| |
| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" > |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>Filesystem Interface — Apache Arrow v1.0.1</title> |
| |
| |
| |
| <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../_static/pygments.css" type="text/css" /> |
| |
| |
| |
| |
| |
| |
| |
| <!--[if lt IE 9]> |
| <script src="../_static/js/html5shiv.min.js"></script> |
| <![endif]--> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script> |
| <script src="../_static/jquery.js"></script> |
| <script src="../_static/underscore.js"></script> |
| <script src="../_static/doctools.js"></script> |
| <script src="../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../_static/js/theme.js"></script> |
| |
| |
| <link rel="canonical" href="https://arrow.apache.org/docs/python/filesystems.html" /> |
| <link rel="index" title="Index" href="../genindex.html" /> |
| <link rel="search" title="Search" href="../search.html" /> |
| <link rel="next" title="Filesystem Interface (legacy)" href="filesystems_deprecated.html" /> |
| <link rel="prev" title="Streaming, Serialization, and IPC" href="ipc.html" /> |
|
|
|
|
| <!-- Matomo -->
|
| <script>
|
| var _paq = window._paq = window._paq || [];
|
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */
|
| _paq.push(["setDoNotTrack", true]);
|
| _paq.push(["disableCookies"]);
|
| _paq.push(['trackPageView']);
|
| _paq.push(['enableLinkTracking']);
|
| (function() {
|
| var u="https://analytics.apache.org/";
|
| _paq.push(['setTrackerUrl', u+'matomo.php']);
|
| _paq.push(['setSiteId', '20']);
|
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
|
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
|
| })();
|
| </script>
|
| <!-- End Matomo Code -->
|
|
|
| </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" alt="Documentation Home"> Apache Arrow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.0.1 |
| </div> |
| |
| |
| |
| |
| <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"> |
| |
| |
| |
| |
| |
| |
| <p class="caption"><span class="caption-text">Specifications and Protocols</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Versioning.html">Format Versioning and Stability</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Columnar.html">Arrow Columnar Format</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Flight.html">Arrow Flight RPC</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Integration.html">Integration Testing</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/CDataInterface.html">The Arrow C data interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Other.html">Other Data Structures</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">Libraries</span></p> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../status.html">Implementation Status</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/c_glib/">C/GLib</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../cpp/index.html">C++</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/csharp/README.md">C#</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://godoc.org/github.com/apache/arrow/go/arrow">Go</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../java/index.html">Java</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/js/">JavaScript</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/matlab/README.md">MATLAB</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="index.html">Python</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="install.html">Installing PyArrow</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="memory.html">Memory and IO Interfaces</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="data.html">Data Types and In-Memory Data Model</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="ipc.html">Streaming, Serialization, and IPC</a></li> |
| <li class="toctree-l2 current"><a class="current reference internal" href="#">Filesystem Interface</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="#types">Types</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="#example">Example</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="filesystems_deprecated.html">Filesystem Interface (legacy)</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="plasma.html">The Plasma In-Memory Object Store</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="numpy.html">NumPy Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="pandas.html">Pandas Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="timestamps.html">Timestamps</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="csv.html">Reading CSV files</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="feather.html">Feather File Format</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="json.html">Reading JSON files</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="parquet.html">Reading and Writing the Apache Parquet Format</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="dataset.html">Tabular Datasets</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="cuda.html">CUDA Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="extending_types.html">Extending pyarrow</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="extending.html">Using pyarrow from C++ and Cython Code</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="api.html">API Reference</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="getting_involved.html">Getting Involved</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="benchmarks.html">Benchmarks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/r/">R</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/ruby/README.md">Ruby</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://docs.rs/crate/arrow/">Rust</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">Development</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/contributing.html">Contributing to Apache Arrow</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/cpp/index.html">C++ Development</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/python.html">Python Development</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/archery.html">Daily Development using Archery</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/crossbow.html">Packaging and Testing with Crossbow</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/docker.html">Running Docker Builds</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/benchmarks.html">Benchmarks</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/documentation.html">Building the Documentation</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 Arrow</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" class="icon icon-home"></a> »</li> |
| |
| <li><a href="index.html">Python bindings</a> »</li> |
| |
| <li>Filesystem Interface</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="../_sources/python/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"> |
| |
| <div class="section" id="filesystem-interface"> |
| <span id="filesystem"></span><h1>Filesystem Interface<a class="headerlink" href="#filesystem-interface" title="Permalink to this headline">¶</a></h1> |
| <p>PyArrow comes with an abstract filesystem interface, as well as concrete |
| implementations for various storage types.</p> |
| <p>The filesystem interface provides input and output streams as well as |
| directory operations. A simplified view of the underlying data |
| storage is exposed. Data paths are represented as <em>abstract paths</em>, which |
| are <code class="docutils literal notranslate"><span class="pre">/</span></code>-separated, even on Windows, and shouldn’t include special path |
| components such as <code class="docutils literal notranslate"><span class="pre">.</span></code> and <code class="docutils literal notranslate"><span class="pre">..</span></code>. Symbolic links, if supported by the |
| underlying storage, are automatically dereferenced. Only basic |
| <a class="reference internal" href="generated/pyarrow.fs.FileStats.html#pyarrow.fs.FileStats" title="pyarrow.fs.FileStats"><code class="xref py py-class docutils literal notranslate"><span class="pre">metadata</span></code></a> about file entries, such as the file size |
| and modification time, is made available.</p> |
| <div class="section" id="types"> |
| <h2>Types<a class="headerlink" href="#types" title="Permalink to this headline">¶</a></h2> |
| <p>The core interface is represented by the base class <a class="reference internal" href="generated/pyarrow.fs.FileSystem.html#pyarrow.fs.FileSystem" title="pyarrow.fs.FileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">FileSystem</span></code></a>. |
| Concrete subclasses are available for various kinds of storage: |
| <a class="reference internal" href="generated/pyarrow.fs.LocalFileSystem.html#pyarrow.fs.LocalFileSystem" title="pyarrow.fs.LocalFileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">local</span> <span class="pre">filesystem</span> <span class="pre">access</span></code></a>, |
| <a class="reference internal" href="generated/pyarrow.fs.HadoopFileSystem.html#pyarrow.fs.HadoopFileSystem" title="pyarrow.fs.HadoopFileSystem"><code class="xref py py-class docutils literal notranslate"><span class="pre">HDFS</span></code></a> and |
| <code class="xref py py-class docutils literal notranslate"><span class="pre">Amazon</span> <span class="pre">S3-compatible</span> <span class="pre">storage</span></code>.</p> |
| </div> |
| <div class="section" id="example"> |
| <h2>Example<a class="headerlink" href="#example" title="Permalink to this headline">¶</a></h2> |
| <p>Assuming your S3 credentials are correctly configured (for example by setting |
| the <code class="docutils literal notranslate"><span class="pre">AWS_ACCESS_KEY_ID</span></code> and <code class="docutils literal notranslate"><span class="pre">AWS_SECRET_ACCESS_KEY</span></code> environment variables), |
| here is how you can read contents from a S3 bucket:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="kn">from</span> <span class="nn">pyarrow</span> <span class="k">import</span> <span class="n">fs</span> |
| <span class="gp">>>> </span><span class="n">s3</span> <span class="o">=</span> <span class="n">fs</span><span class="o">.</span><span class="n">S3FileSystem</span><span class="p">(</span><span class="n">region</span><span class="o">=</span><span class="s1">'eu-west-3'</span><span class="p">)</span> |
| |
| <span class="go"># List all contents in a bucket, recursively</span> |
| <span class="gp">>>> </span><span class="n">s3</span><span class="o">.</span><span class="n">get_target_stats</span><span class="p">(</span><span class="n">fs</span><span class="o">.</span><span class="n">FileSelector</span><span class="p">(</span><span class="s1">'my-test-bucket'</span><span class="p">,</span> <span class="n">recursive</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span> |
| <span class="go">[<FileStats for 'my-test-bucket/File1': type=FileType.File, size=10>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/File5': type=FileType.File, size=10>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir1': type=FileType.Directory>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir2': type=FileType.Directory>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/EmptyDir': type=FileType.Directory>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir1/File2': type=FileType.File, size=11>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir1/Subdir': type=FileType.Directory>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir2/Subdir': type=FileType.Directory>,</span> |
| <span class="go"> <FileStats for 'my-test-bucket/Dir2/Subdir/File3': type=FileType.File, size=10>]</span> |
| |
| <span class="go"># Open a file for reading and download its contents</span> |
| <span class="gp">>>> </span><span class="n">f</span> <span class="o">=</span> <span class="n">s3</span><span class="o">.</span><span class="n">open_input_stream</span><span class="p">(</span><span class="s1">'my-test-bucket/Dir1/File2'</span><span class="p">)</span> |
| <span class="gp">>>> </span><span class="n">f</span><span class="o">.</span><span class="n">readall</span><span class="p">()</span> |
| <span class="go">b'some data'</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="filesystems_deprecated.html" class="btn btn-neutral float-right" title="Filesystem Interface (legacy)" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="ipc.html" class="btn btn-neutral float-left" title="Streaming, Serialization, and IPC" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| © Copyright 2016-2019 Apache Software Foundation |
| |
| </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> |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="/docs/_static/versionwarning.js"></script></body> |
| </html> |
