264 lines
24 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.recoll &#8212; SearXNG Documentation (2025.10.27+ea4a55fa5)</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=d52f7eb8"></script>
<script src="../../../_static/doctools.js?v=9bcbadda"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script data-project="searxng" data-version="2025.10.27+ea4a55fa5" 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 (2025.10.27+ea4a55fa5)</a> &#187;</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">searx.engines.recoll</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.engines.recoll</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
<span class="sd">&quot;&quot;&quot;.. sidebar:: info</span>
<span class="sd"> - `Recoll &lt;https://www.lesbonscomptes.com/recoll/&gt;`_</span>
<span class="sd"> - `recoll-webui &lt;https://framagit.org/medoc92/recollwebui.git&gt;`_</span>
<span class="sd"> - :origin:`searx/engines/recoll.py`</span>
<span class="sd">Recoll_ is a desktop full-text search tool based on Xapian. By itself Recoll_</span>
<span class="sd">does not offer WEB or API access, this can be achieved using recoll-webui_</span>
<span class="sd">Configuration</span>
<span class="sd">=============</span>
<span class="sd">You must configure the following settings:</span>
<span class="sd">- :py:obj:`base_url`</span>
<span class="sd">- :py:obj:`mount_prefix`</span>
<span class="sd">- :py:obj:`dl_prefix`</span>
<span class="sd">- :py:obj:`search_dir`</span>
<span class="sd">Example scenario:</span>
<span class="sd">#. Recoll indexes a local filesystem mounted in ``/export/documents/reference``,</span>
<span class="sd">#. the Recoll search interface can be reached at https://recoll.example.org/ and</span>
<span class="sd">#. the contents of this filesystem can be reached though https://download.example.org/reference</span>
<span class="sd">.. code:: yaml</span>
<span class="sd"> base_url: https://recoll.example.org</span>
<span class="sd"> mount_prefix: /export/documents</span>
<span class="sd"> dl_prefix: https://download.example.org</span>
<span class="sd"> search_dir: &quot;&quot;</span>
<span class="sd">Implementations</span>
<span class="sd">===============</span>
<span class="sd">&quot;&quot;&quot;</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">datetime</span><span class="w"> </span><span class="kn">import</span> <span class="n">date</span><span class="p">,</span> <span class="n">timedelta</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">quote</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.result_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineResults</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="n">about</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
<span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s2">&quot;Q15735774&quot;</span><span class="p">,</span>
<span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="s2">&quot;https://www.lesbonscomptes.com/recoll/&quot;</span><span class="p">,</span>
<span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
<span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s2">&quot;JSON&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">base_url</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="sd">&quot;&quot;&quot;Location where recoll-webui can be reached.&quot;&quot;&quot;</span>
<span class="n">mount_prefix</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="sd">&quot;&quot;&quot;Location where the file hierarchy is mounted on your *local* filesystem.&quot;&quot;&quot;</span>
<span class="n">dl_prefix</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="sd">&quot;&quot;&quot;Location where the file hierarchy as indexed by recoll can be reached.&quot;&quot;&quot;</span>
<span class="n">search_dir</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="sd">&quot;&quot;&quot;Part of the indexed file hierarchy to be search, if empty the full domain is</span>
<span class="sd">searched.&quot;&quot;&quot;</span>
<span class="n">_s2i</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="kc">None</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;day&quot;</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">&quot;week&quot;</span><span class="p">:</span> <span class="mi">7</span><span class="p">,</span> <span class="s2">&quot;month&quot;</span><span class="p">:</span> <span class="mi">30</span><span class="p">,</span> <span class="s2">&quot;year&quot;</span><span class="p">:</span> <span class="mi">365</span><span class="p">}</span>
<div class="viewcode-block" id="setup">
<a class="viewcode-back" href="../../../dev/engines/online/recoll.html#searx.engines.recoll.setup">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">setup</span><span class="p">(</span><span class="n">engine_settings</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">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialization of the Recoll engine, checks if the mandatory values are</span>
<span class="sd"> configured.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">missing</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">cfg_name</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;base_url&quot;</span><span class="p">,</span> <span class="s2">&quot;mount_prefix&quot;</span><span class="p">,</span> <span class="s2">&quot;dl_prefix&quot;</span><span class="p">]:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">engine_settings</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">cfg_name</span><span class="p">):</span>
<span class="n">missing</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">cfg_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">missing</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">&quot;missing recoll configuration: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">missing</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">if</span> <span class="n">engine_settings</span><span class="p">[</span><span class="s2">&quot;base_url&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">&quot;/&quot;</span><span class="p">):</span>
<span class="n">engine_settings</span><span class="p">[</span><span class="s2">&quot;base_url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">engine_settings</span><span class="p">[</span><span class="s2">&quot;base_url&quot;</span><span class="p">][:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">return</span> <span class="kc">True</span></div>
<span class="k">def</span><span class="w"> </span><span class="nf">search_after</span><span class="p">(</span><span class="n">time_range</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="n">offset</span> <span class="o">=</span> <span class="n">_s2i</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">time_range</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">offset</span><span class="p">:</span>
<span class="k">return</span> <span class="s2">&quot;&quot;</span>
<span class="k">return</span> <span class="p">(</span><span class="n">date</span><span class="o">.</span><span class="n">today</span><span class="p">()</span> <span class="o">-</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">days</span><span class="o">=</span><span class="n">offset</span><span class="p">))</span><span class="o">.</span><span class="n">isoformat</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">&quot;OnlineParams&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">args</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;query&quot;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
<span class="s2">&quot;page&quot;</span><span class="p">:</span> <span class="n">params</span><span class="p">[</span><span class="s2">&quot;pageno&quot;</span><span class="p">],</span>
<span class="s2">&quot;after&quot;</span><span class="p">:</span> <span class="n">search_after</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">&quot;time_range&quot;</span><span class="p">]),</span>
<span class="s2">&quot;dir&quot;</span><span class="p">:</span> <span class="n">search_dir</span><span class="p">,</span>
<span class="s2">&quot;highlight&quot;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">params</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">base_url</span><span class="si">}</span><span class="s2">/json?</span><span class="si">{</span><span class="n">urlencode</span><span class="p">(</span><span class="n">args</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</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">&quot;SXNG_Response&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">EngineResults</span><span class="p">:</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
<span class="n">json_data</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">json</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">json_data</span><span class="p">:</span>
<span class="k">return</span> <span class="n">res</span>
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">json_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;results&quot;</span><span class="p">,</span> <span class="p">[]):</span>
<span class="n">url</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">&quot;url&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;file://&quot;</span> <span class="o">+</span> <span class="n">mount_prefix</span><span class="p">,</span> <span class="n">dl_prefix</span><span class="p">)</span>
<span class="n">mtype</span> <span class="o">=</span> <span class="n">subtype</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">&quot;mime&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mtype</span><span class="p">:</span>
<span class="n">mtype</span><span class="p">,</span> <span class="n">subtype</span> <span class="o">=</span> <span class="p">(</span><span class="n">mtype</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;/&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="p">[</span><span class="s2">&quot;&quot;</span><span class="p">])[:</span><span class="mi">2</span><span class="p">]</span>
<span class="c1"># facilitate preview support for known mime types</span>
<span class="n">thumbnail</span> <span class="o">=</span> <span class="n">embedded</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
<span class="k">if</span> <span class="n">mtype</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;audio&quot;</span><span class="p">,</span> <span class="s2">&quot;video&quot;</span><span class="p">]:</span>
<span class="n">embedded_url</span> <span class="o">=</span> <span class="s1">&#39;&lt;</span><span class="si">{ttype}</span><span class="s1"> controls height=&quot;166px&quot; &#39;</span> <span class="o">+</span> <span class="s1">&#39;src=&quot;</span><span class="si">{url}</span><span class="s1">&quot; type=&quot;</span><span class="si">{mtype}</span><span class="s1">&quot;&gt;&lt;/</span><span class="si">{ttype}</span><span class="s1">&gt;&#39;</span>
<span class="n">embedded</span> <span class="o">=</span> <span class="n">embedded_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">ttype</span><span class="o">=</span><span class="n">mtype</span><span class="p">,</span> <span class="n">url</span><span class="o">=</span><span class="n">quote</span><span class="p">(</span><span class="n">url</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s2">&quot;utf8&quot;</span><span class="p">),</span> <span class="s2">&quot;/:&quot;</span><span class="p">),</span> <span class="n">mtype</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">&quot;mtype&quot;</span><span class="p">])</span>
<span class="k">if</span> <span class="n">mtype</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;image&quot;</span><span class="p">]</span> <span class="ow">and</span> <span class="n">subtype</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">&quot;bmp&quot;</span><span class="p">,</span> <span class="s2">&quot;gif&quot;</span><span class="p">,</span> <span class="s2">&quot;jpeg&quot;</span><span class="p">,</span> <span class="s2">&quot;png&quot;</span><span class="p">]:</span>
<span class="n">thumbnail</span> <span class="o">=</span> <span class="n">url</span>
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span>
<span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">File</span><span class="p">(</span>
<span class="n">title</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">&quot;label&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">url</span><span class="o">=</span><span class="n">url</span><span class="p">,</span>
<span class="n">content</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">&quot;snippet&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">size</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">&quot;size&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">filename</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">&quot;filename&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">abstract</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">&quot;abstract&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">author</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">&quot;author&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">mtype</span><span class="o">=</span><span class="n">mtype</span><span class="p">,</span>
<span class="n">subtype</span><span class="o">=</span><span class="n">subtype</span><span class="p">,</span>
<span class="n">time</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">&quot;time&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">),</span>
<span class="n">embedded</span><span class="o">=</span><span class="n">embedded</span><span class="p">,</span>
<span class="n">thumbnail</span><span class="o">=</span><span class="n">thumbnail</span><span class="p">,</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">res</span>
</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">
&#169; Copyright SearXNG team.
</div>
</body>
</html>