blob: 4a739e94658aae03e89f2324c5181a46287d88ff [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>apache_beam.io.hadoopfilesystem module &mdash; Apache Beam documentation</title>
<script type="text/javascript" src="_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
<script type="text/javascript" src="_static/jquery.js"></script>
<script type="text/javascript" src="_static/underscore.js"></script>
<script type="text/javascript" src="_static/doctools.js"></script>
<script type="text/javascript" src="_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="_static/js/theme.js"></script>
<link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="apache_beam.io.iobase module" href="apache_beam.io.iobase.html" />
<link rel="prev" title="apache_beam.io.filesystems module" href="apache_beam.io.filesystems.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="index.html" class="icon icon-home"> Apache Beam
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="apache_beam.io.html#subpackages">Subpackages</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="apache_beam.io.html#submodules">Submodules</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.avroio.html">apache_beam.io.avroio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.concat_source.html">apache_beam.io.concat_source module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.debezium.html">apache_beam.io.debezium module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filebasedsink.html">apache_beam.io.filebasedsink module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filebasedsource.html">apache_beam.io.filebasedsource module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.fileio.html">apache_beam.io.fileio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystem.html">apache_beam.io.filesystem module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystemio.html">apache_beam.io.filesystemio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystems.html">apache_beam.io.filesystems module</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">apache_beam.io.hadoopfilesystem module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.iobase.html">apache_beam.io.iobase module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.jdbc.html">apache_beam.io.jdbc module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.kafka.html">apache_beam.io.kafka module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.kinesis.html">apache_beam.io.kinesis module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.localfilesystem.html">apache_beam.io.localfilesystem module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.mongodbio.html">apache_beam.io.mongodbio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.parquetio.html">apache_beam.io.parquetio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.range_trackers.html">apache_beam.io.range_trackers module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.restriction_trackers.html">apache_beam.io.restriction_trackers module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.snowflake.html">apache_beam.io.snowflake module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.source_test_utils.html">apache_beam.io.source_test_utils module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.textio.html">apache_beam.io.textio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.tfrecordio.html">apache_beam.io.tfrecordio module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.utils.html">apache_beam.io.utils module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.io.watermark_estimators.html">apache_beam.io.watermark_estimators module</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="index.html">Docs</a> &raquo;</li>
<li><a href="apache_beam.io.html">apache_beam.io package</a> &raquo;</li>
<li>apache_beam.io.hadoopfilesystem module</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/apache_beam.io.hadoopfilesystem.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="module-apache_beam.io.hadoopfilesystem">
<span id="apache-beam-io-hadoopfilesystem-module"></span><h1>apache_beam.io.hadoopfilesystem module<a class="headerlink" href="#module-apache_beam.io.hadoopfilesystem" title="Permalink to this headline"></a></h1>
<p><a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.FileSystem" title="apache_beam.io.filesystem.FileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">FileSystem</span></code></a> implementation for accessing
Hadoop Distributed File System files.</p>
<dl class="class">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem">
<em class="property">class </em><code class="descclassname">apache_beam.io.hadoopfilesystem.</code><code class="descname">HadoopFileSystem</code><span class="sig-paren">(</span><em>pipeline_options</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.FileSystem" title="apache_beam.io.filesystem.FileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.io.filesystem.FileSystem</span></code></a></p>
<p><code class="docutils literal notranslate"><span class="pre">FileSystem</span></code> implementation that supports HDFS.</p>
<p>URL arguments to methods expect strings starting with <code class="docutils literal notranslate"><span class="pre">hdfs://</span></code>.</p>
<p>Initializes a connection to HDFS.</p>
<p>Connection configuration is done by passing pipeline options.
See <a class="reference internal" href="apache_beam.options.pipeline_options.html#apache_beam.options.pipeline_options.HadoopFileSystemOptions" title="apache_beam.options.pipeline_options.HadoopFileSystemOptions"><code class="xref py py-class docutils literal notranslate"><span class="pre">HadoopFileSystemOptions</span></code></a>.</p>
<dl class="classmethod">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.scheme">
<em class="property">classmethod </em><code class="descname">scheme</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.scheme"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.scheme" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.join">
<code class="descname">join</code><span class="sig-paren">(</span><em>base_url</em>, <em>*paths</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.join"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.join" title="Permalink to this definition"></a></dt>
<dd><p>Join two or more pathname components.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>base_url</strong> – string path of the first component of the path.
Must start with hdfs://.</li>
<li><strong>paths</strong> – path components to be added</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">Full url after combining all the passed components.</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.split">
<code class="descname">split</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.split"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.split" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.mkdirs">
<code class="descname">mkdirs</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.mkdirs"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.mkdirs" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.has_dirs">
<code class="descname">has_dirs</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.has_dirs"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.has_dirs" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.create">
<code class="descname">create</code><span class="sig-paren">(</span><em>url</em>, <em>mime_type='application/octet-stream'</em>, <em>compression_type='auto'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.create"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.create" title="Permalink to this definition"></a></dt>
<dd><table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">A Python File-like object.</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.open">
<code class="descname">open</code><span class="sig-paren">(</span><em>url</em>, <em>mime_type='application/octet-stream'</em>, <em>compression_type='auto'</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.open"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.open" title="Permalink to this definition"></a></dt>
<dd><table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">A Python File-like object.</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.copy">
<code class="descname">copy</code><span class="sig-paren">(</span><em>source_file_names</em>, <em>destination_file_names</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.copy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.copy" title="Permalink to this definition"></a></dt>
<dd><p>It is an error if any file to copy already exists at the destination.</p>
<p>Raises <code class="docutils literal notranslate"><span class="pre">BeamIOError</span></code> if any error occurred.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>source_file_names</strong> – iterable of URLs.</li>
<li><strong>destination_file_names</strong> – iterable of URLs.</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.rename">
<code class="descname">rename</code><span class="sig-paren">(</span><em>source_file_names</em>, <em>destination_file_names</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.rename"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.rename" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.exists">
<code class="descname">exists</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.exists"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.exists" title="Permalink to this definition"></a></dt>
<dd><p>Checks existence of url in HDFS.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>url</strong> – String in the form hdfs://…</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">True if url exists as a file or directory in HDFS.</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.size">
<code class="descname">size</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.size"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.size" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.last_updated">
<code class="descname">last_updated</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.last_updated"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.last_updated" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.checksum">
<code class="descname">checksum</code><span class="sig-paren">(</span><em>url</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.checksum"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.checksum" title="Permalink to this definition"></a></dt>
<dd><p>Fetches a checksum description for a URL.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">String describing the checksum.</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="apache_beam.io.hadoopfilesystem.HadoopFileSystem.delete">
<code class="descname">delete</code><span class="sig-paren">(</span><em>urls</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/hadoopfilesystem.html#HadoopFileSystem.delete"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.hadoopfilesystem.HadoopFileSystem.delete" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="apache_beam.io.iobase.html" class="btn btn-neutral float-right" title="apache_beam.io.iobase module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="apache_beam.io.filesystems.html" class="btn btn-neutral float-left" title="apache_beam.io.filesystems module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>