mirror of
https://github.com/searxng/searxng.git
synced 2026-07-18 22:11:23 +00:00
949 lines
136 KiB
HTML
949 lines
136 KiB
HTML
<!DOCTYPE html>
|
|
|
|
<html lang="en" data-content_root="../../../">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<title>searx.engines.wikidata — SearXNG Documentation (2026.5.6+a9909c497)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
|
<script src="../../../_static/documentation_options.js?v=248240e6"></script>
|
|
<script src="../../../_static/doctools.js?v=fd6eb6e6"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=6ffebe34"></script>
|
|
<script data-project="searxng" data-version="2026.5.6+a9909c497" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
</head><body>
|
|
<div class="related" role="navigation" aria-label="Related">
|
|
<h3>Navigation</h3>
|
|
<ul>
|
|
<li class="right" style="margin-right: 10px">
|
|
<a href="../../../genindex.html" title="General Index"
|
|
accesskey="I">index</a></li>
|
|
<li class="right" >
|
|
<a href="../../../py-modindex.html" title="Python Module Index"
|
|
>modules</a> |</li>
|
|
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2026.5.6+a9909c497)</a> »</li>
|
|
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
|
|
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> »</li>
|
|
<li class="nav-item nav-item-this"><a href="">searx.engines.wikidata</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.wikidata</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="sd">"""This module implements the Wikidata engine. Some implementations are shared</span>
|
|
<span class="sd">from :ref:`wikipedia engine`.</span>
|
|
|
|
<span class="sd">"""</span>
|
|
<span class="c1"># pylint: disable=missing-class-docstring</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">t</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">hashlib</span><span class="w"> </span><span class="kn">import</span> <span class="n">md5</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">urllib.parse</span><span class="w"> </span><span class="kn">import</span> <span class="n">urlencode</span><span class="p">,</span> <span class="n">unquote</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">json</span><span class="w"> </span><span class="kn">import</span> <span class="n">loads</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">dateutil.parser</span><span class="w"> </span><span class="kn">import</span> <span class="n">isoparse</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">babel.dates</span><span class="w"> </span><span class="kn">import</span> <span class="n">format_datetime</span><span class="p">,</span> <span class="n">format_date</span><span class="p">,</span> <span class="n">format_time</span><span class="p">,</span> <span class="n">get_datetime_format</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">WIKIDATA_UNITS</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </span><span class="kn">import</span> <span class="n">post</span><span class="p">,</span> <span class="n">get</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">searxng_useragent</span><span class="p">,</span> <span class="n">get_string_replaces_function</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.external_urls</span><span class="w"> </span><span class="kn">import</span> <span class="n">get_external_url</span><span class="p">,</span> <span class="n">get_earth_coordinates_url</span><span class="p">,</span> <span class="n">area_to_osm_zoom</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.engines.wikipedia</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
|
|
<span class="n">fetch_wikimedia_traits</span><span class="p">,</span>
|
|
<span class="n">get_wiki_params</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.enginelib.traits</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineTraits</span>
|
|
|
|
<span class="k">if</span> <span class="n">t</span><span class="o">.</span><span class="n">TYPE_CHECKING</span><span class="p">:</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.extended_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">SXNG_Response</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.search.processors</span><span class="w"> </span><span class="kn">import</span> <span class="n">OnlineParams</span>
|
|
|
|
|
|
<span class="c1"># about</span>
|
|
<span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s1">'https://wikidata.org/'</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q2013'</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://query.wikidata.org/'</span><span class="p">,</span>
|
|
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
|
|
<span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"results"</span><span class="p">:</span> <span class="s1">'JSON'</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">display_type</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"infobox"</span><span class="p">]</span>
|
|
<span class="sd">"""A list of display types composed from ``infobox`` and ``list``. The latter</span>
|
|
<span class="sd">one will add a hit to the result list. The first one will show a hit in the</span>
|
|
<span class="sd">info box. Both values can be set, or one of the two can be set."""</span>
|
|
|
|
|
|
<span class="c1"># SPARQL</span>
|
|
<span class="n">SPARQL_ENDPOINT_URL</span> <span class="o">=</span> <span class="s2">"https://query.wikidata.org/sparql"</span>
|
|
<span class="n">SPARQL_EXPLAIN_URL</span> <span class="o">=</span> <span class="s2">"https://query.wikidata.org/bigdata/namespace/wdq/sparql?explain"</span>
|
|
<span class="n">WIKIDATA_PROPERTIES</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span> <span class="o">|</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">],</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"P434"</span><span class="p">:</span> <span class="s2">"MusicBrainz"</span><span class="p">,</span>
|
|
<span class="s2">"P435"</span><span class="p">:</span> <span class="s2">"MusicBrainz"</span><span class="p">,</span>
|
|
<span class="s2">"P436"</span><span class="p">:</span> <span class="s2">"MusicBrainz"</span><span class="p">,</span>
|
|
<span class="s2">"P966"</span><span class="p">:</span> <span class="s2">"MusicBrainz"</span><span class="p">,</span>
|
|
<span class="s2">"P345"</span><span class="p">:</span> <span class="s2">"IMDb"</span><span class="p">,</span>
|
|
<span class="s2">"P2397"</span><span class="p">:</span> <span class="s2">"YouTube"</span><span class="p">,</span>
|
|
<span class="s2">"P1651"</span><span class="p">:</span> <span class="s2">"YouTube"</span><span class="p">,</span>
|
|
<span class="s2">"P2002"</span><span class="p">:</span> <span class="s2">"Twitter"</span><span class="p">,</span>
|
|
<span class="s2">"P2013"</span><span class="p">:</span> <span class="s2">"Facebook"</span><span class="p">,</span>
|
|
<span class="s2">"P2003"</span><span class="p">:</span> <span class="s2">"Instagram"</span><span class="p">,</span>
|
|
<span class="s2">"P4033"</span><span class="p">:</span> <span class="s2">"Mastodon"</span><span class="p">,</span>
|
|
<span class="s2">"P11947"</span><span class="p">:</span> <span class="s2">"Lemmy"</span><span class="p">,</span>
|
|
<span class="s2">"P12622"</span><span class="p">:</span> <span class="s2">"PeerTube"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="c1"># SERVICE wikibase:mwapi : https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual/MWAPI</span>
|
|
<span class="c1"># SERVICE wikibase:label: https://en.wikibooks.org/wiki/SPARQL/SERVICE_-_Label#Manual_Label_SERVICE</span>
|
|
<span class="c1"># https://en.wikibooks.org/wiki/SPARQL/WIKIDATA_Precision,_Units_and_Coordinates</span>
|
|
<span class="c1"># https://www.mediawiki.org/wiki/Wikibase/Indexing/RDF_Dump_Format#Data_model</span>
|
|
<span class="c1"># optimization:</span>
|
|
<span class="c1"># * https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service/query_optimization</span>
|
|
<span class="c1"># * https://github.com/blazegraph/database/wiki/QueryHints</span>
|
|
<span class="n">QUERY_TEMPLATE</span> <span class="o">=</span> <span class="s2">"""</span>
|
|
<span class="s2">SELECT ?item ?itemLabel ?itemDescription ?lat ?long %SELECT%</span>
|
|
<span class="s2">WHERE</span>
|
|
<span class="s2">{</span>
|
|
<span class="s2"> SERVICE wikibase:mwapi {</span>
|
|
<span class="s2"> bd:serviceParam wikibase:endpoint "www.wikidata.org";</span>
|
|
<span class="s2"> wikibase:api "EntitySearch";</span>
|
|
<span class="s2"> wikibase:limit 1;</span>
|
|
<span class="s2"> mwapi:search "%QUERY%";</span>
|
|
<span class="s2"> mwapi:language "%LANGUAGE%".</span>
|
|
<span class="s2"> ?item wikibase:apiOutputItem mwapi:item.</span>
|
|
<span class="s2"> }</span>
|
|
<span class="s2"> hint:Prior hint:runFirst "true".</span>
|
|
|
|
<span class="s2"> %WHERE%</span>
|
|
|
|
<span class="s2"> SERVICE wikibase:label {</span>
|
|
<span class="s2"> bd:serviceParam wikibase:language "%LANGUAGE%,en".</span>
|
|
<span class="s2"> ?item rdfs:label ?itemLabel .</span>
|
|
<span class="s2"> ?item schema:description ?itemDescription .</span>
|
|
<span class="s2"> %WIKIBASE_LABELS%</span>
|
|
<span class="s2"> }</span>
|
|
|
|
<span class="s2">}</span>
|
|
<span class="s2">GROUP BY ?item ?itemLabel ?itemDescription ?lat ?long </span><span class="si">%G</span><span class="s2">ROUP_BY%</span>
|
|
<span class="s2">"""</span>
|
|
|
|
<span class="c1"># Get the calendar names and the property names</span>
|
|
<span class="n">QUERY_PROPERTY_NAMES</span> <span class="o">=</span> <span class="s2">"""</span>
|
|
<span class="s2">SELECT ?item ?name</span>
|
|
<span class="s2">WHERE {</span>
|
|
<span class="s2"> {</span>
|
|
<span class="s2"> SELECT ?item</span>
|
|
<span class="s2"> WHERE { ?item wdt:P279* wd:Q12132 }</span>
|
|
<span class="s2"> } UNION {</span>
|
|
<span class="s2"> VALUES ?item { %ATTRIBUTES% }</span>
|
|
<span class="s2"> }</span>
|
|
<span class="s2"> OPTIONAL { ?item rdfs:label ?name. }</span>
|
|
<span class="s2">}</span>
|
|
<span class="s2">"""</span>
|
|
|
|
<span class="c1"># see the property "dummy value" of https://www.wikidata.org/wiki/Q2013 (Wikidata)</span>
|
|
<span class="c1"># hard coded here to avoid to an additional SPARQL request when the server starts</span>
|
|
<span class="n">DUMMY_ENTITY_URLS</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span>
|
|
<span class="s2">"http://www.wikidata.org/entity/"</span> <span class="o">+</span> <span class="n">wid</span> <span class="k">for</span> <span class="n">wid</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">"Q4115189"</span><span class="p">,</span> <span class="s2">"Q13406268"</span><span class="p">,</span> <span class="s2">"Q15397819"</span><span class="p">,</span> <span class="s2">"Q17339402"</span><span class="p">)</span>
|
|
<span class="p">)</span>
|
|
|
|
|
|
<span class="c1"># https://www.w3.org/TR/sparql11-query/#rSTRING_LITERAL1</span>
|
|
<span class="c1"># https://lists.w3.org/Archives/Public/public-rdf-dawg/2011OctDec/0175.html</span>
|
|
<span class="n">sparql_string_escape</span> <span class="o">=</span> <span class="n">get_string_replaces_function</span><span class="p">(</span>
|
|
<span class="c1"># fmt: off</span>
|
|
<span class="p">{</span>
|
|
<span class="s2">"</span><span class="se">\t</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\t</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\n</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\r</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\r</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\b</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\b</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\f</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\f</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\"</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\"</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\'</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\'</span><span class="s2">"</span><span class="p">,</span>
|
|
<span class="s2">"</span><span class="se">\\</span><span class="s2">"</span><span class="p">:</span> <span class="s2">"</span><span class="se">\\\\</span><span class="s2">"</span>
|
|
<span class="p">}</span>
|
|
<span class="c1"># fmt: on</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="n">replace_http_by_https</span> <span class="o">=</span> <span class="n">get_string_replaces_function</span><span class="p">({</span><span class="s2">"http:"</span><span class="p">:</span> <span class="s2">"https:"</span><span class="p">})</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDAttribute</span><span class="p">:</span>
|
|
<span class="vm">__slots__</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"name"</span><span class="p">,)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">name</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"(group_concat(distinct ?</span><span class="si">{name}</span><span class="s2">;separator=', ') as ?</span><span class="si">{name}</span><span class="s2">s)"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">get_label_for_entity</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"OPTIONAL { ?item wdt:</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2"> . }"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_wikibase_label</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">""</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_group_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">""</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">],</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span> <span class="c1"># pylint: disable=unused-argument</span>
|
|
<span class="k">return</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"s"</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"<"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span> <span class="o">+</span> <span class="s2">":"</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">">"</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDAmountAttribute</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"?</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2">Unit"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">""" OPTIONAL { ?item p:</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2">Node .</span>
|
|
<span class="s2"> ?</span><span class="si">{name}</span><span class="s2">Node rdf:type wikibase:BestRank ; ps:</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2"> .</span>
|
|
<span class="s2"> OPTIONAL { ?</span><span class="si">{name}</span><span class="s2">Node psv:</span><span class="si">{name}</span><span class="s2">/wikibase:quantityUnit ?</span><span class="si">{name}</span><span class="s2">Unit. } }"""</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
|
|
<span class="s1">'</span><span class="si">{name}</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_group_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_select</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">],</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">unit</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Unit"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">unit</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">unit</span> <span class="o">=</span> <span class="n">unit</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"http://www.wikidata.org/entity/"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">value</span> <span class="o">+</span> <span class="s2">" "</span> <span class="o">+</span> <span class="n">get_label_for_entity</span><span class="p">(</span><span class="n">unit</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">value</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDArticle</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="s2">"wikipedia"</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">language</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">language</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="n">kwargs</span> <span class="ow">or</span> <span class="p">{}</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="c1"># language parameter is ignored</span>
|
|
<span class="k">return</span> <span class="s2">"Wikipedia (</span><span class="si">{language}</span><span class="s2">)"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{language}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">language</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"?article</span><span class="si">{language}</span><span class="s2"> ?articleName</span><span class="si">{language}</span><span class="s2">"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{language}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">language</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"""OPTIONAL { ?article</span><span class="si">{language}</span><span class="s2"> schema:about ?item ;</span>
|
|
<span class="s2"> schema:inLanguage "</span><span class="si">{language}</span><span class="s2">" ;</span>
|
|
<span class="s2"> schema:isPartOf <https://</span><span class="si">{language}</span><span class="s2">.wikipedia.org/> ;</span>
|
|
<span class="s2"> schema:name ?articleName</span><span class="si">{language}</span><span class="s2"> . }"""</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
|
|
<span class="s1">'</span><span class="si">{language}</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">language</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_group_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_select</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">key</span> <span class="o">=</span> <span class="s2">"article</span><span class="si">{language}</span><span class="s2">"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{language}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">language</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDLabelAttribute</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"(group_concat(distinct ?</span><span class="si">{name}</span><span class="s2">Label;separator=', ') as ?</span><span class="si">{name}</span><span class="s2">Labels)"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"OPTIONAL { ?item wdt:</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2"> . }"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_wikibase_label</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"?</span><span class="si">{name}</span><span class="s2"> rdfs:label ?</span><span class="si">{name}</span><span class="s2">Label ."</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">language</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Labels"</span><span class="p">)</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDURLAttribute</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
|
|
<span class="n">HTTP_WIKIMEDIA_IMAGE</span> <span class="o">=</span> <span class="s2">"http://commons.wikimedia.org/wiki/Special:FilePath/"</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span>
|
|
<span class="bp">self</span><span class="p">,</span>
|
|
<span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
|
|
<span class="n">url_id</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="n">url_path_prefix</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="n">kwargs</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""</span>
|
|
<span class="sd"> :param url_id: ID matching one key in ``external_urls.json`` for</span>
|
|
<span class="sd"> converting IDs to full URLs.</span>
|
|
|
|
<span class="sd"> :param url_path_prefix: Path prefix if the values are of format</span>
|
|
<span class="sd"> ``account@domain``. If provided, value are rewritten to</span>
|
|
<span class="sd"> ``https://<domain><url_path_prefix><account>``. For example::</span>
|
|
|
|
<span class="sd"> WDURLAttribute('P4033', url_path_prefix='/@')</span>
|
|
|
|
<span class="sd"> Adds Property `P4033 <https://www.wikidata.org/wiki/Property:P4033>`_</span>
|
|
<span class="sd"> to the wikidata query. This field might return for example</span>
|
|
<span class="sd"> ``libreoffice@fosstodon.org`` and the URL built from this is then:</span>
|
|
|
|
<span class="sd"> - account: ``libreoffice``</span>
|
|
<span class="sd"> - domain: ``fosstodon.org``</span>
|
|
<span class="sd"> - result url: https://fosstodon.org/@libreoffice</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">url_id</span> <span class="o">=</span> <span class="n">url_id</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">url_path_prefix</span> <span class="o">=</span> <span class="n">url_path_prefix</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span> <span class="o">=</span> <span class="n">kwargs</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"s"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">value</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">","</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">url_id</span><span class="p">:</span>
|
|
<span class="n">url_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">url_id</span>
|
|
<span class="k">if</span> <span class="n">value</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">WDURLAttribute</span><span class="o">.</span><span class="n">HTTP_WIKIMEDIA_IMAGE</span><span class="p">):</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">value</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">WDURLAttribute</span><span class="o">.</span><span class="n">HTTP_WIKIMEDIA_IMAGE</span><span class="p">)</span> <span class="p">:]</span>
|
|
<span class="n">url_id</span> <span class="o">=</span> <span class="s2">"wikimedia_image"</span>
|
|
<span class="k">return</span> <span class="n">get_external_url</span><span class="p">(</span><span class="n">url_id</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">url_path_prefix</span><span class="p">:</span>
|
|
<span class="p">[</span><span class="n">account</span><span class="p">,</span> <span class="n">domain</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s2">"@ "</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">value</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">"@"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)]</span>
|
|
<span class="k">return</span> <span class="sa">f</span><span class="s2">"https://</span><span class="si">{</span><span class="n">domain</span><span class="si">}{</span><span class="bp">self</span><span class="o">.</span><span class="n">url_path_prefix</span><span class="si">}{</span><span class="n">account</span><span class="si">}</span><span class="s2">"</span>
|
|
|
|
<span class="k">return</span> <span class="n">value</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDGeoAttribute</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_label</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"OpenStreetMap"</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"?</span><span class="si">{name}</span><span class="s2">Lat ?</span><span class="si">{name}</span><span class="s2">Long"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"""OPTIONAL { ?item p:</span><span class="si">{name}</span><span class="s2">/psv:</span><span class="si">{name}</span><span class="s2"> [</span>
|
|
<span class="s2"> wikibase:geoLatitude ?</span><span class="si">{name}</span><span class="s2">Lat ;</span>
|
|
<span class="s2"> wikibase:geoLongitude ?</span><span class="si">{name}</span><span class="s2">Long ] }"""</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
|
|
<span class="s1">'</span><span class="si">{name}</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_group_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_select</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">latitude</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Lat"</span><span class="p">)</span>
|
|
<span class="n">longitude</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Long"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">latitude</span> <span class="ow">and</span> <span class="n">longitude</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">latitude</span> <span class="o">+</span> <span class="s2">" "</span> <span class="o">+</span> <span class="n">longitude</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_geo_url</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">osm_zoom</span><span class="o">=</span><span class="mi">19</span><span class="p">):</span>
|
|
<span class="n">latitude</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Lat"</span><span class="p">)</span>
|
|
<span class="n">longitude</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"Long"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">latitude</span> <span class="ow">and</span> <span class="n">longitude</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">get_earth_coordinates_url</span><span class="p">(</span><span class="n">latitude</span><span class="p">,</span> <span class="n">longitude</span><span class="p">,</span> <span class="n">osm_zoom</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDImageAttribute</span><span class="p">(</span><span class="n">WDURLAttribute</span><span class="p">):</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">100</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">url_id</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">priority</span> <span class="o">=</span> <span class="n">priority</span>
|
|
|
|
|
|
<span class="k">class</span><span class="w"> </span><span class="nc">WDDateAttribute</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">):</span>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_select</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="s2">"?</span><span class="si">{name}</span><span class="s2"> ?</span><span class="si">{name}</span><span class="s2">timePrecision ?</span><span class="si">{name}</span><span class="s2">timeZone ?</span><span class="si">{name}</span><span class="s2">timeCalendar"</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{name}</span><span class="s2">"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_where</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="c1"># To remove duplicate, add</span>
|
|
<span class="c1"># FILTER NOT EXISTS { ?item p:{name}/psv:{name}/wikibase:timeValue ?{name}bis FILTER (?{name}bis < ?{name}) }</span>
|
|
<span class="c1"># this filter is too slow, so the response function ignore duplicate results</span>
|
|
<span class="c1"># (see the seen_entities variable)</span>
|
|
<span class="k">return</span> <span class="s2">"""OPTIONAL { ?item p:</span><span class="si">{name}</span><span class="s2">/psv:</span><span class="si">{name}</span><span class="s2"> [</span>
|
|
<span class="s2"> wikibase:timeValue ?</span><span class="si">{name}</span><span class="s2"> ;</span>
|
|
<span class="s2"> wikibase:timePrecision ?</span><span class="si">{name}</span><span class="s2">timePrecision ;</span>
|
|
<span class="s2"> wikibase:timeTimezone ?</span><span class="si">{name}</span><span class="s2">timeZone ;</span>
|
|
<span class="s2"> wikibase:timeCalendarModel ?</span><span class="si">{name}</span><span class="s2">timeCalendar ] . }</span>
|
|
<span class="s2"> hint:Prior hint:rangeSafe true;"""</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span>
|
|
<span class="s1">'</span><span class="si">{name}</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_group_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_select</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_8</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span> <span class="c1"># pylint: disable=unused-argument</span>
|
|
<span class="c1"># precision: less than a year</span>
|
|
<span class="k">return</span> <span class="n">value</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_9</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">year</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="c1"># precision: year</span>
|
|
<span class="k">if</span> <span class="n">year</span> <span class="o"><</span> <span class="mi">1584</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">year</span> <span class="o"><</span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">year</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">year</span><span class="p">)</span>
|
|
<span class="n">timestamp</span> <span class="o">=</span> <span class="n">isoparse</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">format_date</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="nb">format</span><span class="o">=</span><span class="s2">"yyyy"</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_10</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="c1"># precision: month</span>
|
|
<span class="n">timestamp</span> <span class="o">=</span> <span class="n">isoparse</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">format_date</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="nb">format</span><span class="o">=</span><span class="s2">"MMMM y"</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_11</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="c1"># precision: day</span>
|
|
<span class="n">timestamp</span> <span class="o">=</span> <span class="n">isoparse</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">format_date</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="nb">format</span><span class="o">=</span><span class="s2">"full"</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_13</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">timestamp</span> <span class="o">=</span> <span class="n">isoparse</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="c1"># precision: minute</span>
|
|
<span class="k">return</span> <span class="p">(</span>
|
|
<span class="n">get_datetime_format</span><span class="p">(</span><span class="nb">format</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">)</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"'"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{0}</span><span class="s2">"</span><span class="p">,</span> <span class="n">format_time</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="s2">"full"</span><span class="p">,</span> <span class="n">tzinfo</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">{1}</span><span class="s2">"</span><span class="p">,</span> <span class="n">format_date</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="s2">"short"</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">))</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">format_14</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">locale</span><span class="p">):</span>
|
|
<span class="c1"># precision: second.</span>
|
|
<span class="k">return</span> <span class="n">format_datetime</span><span class="p">(</span><span class="n">isoparse</span><span class="p">(</span><span class="n">value</span><span class="p">),</span> <span class="nb">format</span><span class="o">=</span><span class="s2">"full"</span><span class="p">,</span> <span class="n">locale</span><span class="o">=</span><span class="n">locale</span><span class="p">)</span>
|
|
|
|
<span class="n">DATE_FORMAT</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"0"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">1000000000</span><span class="p">),</span>
|
|
<span class="s2">"1"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">100000000</span><span class="p">),</span>
|
|
<span class="s2">"2"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">10000000</span><span class="p">),</span>
|
|
<span class="s2">"3"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">1000000</span><span class="p">),</span>
|
|
<span class="s2">"4"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">100000</span><span class="p">),</span>
|
|
<span class="s2">"5"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">10000</span><span class="p">),</span>
|
|
<span class="s2">"6"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">1000</span><span class="p">),</span>
|
|
<span class="s2">"7"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">100</span><span class="p">),</span>
|
|
<span class="s2">"8"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_8"</span><span class="p">,</span> <span class="mi">10</span><span class="p">),</span>
|
|
<span class="s2">"9"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_9"</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="c1"># year</span>
|
|
<span class="s2">"10"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_10"</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span> <span class="c1"># month</span>
|
|
<span class="s2">"11"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_11"</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="c1"># day</span>
|
|
<span class="s2">"12"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_13"</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="c1"># hour (not supported by babel, display minute)</span>
|
|
<span class="s2">"13"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_13"</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="c1"># minute</span>
|
|
<span class="s2">"14"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"format_14"</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="c1"># second</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_str</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">result</span><span class="p">,</span> <span class="n">language</span><span class="p">):</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">value</span> <span class="o">==</span> <span class="s2">""</span> <span class="ow">or</span> <span class="n">value</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
<span class="n">precision</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">+</span> <span class="s2">"timePrecision"</span><span class="p">)</span>
|
|
<span class="n">date_format</span> <span class="o">=</span> <span class="n">WDDateAttribute</span><span class="o">.</span><span class="n">DATE_FORMAT</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">precision</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">date_format</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">format_method</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">date_format</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
|
<span class="n">precision</span> <span class="o">=</span> <span class="n">date_format</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">precision</span> <span class="o">>=</span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="n">_t</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"-"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">value</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"-"</span><span class="p">):</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="s2">"-"</span> <span class="o">+</span> <span class="n">_t</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">_t</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">return</span> <span class="n">format_method</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
<span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
|
|
<span class="k">return</span> <span class="n">value</span>
|
|
<span class="k">return</span> <span class="n">value</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_headers</span><span class="p">()</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
|
|
<span class="c1"># user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits</span>
|
|
<span class="k">return</span> <span class="p">{</span><span class="s2">"Accept"</span><span class="p">:</span> <span class="s2">"application/sparql-results+json"</span><span class="p">,</span> <span class="s2">"User-Agent"</span><span class="p">:</span> <span class="n">searxng_useragent</span><span class="p">()}</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_label_for_entity</span><span class="p">(</span><span class="n">entity_id</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">WIKIDATA_PROPERTIES</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">entity_id</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">WIKIDATA_PROPERTIES</span><span class="o">.</span><span class="n">get</span><span class="p">((</span><span class="n">entity_id</span><span class="p">,</span> <span class="n">language</span><span class="p">))</span>
|
|
<span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">WIKIDATA_PROPERTIES</span><span class="o">.</span><span class="n">get</span><span class="p">((</span><span class="n">entity_id</span><span class="p">,</span> <span class="n">language</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"-"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]))</span>
|
|
<span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">WIKIDATA_PROPERTIES</span><span class="o">.</span><span class="n">get</span><span class="p">((</span><span class="n">entity_id</span><span class="p">,</span> <span class="s2">"en"</span><span class="p">))</span>
|
|
<span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">entity_id</span>
|
|
<span class="k">return</span> <span class="n">name</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">send_wikidata_query</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s2">"GET"</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]:</span>
|
|
<span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="s2">"GET"</span><span class="p">:</span>
|
|
<span class="c1"># query will be cached by wikidata</span>
|
|
<span class="n">http_response</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="n">SPARQL_ENDPOINT_URL</span> <span class="o">+</span> <span class="s2">"?"</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s2">"query"</span><span class="p">:</span> <span class="n">query</span><span class="p">}),</span> <span class="n">headers</span><span class="o">=</span><span class="n">get_headers</span><span class="p">(),</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="c1"># query won't be cached by wikidata</span>
|
|
<span class="n">http_response</span> <span class="o">=</span> <span class="n">post</span><span class="p">(</span><span class="n">SPARQL_ENDPOINT_URL</span><span class="p">,</span> <span class="n">data</span><span class="o">=</span><span class="p">{</span><span class="s2">"query"</span><span class="p">:</span> <span class="n">query</span><span class="p">},</span> <span class="n">headers</span><span class="o">=</span><span class="n">get_headers</span><span class="p">(),</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">http_response</span><span class="o">.</span><span class="n">status_code</span> <span class="o">!=</span> <span class="mi">200</span><span class="p">:</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"SPARQL endpoint error </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">http_response</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">decode</span><span class="p">())</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"request time </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">http_response</span><span class="o">.</span><span class="n">elapsed</span><span class="p">))</span>
|
|
<span class="n">http_response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
|
|
<span class="k">return</span> <span class="n">loads</span><span class="p">(</span><span class="n">http_response</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">decode</span><span class="p">())</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="s2">"OnlineParams"</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
|
|
|
<span class="n">attributes</span><span class="p">:</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">list</span><span class="p">[</span><span class="n">WDAttribute</span> <span class="o">|</span> <span class="n">WDAmountAttribute</span> <span class="o">|</span> <span class="n">WDLabelAttribute</span> <span class="o">|</span> <span class="n">WDImageAttribute</span><span class="p">]]</span>
|
|
<span class="n">eng_tag</span><span class="p">,</span> <span class="n">_wiki_netloc</span> <span class="o">=</span> <span class="n">get_wiki_params</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"searxng_locale"</span><span class="p">],</span> <span class="n">traits</span><span class="p">)</span>
|
|
<span class="n">query</span><span class="p">,</span> <span class="n">attributes</span> <span class="o">=</span> <span class="n">get_query</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">)</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"request --> language </span><span class="si">%s</span><span class="s2"> // len(attributes): </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">attributes</span><span class="p">))</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"method"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"POST"</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"url"</span><span class="p">]</span> <span class="o">=</span> <span class="n">SPARQL_ENDPOINT_URL</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"data"</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"query"</span><span class="p">:</span> <span class="n">query</span><span class="p">}</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"headers"</span><span class="p">]</span> <span class="o">=</span> <span class="n">get_headers</span><span class="p">()</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"language"</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_tag</span> <span class="c1"># type: ignore</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"attributes"</span><span class="p">]</span> <span class="o">=</span> <span class="n">attributes</span> <span class="c1"># type: ignore</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">:</span> <span class="s2">"SXNG_Response"</span><span class="p">)</span> <span class="o">-></span> <span class="nb">list</span><span class="p">[</span><span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]]:</span>
|
|
|
|
<span class="n">results</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">jsonresponse</span> <span class="o">=</span> <span class="n">loads</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">decode</span><span class="p">())</span>
|
|
|
|
<span class="n">language</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s2">"language"</span><span class="p">]</span> <span class="c1"># type: ignore</span>
|
|
<span class="n">attributes</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s2">"attributes"</span><span class="p">]</span> <span class="c1"># type: ignore</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"request --> language </span><span class="si">%s</span><span class="s2"> // len(attributes): </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">language</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">attributes</span><span class="p">))</span>
|
|
|
|
<span class="n">seen_entities</span><span class="p">:</span> <span class="nb">set</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">jsonresponse</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"results"</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"bindings"</span><span class="p">,</span> <span class="p">[]):</span>
|
|
<span class="n">attribute_result</span> <span class="o">=</span> <span class="p">{</span><span class="n">key</span><span class="p">:</span> <span class="n">value</span><span class="p">[</span><span class="s2">"value"</span><span class="p">]</span> <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">result</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
|
|
<span class="n">entity_url</span> <span class="o">=</span> <span class="n">attribute_result</span><span class="p">[</span><span class="s2">"item"</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="n">entity_url</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">seen_entities</span> <span class="ow">and</span> <span class="n">entity_url</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">DUMMY_ENTITY_URLS</span><span class="p">:</span>
|
|
<span class="n">seen_entities</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">entity_url</span><span class="p">)</span>
|
|
<span class="n">results</span> <span class="o">+=</span> <span class="n">get_results</span><span class="p">(</span><span class="n">attribute_result</span><span class="p">,</span> <span class="n">attributes</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"The SPARQL request returns duplicate entities: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">attribute_result</span><span class="p">))</span>
|
|
|
|
<span class="k">return</span> <span class="n">results</span>
|
|
|
|
|
|
<span class="n">_IMG_SRC_DEFAULT_URL_PREFIX</span> <span class="o">=</span> <span class="s2">"https://commons.wikimedia.org/wiki/Special:FilePath/"</span>
|
|
<span class="n">_IMG_SRC_NEW_URL_PREFIX</span> <span class="o">=</span> <span class="s2">"https://upload.wikimedia.org/wikipedia/commons/thumb/"</span>
|
|
|
|
|
|
<div class="viewcode-block" id="get_thumbnail">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/wikipedia.html#searx.engines.wikidata.get_thumbnail">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_thumbnail</span><span class="p">(</span><span class="n">img_src</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""Get Thumbnail image from wikimedia commons</span>
|
|
|
|
<span class="sd"> Images from commons.wikimedia.org are (HTTP) redirected to</span>
|
|
<span class="sd"> upload.wikimedia.org. The redirected URL can be calculated by this</span>
|
|
<span class="sd"> function.</span>
|
|
|
|
<span class="sd"> - https://stackoverflow.com/a/33691240</span>
|
|
|
|
<span class="sd"> """</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"get_thumbnail(): </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">img_src</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">img_src</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">_IMG_SRC_DEFAULT_URL_PREFIX</span> <span class="ow">in</span> <span class="n">img_src</span><span class="o">.</span><span class="n">split</span><span class="p">()[</span><span class="mi">0</span><span class="p">]:</span>
|
|
<span class="n">img_src_name</span> <span class="o">=</span> <span class="n">unquote</span><span class="p">(</span><span class="n">img_src</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">_IMG_SRC_DEFAULT_URL_PREFIX</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"?"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%20"</span><span class="p">,</span> <span class="s2">"_"</span><span class="p">))</span>
|
|
<span class="n">img_src_name_first</span> <span class="o">=</span> <span class="n">img_src_name</span>
|
|
<span class="n">img_src_name_second</span> <span class="o">=</span> <span class="n">img_src_name</span>
|
|
|
|
<span class="k">if</span> <span class="s2">".svg"</span> <span class="ow">in</span> <span class="n">img_src_name</span><span class="o">.</span><span class="n">split</span><span class="p">()[</span><span class="mi">0</span><span class="p">]:</span>
|
|
<span class="n">img_src_name_second</span> <span class="o">=</span> <span class="n">img_src_name</span> <span class="o">+</span> <span class="s2">".png"</span>
|
|
|
|
<span class="n">img_src_size</span> <span class="o">=</span> <span class="n">img_src</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">_IMG_SRC_DEFAULT_URL_PREFIX</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"?"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="n">img_src_size</span> <span class="o">=</span> <span class="n">img_src_size</span><span class="p">[</span><span class="n">img_src_size</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"="</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">img_src_size</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"&"</span><span class="p">)]</span>
|
|
<span class="n">img_src_name_md5</span> <span class="o">=</span> <span class="n">md5</span><span class="p">(</span><span class="n">img_src_name</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">))</span><span class="o">.</span><span class="n">hexdigest</span><span class="p">()</span>
|
|
<span class="n">img_src</span> <span class="o">=</span> <span class="p">(</span>
|
|
<span class="n">_IMG_SRC_NEW_URL_PREFIX</span>
|
|
<span class="o">+</span> <span class="n">img_src_name_md5</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="o">+</span> <span class="s2">"/"</span>
|
|
<span class="o">+</span> <span class="n">img_src_name_md5</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="mi">2</span><span class="p">]</span>
|
|
<span class="o">+</span> <span class="s2">"/"</span>
|
|
<span class="o">+</span> <span class="n">img_src_name_first</span>
|
|
<span class="o">+</span> <span class="s2">"/"</span>
|
|
<span class="o">+</span> <span class="n">img_src_size</span>
|
|
<span class="o">+</span> <span class="s2">"px-"</span>
|
|
<span class="o">+</span> <span class="n">img_src_name_second</span>
|
|
<span class="p">)</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"get_thumbnail() redirected: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">img_src</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">img_src</span></div>
|
|
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_results</span><span class="p">(</span><span class="n">attribute_result</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">],</span> <span class="n">attributes</span><span class="p">,</span> <span class="n">language</span><span class="p">):</span>
|
|
<span class="c1"># pylint: disable=too-many-branches</span>
|
|
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">infobox_title</span> <span class="o">=</span> <span class="n">attribute_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"itemLabel"</span><span class="p">)</span>
|
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">attribute_result</span><span class="p">[</span><span class="s2">"item"</span><span class="p">]</span>
|
|
<span class="n">infobox_id_lang</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="n">infobox_urls</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">infobox_attributes</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">infobox_content</span> <span class="o">=</span> <span class="n">attribute_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"itemDescription"</span><span class="p">,</span> <span class="p">[])</span>
|
|
<span class="n">img_src</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="n">img_src_priority</span> <span class="o">=</span> <span class="mi">0</span>
|
|
|
|
<span class="k">for</span> <span class="n">attribute</span> <span class="ow">in</span> <span class="n">attributes</span><span class="p">:</span>
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">attribute</span><span class="o">.</span><span class="n">get_str</span><span class="p">(</span><span class="n">attribute_result</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">value</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">value</span> <span class="o">!=</span> <span class="s2">""</span><span class="p">:</span>
|
|
<span class="n">attribute_type</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="n">attribute</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">attribute_type</span> <span class="ow">in</span> <span class="p">(</span><span class="n">WDURLAttribute</span><span class="p">,</span> <span class="n">WDArticle</span><span class="p">):</span>
|
|
<span class="c1"># get_select() method : there is group_concat(distinct ...;separator=", ")</span>
|
|
<span class="c1"># split the value here</span>
|
|
<span class="k">for</span> <span class="n">url</span> <span class="ow">in</span> <span class="n">value</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">", "</span><span class="p">):</span>
|
|
<span class="n">infobox_urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">"title"</span><span class="p">:</span> <span class="n">attribute</span><span class="o">.</span><span class="n">get_label</span><span class="p">(</span><span class="n">language</span><span class="p">),</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="o">**</span><span class="n">attribute</span><span class="o">.</span><span class="n">kwargs</span><span class="p">})</span>
|
|
<span class="c1"># "normal" results (not infobox) include official website and Wikipedia links.</span>
|
|
<span class="k">if</span> <span class="s2">"list"</span> <span class="ow">in</span> <span class="n">display_type</span> <span class="ow">and</span> <span class="p">(</span><span class="n">attribute</span><span class="o">.</span><span class="n">kwargs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"official"</span><span class="p">)</span> <span class="ow">or</span> <span class="n">attribute_type</span> <span class="o">==</span> <span class="n">WDArticle</span><span class="p">):</span>
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">"title"</span><span class="p">:</span> <span class="n">infobox_title</span><span class="p">,</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="n">infobox_content</span><span class="p">})</span>
|
|
|
|
<span class="c1"># update the infobox_id with the wikipedia URL</span>
|
|
<span class="c1"># first the local wikipedia URL, and as fallback the english wikipedia URL</span>
|
|
<span class="k">if</span> <span class="n">attribute_type</span> <span class="o">==</span> <span class="n">WDArticle</span> <span class="ow">and</span> <span class="p">(</span>
|
|
<span class="p">(</span><span class="n">attribute</span><span class="o">.</span><span class="n">language</span> <span class="o">==</span> <span class="s2">"en"</span> <span class="ow">and</span> <span class="n">infobox_id_lang</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">)</span> <span class="ow">or</span> <span class="n">attribute</span><span class="o">.</span><span class="n">language</span> <span class="o">!=</span> <span class="s2">"en"</span>
|
|
<span class="p">):</span>
|
|
<span class="n">infobox_id_lang</span> <span class="o">=</span> <span class="n">attribute</span><span class="o">.</span><span class="n">language</span>
|
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">url</span>
|
|
<span class="k">elif</span> <span class="n">attribute_type</span> <span class="o">==</span> <span class="n">WDImageAttribute</span><span class="p">:</span>
|
|
<span class="c1"># this attribute is an image.</span>
|
|
<span class="c1"># replace the current image only the priority is lower</span>
|
|
<span class="c1"># (the infobox contain only one image).</span>
|
|
<span class="k">if</span> <span class="n">attribute</span><span class="o">.</span><span class="n">priority</span> <span class="o">></span> <span class="n">img_src_priority</span><span class="p">:</span>
|
|
<span class="n">img_src</span> <span class="o">=</span> <span class="n">get_thumbnail</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
|
|
<span class="n">img_src_priority</span> <span class="o">=</span> <span class="n">attribute</span><span class="o">.</span><span class="n">priority</span>
|
|
<span class="k">elif</span> <span class="n">attribute_type</span> <span class="o">==</span> <span class="n">WDGeoAttribute</span><span class="p">:</span>
|
|
<span class="c1"># geocoordinate link</span>
|
|
<span class="c1"># use the area to get the OSM zoom</span>
|
|
<span class="c1"># Note: ignore the unit (must be km² otherwise the calculation is wrong)</span>
|
|
<span class="c1"># Should use normalized value p:P2046/psn:P2046/wikibase:quantityAmount</span>
|
|
<span class="n">area</span> <span class="o">=</span> <span class="n">attribute_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"P2046"</span><span class="p">)</span>
|
|
<span class="n">osm_zoom</span> <span class="o">=</span> <span class="n">area_to_osm_zoom</span><span class="p">(</span><span class="n">area</span><span class="p">)</span> <span class="k">if</span> <span class="n">area</span> <span class="k">else</span> <span class="mi">19</span>
|
|
<span class="n">url</span> <span class="o">=</span> <span class="n">attribute</span><span class="o">.</span><span class="n">get_geo_url</span><span class="p">(</span><span class="n">attribute_result</span><span class="p">,</span> <span class="n">osm_zoom</span><span class="o">=</span><span class="n">osm_zoom</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">url</span><span class="p">:</span>
|
|
<span class="n">infobox_urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">"title"</span><span class="p">:</span> <span class="n">attribute</span><span class="o">.</span><span class="n">get_label</span><span class="p">(</span><span class="n">language</span><span class="p">),</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s2">"entity"</span><span class="p">:</span> <span class="n">attribute</span><span class="o">.</span><span class="n">name</span><span class="p">})</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">infobox_attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
|
|
<span class="p">{</span><span class="s2">"label"</span><span class="p">:</span> <span class="n">attribute</span><span class="o">.</span><span class="n">get_label</span><span class="p">(</span><span class="n">language</span><span class="p">),</span> <span class="s2">"value"</span><span class="p">:</span> <span class="n">value</span><span class="p">,</span> <span class="s2">"entity"</span><span class="p">:</span> <span class="n">attribute</span><span class="o">.</span><span class="n">name</span><span class="p">}</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">infobox_id</span><span class="p">:</span>
|
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">replace_http_by_https</span><span class="p">(</span><span class="n">infobox_id</span><span class="p">)</span>
|
|
|
|
<span class="c1"># add the wikidata URL at the end</span>
|
|
<span class="n">infobox_urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">"title"</span><span class="p">:</span> <span class="s2">"Wikidata"</span><span class="p">,</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">attribute_result</span><span class="p">[</span><span class="s2">"item"</span><span class="p">]})</span>
|
|
|
|
<span class="k">if</span> <span class="p">(</span>
|
|
<span class="s2">"list"</span> <span class="ow">in</span> <span class="n">display_type</span>
|
|
<span class="ow">and</span> <span class="n">img_src</span> <span class="ow">is</span> <span class="kc">None</span>
|
|
<span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">infobox_attributes</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span>
|
|
<span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">infobox_urls</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span>
|
|
<span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">infobox_content</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span>
|
|
<span class="p">):</span>
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s2">"url"</span><span class="p">:</span> <span class="n">infobox_urls</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s2">"url"</span><span class="p">],</span> <span class="s2">"title"</span><span class="p">:</span> <span class="n">infobox_title</span><span class="p">,</span> <span class="s2">"content"</span><span class="p">:</span> <span class="n">infobox_content</span><span class="p">})</span>
|
|
<span class="k">elif</span> <span class="s2">"infobox"</span> <span class="ow">in</span> <span class="n">display_type</span><span class="p">:</span>
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
|
|
<span class="p">{</span>
|
|
<span class="s2">"infobox"</span><span class="p">:</span> <span class="n">infobox_title</span><span class="p">,</span>
|
|
<span class="s2">"id"</span><span class="p">:</span> <span class="n">infobox_id</span><span class="p">,</span>
|
|
<span class="s2">"content"</span><span class="p">:</span> <span class="n">infobox_content</span><span class="p">,</span>
|
|
<span class="s2">"img_src"</span><span class="p">:</span> <span class="n">img_src</span><span class="p">,</span>
|
|
<span class="s2">"urls"</span><span class="p">:</span> <span class="n">infobox_urls</span><span class="p">,</span>
|
|
<span class="s2">"attributes"</span><span class="p">:</span> <span class="n">infobox_attributes</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">results</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_query</span><span class="p">(</span>
|
|
<span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">language</span><span class="p">:</span> <span class="nb">str</span>
|
|
<span class="p">)</span> <span class="o">-></span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">list</span><span class="p">[</span><span class="n">WDAttribute</span> <span class="o">|</span> <span class="n">WDAmountAttribute</span> <span class="o">|</span> <span class="n">WDLabelAttribute</span> <span class="o">|</span> <span class="n">WDImageAttribute</span><span class="p">]]:</span>
|
|
<span class="n">attributes</span> <span class="o">=</span> <span class="n">get_attributes</span><span class="p">(</span><span class="n">language</span><span class="p">)</span>
|
|
<span class="n">select</span> <span class="o">=</span> <span class="p">[</span><span class="n">a</span><span class="o">.</span><span class="n">get_select</span><span class="p">()</span> <span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">attributes</span><span class="p">]</span>
|
|
<span class="n">where</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">s</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="n">a</span><span class="o">.</span><span class="n">get_where</span><span class="p">()</span> <span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">attributes</span><span class="p">]))</span>
|
|
<span class="n">wikibase_label</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">s</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="n">a</span><span class="o">.</span><span class="n">get_wikibase_label</span><span class="p">()</span> <span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">attributes</span><span class="p">]))</span>
|
|
<span class="n">group_by</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">filter</span><span class="p">(</span><span class="k">lambda</span> <span class="n">s</span><span class="p">:</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">,</span> <span class="p">[</span><span class="n">a</span><span class="o">.</span><span class="n">get_group_by</span><span class="p">()</span> <span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">attributes</span><span class="p">]))</span>
|
|
<span class="n">query</span> <span class="o">=</span> <span class="p">(</span>
|
|
<span class="n">QUERY_TEMPLATE</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%QUERY%"</span><span class="p">,</span> <span class="n">sparql_string_escape</span><span class="p">(</span><span class="n">query</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%SELECT%"</span><span class="p">,</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">select</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%WHERE%"</span><span class="p">,</span> <span class="s2">"</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">where</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%WIKIBASE_LABELS%"</span><span class="p">,</span> <span class="s2">"</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">wikibase_label</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"</span><span class="si">%G</span><span class="s2">ROUP_BY%"</span><span class="p">,</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">group_by</span><span class="p">))</span>
|
|
<span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%LANGUAGE%"</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
<span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">query</span><span class="p">,</span> <span class="n">attributes</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_attributes</span><span class="p">(</span><span class="n">language</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="c1"># pylint: disable=too-many-statements</span>
|
|
<span class="n">attributes</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="n">WDAttribute</span> <span class="o">|</span> <span class="n">WDAmountAttribute</span> <span class="o">|</span> <span class="n">WDLabelAttribute</span> <span class="o">|</span> <span class="n">WDImageAttribute</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_value</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_amount</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDAmountAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_label</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDLabelAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_url</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">url_id</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">url_path_prefix</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDURLAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">url_id</span><span class="p">,</span> <span class="n">url_path_prefix</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">))</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_image</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">url_id</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">priority</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDImageAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">url_id</span><span class="p">,</span> <span class="n">priority</span><span class="p">))</span>
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">add_date</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDDateAttribute</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
|
|
|
|
<span class="c1"># Dates</span>
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s2">"P571"</span><span class="p">,</span> <span class="c1"># inception date</span>
|
|
<span class="s2">"P576"</span><span class="p">,</span> <span class="c1"># dissolution date</span>
|
|
<span class="s2">"P580"</span><span class="p">,</span> <span class="c1"># start date</span>
|
|
<span class="s2">"P582"</span><span class="p">,</span> <span class="c1"># end date</span>
|
|
<span class="s2">"P569"</span><span class="p">,</span> <span class="c1"># date of birth</span>
|
|
<span class="s2">"P570"</span><span class="p">,</span> <span class="c1"># date of death</span>
|
|
<span class="s2">"P619"</span><span class="p">,</span> <span class="c1"># date of spacecraft launch</span>
|
|
<span class="s2">"P620"</span><span class="p">,</span>
|
|
<span class="p">]:</span> <span class="c1"># date of spacecraft landing</span>
|
|
<span class="n">add_date</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s2">"P27"</span><span class="p">,</span> <span class="c1"># country of citizenship</span>
|
|
<span class="s2">"P495"</span><span class="p">,</span> <span class="c1"># country of origin</span>
|
|
<span class="s2">"P17"</span><span class="p">,</span> <span class="c1"># country</span>
|
|
<span class="s2">"P159"</span><span class="p">,</span>
|
|
<span class="p">]:</span> <span class="c1"># headquarters location</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
|
|
|
|
<span class="c1"># Places</span>
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s2">"P36"</span><span class="p">,</span> <span class="c1"># capital</span>
|
|
<span class="s2">"P35"</span><span class="p">,</span> <span class="c1"># head of state</span>
|
|
<span class="s2">"P6"</span><span class="p">,</span> <span class="c1"># head of government</span>
|
|
<span class="s2">"P122"</span><span class="p">,</span> <span class="c1"># basic form of government</span>
|
|
<span class="s2">"P37"</span><span class="p">,</span>
|
|
<span class="p">]:</span> <span class="c1"># official language</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
|
|
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P1082"</span><span class="p">)</span> <span class="c1"># population</span>
|
|
<span class="n">add_amount</span><span class="p">(</span><span class="s2">"P2046"</span><span class="p">)</span> <span class="c1"># area</span>
|
|
<span class="n">add_amount</span><span class="p">(</span><span class="s2">"P281"</span><span class="p">)</span> <span class="c1"># postal code</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P38"</span><span class="p">)</span> <span class="c1"># currency</span>
|
|
<span class="n">add_amount</span><span class="p">(</span><span class="s2">"P2048"</span><span class="p">)</span> <span class="c1"># height (building)</span>
|
|
|
|
<span class="c1"># Media</span>
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="p">[</span>
|
|
<span class="s2">"P400"</span><span class="p">,</span> <span class="c1"># platform (videogames, computing)</span>
|
|
<span class="s2">"P50"</span><span class="p">,</span> <span class="c1"># author</span>
|
|
<span class="s2">"P170"</span><span class="p">,</span> <span class="c1"># creator</span>
|
|
<span class="s2">"P57"</span><span class="p">,</span> <span class="c1"># director</span>
|
|
<span class="s2">"P175"</span><span class="p">,</span> <span class="c1"># performer</span>
|
|
<span class="s2">"P178"</span><span class="p">,</span> <span class="c1"># developer</span>
|
|
<span class="s2">"P162"</span><span class="p">,</span> <span class="c1"># producer</span>
|
|
<span class="s2">"P176"</span><span class="p">,</span> <span class="c1"># manufacturer</span>
|
|
<span class="s2">"P58"</span><span class="p">,</span> <span class="c1"># screenwriter</span>
|
|
<span class="s2">"P272"</span><span class="p">,</span> <span class="c1"># production company</span>
|
|
<span class="s2">"P264"</span><span class="p">,</span> <span class="c1"># record label</span>
|
|
<span class="s2">"P123"</span><span class="p">,</span> <span class="c1"># publisher</span>
|
|
<span class="s2">"P449"</span><span class="p">,</span> <span class="c1"># original network</span>
|
|
<span class="s2">"P750"</span><span class="p">,</span> <span class="c1"># distributed by</span>
|
|
<span class="s2">"P86"</span><span class="p">,</span>
|
|
<span class="p">]:</span> <span class="c1"># composer</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
|
|
|
|
<span class="n">add_date</span><span class="p">(</span><span class="s2">"P577"</span><span class="p">)</span> <span class="c1"># publication date</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P136"</span><span class="p">)</span> <span class="c1"># genre (music, film, artistic...)</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P364"</span><span class="p">)</span> <span class="c1"># original language</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P212"</span><span class="p">)</span> <span class="c1"># ISBN-13</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P957"</span><span class="p">)</span> <span class="c1"># ISBN-10</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P275"</span><span class="p">)</span> <span class="c1"># copyright license</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P277"</span><span class="p">)</span> <span class="c1"># programming language</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P348"</span><span class="p">)</span> <span class="c1"># version</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P840"</span><span class="p">)</span> <span class="c1"># narrative location</span>
|
|
|
|
<span class="c1"># Languages</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P1098"</span><span class="p">)</span> <span class="c1"># number of speakers</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P282"</span><span class="p">)</span> <span class="c1"># writing system</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P1018"</span><span class="p">)</span> <span class="c1"># language regulatory body</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P218"</span><span class="p">)</span> <span class="c1"># language code (ISO 639-1)</span>
|
|
|
|
<span class="c1"># Other</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P169"</span><span class="p">)</span> <span class="c1"># ceo</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P112"</span><span class="p">)</span> <span class="c1"># founded by</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P1454"</span><span class="p">)</span> <span class="c1"># legal form (company, organization)</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P137"</span><span class="p">)</span> <span class="c1"># operator (service, facility, ...)</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P1029"</span><span class="p">)</span> <span class="c1"># crew members (tripulation)</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P225"</span><span class="p">)</span> <span class="c1"># taxon name</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P274"</span><span class="p">)</span> <span class="c1"># chemical formula</span>
|
|
<span class="n">add_label</span><span class="p">(</span><span class="s2">"P1346"</span><span class="p">)</span> <span class="c1"># winner (sports, contests, ...)</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P1120"</span><span class="p">)</span> <span class="c1"># number of deaths</span>
|
|
<span class="n">add_value</span><span class="p">(</span><span class="s2">"P498"</span><span class="p">)</span> <span class="c1"># currency code (ISO 4217)</span>
|
|
|
|
<span class="c1"># URL</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P856"</span><span class="p">,</span> <span class="n">official</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> <span class="c1"># official website</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDArticle</span><span class="p">(</span><span class="n">language</span><span class="p">))</span> <span class="c1"># wikipedia (user language)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">language</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"en"</span><span class="p">):</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDArticle</span><span class="p">(</span><span class="s2">"en"</span><span class="p">))</span> <span class="c1"># wikipedia (english)</span>
|
|
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P1324"</span><span class="p">)</span> <span class="c1"># source code repository</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P1581"</span><span class="p">)</span> <span class="c1"># blog</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P434"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"musicbrainz_artist"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P435"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"musicbrainz_work"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P436"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"musicbrainz_release_group"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P966"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"musicbrainz_label"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P345"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"imdb_id"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P2397"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"youtube_channel"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P1651"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"youtube_video"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P2002"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"twitter_profile"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P2013"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"facebook_profile"</span><span class="p">)</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P2003"</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"instagram_profile"</span><span class="p">)</span>
|
|
|
|
<span class="c1"># Fediverse</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P4033"</span><span class="p">,</span> <span class="n">url_path_prefix</span><span class="o">=</span><span class="s2">"/@"</span><span class="p">)</span> <span class="c1"># Mastodon user</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P11947"</span><span class="p">,</span> <span class="n">url_path_prefix</span><span class="o">=</span><span class="s2">"/c/"</span><span class="p">)</span> <span class="c1"># Lemmy community</span>
|
|
<span class="n">add_url</span><span class="p">(</span><span class="s2">"P12622"</span><span class="p">,</span> <span class="n">url_path_prefix</span><span class="o">=</span><span class="s2">"/c/"</span><span class="p">)</span> <span class="c1"># PeerTube channel</span>
|
|
|
|
<span class="c1"># Map</span>
|
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">WDGeoAttribute</span><span class="p">(</span><span class="s2">"P625"</span><span class="p">))</span>
|
|
|
|
<span class="c1"># Image</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P15"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># route map</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P242"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># locator map</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P154"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># logo</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P18"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># image</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P41"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># flag</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P2716"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">6</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># collage</span>
|
|
<span class="n">add_image</span><span class="p">(</span><span class="s2">"P2910"</span><span class="p">,</span> <span class="n">priority</span><span class="o">=</span><span class="mi">7</span><span class="p">,</span> <span class="n">url_id</span><span class="o">=</span><span class="s2">"wikimedia_image"</span><span class="p">)</span> <span class="c1"># icon</span>
|
|
|
|
<span class="k">return</span> <span class="n">attributes</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">debug_explain_wikidata_query</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">method</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">"GET"</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">method</span> <span class="o">==</span> <span class="s2">"GET"</span><span class="p">:</span>
|
|
<span class="n">http_response</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="n">SPARQL_EXPLAIN_URL</span> <span class="o">+</span> <span class="s2">"&"</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s2">"query"</span><span class="p">:</span> <span class="n">query</span><span class="p">}),</span> <span class="n">headers</span><span class="o">=</span><span class="n">get_headers</span><span class="p">())</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">http_response</span> <span class="o">=</span> <span class="n">post</span><span class="p">(</span><span class="n">SPARQL_EXPLAIN_URL</span><span class="p">,</span> <span class="n">data</span><span class="o">=</span><span class="p">{</span><span class="s2">"query"</span><span class="p">:</span> <span class="n">query</span><span class="p">},</span> <span class="n">headers</span><span class="o">=</span><span class="n">get_headers</span><span class="p">())</span>
|
|
<span class="n">http_response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
|
|
<span class="k">return</span> <span class="n">http_response</span><span class="o">.</span><span class="n">content</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">init</span><span class="p">(</span><span class="n">engine_settings</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> <span class="c1"># pylint: disable=unused-argument</span>
|
|
<span class="c1"># WIKIDATA_PROPERTIES : add unit symbols</span>
|
|
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">WIKIDATA_UNITS</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
|
<span class="n">WIKIDATA_PROPERTIES</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span><span class="p">[</span><span class="s2">"symbol"</span><span class="p">]</span>
|
|
|
|
<span class="c1"># WIKIDATA_PROPERTIES : add property labels</span>
|
|
<span class="n">wikidata_property_names</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">attribute</span> <span class="ow">in</span> <span class="n">get_attributes</span><span class="p">(</span><span class="s2">"en"</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">attribute</span><span class="p">)</span> <span class="ow">in</span> <span class="p">(</span><span class="n">WDAttribute</span><span class="p">,</span> <span class="n">WDAmountAttribute</span><span class="p">,</span> <span class="n">WDURLAttribute</span><span class="p">,</span> <span class="n">WDDateAttribute</span><span class="p">,</span> <span class="n">WDLabelAttribute</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">attribute</span><span class="o">.</span><span class="n">name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">WIKIDATA_PROPERTIES</span><span class="p">:</span>
|
|
<span class="n">wikidata_property_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"wd:"</span> <span class="o">+</span> <span class="n">attribute</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
|
|
<span class="n">query</span> <span class="o">=</span> <span class="n">QUERY_PROPERTY_NAMES</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"%ATTRIBUTES%"</span><span class="p">,</span> <span class="s2">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">wikidata_property_names</span><span class="p">))</span>
|
|
<span class="n">jsonresponse</span> <span class="o">=</span> <span class="n">send_wikidata_query</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="mi">20</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">jsonresponse</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"results"</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"bindings"</span><span class="p">,</span> <span class="p">{}):</span>
|
|
<span class="n">name_field</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"name"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">name_field</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">name_field</span><span class="p">[</span><span class="s2">"value"</span><span class="p">]</span>
|
|
<span class="n">lang</span> <span class="o">=</span> <span class="n">name_field</span><span class="p">[</span><span class="s2">"xml:lang"</span><span class="p">]</span>
|
|
<span class="n">entity_id</span> <span class="o">=</span> <span class="n">result</span><span class="p">[</span><span class="s2">"item"</span><span class="p">][</span><span class="s2">"value"</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"http://www.wikidata.org/entity/"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
|
|
<span class="n">WIKIDATA_PROPERTIES</span><span class="p">[(</span><span class="n">entity_id</span><span class="p">,</span> <span class="n">lang</span><span class="p">)]</span> <span class="o">=</span> <span class="n">name</span><span class="o">.</span><span class="n">capitalize</span><span class="p">()</span>
|
|
|
|
|
|
<div class="viewcode-block" id="fetch_traits">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/wikipedia.html#searx.engines.wikidata.fetch_traits">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Uses languages evaluated from :py:obj:`wikipedia.fetch_wikimedia_traits</span>
|
|
<span class="sd"> <searx.engines.wikipedia.fetch_wikimedia_traits>` and removes</span>
|
|
|
|
<span class="sd"> - ``traits.custom['wiki_netloc']``: wikidata does not have net-locations for</span>
|
|
<span class="sd"> the languages and the list of all</span>
|
|
|
|
<span class="sd"> - ``traits.custom['WIKIPEDIA_LANGUAGES']``: not used in the wikipedia engine</span>
|
|
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="n">fetch_wikimedia_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">)</span>
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"wiki_netloc"</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"WIKIPEDIA_LANGUAGES"</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span></div>
|
|
|
|
</pre></div>
|
|
|
|
<div class="clearer"></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<span id="sidebar-top"></span>
|
|
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
|
<div class="sphinxsidebarwrapper">
|
|
|
|
|
|
<p class="logo"><a href="../../../index.html">
|
|
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
|
|
</a></p>
|
|
|
|
|
|
<h3><a href="../../../index.html">Table of Contents</a></h3>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
|
|
</ul>
|
|
|
|
<h3>Project Links</h3>
|
|
<ul>
|
|
<li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
|
|
|
|
<li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
|
|
|
|
<li><a href="https://searx.space">Public instances</a>
|
|
|
|
<li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
|
|
</ul><h3>Navigation</h3>
|
|
<ul>
|
|
<li><a href="../../../index.html">Overview</a>
|
|
<ul>
|
|
<li><a href="../../index.html">Module code</a>
|
|
<ul>
|
|
<li><a href="../engines.html">searx.engines</a>
|
|
|
|
|
|
</ul>
|
|
</li></ul>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<search id="searchbox" style="display: none" role="search">
|
|
<h3 id="searchlabel">Quick search</h3>
|
|
<div class="searchformwrapper">
|
|
<form class="search" action="../../../search.html" method="get">
|
|
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
|
<input type="submit" value="Go" />
|
|
</form>
|
|
</div>
|
|
</search>
|
|
<script>document.getElementById('searchbox').style.display = "block"</script>
|
|
</div>
|
|
</div>
|
|
<div class="clearer"></div>
|
|
</div>
|
|
<div class="footer" role="contentinfo">
|
|
© Copyright SearXNG team.
|
|
</div>
|
|
</body>
|
|
</html> |