blob: 6ce1591ca6c4860137b5c449522a21d03ed5e76a [file] [log] [blame]
<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="./">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>apache_beam.io.filebasedsink module &mdash; Apache Beam 2.67.0 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" />
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" />
<script src="_static/jquery.js?v=5d32c60e"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="_static/documentation_options.js?v=959b4fbe"></script>
<script src="_static/doctools.js?v=9a2dae69"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/js/theme.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="apache_beam.io.filebasedsource module" href="apache_beam.io.filebasedsource.html" />
<link rel="prev" title="apache_beam.io.debezium module" href="apache_beam.io.debezium.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" aria-label="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="Navigation menu">
<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 current"><a class="current reference internal" href="#">apache_beam.io.filebasedsink module</a><ul>
<li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.filebasedsink.FileBasedSink"><code class="docutils literal notranslate"><span class="pre">FileBasedSink</span></code></a></li>
</ul>
</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"><a class="reference internal" href="apache_beam.io.hadoopfilesystem.html">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.requestresponse.html">apache_beam.io.requestresponse 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.testing.html">apache_beam.testing 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>
<li class="toctree-l1"><a class="reference internal" href="apache_beam.yaml.html">apache_beam.yaml 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="Mobile navigation menu" >
<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="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="apache_beam.io.html">apache_beam.io package</a></li>
<li class="breadcrumb-item active">apache_beam.io.filebasedsink module</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/apache_beam.io.filebasedsink.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">
<section id="module-apache_beam.io.filebasedsink">
<span id="apache-beam-io-filebasedsink-module"></span><h1>apache_beam.io.filebasedsink module<a class="headerlink" href="#module-apache_beam.io.filebasedsink" title="Link to this heading"></a></h1>
<p>File-based sink.</p>
<dl class="py class">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.io.filebasedsink.</span></span><span class="sig-name descname"><span class="pre">FileBasedSink</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_path_prefix</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">coder</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name_suffix</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">''</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_shards</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">shard_name_template</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">mime_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'application/octet-stream'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compression_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'auto'</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_records_per_shard</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_bytes_per_shard</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_if_empty</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink" title="Link to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.Sink" title="apache_beam.io.iobase.Sink"><code class="xref py py-class docutils literal notranslate"><span class="pre">Sink</span></code></a></p>
<p>A sink to a GCS or local files.</p>
<p>To implement a file-based sink, extend this class and override
either <a class="reference internal" href="#apache_beam.io.filebasedsink.FileBasedSink.write_record" title="apache_beam.io.filebasedsink.FileBasedSink.write_record"><code class="xref py py-meth docutils literal notranslate"><span class="pre">write_record()</span></code></a> or <a class="reference internal" href="#apache_beam.io.filebasedsink.FileBasedSink.write_encoded_record" title="apache_beam.io.filebasedsink.FileBasedSink.write_encoded_record"><code class="xref py py-meth docutils literal notranslate"><span class="pre">write_encoded_record()</span></code></a>.</p>
<p>If needed, also overwrite <a class="reference internal" href="#apache_beam.io.filebasedsink.FileBasedSink.open" title="apache_beam.io.filebasedsink.FileBasedSink.open"><code class="xref py py-meth docutils literal notranslate"><span class="pre">open()</span></code></a> and/or <a class="reference internal" href="#apache_beam.io.filebasedsink.FileBasedSink.close" title="apache_beam.io.filebasedsink.FileBasedSink.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a> to customize
the file handling or write headers and footers.</p>
<p>The output of this write is a <a class="reference internal" href="apache_beam.pvalue.html#apache_beam.pvalue.PCollection" title="apache_beam.pvalue.PCollection"><code class="xref py py-class docutils literal notranslate"><span class="pre">PCollection</span></code></a> of
all written shards.</p>
<dl class="field-list simple">
<dt class="field-odd">Raises<span class="colon">:</span></dt>
<dd class="field-odd"><ul class="simple">
<li><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#TypeError" title="(in Python v3.13)"><strong>TypeError</strong></a> – if file path parameters are not a <a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a> or
<a class="reference internal" href="apache_beam.options.value_provider.html#apache_beam.options.value_provider.ValueProvider" title="apache_beam.options.value_provider.ValueProvider"><code class="xref py py-class docutils literal notranslate"><span class="pre">ValueProvider</span></code></a>, or if
<strong>compression_type</strong> is not member of
<a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.CompressionTypes" title="apache_beam.io.filesystem.CompressionTypes"><code class="xref py py-class docutils literal notranslate"><span class="pre">CompressionTypes</span></code></a>.</p></li>
<li><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#ValueError" title="(in Python v3.13)"><strong>ValueError</strong></a> – if <strong>shard_name_template</strong> is not of expected
format.</p></li>
</ul>
</dd>
</dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.display_data">
<span class="sig-name descname"><span class="pre">display_data</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.display_data"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.display_data" title="Link to this definition"></a></dt>
<dd></dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.open">
<span class="sig-name descname"><span class="pre">open</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">temp_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.open"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.open" title="Link to this definition"></a></dt>
<dd><p>Opens <code class="docutils literal notranslate"><span class="pre">temp_path</span></code>, returning an opaque file handle object.</p>
<p>The returned file handle is passed to <code class="docutils literal notranslate"><span class="pre">write_[encoded_]record</span></code> and
<code class="docutils literal notranslate"><span class="pre">close</span></code>.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.write_record">
<span class="sig-name descname"><span class="pre">write_record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_handle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.write_record"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.write_record" title="Link to this definition"></a></dt>
<dd><p>Writes a single record go the file handle returned by <code class="docutils literal notranslate"><span class="pre">open()</span></code>.</p>
<p>By default, calls <code class="docutils literal notranslate"><span class="pre">write_encoded_record</span></code> after encoding the record with
this sink’s Coder.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.write_encoded_record">
<span class="sig-name descname"><span class="pre">write_encoded_record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_handle</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">encoded_value</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.write_encoded_record"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.write_encoded_record" title="Link to this definition"></a></dt>
<dd><p>Writes a single encoded record to the file handle returned by <code class="docutils literal notranslate"><span class="pre">open()</span></code>.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.close">
<span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file_handle</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.close"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.close" title="Link to this definition"></a></dt>
<dd><p>Finalize and close the file handle returned from <code class="docutils literal notranslate"><span class="pre">open()</span></code>.</p>
<p>Called after all records are written.</p>
<p>By default, calls <code class="docutils literal notranslate"><span class="pre">file_handle.close()</span></code> iff it is not None.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.initialize_write">
<span class="sig-name descname"><span class="pre">initialize_write</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.initialize_write"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.initialize_write" title="Link to this definition"></a></dt>
<dd></dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.open_writer">
<span class="sig-name descname"><span class="pre">open_writer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">uid</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.open_writer"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.open_writer" title="Link to this definition"></a></dt>
<dd></dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.pre_finalize">
<span class="sig-name descname"><span class="pre">pre_finalize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">writer_results</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.pre_finalize"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.pre_finalize" title="Link to this definition"></a></dt>
<dd></dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.io.filebasedsink.FileBasedSink.finalize_write">
<span class="sig-name descname"><span class="pre">finalize_write</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">init_result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">writer_results</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unused_pre_finalize_results</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filebasedsink.html#FileBasedSink.finalize_write"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filebasedsink.FileBasedSink.finalize_write" title="Link to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="apache_beam.io.debezium.html" class="btn btn-neutral float-left" title="apache_beam.io.debezium module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="apache_beam.io.filebasedsource.html" class="btn btn-neutral float-right" title="apache_beam.io.filebasedsource module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright %Y, Apache Beam.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>