| |
| |
| <!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.filesystems — Apache Beam documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| |
| |
| |
| |
| |
| <link rel="index" title="Index" |
| href="../../../genindex.html"/> |
| <link rel="search" title="Search" href="../../../search.html"/> |
| <link rel="top" title="Apache Beam documentation" href="../../../index.html"/> |
| <link rel="up" title="Module code" href="../../index.html"/> |
| |
| |
| <script src="../../../_static/js/modernizr.min.js"></script> |
| |
| </head> |
| |
| <body class="wy-body-for-nav" role="document"> |
| |
| |
| <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> |
| <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.internal.html">apache_beam.internal package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></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.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.tools.html">apache_beam.tools 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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.version.html">apache_beam.version module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" role="navigation" 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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.filesystems</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for apache_beam.io.filesystems</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""FileSystems interface class for accessing the correct filesystem"""</span> |
| |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span> |
| |
| <span class="kn">from</span> <span class="nn">past.builtins</span> <span class="k">import</span> <span class="n">unicode</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystem</span> <span class="k">import</span> <span class="n">BeamIOError</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystem</span> <span class="k">import</span> <span class="n">CompressionTypes</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.filesystem</span> <span class="k">import</span> <span class="n">FileSystem</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.value_provider</span> <span class="k">import</span> <span class="n">RuntimeValueProvider</span> |
| |
| <span class="c1"># All filesystem implements should be added here as</span> |
| <span class="c1"># best effort imports. We don't want to force loading</span> |
| <span class="c1"># a module if the user doesn't supply the correct</span> |
| <span class="c1"># packages that these filesystems rely on.</span> |
| <span class="c1">#</span> |
| <span class="c1"># pylint: disable=wrong-import-position, unused-import</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.hadoopfilesystem</span> <span class="k">import</span> <span class="n">HadoopFileSystem</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.localfilesystem</span> <span class="k">import</span> <span class="n">LocalFileSystem</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.gcsfilesystem</span> <span class="k">import</span> <span class="n">GCSFileSystem</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| |
| |
| <span class="c1"># pylint: enable=wrong-import-position, unused-import</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'FileSystems'</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="FileSystems"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems">[docs]</a><span class="k">class</span> <span class="nc">FileSystems</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""A class that defines the functions that can be performed on a filesystem.</span> |
| <span class="sd"> All methods are static and access the underlying registered filesystems.</span> |
| <span class="sd"> """</span> |
| <span class="n">URI_SCHEMA_PATTERN</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="s1">'(?P<scheme>[a-zA-Z][-a-zA-Z0-9+.]*)://.*'</span><span class="p">)</span> |
| |
| <span class="n">_pipeline_options</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <div class="viewcode-block" id="FileSystems.set_options"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.set_options">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">set_options</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pipeline_options</span><span class="p">):</span> |
| <span class="sd">"""Set filesystem options.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> pipeline_options: Instance of ``PipelineOptions``.</span> |
| <span class="sd"> """</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_pipeline_options</span> <span class="o">=</span> <span class="n">pipeline_options</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.get_scheme"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.get_scheme">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_scheme</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="n">match_result</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">URI_SCHEMA_PATTERN</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">path</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span> |
| <span class="k">if</span> <span class="n">match_result</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">return</span> <span class="n">match_result</span><span class="o">.</span><span class="n">groupdict</span><span class="p">()[</span><span class="s1">'scheme'</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.get_filesystem"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.get_filesystem">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Get the correct filesystem for the specified path</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">path_scheme</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_scheme</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="n">systems</span> <span class="o">=</span> <span class="p">[</span><span class="n">fs</span> <span class="k">for</span> <span class="n">fs</span> <span class="ow">in</span> <span class="n">FileSystem</span><span class="o">.</span><span class="n">get_all_subclasses</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">fs</span><span class="o">.</span><span class="n">scheme</span><span class="p">()</span> <span class="o">==</span> <span class="n">path_scheme</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">systems</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unable to get the Filesystem for path </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">path</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">systems</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="c1"># Pipeline options could come either from the Pipeline itself (using</span> |
| <span class="c1"># direct runner), or via RuntimeValueProvider (other runners).</span> |
| <span class="n">options</span> <span class="o">=</span> <span class="p">(</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">_pipeline_options</span> <span class="ow">or</span> |
| <span class="n">RuntimeValueProvider</span><span class="o">.</span><span class="n">runtime_options</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">systems</span><span class="p">[</span><span class="mi">0</span><span class="p">](</span><span class="n">pipeline_options</span><span class="o">=</span><span class="n">options</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Found more than one filesystem for path </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">path</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="k">raise</span> |
| <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s1">'Unable to get the Filesystem'</span><span class="p">,</span> <span class="p">{</span><span class="n">path</span><span class="p">:</span> <span class="n">e</span><span class="p">})</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.join"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.join">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">join</span><span class="p">(</span><span class="n">basepath</span><span class="p">,</span> <span class="o">*</span><span class="n">paths</span><span class="p">):</span> |
| <span class="sd">"""Join two or more pathname components for the filesystem</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> basepath: string path of the first component of the path</span> |
| <span class="sd"> paths: path components to be added</span> |
| |
| <span class="sd"> Returns: full path after combining all the passed components</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">basepath</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">basepath</span><span class="p">,</span> <span class="o">*</span><span class="n">paths</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.split"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.split">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">split</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Splits the given path into two parts.</span> |
| |
| <span class="sd"> Splits the path into a pair (head, tail) such that tail contains the last</span> |
| <span class="sd"> component of the path and head contains everything up to that.</span> |
| |
| <span class="sd"> For file-systems other than the local file-system, head should include the</span> |
| <span class="sd"> prefix.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: path as a string</span> |
| <span class="sd"> Returns:</span> |
| <span class="sd"> a pair of path components as strings.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.mkdirs"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.mkdirs">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">mkdirs</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Recursively create directories for the provided path.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path of the directory structure that should be created</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> IOError if leaf directory already exists.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">mkdirs</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.match"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.match">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">match</span><span class="p">(</span><span class="n">patterns</span><span class="p">,</span> <span class="n">limits</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Find all matching paths to the patterns provided.</span> |
| |
| <span class="sd"> Pattern matching is done using each filesystem's ``match`` method (e.g.</span> |
| <span class="sd"> :meth:`.filesystem.FileSystem.match`).</span> |
| |
| <span class="sd"> .. note::</span> |
| <span class="sd"> - Depending on the :class:`.FileSystem` implementation, file listings</span> |
| <span class="sd"> (the ``.FileSystem._list`` method) may not be recursive.</span> |
| <span class="sd"> - If the file listing is not recursive, a pattern like</span> |
| <span class="sd"> ``scheme://path/*/foo`` will not be able to mach any files.</span> |
| |
| <span class="sd"> See Also:</span> |
| <span class="sd"> :meth:`.filesystem.FileSystem.match`</span> |
| |
| <span class="sd"> Pattern syntax:</span> |
| <span class="sd"> The pattern syntax is based on the fnmatch_ syntax, with the following</span> |
| <span class="sd"> differences:</span> |
| |
| <span class="sd"> - ``*`` Is equivalent to ``[^/\\]*`` rather than ``.*``.</span> |
| <span class="sd"> - ``**`` Is equivalent to ``.*``.</span> |
| |
| <span class="sd"> .. _`fnmatch`: https://docs.python.org/2/library/fnmatch.html</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> patterns: list of string for the file path pattern to match against</span> |
| <span class="sd"> limits: list of maximum number of responses that need to be fetched</span> |
| |
| <span class="sd"> Returns: list of ``MatchResult`` objects.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if any of the pattern match operations fail</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">patterns</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">patterns</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">patterns</span><span class="p">,</span> <span class="n">limits</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.create"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.create">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">create</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">,</span> |
| <span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">):</span> |
| <span class="sd">"""Returns a write channel for the given file path.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path of the file object to be written to the system</span> |
| <span class="sd"> mime_type: MIME type to specify the type of content in the file object</span> |
| <span class="sd"> compression_type: Type of compression to be used for this object. See</span> |
| <span class="sd"> ``CompressionTypes`` for possible values.</span> |
| |
| <span class="sd"> Returns: file handle with a ``close`` function for the user to use.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.open"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.open">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">'application/octet-stream'</span><span class="p">,</span> |
| <span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">):</span> |
| <span class="sd">"""Returns a read channel for the given file path.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path of the file object to be written to the system</span> |
| <span class="sd"> mime_type: MIME type to specify the type of content in the file object</span> |
| <span class="sd"> compression_type: Type of compression to be used for this object. See</span> |
| <span class="sd"> ``CompressionTypes`` for possible values.</span> |
| |
| <span class="sd"> Returns: file handle with a ``close`` function for the user to use.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.copy"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.copy">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">,</span> <span class="n">destination_file_names</span><span class="p">):</span> |
| <span class="sd">"""Recursively copy the file list from the source to the destination</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source_file_names: list of source file objects that needs to be copied</span> |
| <span class="sd"> destination_file_names: list of destination of the new object</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if any of the copy operations fail</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">,</span> <span class="n">destination_file_names</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.rename"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.rename">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">rename</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">,</span> <span class="n">destination_file_names</span><span class="p">):</span> |
| <span class="sd">"""Rename the files at the source list to the destination list.</span> |
| <span class="sd"> Source and destination lists should be of the same size.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source_file_names: List of file paths that need to be moved</span> |
| <span class="sd"> destination_file_names: List of destination_file_names for the files</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if any of the rename operations fail</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span><span class="n">source_file_names</span><span class="p">,</span> <span class="n">destination_file_names</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.exists"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.exists">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">exists</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Check if the provided path exists on the FileSystem.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path that needs to be checked.</span> |
| |
| <span class="sd"> Returns: boolean flag indicating if path exists</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.last_updated"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.last_updated">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">last_updated</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Get UNIX Epoch time in seconds on the FileSystem.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path of file.</span> |
| |
| <span class="sd"> Returns: float UNIX Epoch time</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if path doesn't exist.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">last_updated</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.checksum"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.checksum">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">checksum</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Fetch checksum metadata of a file on the</span> |
| <span class="sd"> :class:`~apache_beam.io.filesystem.FileSystem`.</span> |
| |
| <span class="sd"> This operation returns checksum metadata as stored in the underlying</span> |
| <span class="sd"> FileSystem. It should not read any file data. Checksum type and format are</span> |
| <span class="sd"> FileSystem dependent and are not compatible between FileSystems.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path of a file.</span> |
| |
| <span class="sd"> Returns: string containing checksum</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if path isn't a file or doesn't exist.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">checksum</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.delete"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.delete">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">delete</span><span class="p">(</span><span class="n">paths</span><span class="p">):</span> |
| <span class="sd">"""Deletes files or directories at the provided paths.</span> |
| <span class="sd"> Directories will be deleted recursively.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> paths: list of paths that give the file objects to be deleted</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if any of the delete operations fail</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">paths</span><span class="p">,</span> <span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">unicode</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s1">'Delete passed string argument instead of list: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="n">paths</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">paths</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">paths</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">paths</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="FileSystems.get_chunk_size"><a class="viewcode-back" href="../../../apache_beam.io.filesystems.html#apache_beam.io.filesystems.FileSystems.get_chunk_size">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_chunk_size</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Get the correct chunk size for the FileSystem.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path that needs to be checked.</span> |
| |
| <span class="sd"> Returns: integer size for parallelization in the FS operations.</span> |
| <span class="sd"> """</span> |
| <span class="n">filesystem</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">get_filesystem</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">filesystem</span><span class="o">.</span><span class="n">CHUNK_SIZE</span></div></div> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright . |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/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"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT:'../../../', |
| VERSION:'', |
| COLLAPSE_INDEX:false, |
| FILE_SUFFIX:'.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </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/js/theme.js"></script> |
| |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.StickyNav.enable(); |
| }); |
| </script> |
| |
| |
| </body> |
| </html> |