File: //usr/share/doc/python3-xapian/html/examples.html
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
<title>Examples — Xapian Python3 Bindings 1.4.18 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="_static/classic.css" />
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
<script src="_static/jquery.js"></script>
<script src="_static/underscore.js"></script>
<script src="_static/doctools.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="xapian Package" href="xapian.html" />
<link rel="prev" title="Python3 bindings for Xapian" href="introduction.html" />
</head><body>
<div class="related" role="navigation" aria-label="related navigation">
<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="xapian.html" title="xapian Package"
accesskey="N">next</a> |</li>
<li class="right" >
<a href="introduction.html" title="Python3 bindings for Xapian"
accesskey="P">previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">Xapian Python3 Bindings 1.4.18 documentation</a> »</li>
<li class="nav-item nav-item-this"><a href="">Examples</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<section id="examples">
<h1>Examples<a class="headerlink" href="#examples" title="Permalink to this headline">¶</a></h1>
<section id="simplesearch-py">
<span id="simplesearch"></span><h2>simplesearch.py<a class="headerlink" href="#simplesearch-py" title="Permalink to this headline">¶</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="ch">#!/usr/bin/env python</span>
<span class="linenos"> 2</span><span class="c1">#</span>
<span class="linenos"> 3</span><span class="c1"># Simple command-line search script.</span>
<span class="linenos"> 4</span><span class="c1">#</span>
<span class="linenos"> 5</span><span class="c1"># Copyright (C) 2003 James Aylett</span>
<span class="linenos"> 6</span><span class="c1"># Copyright (C) 2004,2007,2009,2013 Olly Betts</span>
<span class="linenos"> 7</span><span class="c1">#</span>
<span class="linenos"> 8</span><span class="c1"># This program is free software; you can redistribute it and/or</span>
<span class="linenos"> 9</span><span class="c1"># modify it under the terms of the GNU General Public License as</span>
<span class="linenos">10</span><span class="c1"># published by the Free Software Foundation; either version 2 of the</span>
<span class="linenos">11</span><span class="c1"># License, or (at your option) any later version.</span>
<span class="hll"><span class="linenos">12</span><span class="c1">#</span>
</span><span class="linenos">13</span><span class="c1"># This program is distributed in the hope that it will be useful,</span>
<span class="linenos">14</span><span class="c1"># but WITHOUT ANY WARRANTY; without even the implied warranty of</span>
<span class="hll"><span class="linenos">15</span><span class="c1"># MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</span>
</span><span class="hll"><span class="linenos">16</span><span class="c1"># GNU General Public License for more details.</span>
</span><span class="hll"><span class="linenos">17</span><span class="c1">#</span>
</span><span class="hll"><span class="linenos">18</span><span class="c1"># You should have received a copy of the GNU General Public License</span>
</span><span class="linenos">19</span><span class="c1"># along with this program; if not, write to the Free Software</span>
<span class="linenos">20</span><span class="c1"># Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301</span>
<span class="linenos">21</span><span class="c1"># USA</span>
<span class="linenos">22</span>
<span class="linenos">23</span><span class="kn">import</span> <span class="nn">sys</span>
<span class="linenos">24</span><span class="kn">import</span> <span class="nn">xapian</span>
<span class="linenos">25</span>
<span class="linenos">26</span><span class="c1"># We require at least two command line arguments.</span>
<span class="linenos">27</span><span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
<span class="linenos">28</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Usage: </span><span class="si">%s</span><span class="s2"> PATH_TO_DATABASE QUERY"</span> <span class="o">%</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">29</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="linenos">30</span>
<span class="linenos">31</span><span class="k">try</span><span class="p">:</span>
<span class="linenos">32</span> <span class="c1"># Open the database for searching.</span>
<span class="linenos">33</span> <span class="n">database</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Database</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="linenos">34</span>
<span class="linenos">35</span> <span class="c1"># Start an enquire session.</span>
<span class="linenos">36</span> <span class="n">enquire</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Enquire</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">37</span>
<span class="linenos">38</span> <span class="c1"># Combine the rest of the command line arguments with spaces between</span>
<span class="linenos">39</span> <span class="c1"># them, so that simple queries don't have to be quoted at the shell</span>
<span class="linenos">40</span> <span class="c1"># level.</span>
<span class="linenos">41</span> <span class="n">query_string</span> <span class="o">=</span> <span class="nb">str</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">' '</span><span class="p">,</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">:])</span>
<span class="linenos">42</span>
<span class="linenos">43</span> <span class="c1"># Parse the query string to produce a Xapian::Query object.</span>
<span class="linenos">44</span> <span class="n">qp</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="p">()</span>
<span class="linenos">45</span> <span class="n">stemmer</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Stem</span><span class="p">(</span><span class="s2">"english"</span><span class="p">)</span>
<span class="linenos">46</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemmer</span><span class="p">(</span><span class="n">stemmer</span><span class="p">)</span>
<span class="linenos">47</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_database</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">48</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemming_strategy</span><span class="p">(</span><span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="o">.</span><span class="n">STEM_SOME</span><span class="p">)</span>
<span class="linenos">49</span> <span class="n">query</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">parse_query</span><span class="p">(</span><span class="n">query_string</span><span class="p">)</span>
<span class="linenos">50</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Parsed query is: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">query</span><span class="p">))</span>
<span class="linenos">51</span>
<span class="linenos">52</span> <span class="c1"># Find the top 10 results for the query.</span>
<span class="linenos">53</span> <span class="n">enquire</span><span class="o">.</span><span class="n">set_query</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
<span class="linenos">54</span> <span class="n">matches</span> <span class="o">=</span> <span class="n">enquire</span><span class="o">.</span><span class="n">get_mset</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
<span class="linenos">55</span>
<span class="linenos">56</span> <span class="c1"># Display the results.</span>
<span class="linenos">57</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2"> results found."</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">get_matches_estimated</span><span class="p">())</span>
<span class="linenos">58</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Results 1-</span><span class="si">%i</span><span class="s2">:"</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">size</span><span class="p">())</span>
<span class="linenos">59</span>
<span class="linenos">60</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">matches</span><span class="p">:</span>
<span class="linenos">61</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2">: </span><span class="si">%i%%</span><span class="s2"> docid=</span><span class="si">%i</span><span class="s2"> [</span><span class="si">%s</span><span class="s2">]"</span> <span class="o">%</span> <span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">rank</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">percent</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">docid</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">document</span><span class="o">.</span><span class="n">get_data</span><span class="p">()</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)))</span>
<span class="linenos">62</span>
<span class="linenos">63</span><span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="linenos">64</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Exception: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">65</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="simpleindex-py">
<span id="simpleindex"></span><h2>simpleindex.py<a class="headerlink" href="#simpleindex-py" title="Permalink to this headline">¶</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="ch">#!/usr/bin/env python</span>
<span class="linenos"> 2</span><span class="c1">#</span>
<span class="linenos"> 3</span><span class="c1"># Index each paragraph of a text file as a Xapian document.</span>
<span class="linenos"> 4</span><span class="c1">#</span>
<span class="linenos"> 5</span><span class="c1"># Copyright (C) 2003 James Aylett</span>
<span class="linenos"> 6</span><span class="c1"># Copyright (C) 2004,2007,2013,2014 Olly Betts</span>
<span class="linenos"> 7</span><span class="c1">#</span>
<span class="linenos"> 8</span><span class="c1"># This program is free software; you can redistribute it and/or</span>
<span class="linenos"> 9</span><span class="c1"># modify it under the terms of the GNU General Public License as</span>
<span class="linenos">10</span><span class="c1"># published by the Free Software Foundation; either version 2 of the</span>
<span class="linenos">11</span><span class="c1"># License, or (at your option) any later version.</span>
<span class="hll"><span class="linenos">12</span><span class="c1">#</span>
</span><span class="linenos">13</span><span class="c1"># This program is distributed in the hope that it will be useful,</span>
<span class="linenos">14</span><span class="c1"># but WITHOUT ANY WARRANTY; without even the implied warranty of</span>
<span class="hll"><span class="linenos">15</span><span class="c1"># MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</span>
</span><span class="hll"><span class="linenos">16</span><span class="c1"># GNU General Public License for more details.</span>
</span><span class="hll"><span class="linenos">17</span><span class="c1">#</span>
</span><span class="hll"><span class="linenos">18</span><span class="c1"># You should have received a copy of the GNU General Public License</span>
</span><span class="linenos">19</span><span class="c1"># along with this program; if not, write to the Free Software</span>
<span class="linenos">20</span><span class="c1"># Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301</span>
<span class="linenos">21</span><span class="c1"># USA</span>
<span class="linenos">22</span>
<span class="linenos">23</span><span class="kn">import</span> <span class="nn">sys</span>
<span class="linenos">24</span><span class="kn">import</span> <span class="nn">xapian</span>
<span class="linenos">25</span><span class="kn">import</span> <span class="nn">string</span>
<span class="linenos">26</span>
<span class="linenos">27</span><span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">:</span>
<span class="linenos">28</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Usage: </span><span class="si">%s</span><span class="s2"> PATH_TO_DATABASE"</span> <span class="o">%</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">29</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="linenos">30</span>
<span class="linenos">31</span><span class="k">try</span><span class="p">:</span>
<span class="linenos">32</span> <span class="c1"># Open the database for update, creating a new database if necessary.</span>
<span class="linenos">33</span> <span class="n">database</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">WritableDatabase</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">xapian</span><span class="o">.</span><span class="n">DB_CREATE_OR_OPEN</span><span class="p">)</span>
<span class="linenos">34</span>
<span class="linenos">35</span> <span class="n">indexer</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">TermGenerator</span><span class="p">()</span>
<span class="linenos">36</span> <span class="n">stemmer</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Stem</span><span class="p">(</span><span class="s2">"english"</span><span class="p">)</span>
<span class="linenos">37</span> <span class="n">indexer</span><span class="o">.</span><span class="n">set_stemmer</span><span class="p">(</span><span class="n">stemmer</span><span class="p">)</span>
<span class="linenos">38</span>
<span class="linenos">39</span> <span class="n">para</span> <span class="o">=</span> <span class="s1">''</span>
<span class="linenos">40</span> <span class="k">try</span><span class="p">:</span>
<span class="linenos">41</span> <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">sys</span><span class="o">.</span><span class="n">stdin</span><span class="p">:</span>
<span class="linenos">42</span> <span class="n">line</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
<span class="linenos">43</span> <span class="k">if</span> <span class="n">line</span> <span class="o">==</span> <span class="s1">''</span><span class="p">:</span>
<span class="linenos">44</span> <span class="k">if</span> <span class="n">para</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span>
<span class="linenos">45</span> <span class="c1"># We've reached the end of a paragraph, so index it.</span>
<span class="linenos">46</span> <span class="n">doc</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Document</span><span class="p">()</span>
<span class="linenos">47</span> <span class="n">doc</span><span class="o">.</span><span class="n">set_data</span><span class="p">(</span><span class="n">para</span><span class="p">)</span>
<span class="linenos">48</span>
<span class="linenos">49</span> <span class="n">indexer</span><span class="o">.</span><span class="n">set_document</span><span class="p">(</span><span class="n">doc</span><span class="p">)</span>
<span class="linenos">50</span> <span class="n">indexer</span><span class="o">.</span><span class="n">index_text</span><span class="p">(</span><span class="n">para</span><span class="p">)</span>
<span class="linenos">51</span>
<span class="linenos">52</span> <span class="c1"># Add the document to the database.</span>
<span class="linenos">53</span> <span class="n">database</span><span class="o">.</span><span class="n">add_document</span><span class="p">(</span><span class="n">doc</span><span class="p">)</span>
<span class="linenos">54</span> <span class="n">para</span> <span class="o">=</span> <span class="s1">''</span>
<span class="linenos">55</span> <span class="k">else</span><span class="p">:</span>
<span class="linenos">56</span> <span class="k">if</span> <span class="n">para</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span>
<span class="linenos">57</span> <span class="n">para</span> <span class="o">+=</span> <span class="s1">' '</span>
<span class="linenos">58</span> <span class="n">para</span> <span class="o">+=</span> <span class="n">line</span>
<span class="linenos">59</span> <span class="k">except</span> <span class="ne">StopIteration</span><span class="p">:</span>
<span class="linenos">60</span> <span class="k">pass</span>
<span class="linenos">61</span>
<span class="linenos">62</span><span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="linenos">63</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Exception: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">64</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="simpleexpand-py">
<span id="simpleexpand"></span><h2>simpleexpand.py<a class="headerlink" href="#simpleexpand-py" title="Permalink to this headline">¶</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="ch">#!/usr/bin/env python</span>
<span class="linenos"> 2</span><span class="c1">#</span>
<span class="linenos"> 3</span><span class="c1"># Simple example script demonstrating query expansion.</span>
<span class="linenos"> 4</span><span class="c1">#</span>
<span class="linenos"> 5</span><span class="c1"># Copyright (C) 2003 James Aylett</span>
<span class="linenos"> 6</span><span class="c1"># Copyright (C) 2004,2006,2007,2012,2013,2014 Olly Betts</span>
<span class="linenos"> 7</span><span class="c1">#</span>
<span class="linenos"> 8</span><span class="c1"># This program is free software; you can redistribute it and/or</span>
<span class="linenos"> 9</span><span class="c1"># modify it under the terms of the GNU General Public License as</span>
<span class="linenos">10</span><span class="c1"># published by the Free Software Foundation; either version 2 of the</span>
<span class="linenos">11</span><span class="c1"># License, or (at your option) any later version.</span>
<span class="hll"><span class="linenos">12</span><span class="c1">#</span>
</span><span class="linenos">13</span><span class="c1"># This program is distributed in the hope that it will be useful,</span>
<span class="linenos">14</span><span class="c1"># but WITHOUT ANY WARRANTY; without even the implied warranty of</span>
<span class="hll"><span class="linenos">15</span><span class="c1"># MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</span>
</span><span class="hll"><span class="linenos">16</span><span class="c1"># GNU General Public License for more details.</span>
</span><span class="hll"><span class="linenos">17</span><span class="c1">#</span>
</span><span class="hll"><span class="linenos">18</span><span class="c1"># You should have received a copy of the GNU General Public License</span>
</span><span class="linenos">19</span><span class="c1"># along with this program; if not, write to the Free Software</span>
<span class="linenos">20</span><span class="c1"># Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301</span>
<span class="linenos">21</span><span class="c1"># USA</span>
<span class="linenos">22</span>
<span class="linenos">23</span><span class="kn">import</span> <span class="nn">sys</span>
<span class="linenos">24</span><span class="kn">import</span> <span class="nn">xapian</span>
<span class="linenos">25</span>
<span class="linenos">26</span><span class="c1"># We require at least two command line arguments.</span>
<span class="linenos">27</span><span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
<span class="linenos">28</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Usage: </span><span class="si">%s</span><span class="s2"> PATH_TO_DATABASE QUERY [-- [DOCID...]]"</span> <span class="o">%</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">29</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="linenos">30</span>
<span class="linenos">31</span><span class="k">try</span><span class="p">:</span>
<span class="linenos">32</span> <span class="c1"># Open the database for searching.</span>
<span class="linenos">33</span> <span class="n">database</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Database</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="linenos">34</span>
<span class="linenos">35</span> <span class="c1"># Start an enquire session.</span>
<span class="linenos">36</span> <span class="n">enquire</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Enquire</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">37</span>
<span class="linenos">38</span> <span class="c1"># Combine command line arguments up to "--" with spaces between</span>
<span class="linenos">39</span> <span class="c1"># them, so that simple queries don't have to be quoted at the shell</span>
<span class="linenos">40</span> <span class="c1"># level.</span>
<span class="linenos">41</span> <span class="n">query_string</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
<span class="linenos">42</span> <span class="n">index</span> <span class="o">=</span> <span class="mi">3</span>
<span class="linenos">43</span> <span class="k">while</span> <span class="n">index</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">):</span>
<span class="linenos">44</span> <span class="n">arg</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="n">index</span><span class="p">]</span>
<span class="linenos">45</span> <span class="n">index</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="linenos">46</span> <span class="k">if</span> <span class="n">arg</span> <span class="o">==</span> <span class="s1">'--'</span><span class="p">:</span>
<span class="linenos">47</span> <span class="c1"># Passed marker, move to parsing relevant docids.</span>
<span class="linenos">48</span> <span class="k">break</span>
<span class="linenos">49</span> <span class="n">query_string</span> <span class="o">+=</span> <span class="s1">' '</span>
<span class="linenos">50</span> <span class="n">query_string</span> <span class="o">+=</span> <span class="n">arg</span>
<span class="linenos">51</span>
<span class="linenos">52</span> <span class="c1"># Create an RSet with the listed docids in.</span>
<span class="linenos">53</span> <span class="n">reldocs</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">RSet</span><span class="p">()</span>
<span class="linenos">54</span> <span class="k">for</span> <span class="n">index</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">index</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)):</span>
<span class="linenos">55</span> <span class="n">reldocs</span><span class="o">.</span><span class="n">add_document</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="n">index</span><span class="p">]))</span>
<span class="linenos">56</span>
<span class="linenos">57</span> <span class="c1"># Parse the query string to produce a Xapian::Query object.</span>
<span class="linenos">58</span> <span class="n">qp</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="p">()</span>
<span class="linenos">59</span> <span class="n">stemmer</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Stem</span><span class="p">(</span><span class="s2">"english"</span><span class="p">)</span>
<span class="linenos">60</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemmer</span><span class="p">(</span><span class="n">stemmer</span><span class="p">)</span>
<span class="linenos">61</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_database</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">62</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemming_strategy</span><span class="p">(</span><span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="o">.</span><span class="n">STEM_SOME</span><span class="p">)</span>
<span class="linenos">63</span> <span class="n">query</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">parse_query</span><span class="p">(</span><span class="n">query_string</span><span class="p">)</span>
<span class="linenos">64</span>
<span class="linenos">65</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">query</span><span class="o">.</span><span class="n">empty</span><span class="p">():</span>
<span class="linenos">66</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Parsed query is: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">query</span><span class="p">))</span>
<span class="linenos">67</span>
<span class="linenos">68</span> <span class="c1"># Find the top 10 results for the query.</span>
<span class="linenos">69</span> <span class="n">enquire</span><span class="o">.</span><span class="n">set_query</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
<span class="linenos">70</span> <span class="n">matches</span> <span class="o">=</span> <span class="n">enquire</span><span class="o">.</span><span class="n">get_mset</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="n">reldocs</span><span class="p">)</span>
<span class="linenos">71</span>
<span class="linenos">72</span> <span class="c1"># Display the results.</span>
<span class="linenos">73</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2"> results found."</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">get_matches_estimated</span><span class="p">())</span>
<span class="linenos">74</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Results 1-</span><span class="si">%i</span><span class="s2">:"</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">size</span><span class="p">())</span>
<span class="linenos">75</span>
<span class="linenos">76</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">matches</span><span class="p">:</span>
<span class="linenos">77</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2">: </span><span class="si">%i%%</span><span class="s2"> docid=</span><span class="si">%i</span><span class="s2"> [</span><span class="si">%s</span><span class="s2">]"</span> <span class="o">%</span> <span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">rank</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">percent</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">docid</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">document</span><span class="o">.</span><span class="n">get_data</span><span class="p">()))</span>
<span class="linenos">78</span>
<span class="linenos">79</span> <span class="c1"># Put the top 5 (at most) docs into the rset if rset is empty</span>
<span class="linenos">80</span> <span class="k">if</span> <span class="n">reldocs</span><span class="o">.</span><span class="n">empty</span><span class="p">():</span>
<span class="linenos">81</span> <span class="n">rel_count</span> <span class="o">=</span> <span class="mi">0</span>
<span class="linenos">82</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">matches</span><span class="p">:</span>
<span class="linenos">83</span> <span class="n">reldocs</span><span class="o">.</span><span class="n">add_document</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">docid</span><span class="p">)</span>
<span class="linenos">84</span> <span class="n">rel_count</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="linenos">85</span> <span class="k">if</span> <span class="n">rel_count</span> <span class="o">==</span> <span class="mi">5</span><span class="p">:</span>
<span class="linenos">86</span> <span class="k">break</span>
<span class="linenos">87</span>
<span class="linenos">88</span> <span class="c1"># Get the suggested expand terms</span>
<span class="linenos">89</span> <span class="n">eterms</span> <span class="o">=</span> <span class="n">enquire</span><span class="o">.</span><span class="n">get_eset</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="n">reldocs</span><span class="p">)</span>
<span class="linenos">90</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2"> suggested additional terms"</span> <span class="o">%</span> <span class="n">eterms</span><span class="o">.</span><span class="n">size</span><span class="p">())</span>
<span class="linenos">91</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">eterms</span><span class="p">:</span>
<span class="linenos">92</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">k</span><span class="o">.</span><span class="n">term</span><span class="p">,</span> <span class="n">k</span><span class="o">.</span><span class="n">weight</span><span class="p">))</span>
<span class="linenos">93</span>
<span class="linenos">94</span><span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="linenos">95</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Exception: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">96</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="simplematchdecider-py">
<span id="simplematchdecider"></span><h2>simplematchdecider.py<a class="headerlink" href="#simplematchdecider-py" title="Permalink to this headline">¶</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="ch">#!/usr/bin/env python</span>
<span class="linenos"> 2</span><span class="c1">#</span>
<span class="linenos"> 3</span><span class="c1"># Simple command-line match decider example</span>
<span class="linenos"> 4</span><span class="c1">#</span>
<span class="linenos"> 5</span><span class="c1"># Copyright (C) 2003 James Aylett</span>
<span class="linenos"> 6</span><span class="c1"># Copyright (C) 2004,2007,2009,2013 Olly Betts</span>
<span class="linenos"> 7</span><span class="c1">#</span>
<span class="linenos"> 8</span><span class="c1"># This program is free software; you can redistribute it and/or</span>
<span class="linenos"> 9</span><span class="c1"># modify it under the terms of the GNU General Public License as</span>
<span class="linenos">10</span><span class="c1"># published by the Free Software Foundation; either version 2 of the</span>
<span class="linenos">11</span><span class="c1"># License, or (at your option) any later version.</span>
<span class="hll"><span class="linenos">12</span><span class="c1">#</span>
</span><span class="linenos">13</span><span class="c1"># This program is distributed in the hope that it will be useful,</span>
<span class="linenos">14</span><span class="c1"># but WITHOUT ANY WARRANTY; without even the implied warranty of</span>
<span class="hll"><span class="linenos">15</span><span class="c1"># MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the</span>
</span><span class="hll"><span class="linenos">16</span><span class="c1"># GNU General Public License for more details.</span>
</span><span class="hll"><span class="linenos">17</span><span class="c1">#</span>
</span><span class="hll"><span class="linenos">18</span><span class="c1"># You should have received a copy of the GNU General Public License</span>
</span><span class="linenos">19</span><span class="c1"># along with this program; if not, write to the Free Software</span>
<span class="linenos">20</span><span class="c1"># Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301</span>
<span class="linenos">21</span><span class="c1"># USA</span>
<span class="linenos">22</span>
<span class="linenos">23</span><span class="kn">import</span> <span class="nn">sys</span>
<span class="linenos">24</span><span class="kn">import</span> <span class="nn">xapian</span>
<span class="linenos">25</span>
<span class="linenos">26</span><span class="c1"># This example runs a query like simplesearch does, but uses a MatchDecider</span>
<span class="linenos">27</span><span class="c1"># (mymatchdecider) to discard any document for which value 0 is equal to</span>
<span class="linenos">28</span><span class="c1"># the string passed as the second command line argument.</span>
<span class="linenos">29</span>
<span class="linenos">30</span><span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">4</span><span class="p">:</span>
<span class="linenos">31</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Usage: </span><span class="si">%s</span><span class="s2"> PATH_TO_DATABASE AVOID_VALUE QUERY"</span> <span class="o">%</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">32</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="linenos">33</span>
<span class="linenos">34</span><span class="k">class</span> <span class="nc">mymatchdecider</span><span class="p">(</span><span class="n">xapian</span><span class="o">.</span><span class="n">MatchDecider</span><span class="p">):</span>
<span class="linenos">35</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">avoidvalue</span><span class="p">):</span>
<span class="linenos">36</span> <span class="n">xapian</span><span class="o">.</span><span class="n">MatchDecider</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
<span class="linenos">37</span> <span class="bp">self</span><span class="o">.</span><span class="n">avoidvalue</span> <span class="o">=</span> <span class="n">avoidvalue</span>
<span class="linenos">38</span>
<span class="linenos">39</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">doc</span><span class="p">):</span>
<span class="linenos">40</span> <span class="k">return</span> <span class="n">doc</span><span class="o">.</span><span class="n">get_value</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">avoidvalue</span>
<span class="linenos">41</span>
<span class="linenos">42</span><span class="k">try</span><span class="p">:</span>
<span class="linenos">43</span> <span class="c1"># Open the database for searching.</span>
<span class="linenos">44</span> <span class="n">database</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Database</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="linenos">45</span>
<span class="linenos">46</span> <span class="c1"># Start an enquire session.</span>
<span class="linenos">47</span> <span class="n">enquire</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Enquire</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">48</span>
<span class="linenos">49</span> <span class="c1"># Combine the rest of the command line arguments with spaces between</span>
<span class="linenos">50</span> <span class="c1"># them, so that simple queries don't have to be quoted at the shell</span>
<span class="linenos">51</span> <span class="c1"># level.</span>
<span class="linenos">52</span> <span class="n">avoid_value</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
<span class="linenos">53</span> <span class="n">query_string</span> <span class="o">=</span> <span class="nb">str</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">' '</span><span class="p">,</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">3</span><span class="p">:])</span>
<span class="linenos">54</span>
<span class="linenos">55</span> <span class="c1"># Parse the query string to produce a Xapian::Query object.</span>
<span class="linenos">56</span> <span class="n">qp</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="p">()</span>
<span class="linenos">57</span> <span class="n">stemmer</span> <span class="o">=</span> <span class="n">xapian</span><span class="o">.</span><span class="n">Stem</span><span class="p">(</span><span class="s2">"english"</span><span class="p">)</span>
<span class="linenos">58</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemmer</span><span class="p">(</span><span class="n">stemmer</span><span class="p">)</span>
<span class="linenos">59</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_database</span><span class="p">(</span><span class="n">database</span><span class="p">)</span>
<span class="linenos">60</span> <span class="n">qp</span><span class="o">.</span><span class="n">set_stemming_strategy</span><span class="p">(</span><span class="n">xapian</span><span class="o">.</span><span class="n">QueryParser</span><span class="o">.</span><span class="n">STEM_SOME</span><span class="p">)</span>
<span class="linenos">61</span> <span class="n">query</span> <span class="o">=</span> <span class="n">qp</span><span class="o">.</span><span class="n">parse_query</span><span class="p">(</span><span class="n">query_string</span><span class="p">)</span>
<span class="linenos">62</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Parsed query is: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">query</span><span class="p">))</span>
<span class="linenos">63</span>
<span class="linenos">64</span> <span class="c1"># Find the top 10 results for the query.</span>
<span class="linenos">65</span> <span class="n">enquire</span><span class="o">.</span><span class="n">set_query</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
<span class="linenos">66</span> <span class="n">mdecider</span> <span class="o">=</span> <span class="n">mymatchdecider</span><span class="p">(</span><span class="n">avoid_value</span><span class="p">)</span>
<span class="linenos">67</span> <span class="n">matches</span> <span class="o">=</span> <span class="n">enquire</span><span class="o">.</span><span class="n">get_mset</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">mdecider</span><span class="p">)</span>
<span class="linenos">68</span>
<span class="linenos">69</span> <span class="c1"># Display the results.</span>
<span class="linenos">70</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2"> results found."</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">get_matches_estimated</span><span class="p">())</span>
<span class="linenos">71</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Results 1-</span><span class="si">%i</span><span class="s2">:"</span> <span class="o">%</span> <span class="n">matches</span><span class="o">.</span><span class="n">size</span><span class="p">())</span>
<span class="linenos">72</span>
<span class="linenos">73</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">matches</span><span class="p">:</span>
<span class="linenos">74</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%i</span><span class="s2">: </span><span class="si">%i%%</span><span class="s2"> docid=</span><span class="si">%i</span><span class="s2"> [</span><span class="si">%s</span><span class="s2">]"</span> <span class="o">%</span> <span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">rank</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">percent</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">docid</span><span class="p">,</span> <span class="n">m</span><span class="o">.</span><span class="n">document</span><span class="o">.</span><span class="n">get_data</span><span class="p">()))</span>
<span class="linenos">75</span>
<span class="linenos">76</span><span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="linenos">77</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Exception: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">),</span> <span class="n">file</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
<span class="linenos">78</span> <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
</section>
</section>
<div class="clearer"></div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<h3><a href="index.html">Table of Contents</a></h3>
<ul>
<li><a class="reference internal" href="#">Examples</a><ul>
<li><a class="reference internal" href="#simplesearch-py">simplesearch.py</a></li>
<li><a class="reference internal" href="#simpleindex-py">simpleindex.py</a></li>
<li><a class="reference internal" href="#simpleexpand-py">simpleexpand.py</a></li>
<li><a class="reference internal" href="#simplematchdecider-py">simplematchdecider.py</a></li>
</ul>
</li>
</ul>
<h4>Previous topic</h4>
<p class="topless"><a href="introduction.html"
title="previous chapter">Python3 bindings for Xapian</a></p>
<h4>Next topic</h4>
<p class="topless"><a href="xapian.html"
title="next chapter">xapian Package</a></p>
<div role="note" aria-label="source link">
<h3>This Page</h3>
<ul class="this-page-menu">
<li><a href="_sources/examples.rst.txt"
rel="nofollow">Show Source</a></li>
</ul>
</div>
<div 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>
</div>
<script>$('#searchbox').show(0);</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="genindex.html" title="General Index"
>index</a></li>
<li class="right" >
<a href="xapian.html" title="xapian Package"
>next</a> |</li>
<li class="right" >
<a href="introduction.html" title="Python3 bindings for Xapian"
>previous</a> |</li>
<li class="nav-item nav-item-0"><a href="index.html">Xapian Python3 Bindings 1.4.18 documentation</a> »</li>
<li class="nav-item nav-item-this"><a href="">Examples</a></li>
</ul>
</div>
<div class="footer" role="contentinfo">
© Copyright .
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 4.3.2.
</div>
</body>
</html>