david
/
xowa
-ын хуулбар https://github.com/gnosygnu/xowa.git


			
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214
							<!DOCTYPE html>
<html dir="ltr">
<head>
  <meta http-equiv="content-type" content="text/html;charset=UTF-8" />
  <title>Dev/Command-line/Site meta - XOWA</title>
  <link rel="shortcut icon" href="https://gnosygnu.github.io/xowa/xowa_logo.png" />
  <link rel="stylesheet" href="https://gnosygnu.github.io/xowa/xowa_common.css" type="text/css">
  <style data-source="xowa" type="text/css">
.console   {font-family: monospace; color: #EEEEEE ; background-color: black    ; border: medium solid black;}
  .code
  ,.path
  ,.url      {font-family: monospace; color: black   ; background-color: #f9f9f9  ; border: medium solid #f9f9f9;}
  .bold      {font-weight: 900;}
</style>

</head>
<body class="mediawiki ltr sitedir-ltr ns-0 ns-subject skin-vector action-submit vector-animateLayout" spellcheck="false">
<div id="mw-page-base" class="noprint"></div>
<div id="mw-head-base" class="noprint"></div>
<div id="content" class="mw-body">
  <h1 id="firstHeading" class="firstHeading"><span>Dev/Command-line/Site meta</span></h1>
  <div id="bodyContent" class="mw-body-content">
    <div id="siteSub">From XOWA: the free, open-source, offline wiki application</div>
    <div id="contentSub"></div>
    <div id="mw-content-text" lang="en" dir="ltr" class="mw-content-ltr">
    
    <div id="toc" class="toc">
      <div id="toctitle" class="toctitle">
        <h2>
          Contents
        </h2>
      </div>
      <ul>
        <li class="toclevel-1 tocsection-1">
          <a href="#Background"><span class="tocnumber">1</span> <span class="toctext">Background</span></a>
        </li>
        <li class="toclevel-1 tocsection-2">
          <a href="#Process"><span class="tocnumber">2</span> <span class="toctext">Process</span></a>
        </li>
      </ul>
    </div>
    <p>
      XOWA can download the metadata for the Wikimedia wikis
    </p>
    <h2>
      <span class="mw-headline" id="Background">Background</span>
    </h2>
    <p>
      Wikimedia exposes an API for accessing the meta-data for a given wiki. For example, for English Wikipedia, the following will return most of the meta-data around the wiki installation.
    </p>
<pre class='code'>
https://en.wikipedia.org/w/api.php?action=query&amp;meta=siteinfo&amp;siprop=general|namespaces|statistics|interwikimap|namespacealiases|specialpagealiases|libraries|extensions|skins|magicwords|functionhooks|showhooks|extensiontags|protocols|defaultoptions|languages
</pre>
    <p>
      XOWA can call this API to download metadata for each wiki and save them in a database for data-processing. XOWA uses this info to resolve namespaces, but it will also incorporate other metadata from this API in future releases.
    </p>
    <h2>
      <span class="mw-headline" id="Process">Process</span>
    </h2>
    <p>
      Assuming you are on a Windows system with XOWA installed at <code>C:\xowa</code>
    </p>
    <ul>
      <li>
        Create a plain text-file called "C:\xowa\build_site_meta.gfs"
      </li>
      <li>
        Save the following text to the file:
      </li>
    </ul>
<pre class='code'>
app.bldr.pause_at_end_('n');
app.scripts.run_file_by_type('xowa_cfg_app');
app.bldr.cmds {

  // NOTE: wiki doesn't matter; just use any wiki name that is on your system
  add('simple.wikipedia.org', 'util.site_meta') {

    // path of the database to generate; default is C:\xowa\bin\any\xowa\cfg\wiki\site_meta.sqlite3
    db_url = 'C:\xowa\site_meta__enwiki.sqlite3';

    // skip any wikis which have been downloaded after this time. default is now() - 1 day
    // the purpose of this argument is to avoid recalling the api if it's already been called recently.
    // for example, if the script runs for 800 wikis and fails for 3 wikis,
    // you can rerun the script again and it will only download the 3 failed ones; not all 800
    cutoff_time = '2015-07-01';

    // list of wikis to download; note that each wiki must be separated by a new-line. default is all wikis listed in [[Dashboard/Import/Online]]
    wikis  = 
'en.wikipedia.org
en.wiktionary.org';
  }
}
app.bldr.run;
</pre>
    <ul>
      <li>
        Run the file with the following:
      </li>
    </ul>
<pre class='code'>
java -jar xowa_windows.jar --app_mode cmd --cmd_file C:\xowa\build_site_meta.gfs
</pre>
    <ul>
      <li>
        Open C:\xowa\site_meta__enwiki.sqlite3 in a sqlite shell and run the following:
      </li>
    </ul>
<pre class='code'>
SELECT * FROM site_statistic;
</pre>
  
    </div>
  </div>
</div>


<div id="mw-head" class="noprint">
  <div id="left-navigation">
    <div id="p-namespaces" class="vectorTabs">
      <h3>Namespaces</h3>
      <ul>
        <li  id="ca-nstab-main" class="selected"><span><a id="ca-nstab-main-href" href="index.html">Page</a></span></li>
      </ul>
    </div>
  </div>
</div>

<div id='mw-panel' class='noprint'>
  <div id='p-logo'>
    <a style="background-image: url(https://gnosygnu.github.io/xowa/xowa_logo.png);" href="http://xowa.org/" title="Visit the main page"></a>
  </div>
  <div class="portal" id='xowa-portal-home'>
    <h3>XOWA</h3>
    <div class="body">
      <ul>
        <li><a href="http://xowa.org/index.html" title='Visit the main page'>Main page</a></li>
        <li><a href="http://xowa.org/screenshots.html" title='See screenshots of XOWA'>Screenshots</a></li>
        <li><a href="https://www.youtube.com/watch?v=q0qbXYXEH6M" title="See a video of XOWA Desktop in action">Video</a></li>
        <li><a href="http://xowa.org/home/wiki/Help/Download_XOWA.html" title='Download the XOWA application'>Download XOWA</a></li>
        <li><a href="http://xowa.org/home/wiki/Dashboard/Image_databases.html" title='Download offline wikis and image databases'>Download wikis</a></li>
      </ul>
    </div>
  </div>

  <div class="portal" id='xowa-portal-started'>
    <h3>Getting started</h3>
    <div class="body">
      <ul>
        <li><a href="http://xowa.org/home/wiki/App/Setup/System_requirements.html" title='Get XOWA&apos;s system requirements'>Requirements</a></li>
        <li><a href="http://xowa.org/home/wiki/App/Setup/Installation.html" title='Get instructions for installing XOWA'>Installation</a></li>
        <li><a href="http://xowa.org/home/wiki/App/Import/Simple_Wikipedia.html" title='Learn how to set up Simple Wikipedia'>Simple Wikipedia</a></li>
        <li><a href="http://xowa.org/home/wiki/App/Import/English_Wikipedia.html" title='Learn how to set up English Wikipedia'>English Wikipedia</a></li>
        <li><a href="http://xowa.org/home/wiki/App/Import/Other_wikis.html" title='Learn how to set up other Wikipedias'>Other Wikipedias</a></li>
      </ul>
    </div>
  </div>

  <div class="portal" id='xowa-portal-android'>
    <h3>Android</h3>
    <div class="body">
      <ul>
        <li><a href="http://xowa.org/home/wiki/Android/Setup.html" title='Setup XOWA on your Android device'>Setup</a></li>
        <li><a href="https://www.youtube.com/watch?v=jsMTBxGweUw" title="See a video of XOWA Android in action">Video</a></li>
      </ul>
    </div>
  </div>

  <div class="portal" id='xowa-portal-help'>
    <h3>Help</h3>
    <div class="body">
      <ul>
        <li><a href="http://xowa.org/home/wiki/Help/About.html" title='Get more information about XOWA'>About</a></li>
        <li><a href="http://xowa.org/home/wiki/Help/Contents.html" title='View a list of help topics'>Contents</a></li>
        <li><a href="http://xowa.org/home/wiki/Help/Media.html" title='Read what others have written about XOWA'>Media</a></li>
        <li><a href="http://xowa.org/home/wiki/Help/Feedback.html" title='Questions? Comments? Leave feedback for XOWA'>Feedback</a></li>
      </ul>
    </div>
  </div>
  
  <div class="portal" id='xowa-portal-blog'>
    <h3>Blog</h3>
    <div class="body">
      <ul>
        <li><a href="http://xowa.org/home/wiki/Blog.html" title='Follow XOWA''s development process'>Current</a></li>
      </ul>
    </div>
  </div>

  <div class="portal" id='xowa-portal-links'>
    <h3>Links</h3>
    <div class="body">
      <ul>
        <li><a href="http://dumps.wikimedia.org/backup-index.html" title="Get wiki datababase dumps directly from Wikimedia">Wikimedia dumps</a></li>
        <li><a href="https://archive.org/search.php?query=xowa" title="Search archive.org for XOWA files">XOWA @ archive.org</a></li>
        <li><a href="http://en.wikipedia.org" title="Visit Wikipedia (and compare to XOWA!)">English Wikipedia</a></li>
      </ul>
    </div>
  </div>

  <div class="portal" id='xowa-portal-donate'>
    <h3>Donate</h3>
    <div class="body">
      <ul>
        <li><a href="https://archive.org/donate/index.php" title="Support archive.org!">archive.org</a></li><!-- listed first due to recent fire damages: http://blog.archive.org/2013/11/06/scanning-center-fire-please-help-rebuild/ -->
        <li><a href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector" title="Support Wikipedia!">Wikipedia</a></li>
        <li><a href="http://xowa.org/home/wiki/Help/Donate.html" title="Support XOWA!">XOWA</a></li>
      </ul>
    </div>
  </div>
  
</div>
</body>
</html>