175.html
 sparql_string_escape = get_string_replaces_function(
     # fmt: off
-    {
-        "\t": "\\\t",
-        "\n": "\\\n",
-        "\r": "\\\r",
-        "\b": "\\\b",
-        "\f": "\\\f",
-        "\"": "\\\"",
-        "\'": "\\\'",
-        "\\": "\\\\"
-    }
+    {"\t": "\\\t", "\n": "\\\n", "\r": "\\\r", "\b": "\\\b", "\f": "\\\f", "\"": "\\\"", "'": "\\'", "\\": "\\\\"}
     # fmt: on
 )
 
 replace_http_by_https = get_string_replaces_function({"http:": "https:"})
 
 
-class WDAttribute:
-
-    def __init__(self, name: str):
-        self.name: str = name
-
-    def get_select(self):
-        return "(group_concat(distinct ?{name};separator=', ') as ?{name}s)".replace("{name}", self.name)
-
-    def get_label(self, language: str):
-        return get_label_for_entity(self.name, language)
-
-    def get_where(self):
-        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
-
-    def get_wikibase_label(self) -> str:
-        return ""
-
-    def get_group_by(self) -> str:
-        return ""
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:  # pylint: disable=unused-argument
-        return result.get(self.name + "s")
-
-    def __repr__(self):
-        return "<" + str(type(self).__name__) + ":" + self.name + ">"
-
-
-class WDAmountAttribute(WDAttribute):
-    def get_select(self) -> str:
-        return "?{name} ?{name}Unit".replace("{name}", self.name)
-
-    def get_where(self):
-        return """  OPTIONAL { ?item p:{name} ?{name}Node .
-    ?{name}Node rdf:type wikibase:BestRank ; ps:{name} ?{name} .
-    OPTIONAL { ?{name}Node psv:{name}/wikibase:quantityUnit ?{name}Unit. } }""".replace(
-            '{name}', self.name
-        )
-
-    def get_group_by(self) -> str:
-        return self.get_select()
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        value: str | None = result.get(self.name)
-        unit: str | None = result.get(self.name + "Unit")
-        if unit is not None:
-            unit = unit.replace("http://www.wikidata.org/entity/", "")
-            return str(value) + " " + get_label_for_entity(unit, language)
-        return value
-
-
-class WDArticle(WDAttribute):
-
-    def __init__(self, language: str, kwargs: dict[str, t.Any] | None = None):
-        super().__init__("wikipedia")
-        self.language: str = language
-        self.kwargs: dict[str, t.Any] = kwargs or {}
-
-    def get_label(self, language: str):
-        # language parameter is ignored
-        return "Wikipedia ({language})".replace("{language}", self.language)
-
-    def get_select(self):
-        return "?article{language} ?articleName{language}".replace("{language}", self.language)
-
-    def get_where(self):
-        return """OPTIONAL { ?article{language} schema:about ?item ;
-             schema:inLanguage "{language}" ;
-             schema:isPartOf <https://{language}.wikipedia.org/> ;
-             schema:name ?articleName{language} . }""".replace(
-            '{language}', self.language
-        )
-
-    def get_group_by(self):
-        return self.get_select()
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        key = "article{language}".replace("{language}", self.language)
-        return result.get(key)
-
-
-class WDLabelAttribute(WDAttribute):
-    def get_select(self):
-        return "(group_concat(distinct ?{name}Label;separator=', ') as ?{name}Labels)".replace("{name}", self.name)
-
-    def get_where(self):
-        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
-
-    def get_wikibase_label(self) -> str:
-        return "?{name} rdfs:label ?{name}Label .".replace("{name}", self.name)
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        return result.get(self.name + "Labels")
-
-
-class WDURLAttribute(WDAttribute):
-
-    HTTP_WIKIMEDIA_IMAGE: str = "http://commons.wikimedia.org/wiki/Special:FilePath/"
-
-    def __init__(
-        self,
-        name: str,
-        url_id: str | None = None,
-        url_path_prefix: str | None = None,
-        kwargs: dict[str, t.Any] | None = None,
-    ):
-        """
-        :param url_id: ID matching one key in ``external_urls.json`` for
-            converting IDs to full URLs.
-
-        :param url_path_prefix: Path prefix if the values are of format
-            ``account@domain``.  If provided, value are rewritten to
-            ``https://<domain><url_path_prefix><account>``.  For example::
-
-              WDURLAttribute('P4033', url_path_prefix='/@')
-
-            Adds Property `P4033 <https://www.wikidata.org/wiki/Property:P4033>`_
-            to the wikidata query.  This field might return for example
-            ``libreoffice@fosstodon.org`` and the URL built from this is then:
-
-            - account: ``libreoffice``
-            - domain: ``fosstodon.org``
-            - result url: https://fosstodon.org/@libreoffice
-        """
-
-        super().__init__(name)
-        self.url_id: str | None = url_id
-        self.url_path_prefix: str | None = url_path_prefix
-        self.kwargs: dict[str, t.Any] = kwargs or {}
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        value: str | None = result.get(self.name + "s")
-        if not value:
-            return None
-
-        value = value.split(",")[0]
-        if self.url_id:
-            url_id = self.url_id
-            if value.startswith(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE):
-                value = value[len(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE) :]
-                url_id = "wikimedia_image"
-            return get_external_url(url_id, value)
-
-        if self.url_path_prefix:
-            [account, domain] = [x.strip("@ ") for x in value.rsplit("@", 1)]
-            return f"https://{domain}{self.url_path_prefix}{account}"
-
-        return value
-
-
-class WDGeoAttribute(WDAttribute):
-    def get_label(self, language: str):
-        return "OpenStreetMap"
-
-    def get_select(self):
-        return "?{name}Lat ?{name}Long".replace("{name}", self.name)
-
-    def get_where(self):
-        return """OPTIONAL { ?item p:{name}/psv:{name} [
-    wikibase:geoLatitude ?{name}Lat ;
-    wikibase:geoLongitude ?{name}Long ] }""".replace(
-            '{name}', self.name
-        )
-
-    def get_group_by(self):
-        return self.get_select()
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        latitude: str | None = result.get(self.name + "Lat")
-        longitude: str | None = result.get(self.name + "Long")
-        if latitude and longitude:
-            return latitude + " " + longitude
-        return None
-
-    def get_geo_url(self, result: dict[str, t.Any], osm_zoom: int = 19) -> str | None:
-        latitude: str | None = result.get(self.name + "Lat")
-        longitude: str | None = result.get(self.name + "Long")
-        if latitude and longitude:
-            return get_earth_coordinates_url(latitude, longitude, osm_zoom)
-        return None
-
-
-class WDImageAttribute(WDURLAttribute):
-
-    def __init__(self, name: str, url_id: str | None = None, priority: int = 100):
-        super().__init__(name, url_id)
-        self.priority: int = priority
-
-
-class WDDateAttribute(WDAttribute):
-    def get_select(self):
-        return "?{name} ?{name}timePrecision ?{name}timeZone ?{name}timeCalendar".replace("{name}", self.name)
-
-    def get_where(self):
-        # To remove duplicate, add
-        # FILTER NOT EXISTS { ?item p:{name}/psv:{name}/wikibase:timeValue ?{name}bis FILTER (?{name}bis < ?{name}) }
-        # this filter is too slow, so the response function ignore duplicate results
-        # (see the seen_entities variable)
-        return """OPTIONAL { ?item p:{name}/psv:{name} [
-    wikibase:timeValue ?{name} ;
-    wikibase:timePrecision ?{name}timePrecision ;
-    wikibase:timeTimezone ?{name}timeZone ;
-    wikibase:timeCalendarModel ?{name}timeCalendar ] . }
-    hint:Prior hint:rangeSafe true;""".replace(
-            '{name}', self.name
-        )
-
-    def get_group_by(self):
-        return self.get_select()
-
-    def format_8(self, value: str, locale: str) -> str:  # pylint: disable=unused-argument
-        # precision: less than a year
-        return value
-
-    def format_9(self, value: str, locale: str) -> str:
-        year = int(value)
-        # precision: year
-        if year < 1584:
-            if year < 0:
-                return str(year - 1)
-            return str(year)
-        timestamp = isoparse(value)
-        return format_date(timestamp, format="yyyy", locale=locale)
-
-    def format_10(self, value: str, locale: str) -> str:
-        # precision: month
-        timestamp = isoparse(value)
-        return format_date(timestamp, format="MMMM y", locale=locale)
-
-    def format_11(self, value: str, locale: str) -> str:
-        # precision: day
-        timestamp = isoparse(value)
-        return format_date(timestamp, format="full", locale=locale)
-
-    def format_13(self, value: str, locale: str) -> str:
-        timestamp = isoparse(value)
-        # precision: minute
-        return (
-            get_datetime_format(format, locale=locale)
-            .replace("'", "")
-            .replace("{0}", format_time(timestamp, "full", tzinfo=None, locale=locale))
-            .replace("{1}", format_date(timestamp, "short", locale=locale))
-        )
-
-    def format_14(self, value: str, locale: str) -> str:
-        # precision: second.
-        return format_datetime(isoparse(value), format="full", locale=locale)
-
-    DATE_FORMAT: dict[str, tuple[str, int]] = {
-        "0": ("format_8", 1000000000),
-        "1": ("format_8", 100000000),
-        "2": ("format_8", 10000000),
-        "3": ("format_8", 1000000),
-        "4": ("format_8", 100000),
-        "5": ("format_8", 10000),
-        "6": ("format_8", 1000),
-        "7": ("format_8", 100),
-        "8": ("format_8", 10),
-        "9": ("format_9", 1),  # year
-        "10": ("format_10", 1),  # month
-        "11": ("format_11", 0),  # day
-        "12": ("format_13", 0),  # hour (not supported by babel, display minute)
-        "13": ("format_13", 0),  # minute
-        "14": ("format_14", 0),  # second
-    }
-
-    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
-        value: str | None = result.get(self.name)
-        if value == "" or value is None:
-            return None
-        _p: str = result.get(self.name + "timePrecision") or "1"
-        date_format = WDDateAttribute.DATE_FORMAT.get(_p)
-        if date_format is not None:
-            format_method = getattr(self, date_format[0])
-            precision: int = date_format[1]
-            try:
-                if precision >= 1:
-                    _t = value.split("-")
-                    if value.startswith("-"):
-                        value = "-" + _t[1]
-                    else:
-                        value = _t[0]
-                return format_method(value, language)
-            except Exception:  # pylint: disable=broad-except
-                return value
-        return value
-
-
-WDAttrType = (
-    WDAttribute
-    | WDAmountAttribute
-    | WDArticle
-    | WDLabelAttribute
-    | WDURLAttribute
-    | WDGeoAttribute
-    | WDImageAttribute
-    | WDDateAttribute
-)
-WDAttrList = list[WDAttrType]
-
-
-def get_headers() -> dict[str, str]:
-    # user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits
-    return {
-        "Accept": "application/sparql-results+json",
-        "User-Agent": f"wikidata engine - {searxng_useragent()}",
-    }
-
-
-def get_label_for_entity(entity_id: str, language: str) -> str:
-    name = WIKIDATA_PROPERTIES.get(entity_id)
-    if name is None:
-        name = WIKIDATA_PROPERTIES.get((entity_id, language))
-    if name is None:
-        name = WIKIDATA_PROPERTIES.get((entity_id, language.split("-")[0]))
-    if name is None:
-        name = WIKIDATA_PROPERTIES.get((entity_id, "en"))
-    if name is None:
-        name = entity_id
-    return name
-
-
-def send_wikidata_query(query: str, method: str = "GET", **kwargs: dict[str, t.Any]) -> dict[str, t.Any]:
-    if method == "GET":
-        # query will be cached by wikidata
-        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(), **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))
-    http_response.raise_for_status()
-    return loads(http_response.content.decode())
-
-
 def request(query: str, params: "OnlineParams") -> None:
 
     attributes: WDAttrList
@@ -491,7 +81,7 @@ def request(query: str, params: "OnlineParams") -> None:
     params["method"] = "POST"
     params["url"] = SPARQL_ENDPOINT_URL
     params["data"] = {"query": query}
-    params["headers"] = get_headers()
+    params["headers"] = get_wikidata_headers()
 
     # additional parameters (not a part of OnlineParams)
     params["language"] = eng_tag  # type: ignore
@@ -584,7 +174,6 @@ def get_results(
     for attribute in attributes:
         value: str | None = attribute.get_str(attribute_result, language)
         if value is not None and value != "":
-
             if isinstance(attribute, (WDURLAttribute, WDArticle)):
                 # get_select() method : there is group_concat(distinct ...;separator=", ")
                 # split the value here
@@ -670,212 +259,15 @@ def get_query(query: str, language: str) -> tuple[str, WDAttrList]:
     return query, attributes
 
 
-def get_attributes(language: str):
-    # pylint: disable=too-many-statements
-    attributes: WDAttrList = []
-
-    def add_value(name: str):
-        attributes.append(WDAttribute(name))
-
-    def add_amount(name: str):
-        attributes.append(WDAmountAttribute(name))
-
-    def add_label(name: str):
-        attributes.append(WDLabelAttribute(name))
-
-    def add_url(name: str, url_id: str | None = None, url_path_prefix: str | None = None, **kwargs: dict[str, t.Any]):
-        attributes.append(WDURLAttribute(name, url_id, url_path_prefix, kwargs))
-
-    def add_image(name: str, url_id: str | None = None, priority: int = 1):
-        attributes.append(WDImageAttribute(name, url_id, priority))
-
-    def add_date(name: str):
-        attributes.append(WDDateAttribute(name))
-
-    # Dates
-    for p in [
-        "P571",  # inception date
-        "P576",  # dissolution date
-        "P580",  # start date
-        "P582",  # end date
-        "P569",  # date of birth
-        "P570",  # date of death
-        "P619",  # date of spacecraft launch
-        "P620",
-    ]:  # date of spacecraft landing
-        add_date(p)
-
-    for p in [
-        "P27",  # country of citizenship
-        "P495",  # country of origin
-        "P17",  # country
-        "P159",
-    ]:  # headquarters location
-        add_label(p)
-
-    # Places
-    for p in [
-        "P36",  # capital
-        "P35",  # head of state
-        "P6",  # head of government
-        "P122",  # basic form of government
-        "P37",
-    ]:  # official language
-        add_label(p)
-
-    add_value("P1082")  # population
-    add_amount("P2046")  # area
-    add_amount("P281")  # postal code
-    add_label("P38")  # currency
-    add_amount("P2048")  # height (building)
-
-    # Media
-    for p in [
-        "P400",  # platform (videogames, computing)
-        "P50",  # author
-        "P170",  # creator
-        "P57",  # director
-        "P175",  # performer
-        "P178",  # developer
-        "P162",  # producer
-        "P176",  # manufacturer
-        "P58",  # screenwriter
-        "P272",  # production company
-        "P264",  # record label
-        "P123",  # publisher
-        "P449",  # original network
-        "P750",  # distributed by
-        "P86",
-    ]:  # composer
-        add_label(p)
-
-    add_date("P577")  # publication date
-    add_label("P136")  # genre (music, film, artistic...)
-    add_label("P364")  # original language
-    add_value("P212")  # ISBN-13
-    add_value("P957")  # ISBN-10
-    add_label("P275")  # copyright license
-    add_label("P277")  # programming language
-    add_value("P348")  # version
-    add_label("P840")  # narrative location
-
-    # Languages
-    add_value("P1098")  # number of speakers
-    add_label("P282")  # writing system
-    add_label("P1018")  # language regulatory body
-    add_value("P218")  # language code (ISO 639-1)
-
-    # Other
-    add_label("P169")  # ceo
-    add_label("P112")  # founded by
-    add_label("P1454")  # legal form (company, organization)
-    add_label("P137")  # operator (service, facility, ...)
-    add_label("P1029")  # crew members (tripulation)
-    add_label("P225")  # taxon name
-    add_value("P274")  # chemical formula
-    add_label("P1346")  # winner (sports, contests, ...)
-    add_value("P1120")  # number of deaths
-    add_value("P498")  # currency code (ISO 4217)
-
-    # URL
-    kwargs: dict[str, t.Any] = {"official": True}
-    add_url("P856", **kwargs)  # official website
-    attributes.append(WDArticle(language))  # wikipedia (user language)
-    if not language.startswith("en"):
-        attributes.append(WDArticle("en"))  # wikipedia (english)
-
-    add_url("P1324")  # source code repository
-    add_url("P1581")  # blog
-    add_url("P434", url_id="musicbrainz_artist")
-    add_url("P435", url_id="musicbrainz_work")
-    add_url("P436", url_id="musicbrainz_release_group")
-    add_url("P966", url_id="musicbrainz_label")
-    add_url("P345", url_id="imdb_id")
-    add_url("P2397", url_id="youtube_channel")
-    add_url("P1651", url_id="youtube_video")
-    add_url("P2002", url_id="twitter_profile")
-    add_url("P2013", url_id="facebook_profile")
-    add_url("P2003", url_id="instagram_profile")
-
-    # Fediverse
-    add_url("P4033", url_path_prefix="/@")  # Mastodon user
-    add_url("P11947", url_path_prefix="/c/")  # Lemmy community
-    add_url("P12622", url_path_prefix="/c/")  # PeerTube channel
-
-    # Map
-    attributes.append(WDGeoAttribute("P625"))
-
-    # Image
-    add_image("P15", priority=1, url_id="wikimedia_image")  # route map
-    add_image("P242", priority=2, url_id="wikimedia_image")  # locator map
-    add_image("P154", priority=3, url_id="wikimedia_image")  # logo
-    add_image("P18", priority=4, url_id="wikimedia_image")  # image
-    add_image("P41", priority=5, url_id="wikimedia_image")  # flag
-    add_image("P2716", priority=6, url_id="wikimedia_image")  # collage
-    add_image("P2910", priority=7, url_id="wikimedia_image")  # icon
-
-    return attributes
-
-
 def debug_explain_wikidata_query(query: str, method: str = "GET"):
     if method == "GET":
-        http_response = get(SPARQL_EXPLAIN_URL + "&" + urlencode({"query": query}), headers=get_headers())
+        http_response = get(SPARQL_EXPLAIN_URL + "&" + urlencode({"query": query}), headers=get_wikidata_headers())
     else:
-        http_response = post(SPARQL_EXPLAIN_URL, data={"query": query}, headers=get_headers())
+        http_response = post(SPARQL_EXPLAIN_URL, data={"query": query}, headers=get_wikidata_headers())
     http_response.raise_for_status()
     return http_response.content
 
 
-def init(_):
-    global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache("wikidata")
-
-    # In an environment with competing processes, the initial loading of the
-    # cache is required only once.
-    eng_state: str | None = CACHE.get("eng_state")
-    if not eng_state or not eng_state.startswith("STATE:"):
-        CACHE.set("eng_state", f"STATE: being initialized by PID {os.getpid()}")
-        try:
-            init_wikidata_properties()
-        except Exception:
-            CACHE.set("eng_state", f"ERROR: initialization by PID {os.getpid()} failed.")
-            raise
-    else:
-        logger.debug(eng_state)
-
-
-def init_wikidata_properties():
-    global WIKIDATA_PROPERTIES  # pylint: disable=global-statement
-    p: WDPType = CACHE.get(key="WIKIDATA_PROPERTIES")
-    if p:
-        WIKIDATA_PROPERTIES = p
-        return
-
-    # WIKIDATA_PROPERTIES : add unit symbols
-    for k, v in WIKIDATA_UNITS.items():
-        WIKIDATA_PROPERTIES[k] = v["symbol"]
-
-    # WIKIDATA_PROPERTIES : add property labels
-    wikidata_property_names: list[str] = []
-    for attribute in get_attributes("en"):
-        if type(attribute) in (WDAttribute, WDAmountAttribute, WDURLAttribute, WDDateAttribute, WDLabelAttribute):
-            if attribute.name not in WIKIDATA_PROPERTIES:
-                wikidata_property_names.append("wd:" + attribute.name)
-    query = QUERY_PROPERTY_NAMES.replace("%ATTRIBUTES%", " ".join(wikidata_property_names))
-    kwargs: dict[str, t.Any] = {"timeout": 20}
-    jsonresponse = send_wikidata_query(query, **kwargs)
-    for result in jsonresponse.get("results", {}).get("bindings", {}):
-        name_field = result.get("name")
-        if not name_field:
-            continue
-        name = name_field["value"]
-        lang = name_field["xml:lang"]
-        entity_id = result["item"]["value"].replace("http://www.wikidata.org/entity/", "")
-        WIKIDATA_PROPERTIES[(entity_id, lang)] = name.capitalize()
-
-    CACHE.set(key="WIKIDATA_PROPERTIES", value=WIKIDATA_PROPERTIES)
-
-
 def fetch_traits(engine_traits: EngineTraits):
     """Uses languages evaluated from :py:obj:`wikipedia.fetch_wikimedia_traits
     <searx.engines.wikipedia.fetch_wikimedia_traits>` and removes

searx/engines/wolframalpha_noapi.py

@@ -3,7 +3,6 @@
 Wolfram|Alpha (Science)
 """
 
-
 from json import loads
 from urllib.parse import urlencode
 
@@ -53,7 +52,7 @@ seconds."""
 
 def init(engine_settings):
     global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type:ignore
+    CACHE = EngineCache(engine_settings["name"])  # type: ignore
 
 
 def obtain_token() -> str:

searx/engines/yacy.py

@@ -50,6 +50,7 @@ the engine).
 Implementations
 ===============
 """
+
 # pylint: disable=fixme
 
 

searx/engines/yandex.py

@@ -8,7 +8,6 @@ from lxml import html
 from searx.exceptions import SearxEngineCaptchaException
 from searx.utils import humanize_bytes, eval_xpath, eval_xpath_list, extract_text, extr
 
-
 # Engine metadata
 about = {
     "website": 'https://yandex.com/',

searx/extended_types.py

@@ -19,6 +19,7 @@
    :members:
 
 """
+
 # pylint: disable=invalid-name
 
 __all__ = ["SXNG_Request", "sxng_request", "SXNG_Response"]

searx/external_urls.py

@@ -5,7 +5,6 @@ import math
 
 from searx.data import EXTERNAL_URLS
 
-
 IMDB_PREFIX_TO_URL_ID = {
     'tt': 'imdb_title',
     'mn': 'imdb_name',

searx/favicons/__init__.py

@@ -8,7 +8,6 @@ an example in which the command line is called in the development environment::
   (py3) python -m searx.favicons --help
 """
 
-
 __all__ = ["init", "favicon_url", "favicon_proxy"]
 
 import pathlib

searx/favicons/proxy.py

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations for a favicon proxy"""
 
-
 from typing import Callable
 
 import importlib

searx/favicons/resolvers.py

@@ -6,7 +6,6 @@ timeout``) and returns a tuple ``(data, mime)``.
 
 """
 
-
 __all__ = ["DEFAULT_RESOLVER_MAP", "allesedv", "duckduckgo", "google", "kagi", "yandex"]
 
 from typing import Callable

searx/infopage/__init__.py

@@ -36,7 +36,6 @@ from .. import get_setting
 from ..version import GIT_URL
 from ..locales import LOCALE_NAMES
 
-
 logger = logging.getLogger('searx.infopage')
 _INFO_FOLDER = os.path.abspath(os.path.dirname(__file__))
 INFO_PAGES: 'InfoPageSet'

searx/locales.py

@@ -26,7 +26,6 @@ SearXNG’s locale implementations
 ================================
 """
 
-
 import typing as t
 from pathlib import Path
 

searx/metrics/error_recorder.py

@@ -16,7 +16,6 @@ from searx.exceptions import (
 from searx import searx_parent_dir, settings
 from searx.engines import engines
 
-
 errors_per_engines: dict[str, t.Any] = {}
 
 LogParametersType = tuple[str, ...]

searx/metrics/models.py

@@ -8,7 +8,6 @@ import threading
 
 from searx import logger
 
-
 __all__ = ["Histogram", "HistogramStorage", "CounterStorage"]
 
 logger = logger.getChild('searx.metrics')

searx/network/network.py

@@ -20,7 +20,6 @@ from searx.extended_types import SXNG_Response
 from .client import new_client, get_loop, AsyncHTTPTransportNoHttp
 from .raise_for_httperror import raise_for_httperror
 
-
 logger = logger.getChild('network')
 DEFAULT_NAME = '__DEFAULT__'
 NETWORKS: dict[str, "Network"] = {}

searx/plugins/__init__.py

@@ -94,7 +94,6 @@ Implementation
    :members:
 """
 
-
 __all__ = ["PluginInfo", "Plugin", "PluginStorage", "PluginCfg"]
 
 

searx/plugins/tor_check.py

@@ -4,6 +4,7 @@ user searches for ``tor-check``.  It fetches the tor exit node list from
 :py:obj:`url_exit_list` and parses all the IPs into a list, then checks if the
 user's IP address is in it.
 """
+
 from ipaddress import ip_address
 import typing
 

searx/plugins/unit_converter.py

@@ -8,6 +8,7 @@ converters, each converter is one item in the list (compare
 of measurement are evaluated.  The weighting in the evaluation results from the
 sorting of the :py:obj:`list of unit converters<symbol_to_si>`.
 """
+
 import typing
 import re
 import babel.numbers

searx/result_types/__init__.py

@@ -9,6 +9,7 @@
    gradually.  For more, please read :ref:`result types`.
 
 """
+
 # pylint: disable=too-few-public-methods
 
 

searx/result_types/answer.py

@@ -26,6 +26,7 @@ template.
    :members:
    :show-inheritance:
 """
+
 # pylint: disable=too-few-public-methods
 
 

searx/result_types/code.py

@@ -12,6 +12,7 @@ template.  For highlighting the code passages, Pygments_ is used.
    :show-inheritance:
 
 """
+
 # pylint: disable=too-few-public-methods, disable=invalid-name
 
 __all__ = ["Code"]
@@ -26,7 +27,6 @@ from pygments.formatters import HtmlFormatter  # pylint: disable=no-name-in-modu
 
 from ._base import MainResult
 
-
 _pygments_languages: list[str] = []
 
 

searx/result_types/file.py

@@ -11,6 +11,7 @@ template.
    :show-inheritance:
 
 """
+
 # pylint: disable=too-few-public-methods
 
 

searx/result_types/image.py

@@ -11,6 +11,7 @@ template.
    :members:
 
 """
+
 # pylint: disable=too-few-public-methods
 __all__ = ["Image", "ImageRef"]
 

searx/result_types/keyvalue.py

@@ -11,6 +11,7 @@ template.
    :show-inheritance:
 
 """
+
 # pylint: disable=too-few-public-methods
 
 

searx/result_types/paper.py

@@ -19,6 +19,7 @@ Related topics:
    :show-inheritance:
 
 """
+
 # pylint: disable=too-few-public-methods, disable=invalid-name
 
 __all__ = ["Paper"]

searx/searxng.msg

@@ -8,7 +8,6 @@ from searx import webutils
 from searx import engines
 from searx.weather import WeatherConditionType
 
-
 __all__ = [
     'CONSTANT_NAMES',
     'CATEGORY_NAMES',

searx/settings_defaults.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of the default settings."""
+
 from __future__ import annotations
 
 import typing as t

searx/weather.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations used for weather conditions and forecast."""
+
 # pylint: disable=too-few-public-methods
 
 __all__ = [

searx/webapp.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """WebApp"""
+
 # pylint: disable=use-dict-literal
 
 import json
@@ -118,7 +119,6 @@ from searx.sxng_locales import sxng_locales
 import searx.search
 from searx.network import stream as http_stream, set_context_network_name
 
-
 logger = logger.getChild('webapp')
 
 warnings.simplefilter("always")
@@ -1119,17 +1119,13 @@ def stats():
 
     technical_report = []
     for error in engine_reliabilities.get(selected_engine_name, {}).get('errors', []):
-        technical_report.append(
-            f"\
+        technical_report.append(f"\
             Error: {error['exception_classname'] or error['log_message']} \
             Parameters: {error['log_parameters']} \
             File name: {error['filename'] }:{ error['line_no'] } \
             Error Function: {error['function']} \
             Code: {error['code']} \
-            ".replace(
-                ' ' * 12, ''
-            ).strip()
-        )
+            ".replace(' ' * 12, '').strip())
     technical_report = ' '.join(technical_report)
 
     engine_stats['time'] = sorted(engine_stats['time'], reverse=reverse, key=get_key)

searx/wikidata.py

@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Shared methods for accessing Wikidata."""
+
+import typing as t
+from urllib.parse import urlencode
+
+from searx.network import get, post
+from searx.utils import gen_useragent
+
+# SPARQL
+SPARQL_ENDPOINT_URL = "https://query.wikidata.org/sparql"
+SPARQL_EXPLAIN_URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql?explain"
+
+
+def send_wikidata_query(query: str, method: str = "GET", **kwargs: dict[str, t.Any]) -> dict[str, t.Any]:
+    if method == "GET":
+        # query will be cached by wikidata
+        http_response = get(
+            SPARQL_ENDPOINT_URL + "?" + urlencode({"query": query}), headers=get_wikidata_headers(), **kwargs
+        )
+    else:
+        # query won't be cached by wikidata
+        http_response = post(SPARQL_ENDPOINT_URL, data={"query": query}, headers=get_wikidata_headers(), **kwargs)
+
+    http_response.raise_for_status()
+    return http_response.json()
+
+
+def get_wikidata_headers() -> dict[str, str]:
+    # user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits
+    return {
+        "Accept": "application/sparql-results+json",
+        "User-Agent": gen_useragent(),
+    }

searx/wikidata_properties.py

@@ -0,0 +1,572 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# pylint: disable=missing-class-docstring
+"""Fetch property names from :origin:`searx/engines/wikidata.py` engine."""
+
+import typing as t
+
+from dateutil.parser import isoparse
+from babel.dates import format_datetime, format_date, format_time, get_datetime_format
+
+from searx.external_urls import get_earth_coordinates_url, get_external_url
+from searx.data import WikiDataPropertiesType, WikiDataUnitType
+from searx.wikidata import send_wikidata_query
+
+# SERVICE wikibase:mwapi : https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual/MWAPI
+# SERVICE wikibase:label: https://en.wikibooks.org/wiki/SPARQL/SERVICE_-_Label#Manual_Label_SERVICE
+# https://en.wikibooks.org/wiki/SPARQL/WIKIDATA_Precision,_Units_and_Coordinates
+# https://www.mediawiki.org/wiki/Wikibase/Indexing/RDF_Dump_Format#Data_model
+# optimization:
+# * https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service/query_optimization
+# * https://github.com/blazegraph/database/wiki/QueryHints
+QUERY_TEMPLATE = """
+SELECT ?item ?itemLabel ?itemDescription ?lat ?long %SELECT%
+WHERE
+{
+  SERVICE wikibase:mwapi {
+        bd:serviceParam wikibase:endpoint "www.wikidata.org";
+        wikibase:api "EntitySearch";
+        wikibase:limit 1;
+        mwapi:search "%QUERY%";
+        mwapi:language "%LANGUAGE%".
+        ?item wikibase:apiOutputItem mwapi:item.
+  }
+  hint:Prior hint:runFirst "true".
+
+  %WHERE%
+
+  SERVICE wikibase:label {
+      bd:serviceParam wikibase:language "%LANGUAGE%,en".
+      ?item rdfs:label ?itemLabel .
+      ?item schema:description ?itemDescription .
+      %WIKIBASE_LABELS%
+  }
+
+}
+GROUP BY ?item ?itemLabel ?itemDescription ?lat ?long %GROUP_BY%
+"""
+
+# Get the calendar names and the property names
+QUERY_PROPERTY_NAMES = """
+SELECT ?item ?name
+WHERE {
+    {
+      SELECT ?item
+      WHERE { ?item wdt:P279* wd:Q12132 }
+    } UNION {
+      VALUES ?item { %ATTRIBUTES% }
+    }
+    OPTIONAL { ?item rdfs:label ?name. }
+}
+"""
+
+
+class WDAttribute:
+    def __init__(self, name: str):
+        self.name: str = name
+
+    def get_select(self):
+        return "(group_concat(distinct ?{name};separator=', ') as ?{name}s)".replace("{name}", self.name)
+
+    def get_label(self, language: str):
+        return get_label_for_entity(self.name, language)
+
+    def get_where(self):
+        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
+
+    def get_wikibase_label(self) -> str:
+        return ""
+
+    def get_group_by(self) -> str:
+        return ""
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:  # pylint: disable=unused-argument
+        return result.get(self.name + "s")
+
+    def __repr__(self):
+        return "<" + str(type(self).__name__) + ":" + self.name + ">"
+
+
+class WDAmountAttribute(WDAttribute):
+    def get_select(self) -> str:
+        return "?{name} ?{name}Unit".replace("{name}", self.name)
+
+    def get_where(self):
+        return """  OPTIONAL { ?item p:{name} ?{name}Node .
+    ?{name}Node rdf:type wikibase:BestRank ; ps:{name} ?{name} .
+    OPTIONAL { ?{name}Node psv:{name}/wikibase:quantityUnit ?{name}Unit. } }""".replace('{name}', self.name)
+
+    def get_group_by(self) -> str:
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name)
+        unit: str | None = result.get(self.name + "Unit")
+        if unit is not None:
+            unit = unit.replace("http://www.wikidata.org/entity/", "")
+            return str(value) + " " + get_label_for_entity(unit, language)
+        return value
+
+
+class WDArticle(WDAttribute):
+    def __init__(self, language: str, kwargs: dict[str, t.Any] | None = None):
+        super().__init__("wikipedia")
+        self.language: str = language
+        self.kwargs: dict[str, t.Any] = kwargs or {}
+
+    def get_label(self, language: str):
+        # language parameter is ignored
+        return "Wikipedia ({language})".replace("{language}", self.language)
+
+    def get_select(self):
+        return "?article{language} ?articleName{language}".replace("{language}", self.language)
+
+    def get_where(self):
+        return """OPTIONAL { ?article{language} schema:about ?item ;
+             schema:inLanguage "{language}" ;
+             schema:isPartOf <https://{language}.wikipedia.org/> ;
+             schema:name ?articleName{language} . }""".replace('{language}', self.language)
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        key = "article{language}".replace("{language}", self.language)
+        return result.get(key)
+
+
+class WDLabelAttribute(WDAttribute):
+    def get_select(self):
+        return "(group_concat(distinct ?{name}Label;separator=', ') as ?{name}Labels)".replace("{name}", self.name)
+
+    def get_where(self):
+        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
+
+    def get_wikibase_label(self) -> str:
+        return "?{name} rdfs:label ?{name}Label .".replace("{name}", self.name)
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        return result.get(self.name + "Labels")
+
+
+class WDURLAttribute(WDAttribute):
+    HTTP_WIKIMEDIA_IMAGE: str = "http://commons.wikimedia.org/wiki/Special:FilePath/"
+
+    def __init__(
+        self,
+        name: str,
+        url_id: str | None = None,
+        url_path_prefix: str | None = None,
+        kwargs: dict[str, t.Any] | None = None,
+    ):
+        """
+        :param url_id: ID matching one key in ``external_urls.json`` for
+            converting IDs to full URLs.
+
+        :param url_path_prefix: Path prefix if the values are of format
+            ``account@domain``.  If provided, value are rewritten to
+            ``https://<domain><url_path_prefix><account>``.  For example::
+
+              WDURLAttribute('P4033', url_path_prefix='/@')
+
+            Adds Property `P4033 <https://www.wikidata.org/wiki/Property:P4033>`_
+            to the wikidata query.  This field might return for example
+            ``libreoffice@fosstodon.org`` and the URL built from this is then:
+
+            - account: ``libreoffice``
+            - domain: ``fosstodon.org``
+            - result url: https://fosstodon.org/@libreoffice
+        """
+
+        super().__init__(name)
+        self.url_id: str | None = url_id
+        self.url_path_prefix: str | None = url_path_prefix
+        self.kwargs: dict[str, t.Any] = kwargs or {}
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name + "s")
+        if not value:
+            return None
+
+        value = value.split(",")[0]
+        if self.url_id:
+            url_id = self.url_id
+            if value.startswith(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE):
+                value = value[len(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE) :]
+                url_id = "wikimedia_image"
+            return get_external_url(url_id, value)
+
+        if self.url_path_prefix:
+            [account, domain] = [x.strip("@ ") for x in value.rsplit("@", 1)]
+            return f"https://{domain}{self.url_path_prefix}{account}"
+
+        return value
+
+
+class WDGeoAttribute(WDAttribute):
+    def get_label(self, language: str):
+        return "OpenStreetMap"
+
+    def get_select(self):
+        return "?{name}Lat ?{name}Long".replace("{name}", self.name)
+
+    def get_where(self):
+        return """OPTIONAL { ?item p:{name}/psv:{name} [
+    wikibase:geoLatitude ?{name}Lat ;
+    wikibase:geoLongitude ?{name}Long ] }""".replace('{name}', self.name)
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        latitude: str | None = result.get(self.name + "Lat")
+        longitude: str | None = result.get(self.name + "Long")
+        if latitude and longitude:
+            return latitude + " " + longitude
+        return None
+
+    def get_geo_url(self, result: dict[str, t.Any], osm_zoom: int = 19) -> str | None:
+        latitude: str | None = result.get(self.name + "Lat")
+        longitude: str | None = result.get(self.name + "Long")
+        if latitude and longitude:
+            return get_earth_coordinates_url(latitude, longitude, osm_zoom)
+        return None
+
+
+class WDImageAttribute(WDURLAttribute):
+    def __init__(self, name: str, url_id: str | None = None, priority: int = 100):
+        super().__init__(name, url_id)
+        self.priority: int = priority
+
+
+class WDDateAttribute(WDAttribute):
+    def get_select(self):
+        return "?{name} ?{name}timePrecision ?{name}timeZone ?{name}timeCalendar".replace("{name}", self.name)
+
+    def get_where(self):
+        # To remove duplicate, add
+        # FILTER NOT EXISTS { ?item p:{name}/psv:{name}/wikibase:timeValue ?{name}bis FILTER (?{name}bis < ?{name}) }
+        # this filter is too slow, so the response function ignore duplicate results
+        # (see the seen_entities variable)
+        return """OPTIONAL { ?item p:{name}/psv:{name} [
+    wikibase:timeValue ?{name} ;
+    wikibase:timePrecision ?{name}timePrecision ;
+    wikibase:timeTimezone ?{name}timeZone ;
+    wikibase:timeCalendarModel ?{name}timeCalendar ] . }
+    hint:Prior hint:rangeSafe true;""".replace('{name}', self.name)
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def format_8(self, value: str, locale: str) -> str:  # pylint: disable=unused-argument
+        # precision: less than a year
+        return value
+
+    def format_9(self, value: str, locale: str) -> str:
+        year = int(value)
+        # precision: year
+        if year < 1584:
+            if year < 0:
+                return str(year - 1)
+            return str(year)
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="yyyy", locale=locale)
+
+    def format_10(self, value: str, locale: str) -> str:
+        # precision: month
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="MMMM y", locale=locale)
+
+    def format_11(self, value: str, locale: str) -> str:
+        # precision: day
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="full", locale=locale)
+
+    def format_13(self, value: str, locale: str) -> str:
+        timestamp = isoparse(value)
+        # precision: minute
+        return (
+            get_datetime_format("medium", locale=locale)
+            .replace("'", "")
+            .replace("{0}", format_time(timestamp, "full", tzinfo=None, locale=locale))
+            .replace("{1}", format_date(timestamp, "short", locale=locale))
+        )
+
+    def format_14(self, value: str, locale: str) -> str:
+        # precision: second.
+        return format_datetime(isoparse(value), format="full", locale=locale)
+
+    DATE_FORMAT: dict[str, tuple[str, int]] = {
+        "0": ("format_8", 1000000000),
+        "1": ("format_8", 100000000),
+        "2": ("format_8", 10000000),
+        "3": ("format_8", 1000000),
+        "4": ("format_8", 100000),
+        "5": ("format_8", 10000),
+        "6": ("format_8", 1000),
+        "7": ("format_8", 100),
+        "8": ("format_8", 10),
+        "9": ("format_9", 1),  # year
+        "10": ("format_10", 1),  # month
+        "11": ("format_11", 0),  # day
+        "12": ("format_13", 0),  # hour (not supported by babel, display minute)
+        "13": ("format_13", 0),  # minute
+        "14": ("format_14", 0),  # second
+    }
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name)
+        if value == "" or value is None:
+            return None
+        _p: str = result.get(self.name + "timePrecision") or "1"
+        date_format = WDDateAttribute.DATE_FORMAT.get(_p)
+        if date_format is not None:
+            format_method = getattr(self, date_format[0])
+            precision: int = date_format[1]
+            try:
+                if precision >= 1:
+                    _t = value.split("-")
+                    if value.startswith("-"):
+                        value = "-" + _t[1]
+                    else:
+                        value = _t[0]
+                return format_method(value, language)
+            except Exception:  # pylint: disable=broad-except
+                return value
+        return value
+
+
+WDAttrType = (
+    WDAttribute
+    | WDAmountAttribute
+    | WDArticle
+    | WDLabelAttribute
+    | WDURLAttribute
+    | WDGeoAttribute
+    | WDImageAttribute
+    | WDDateAttribute
+)
+WDAttrList = list[WDAttrType]
+
+_WIKIDATA_PROPERTIES_OVERRIDE: WikiDataPropertiesType = {
+    "P434": "MusicBrainz",
+    "P435": "MusicBrainz",
+    "P436": "MusicBrainz",
+    "P966": "MusicBrainz",
+    "P345": "IMDb",
+    "P2397": "YouTube",
+    "P1651": "YouTube",
+    "P2002": "Twitter",
+    "P2013": "Facebook",
+    "P2003": "Instagram",
+    "P4033": "Mastodon",
+    "P11947": "Lemmy",
+    "P12622": "PeerTube",
+}
+"""Custom hardcoded property names for some Wikidata IDs. Only used if the
+name Wikidata assigned isn't user-friendly."""
+
+
+def fetch_properties(units: dict[str, WikiDataUnitType]) -> WikiDataPropertiesType:
+    properties = _WIKIDATA_PROPERTIES_OVERRIDE
+
+    # WIKIDATA_PROPERTIES : add unit symbols
+    for k, v in units.items():
+        properties[k] = v["symbol"]
+
+    # WIKIDATA_PROPERTIES : add property labels
+    wikidata_property_names: list[str] = []
+    for attribute in get_attributes("en"):
+        if type(attribute) in (WDAttribute, WDAmountAttribute, WDURLAttribute, WDDateAttribute, WDLabelAttribute):
+            if attribute.name not in properties:
+                wikidata_property_names.append("wd:" + attribute.name)
+
+        query = QUERY_PROPERTY_NAMES.replace("%ATTRIBUTES%", " ".join(wikidata_property_names))
+        kwargs: dict[str, t.Any] = {"timeout": 60}
+        json_response = send_wikidata_query(query, **kwargs)
+
+        for result in json_response.get("results", {}).get("bindings", {}):
+            name_field = result.get("name")
+            if not name_field:
+                continue
+            name = name_field["value"]
+            lang = name_field["xml:lang"]
+            entity_id = result["item"]["value"].replace("http://www.wikidata.org/entity/", "")
+
+            if name:
+                prop = properties.get(entity_id) or {}
+                prop[lang] = name.capitalize()  # pyright: ignore[reportIndexIssue]
+                properties[entity_id] = prop
+            else:
+                properties[entity_id] = name.capitalize()
+
+    return properties
+
+
+def get_attributes(language: str):
+    # pylint: disable=too-many-statements
+    attributes: WDAttrList = []
+
+    def add_value(name: str):
+        attributes.append(WDAttribute(name))
+
+    def add_amount(name: str):
+        attributes.append(WDAmountAttribute(name))
+
+    def add_label(name: str):
+        attributes.append(WDLabelAttribute(name))
+
+    def add_url(name: str, url_id: str | None = None, url_path_prefix: str | None = None, **kwargs: dict[str, t.Any]):
+        attributes.append(WDURLAttribute(name, url_id, url_path_prefix, kwargs))
+
+    def add_image(name: str, url_id: str | None = None, priority: int = 1):
+        attributes.append(WDImageAttribute(name, url_id, priority))
+
+    def add_date(name: str):
+        attributes.append(WDDateAttribute(name))
+
+    # Dates
+    for p in [
+        "P571",  # inception date
+        "P576",  # dissolution date
+        "P580",  # start date
+        "P582",  # end date
+        "P569",  # date of birth
+        "P570",  # date of death
+        "P619",  # date of spacecraft launch
+        "P620",
+    ]:  # date of spacecraft landing
+        add_date(p)
+
+    for p in [
+        "P27",  # country of citizenship
+        "P495",  # country of origin
+        "P17",  # country
+        "P159",
+    ]:  # headquarters location
+        add_label(p)
+
+    # Places
+    for p in [
+        "P36",  # capital
+        "P35",  # head of state
+        "P6",  # head of government
+        "P122",  # basic form of government
+        "P37",
+    ]:  # official language
+        add_label(p)
+
+    add_value("P1082")  # population
+    add_amount("P2046")  # area
+    add_amount("P281")  # postal code
+    add_label("P38")  # currency
+    add_amount("P2048")  # height (building)
+
+    # Media
+    for p in [
+        "P400",  # platform (videogames, computing)
+        "P50",  # author
+        "P170",  # creator
+        "P57",  # director
+        "P175",  # performer
+        "P178",  # developer
+        "P162",  # producer
+        "P176",  # manufacturer
+        "P58",  # screenwriter
+        "P272",  # production company
+        "P264",  # record label
+        "P123",  # publisher
+        "P449",  # original network
+        "P750",  # distributed by
+        "P86",
+    ]:  # composer
+        add_label(p)
+
+    add_date("P577")  # publication date
+    add_label("P136")  # genre (music, film, artistic...)
+    add_label("P364")  # original language
+    add_value("P212")  # ISBN-13
+    add_value("P957")  # ISBN-10
+    add_label("P275")  # copyright license
+    add_label("P277")  # programming language
+    add_value("P348")  # version
+    add_label("P840")  # narrative location
+
+    # Languages
+    add_value("P1098")  # number of speakers
+    add_label("P282")  # writing system
+    add_label("P1018")  # language regulatory body
+    add_value("P218")  # language code (ISO 639-1)
+
+    # Other
+    add_label("P169")  # ceo
+    add_label("P112")  # founded by
+    add_label("P1454")  # legal form (company, organization)
+    add_label("P137")  # operator (service, facility, ...)
+    add_label("P1029")  # crew members (tripulation)
+    add_label("P225")  # taxon name
+    add_value("P274")  # chemical formula
+    add_label("P1346")  # winner (sports, contests, ...)
+    add_value("P1120")  # number of deaths
+    add_value("P498")  # currency code (ISO 4217)
+
+    # URL
+    kwargs: dict[str, t.Any] = {"official": True}
+    add_url("P856", **kwargs)  # official website
+    attributes.append(WDArticle(language))  # wikipedia (user language)
+    if not language.startswith("en"):
+        attributes.append(WDArticle("en"))  # wikipedia (english)
+
+    add_url("P1324")  # source code repository
+    add_url("P1581")  # blog
+    add_url("P434", url_id="musicbrainz_artist")
+    add_url("P435", url_id="musicbrainz_work")
+    add_url("P436", url_id="musicbrainz_release_group")
+    add_url("P966", url_id="musicbrainz_label")
+    add_url("P345", url_id="imdb_id")
+    add_url("P2397", url_id="youtube_channel")
+    add_url("P1651", url_id="youtube_video")
+    add_url("P2002", url_id="twitter_profile")
+    add_url("P2013", url_id="facebook_profile")
+    add_url("P2003", url_id="instagram_profile")
+
+    # Fediverse
+    add_url("P4033", url_path_prefix="/@")  # Mastodon user
+    add_url("P11947", url_path_prefix="/c/")  # Lemmy community
+    add_url("P12622", url_path_prefix="/c/")  # PeerTube channel
+
+    # Map
+    attributes.append(WDGeoAttribute("P625"))
+
+    # Image
+    add_image("P15", priority=1, url_id="wikimedia_image")  # route map
+    add_image("P242", priority=2, url_id="wikimedia_image")  # locator map
+    add_image("P154", priority=3, url_id="wikimedia_image")  # logo
+    add_image("P18", priority=4, url_id="wikimedia_image")  # image
+    add_image("P41", priority=5, url_id="wikimedia_image")  # flag
+    add_image("P2716", priority=6, url_id="wikimedia_image")  # collage
+    add_image("P2910", priority=7, url_id="wikimedia_image")  # icon
+
+    return attributes
+
+
+def get_label_for_entity(entity_id: str, language: str) -> str:
+    # only import properties locally to prevent cyclic import when initializing WIKIDATA_PROPERTIES
+    from searx.data import WIKIDATA_PROPERTIES  # pylint: disable=import-outside-toplevel
+
+    property_name = WIKIDATA_PROPERTIES.get(entity_id)
+    if property_name is None:
+        return entity_id
+
+    if isinstance(property_name, str):
+        return property_name
+
+    if name := property_name.get(language):
+        return name
+
+    if name := property_name.get(language.split("-")[0]):
+        return name
+
+    if name := property_name.get("en"):
+        return name
+
+    return entity_id

searx/wikidata_units.py

@@ -11,7 +11,7 @@ __all__ = ["convert_from_si", "convert_to_si", "symbol_to_si"]
 import collections
 
 from searx import data
-from searx.engines import wikidata
+from searx.wikidata import send_wikidata_query
 
 
 class Beaufort:
@@ -142,7 +142,6 @@ def units_by_si_name(si_name):
 
     # build the catalog ..
     for item in symbol_to_si():
-
         item_si_name = item[pos_si_name]
         item_symbol = item[pos_symbol]
 
@@ -266,14 +265,13 @@ ORDER BY ?item DESC(?rank) ?symbol
 """
 
 
-def fetch_units():
+def fetch_units() -> dict[str, data.WikiDataUnitType]:
     """Fetch units from Wikidata.  Function is used to update persistence of
     :py:obj:`searx.data.WIKIDATA_UNITS`."""
 
     results = collections.OrderedDict()
-    response = wikidata.send_wikidata_query(SARQL_REQUEST)
+    response = send_wikidata_query(SARQL_REQUEST)
     for unit in response['results']['bindings']:
-
         symbol = unit['symbol']['value']
         name = unit['item']['value'].rsplit('/', 1)[1]
         si_name = unit.get('tosiUnit', {}).get('value', '')

searxng_extra/update/update_ahmia_blacklist.py

@@ -8,6 +8,7 @@ Output file: :origin:`searx/data/ahmia_blacklist.txt` (:origin:`CI Update data
 .. _Ahmia's blacklist: https://ahmia.fi/blacklist/
 
 """
+
 # pylint: disable=use-dict-literal
 
 import requests

searxng_extra/update/update_currencies.py

@@ -16,6 +16,7 @@ import json
 from searx.locales import LOCALE_NAMES, locales_initialize
 from searx.engines import wikidata, set_loggers
 from searx.data.currencies import CurrenciesDB
+from searx.wikidata import send_wikidata_query
 
 set_loggers(wikidata, 'wikidata')
 locales_initialize()
@@ -90,7 +91,7 @@ def add_currency_label(db, label, iso4217, language):
 
 
 def wikidata_request_result_iterator(request):
-    result = wikidata.send_wikidata_query(request.replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL), timeout=20)
+    result = send_wikidata_query(request.replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL), timeout=20)
     if result is not None:
         yield from result['results']['bindings']
 

searxng_extra/update/update_engine_descriptions.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Fetch website description from websites and from
-:origin:`searx/engines/wikidata.py` engine.
+:origin:`searx/wikidata.py`.
 
 Output file: :origin:`searx/data/engine_descriptions.json`.
 
@@ -17,6 +17,7 @@ from lxml.html import fromstring
 
 import searx.engines
 from searx.engines import wikidata, set_loggers
+from searx.wikidata import send_wikidata_query
 from searx.utils import extract_text
 from searx.locales import LOCALE_NAMES, locales_initialize, match_locale
 from searx import searx_dir
@@ -200,7 +201,6 @@ def initialize():
 
     locale2lang = {"nl-BE": "nl"}
     for sxng_ui_lang in LOCALE_NAMES:
-
         sxng_ui_alias = locale2lang.get(sxng_ui_lang, sxng_ui_lang)
         wiki_lang = None
 
@@ -225,7 +225,7 @@ def initialize():
 def fetch_wikidata_descriptions():
     print("Fetching wikidata descriptions")
     searx.network.set_timeout_for_thread(60)
-    result = wikidata.send_wikidata_query(
+    result = send_wikidata_query(
         SPARQL_DESCRIPTION.replace("%IDS%", IDS).replace("%LANGUAGES_SPARQL%", LANGUAGES_SPARQL)
     )
     if not result:
@@ -249,7 +249,7 @@ def fetch_wikidata_descriptions():
 
 def fetch_wikipedia_descriptions():
     print("Fetching wikipedia descriptions")
-    result = wikidata.send_wikidata_query(
+    result = send_wikidata_query(
         SPARQL_WIKIPEDIA_ARTICLE.replace("%IDS%", IDS).replace("%LANGUAGES_SPARQL%", LANGUAGES_SPARQL)
     )
     if not result:
@@ -307,7 +307,6 @@ def fetch_website_description(engine_name: str, website: str):
     previous_count: int = 0
 
     for lang in languages:
-
         if lang in descriptions[engine_name]:
             continue
 

searxng_extra/update/update_engine_traits.py

@@ -12,6 +12,7 @@ The script :origin:`searxng_extra/update/update_engine_traits.py` is called in
 the :origin:`CI Update data ... <.github/workflows/data-update.yml>`
 
 """
+
 # pylint: disable=invalid-name
 
 import typing as t

searxng_extra/update/update_firefox_version.py

@@ -6,6 +6,7 @@ Output file: :origin:`searx/data/useragents.json` (:origin:`CI Update data ...
 <.github/workflows/data-update.yml>`).
 
 """
+
 # pylint: disable=use-dict-literal
 
 import json

searxng_extra/update/update_locales.py

@@ -6,6 +6,7 @@
 - :py:obj:`searx.locales.RTL_LOCALES`
 - :py:obj:`searx.locales.LOCALE_NAMES`
 """
+
 # pylint: disable=invalid-name
 
 from typing import Set

searxng_extra/update/update_osm_keys_tags.py

@@ -50,6 +50,7 @@ from searx.engines import wikidata, set_loggers
 from searx.sxng_locales import sxng_locales
 from searx.engines.openstreetmap import get_key_rank, VALUE_TO_LINK
 from searx.data import data_dir
+from searx.wikidata import send_wikidata_query
 
 DATA_FILE = data_dir / 'osm_keys_tags.json'
 
@@ -102,7 +103,7 @@ def get_preset_keys():
 
 def get_keys():
     results = get_preset_keys()
-    response = wikidata.send_wikidata_query(SPARQL_KEYS_REQUEST)
+    response = send_wikidata_query(SPARQL_KEYS_REQUEST)
 
     for key in response['results']['bindings']:
         keys = key['key']['value'].split(':')[1:]
@@ -148,7 +149,7 @@ def get_keys():
 
 def get_tags():
     results = collections.OrderedDict()
-    response = wikidata.send_wikidata_query(SPARQL_TAGS_REQUEST)
+    response = send_wikidata_query(SPARQL_TAGS_REQUEST)
     for tag in response['results']['bindings']:
         tag_names = tag['tag']['value'].split(':')[1].split('=')
         if len(tag_names) == 2:
@@ -204,7 +205,6 @@ def optimize_keys(data):
 
 
 if __name__ == '__main__':
-
     set_timeout_for_thread(60)
     result = {
         'keys': optimize_keys(get_keys()),

searxng_extra/update/update_pygments.py

@@ -5,6 +5,7 @@
 Call this script after each upgrade of pygments
 
 """
+
 # pylint: disable=too-few-public-methods
 
 from pathlib import Path

searxng_extra/update/update_wikidata.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Fetch units and property names from :origin:`searx/engines/wikidata.py` engine.
+
+Output files: (:origin:`CI Update data <.github/workflows/data-update.yml>`).
+- :origin:`searx/data/wikidata_units.json`
+- :origin:`searx/data/wikidata_properties.json`
+"""
+
+import json
+
+from searx.engines import wikidata, set_loggers
+from searx.data import data_dir
+from searx.wikidata_properties import fetch_properties
+from searx.wikidata_units import fetch_units
+
+UNITS_DATA_FILE = data_dir / 'wikidata_units.json'
+PROPERTIES_DATA_FILE = data_dir / 'wikidata_properties.json'
+set_loggers(wikidata, 'wikidata')
+
+
+if __name__ == '__main__':
+    units = fetch_units()
+    with UNITS_DATA_FILE.open('w', encoding="utf8") as f:
+        json.dump(units, f, indent=4, sort_keys=True, ensure_ascii=False)
+
+    properties = fetch_properties(units)
+    with PROPERTIES_DATA_FILE.open('w', encoding="utf8") as f:
+        json.dump(properties, f, indent=4, sort_keys=True, ensure_ascii=False)

searxng_extra/update/update_wikidata_units.py

@@ -1,22 +0,0 @@
-#!/usr/bin/env python
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""Fetch units from :origin:`searx/engines/wikidata.py` engine.
-
-Output file: :origin:`searx/data/wikidata_units.json` (:origin:`CI Update data
-...  <.github/workflows/data-update.yml>`).
-
-"""
-
-import json
-
-from searx.engines import wikidata, set_loggers
-from searx.data import data_dir
-from searx.wikidata_units import fetch_units
-
-DATA_FILE = data_dir / 'wikidata_units.json'
-set_loggers(wikidata, 'wikidata')
-
-
-if __name__ == '__main__':
-    with DATA_FILE.open('w', encoding="utf8") as f:
-        json.dump(fetch_units(), f, indent=4, sort_keys=True, ensure_ascii=False)

tests/__init__.py

@@ -5,7 +5,6 @@ import pathlib
 import os
 import aiounittest
 
-
 os.environ.pop('SEARXNG_SETTINGS_PATH', None)
 os.environ['SEARXNG_DISABLE_ETC_SETTINGS'] = '1'
 

tests/unit/test_external_bangs.py

@@ -11,7 +11,6 @@ from searx.external_bang import (
 from searx.search.models import EngineRef, SearchQuery
 from tests import SearxTestCase
 
-
 TEST_DB = {
     'trie': {
         'exam': {

tests/unit/test_js_variable_to_python.py

@@ -7,6 +7,7 @@ https://github.com/Nykakin/chompjs/blob/c1501b5cd82c0044539875331745b820e7bfd067
 
 The commented-out tests are not yet supported by the current implementation.
 """
+
 # pylint: disable=missing-class-docstring, invalid-name
 
 import math

tests/unit/test_preferences.py

@@ -21,7 +21,6 @@ from searx.preferences import Preferences
 from tests import SearxTestCase
 from .test_plugins import PluginMock
 
-
 locales_initialize()
 favicons.init()
 

tests/unit/test_search.py

@@ -8,7 +8,6 @@ from searx.search.models import SearchQuery, EngineRef
 from searx import settings
 from tests import SearxTestCase
 
-
 SAFESEARCH = 0
 PAGENO = 1
 PUBLIC_ENGINE_NAME = "dummy engine"  # from the ./settings/test_settings.yml

utils/lib_sxng_data.sh

@@ -26,7 +26,8 @@ data.all() {
         build_msg DATA "update searx/data/ahmia_blacklist.txt"
         python searxng_extra/update/update_ahmia_blacklist.py
         build_msg DATA "update searx/data/wikidata_units.json"
-        python searxng_extra/update/update_wikidata_units.py
+        build_msg DATA "update searx/data/wikidata_properties.json"
+        python searxng_extra/update/update_wikidata.py
         build_msg DATA "update searx/data/currencies.json"
         python searxng_extra/update/update_currencies.py
         build_msg DATA "update searx/data/external_bangs.json"