| |
| |
| <!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.filesystems module — Apache Beam 2.68.0 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=2388e03a"></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.hadoopfilesystem module" href="apache_beam.io.hadoopfilesystem.html" /> |
| <link rel="prev" title="apache_beam.io.filesystemio module" href="apache_beam.io.filesystemio.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"><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 current"><a class="current reference internal" href="#">apache_beam.io.filesystems module</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.filesystems.FileSystems"><code class="docutils literal notranslate"><span class="pre">FileSystems</span></code></a></li> |
| </ul> |
| </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.filesystems module</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="_sources/apache_beam.io.filesystems.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.filesystems"> |
| <span id="apache-beam-io-filesystems-module"></span><h1>apache_beam.io.filesystems module<a class="headerlink" href="#module-apache_beam.io.filesystems" title="Link to this heading"></a></h1> |
| <p>FileSystems interface class for accessing the correct filesystem</p> |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.io.filesystems.</span></span><span class="sig-name descname"><span class="pre">FileSystems</span></span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.13)"><code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></a></p> |
| <p>A class that defines the functions that can be performed on a filesystem. |
| All methods are static and access the underlying registered filesystems.</p> |
| <dl class="py attribute"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.URI_SCHEMA_PATTERN"> |
| <span class="sig-name descname"><span class="pre">URI_SCHEMA_PATTERN</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">re.compile('(?P<scheme>[a-zA-Z][-a-zA-Z0-9+.]*)://.*')</span></em><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.URI_SCHEMA_PATTERN" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.set_options"> |
| <em class="property"><span class="pre">classmethod</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">set_options</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pipeline_options</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.set_options"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.set_options" title="Link to this definition"></a></dt> |
| <dd><p>Set filesystem options.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>pipeline_options</strong> – Instance of <code class="docutils literal notranslate"><span class="pre">PipelineOptions</span></code>.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.get_scheme"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_scheme</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.get_scheme"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.get_scheme" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.get_filesystem"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_filesystem</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.FileSystem" title="apache_beam.io.filesystem.FileSystem"><span class="pre">FileSystem</span></a></span></span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.get_filesystem"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.get_filesystem" title="Link to this definition"></a></dt> |
| <dd><p>Get the correct filesystem for the specified path</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.join"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">join</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">basepath</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">paths</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.join"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.join" title="Link to this definition"></a></dt> |
| <dd><p>Join two or more pathname components for the filesystem</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>basepath</strong> – string path of the first component of the path</p></li> |
| <li><p><strong>paths</strong> – path components to be added</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>Returns: full path after combining all the passed components</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.split"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">split</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.split"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.split" title="Link to this definition"></a></dt> |
| <dd><p>Splits the given path into two parts.</p> |
| <p>Splits the path into a pair (head, tail) such that tail contains the last |
| component of the path and head contains everything up to that.</p> |
| <p>For file-systems other than the local file-system, head should include the |
| prefix.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – path as a string</p> |
| </dd> |
| <dt class="field-even">Returns<span class="colon">:</span></dt> |
| <dd class="field-even"><p>a pair of path components as strings.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.mkdirs"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">mkdirs</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.mkdirs"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.mkdirs" title="Link to this definition"></a></dt> |
| <dd><p>Recursively create directories for the provided path.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path of the directory structure that should be created</p> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#IOError" title="(in Python v3.13)"><strong>IOError</strong></a> – if leaf directory already exists.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.match"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">match</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">patterns</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">limits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.match"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.match" title="Link to this definition"></a></dt> |
| <dd><p>Find all matching paths to the patterns provided.</p> |
| <p>Pattern matching is done using each filesystem’s <code class="docutils literal notranslate"><span class="pre">match</span></code> method (e.g. |
| <a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.FileSystem.match" title="apache_beam.io.filesystem.FileSystem.match"><code class="xref py py-meth docutils literal notranslate"><span class="pre">filesystem.FileSystem.match()</span></code></a>).</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <ul class="simple"> |
| <li><p>Depending on the <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, file listings |
| (the <code class="docutils literal notranslate"><span class="pre">.FileSystem._list</span></code> method) may not be recursive.</p></li> |
| <li><p>If the file listing is not recursive, a pattern like |
| <code class="docutils literal notranslate"><span class="pre">scheme://path/*/foo</span></code> will not be able to mach any files.</p></li> |
| </ul> |
| </div> |
| <div class="admonition seealso"> |
| <p class="admonition-title">See also</p> |
| <p><a class="reference internal" href="apache_beam.io.filesystem.html#apache_beam.io.filesystem.FileSystem.match" title="apache_beam.io.filesystem.FileSystem.match"><code class="xref py py-meth docutils literal notranslate"><span class="pre">filesystem.FileSystem.match()</span></code></a></p> |
| </div> |
| <dl class="simple"> |
| <dt>Pattern syntax:</dt><dd><p>The pattern syntax is based on the <a class="reference external" href="https://docs.python.org/2/library/fnmatch.html">fnmatch</a> syntax, with the following |
| differences:</p> |
| <ul class="simple"> |
| <li><p><code class="docutils literal notranslate"><span class="pre">*</span></code> Is equivalent to <code class="docutils literal notranslate"><span class="pre">[^/\]*</span></code> rather than <code class="docutils literal notranslate"><span class="pre">.*</span></code>.</p></li> |
| <li><p><code class="docutils literal notranslate"><span class="pre">**</span></code> Is equivalent to <code class="docutils literal notranslate"><span class="pre">.*</span></code>.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>patterns</strong> – list of string for the file path pattern to match against</p></li> |
| <li><p><strong>limits</strong> – list of maximum number of responses that need to be fetched</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>Returns: list of <code class="docutils literal notranslate"><span class="pre">MatchResult</span></code> objects.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Raises<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>BeamIOError</strong> – if any of the pattern match operations fail</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.create"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">create</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</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><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.BinaryIO" title="(in Python v3.13)"><span class="pre">BinaryIO</span></a></span></span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.create"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.create" title="Link to this definition"></a></dt> |
| <dd><p>Returns a write channel for the given file path.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> – string path of the file object to be written to the system</p></li> |
| <li><p><strong>mime_type</strong> – MIME type to specify the type of content in the file object</p></li> |
| <li><p><strong>compression_type</strong> – Type of compression to be used for this object. See |
| <code class="docutils literal notranslate"><span class="pre">CompressionTypes</span></code> for possible values.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>Returns: file handle with a <code class="docutils literal notranslate"><span class="pre">close</span></code> function for the user to use.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.open"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><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">path</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><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.BinaryIO" title="(in Python v3.13)"><span class="pre">BinaryIO</span></a></span></span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.open"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.open" title="Link to this definition"></a></dt> |
| <dd><p>Returns a read channel for the given file path.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> – string path of the file object to be written to the system</p></li> |
| <li><p><strong>mime_type</strong> – MIME type to specify the type of content in the file object</p></li> |
| <li><p><strong>compression_type</strong> – Type of compression to be used for this object. See |
| <code class="docutils literal notranslate"><span class="pre">CompressionTypes</span></code> for possible values.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>Returns: file handle with a <code class="docutils literal notranslate"><span class="pre">close</span></code> function for the user to use.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.copy"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">copy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_file_names</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination_file_names</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.copy"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.copy" title="Link to this definition"></a></dt> |
| <dd><p>Recursively copy the file list from the source to the destination</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source_file_names</strong> – list of source file objects that needs to be copied</p></li> |
| <li><p><strong>destination_file_names</strong> – list of destination of the new object</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><strong>BeamIOError</strong> – if any of the copy operations fail</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.rename"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">rename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_file_names</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">destination_file_names</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.rename"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.rename" title="Link to this definition"></a></dt> |
| <dd><p>Rename the files at the source list to the destination list. |
| Source and destination lists should be of the same size.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source_file_names</strong> – List of file paths that need to be moved</p></li> |
| <li><p><strong>destination_file_names</strong> – List of destination_file_names for the files</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><strong>BeamIOError</strong> – if any of the rename operations fail</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.exists"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">exists</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.exists"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.exists" title="Link to this definition"></a></dt> |
| <dd><p>Check if the provided path exists on the FileSystem.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path that needs to be checked.</p> |
| </dd> |
| </dl> |
| <p>Returns: boolean flag indicating if path exists</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.last_updated"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">last_updated</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.last_updated"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.last_updated" title="Link to this definition"></a></dt> |
| <dd><p>Get UNIX Epoch time in seconds on the FileSystem.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path of file.</p> |
| </dd> |
| </dl> |
| <p>Returns: float UNIX Epoch time</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Raises<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>BeamIOError</strong> – if path doesn’t exist.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.checksum"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">checksum</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.checksum"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.checksum" title="Link to this definition"></a></dt> |
| <dd><p>Fetch checksum metadata of a file on the |
| <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>.</p> |
| <p>This operation returns checksum metadata as stored in the underlying |
| FileSystem. It should not read any file data. Checksum type and format are |
| FileSystem dependent and are not compatible between FileSystems.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path of a file.</p> |
| </dd> |
| </dl> |
| <p>Returns: string containing checksum</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Raises<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>BeamIOError</strong> – if path isn’t a file or doesn’t exist.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.delete"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">delete</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">paths</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.delete"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.delete" title="Link to this definition"></a></dt> |
| <dd><p>Deletes files or directories at the provided paths. |
| Directories will be deleted recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>paths</strong> – list of paths that give the file objects to be deleted</p> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><strong>BeamIOError</strong> – if any of the delete operations fail</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.get_chunk_size"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">get_chunk_size</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.get_chunk_size"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.get_chunk_size" title="Link to this definition"></a></dt> |
| <dd><p>Get the correct chunk size for the FileSystem.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path that needs to be checked.</p> |
| </dd> |
| </dl> |
| <p>Returns: integer size for parallelization in the FS operations.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.report_source_lineage"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">report_source_lineage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.report_source_lineage"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.report_source_lineage" title="Link to this definition"></a></dt> |
| <dd><p>Report source <a class="reference internal" href="apache_beam.metrics.metric.html#apache_beam.metrics.metric.Lineage" title="apache_beam.metrics.metric.Lineage"><code class="xref py py-class docutils literal notranslate"><span class="pre">Lineage</span></code></a>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path to be reported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.io.filesystems.FileSystems.report_sink_lineage"> |
| <em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">report_sink_lineage</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/filesystems.html#FileSystems.report_sink_lineage"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.filesystems.FileSystems.report_sink_lineage" title="Link to this definition"></a></dt> |
| <dd><p>Report sink <a class="reference internal" href="apache_beam.metrics.metric.html#apache_beam.metrics.metric.Lineage" title="apache_beam.metrics.metric.Lineage"><code class="xref py py-class docutils literal notranslate"><span class="pre">Lineage</span></code></a>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>path</strong> – string path to be reported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="apache_beam.io.filesystemio.html" class="btn btn-neutral float-left" title="apache_beam.io.filesystemio module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="apache_beam.io.hadoopfilesystem.html" class="btn btn-neutral float-right" title="apache_beam.io.hadoopfilesystem module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© 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> |
