| |
| |
| <!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.gcp.gcsfilesystem — 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.gcp.gcsfilesystem</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.gcp.gcsfilesystem</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">"""GCS file system implementation for accessing files on GCS."""</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">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">zip</span> |
| |
| <span class="kn">from</span> <span class="nn">future.utils</span> <span class="k">import</span> <span class="n">iteritems</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">CompressedFile</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">FileMetadata</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.io.gcp</span> <span class="k">import</span> <span class="n">gcsio</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'GCSFileSystem'</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="GCSFileSystem"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem">[docs]</a><span class="k">class</span> <span class="nc">GCSFileSystem</span><span class="p">(</span><span class="n">FileSystem</span><span class="p">):</span> |
| <span class="sd">"""A GCS ``FileSystem`` implementation for accessing files on GCS.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">CHUNK_SIZE</span> <span class="o">=</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">MAX_BATCH_OPERATION_SIZE</span> <span class="c1"># Chuck size in batch operations</span> |
| <span class="n">GCS_PREFIX</span> <span class="o">=</span> <span class="s1">'gs://'</span> |
| |
| <div class="viewcode-block" id="GCSFileSystem.scheme"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.scheme">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">scheme</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="sd">"""URI scheme for the FileSystem</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="s1">'gs'</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.join"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.join">[docs]</a> <span class="k">def</span> <span class="nf">join</span><span class="p">(</span><span class="bp">self</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="k">if</span> <span class="ow">not</span> <span class="n">basepath</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">GCSFileSystem</span><span class="o">.</span><span class="n">GCS_PREFIX</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Basepath </span><span class="si">%r</span><span class="s1"> must be GCS path.'</span> <span class="o">%</span> <span class="n">basepath</span><span class="p">)</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="n">basepath</span> |
| <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">:</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="n">path</span><span class="o">.</span><span class="n">rstrip</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'/'</span> <span class="o">+</span> <span class="n">p</span><span class="o">.</span><span class="n">lstrip</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">path</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.split"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.split">[docs]</a> <span class="k">def</span> <span class="nf">split</span><span class="p">(</span><span class="bp">self</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"> Head will include the GCS prefix ('gs://').</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">path</span> <span class="o">=</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="ow">not</span> <span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">GCSFileSystem</span><span class="o">.</span><span class="n">GCS_PREFIX</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Path </span><span class="si">%r</span><span class="s1"> must be GCS path.'</span> <span class="o">%</span> <span class="n">path</span><span class="p">)</span> |
| |
| <span class="n">prefix_len</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">GCSFileSystem</span><span class="o">.</span><span class="n">GCS_PREFIX</span><span class="p">)</span> |
| <span class="n">last_sep</span> <span class="o">=</span> <span class="n">path</span><span class="p">[</span><span class="n">prefix_len</span><span class="p">:]</span><span class="o">.</span><span class="n">rfind</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">last_sep</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">last_sep</span> <span class="o">+=</span> <span class="n">prefix_len</span> |
| |
| <span class="k">if</span> <span class="n">last_sep</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">path</span><span class="p">[:</span><span class="n">last_sep</span><span class="p">],</span> <span class="n">path</span><span class="p">[</span><span class="n">last_sep</span> <span class="o">+</span> <span class="mi">1</span><span class="p">:])</span> |
| <span class="k">elif</span> <span class="n">last_sep</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">path</span><span class="p">,</span> <span class="s1">''</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">'Invalid path: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.mkdirs"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.mkdirs">[docs]</a> <span class="k">def</span> <span class="nf">mkdirs</span><span class="p">(</span><span class="bp">self</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="k">pass</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.has_dirs"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.has_dirs">[docs]</a> <span class="k">def</span> <span class="nf">has_dirs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Whether this FileSystem supports directories."""</span> |
| <span class="k">return</span> <span class="kc">False</span></div> |
| |
| <span class="k">def</span> <span class="nf">_list</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dir_or_prefix</span><span class="p">):</span> |
| <span class="sd">"""List files in a location.</span> |
| |
| <span class="sd"> Listing is non-recursive, for filesystems that support directories.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> dir_or_prefix: (string) A directory or location prefix (for filesystems</span> |
| <span class="sd"> that don't have directories).</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> Generator of ``FileMetadata`` objects.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if listing fails, but not if no files were found.</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">path</span><span class="p">,</span> <span class="n">size</span> <span class="ow">in</span> <span class="n">iteritems</span><span class="p">(</span><span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">list_prefix</span><span class="p">(</span><span class="n">dir_or_prefix</span><span class="p">)):</span> |
| <span class="k">yield</span> <span class="n">FileMetadata</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">size</span><span class="p">)</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="c1"># pylint: disable=broad-except</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s2">"List operation failed"</span><span class="p">,</span> <span class="p">{</span><span class="n">dir_or_prefix</span><span class="p">:</span> <span class="n">e</span><span class="p">})</span> |
| |
| <span class="k">def</span> <span class="nf">_path_open</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">mode</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">"""Helper functions to open a file in the provided mode.</span> |
| <span class="sd"> """</span> |
| <span class="n">compression_type</span> <span class="o">=</span> <span class="n">FileSystem</span><span class="o">.</span><span class="n">_get_compression_type</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">)</span> |
| <span class="n">mime_type</span> <span class="o">=</span> <span class="n">CompressionTypes</span><span class="o">.</span><span class="n">mime_type</span><span class="p">(</span><span class="n">compression_type</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">)</span> |
| <span class="n">raw_file</span> <span class="o">=</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</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">mode</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="n">mime_type</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">compression_type</span> <span class="o">==</span> <span class="n">CompressionTypes</span><span class="o">.</span><span class="n">UNCOMPRESSED</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">raw_file</span> |
| <span class="k">return</span> <span class="n">CompressedFile</span><span class="p">(</span><span class="n">raw_file</span><span class="p">,</span> <span class="n">compression_type</span><span class="o">=</span><span class="n">compression_type</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="GCSFileSystem.create"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.create">[docs]</a> <span class="k">def</span> <span class="nf">create</span><span class="p">(</span><span class="bp">self</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</span> |
| |
| <span class="sd"> Returns: file handle with a close function for the user to use</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path_open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">'wb'</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="GCSFileSystem.open"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.open">[docs]</a> <span class="k">def</span> <span class="nf">open</span><span class="p">(</span><span class="bp">self</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</span> |
| |
| <span class="sd"> Returns: file handle with a close function for the user to use</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path_open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">'rb'</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="GCSFileSystem.copy"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.copy">[docs]</a> <span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</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 tree 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="n">err_msg</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"source_file_names and destination_file_names should "</span> |
| <span class="s2">"be equal in length"</span><span class="p">)</span> |
| <span class="k">assert</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="nb">len</span><span class="p">(</span><span class="n">destination_file_names</span><span class="p">),</span> <span class="n">err_msg</span> |
| |
| <span class="k">def</span> <span class="nf">_copy_path</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">):</span> |
| <span class="sd">"""Recursively copy the file tree from the source to the destination</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">destination</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">GCSFileSystem</span><span class="o">.</span><span class="n">GCS_PREFIX</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Destination </span><span class="si">%r</span><span class="s1"> must be GCS path.'</span> <span class="o">%</span> <span class="n">destination</span><span class="p">)</span> |
| <span class="c1"># Use copy_tree if the path ends with / as it is a directory</span> |
| <span class="k">if</span> <span class="n">source</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">copytree</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">)</span> |
| |
| <span class="n">exceptions</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">source</span><span class="p">,</span> <span class="n">destination</span> <span class="ow">in</span> <span class="nb">zip</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="k">try</span><span class="p">:</span> |
| <span class="n">_copy_path</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">)</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="c1"># pylint: disable=broad-except</span> |
| <span class="n">exceptions</span><span class="p">[(</span><span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">)]</span> <span class="o">=</span> <span class="n">e</span> |
| |
| <span class="k">if</span> <span class="n">exceptions</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s2">"Copy operation failed"</span><span class="p">,</span> <span class="n">exceptions</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.rename"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.rename">[docs]</a> <span class="k">def</span> <span class="nf">rename</span><span class="p">(</span><span class="bp">self</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="n">err_msg</span> <span class="o">=</span> <span class="p">(</span><span class="s2">"source_file_names and destination_file_names should "</span> |
| <span class="s2">"be equal in length"</span><span class="p">)</span> |
| <span class="k">assert</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="nb">len</span><span class="p">(</span><span class="n">destination_file_names</span><span class="p">),</span> <span class="n">err_msg</span> |
| |
| <span class="n">gcs_batches</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">gcs_current_batch</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span> <span class="ow">in</span> <span class="nb">zip</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="n">gcs_current_batch</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">))</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">gcs_current_batch</span><span class="p">)</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">CHUNK_SIZE</span><span class="p">:</span> |
| <span class="n">gcs_batches</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">gcs_current_batch</span><span class="p">)</span> |
| <span class="n">gcs_current_batch</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="n">gcs_current_batch</span><span class="p">:</span> |
| <span class="n">gcs_batches</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">gcs_current_batch</span><span class="p">)</span> |
| |
| <span class="c1"># Execute GCS renames if any and return exceptions.</span> |
| <span class="n">exceptions</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">gcs_batches</span><span class="p">:</span> |
| <span class="n">copy_statuses</span> <span class="o">=</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">copy_batch</span><span class="p">(</span><span class="n">batch</span><span class="p">)</span> |
| <span class="n">copy_succeeded</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">exception</span> <span class="ow">in</span> <span class="n">copy_statuses</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">exception</span><span class="p">:</span> |
| <span class="n">exceptions</span><span class="p">[(</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">)]</span> <span class="o">=</span> <span class="n">exception</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">copy_succeeded</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">))</span> |
| <span class="n">delete_batch</span> <span class="o">=</span> <span class="p">[</span><span class="n">src</span> <span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span> <span class="ow">in</span> <span class="n">copy_succeeded</span><span class="p">]</span> |
| <span class="n">delete_statuses</span> <span class="o">=</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">delete_batch</span><span class="p">(</span><span class="n">delete_batch</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">exception</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">delete_statuses</span><span class="p">):</span> |
| <span class="n">dest</span> <span class="o">=</span> <span class="n">copy_succeeded</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">exception</span><span class="p">:</span> |
| <span class="n">exceptions</span><span class="p">[(</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">)]</span> <span class="o">=</span> <span class="n">exception</span> |
| |
| <span class="k">if</span> <span class="n">exceptions</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s2">"Rename operation failed"</span><span class="p">,</span> <span class="n">exceptions</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.exists"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.exists">[docs]</a> <span class="k">def</span> <span class="nf">exists</span><span class="p">(</span><span class="bp">self</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="k">return</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</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="GCSFileSystem.size"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.size">[docs]</a> <span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Get size of path on the FileSystem.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path: string path in question.</span> |
| |
| <span class="sd"> Returns: int size of path according to the FileSystem.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ``BeamIOError`` if path doesn't exist.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="n">path</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="GCSFileSystem.last_updated"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.last_updated">[docs]</a> <span class="k">def</span> <span class="nf">last_updated</span><span class="p">(</span><span class="bp">self</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="k">return</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</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="GCSFileSystem.checksum"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.checksum">[docs]</a> <span class="k">def</span> <span class="nf">checksum</span><span class="p">(</span><span class="bp">self</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"> 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="k">try</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">checksum</span><span class="p">(</span><span class="n">path</span><span class="p">)</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="c1"># pylint: disable=broad-except</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s2">"Checksum operation failed"</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="GCSFileSystem.delete"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.gcsfilesystem.html#apache_beam.io.gcp.gcsfilesystem.GCSFileSystem.delete">[docs]</a> <span class="k">def</span> <span class="nf">delete</span><span class="p">(</span><span class="bp">self</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"> """</span> |
| <span class="k">def</span> <span class="nf">_delete_path</span><span class="p">(</span><span class="n">path</span><span class="p">):</span> |
| <span class="sd">"""Recursively delete the file or directory at the provided path.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'/'</span><span class="p">):</span> |
| <span class="n">path_to_use</span> <span class="o">=</span> <span class="n">path</span> <span class="o">+</span> <span class="s1">'*'</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">path_to_use</span> <span class="o">=</span> <span class="n">path</span> |
| <span class="n">match_result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">match</span><span class="p">([</span><span class="n">path_to_use</span><span class="p">])[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">statuses</span> <span class="o">=</span> <span class="n">gcsio</span><span class="o">.</span><span class="n">GcsIO</span><span class="p">()</span><span class="o">.</span><span class="n">delete_batch</span><span class="p">(</span> |
| <span class="p">[</span><span class="n">m</span><span class="o">.</span><span class="n">path</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">match_result</span><span class="o">.</span><span class="n">metadata_list</span><span class="p">])</span> |
| <span class="n">failures</span> <span class="o">=</span> <span class="p">[</span><span class="n">e</span> <span class="k">for</span> <span class="p">(</span><span class="n">_</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> <span class="ow">in</span> <span class="n">statuses</span> <span class="k">if</span> <span class="n">e</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">failures</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">failures</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| |
| <span class="n">exceptions</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">_delete_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</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="c1"># pylint: disable=broad-except</span> |
| <span class="n">exceptions</span><span class="p">[</span><span class="n">path</span><span class="p">]</span> <span class="o">=</span> <span class="n">e</span> |
| |
| <span class="k">if</span> <span class="n">exceptions</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">BeamIOError</span><span class="p">(</span><span class="s2">"Delete operation failed"</span><span class="p">,</span> <span class="n">exceptions</span><span class="p">)</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> |