| |
| |
| <!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.runners.interactive.cache_manager — 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.runners.interactive.cache_manager</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.runners.interactive.cache_manager</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="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">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span> |
| |
| <span class="kn">import</span> <span class="nn">collections</span> |
| <span class="kn">import</span> <span class="nn">datetime</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| <span class="kn">import</span> <span class="nn">urllib</span> |
| |
| <span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">coders</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="k">import</span> <span class="n">filesystems</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">combiners</span> |
| |
| <span class="k">try</span><span class="p">:</span> <span class="c1"># Python 3</span> |
| <span class="n">unquote_to_bytes</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">parse</span><span class="o">.</span><span class="n">unquote_to_bytes</span> |
| <span class="n">quote</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">parse</span><span class="o">.</span><span class="n">quote</span> |
| <span class="k">except</span> <span class="ne">AttributeError</span><span class="p">:</span> <span class="c1"># Python 2</span> |
| <span class="c1"># pylint: disable=deprecated-urllib-function</span> |
| <span class="n">unquote_to_bytes</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">unquote</span> |
| <span class="n">quote</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">quote</span> |
| |
| |
| <div class="viewcode-block" id="CacheManager"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager">[docs]</a><span class="k">class</span> <span class="nc">CacheManager</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Abstract class for caching PCollections.</span> |
| |
| <span class="sd"> A PCollection cache is identified by labels, which consist of a prefix (either</span> |
| <span class="sd"> 'full' or 'sample') and a cache_label which is a hash of the PCollection</span> |
| <span class="sd"> derivation.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="CacheManager.exists"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.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="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Returns if the PCollection cache exists."""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="CacheManager.is_latest_version"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.is_latest_version">[docs]</a> <span class="k">def</span> <span class="nf">is_latest_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">version</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Returns if the given version number is the latest."""</span> |
| <span class="k">return</span> <span class="n">version</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_latest_version</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_latest_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Returns the latest version number of the PCollection cache."""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span> |
| |
| <div class="viewcode-block" id="CacheManager.read"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.read">[docs]</a> <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Return the PCollection as a list as well as the version number.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> (List[PCollection])</span> |
| <span class="sd"> (int) the version number</span> |
| |
| <span class="sd"> It is possible that the version numbers from read() and_latest_version()</span> |
| <span class="sd"> are different. This usually means that the cache's been evicted (thus</span> |
| <span class="sd"> unavailable => read() returns version = -1), but it had reached version n</span> |
| <span class="sd"> before eviction.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="CacheManager.source"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.source">[docs]</a> <span class="k">def</span> <span class="nf">source</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Returns a beam.io.Source that reads the PCollection cache."""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="CacheManager.sink"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.sink">[docs]</a> <span class="k">def</span> <span class="nf">sink</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="sd">"""Returns a beam.io.Sink that writes the PCollection cache."""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="CacheManager.cleanup"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.cleanup">[docs]</a> <span class="k">def</span> <span class="nf">cleanup</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Cleans up all the PCollection caches."""</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div> |
| |
| |
| <div class="viewcode-block" id="FileBasedCacheManager"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager">[docs]</a><span class="k">class</span> <span class="nc">FileBasedCacheManager</span><span class="p">(</span><span class="n">CacheManager</span><span class="p">):</span> |
| <span class="sd">"""Maps PCollections to local temp files for materialization."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_dir</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">cache_dir</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span> <span class="o">=</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">join</span><span class="p">(</span> |
| <span class="n">cache_dir</span><span class="p">,</span> |
| <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s2">"cache-%y-%m-</span><span class="si">%d</span><span class="s2">-%H_%M_%S"</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">(</span> |
| <span class="n">prefix</span><span class="o">=</span><span class="s1">'interactive-temp-'</span><span class="p">,</span> <span class="nb">dir</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'TEST_TMPDIR'</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_versions</span> <span class="o">=</span> <span class="n">collections</span><span class="o">.</span><span class="n">defaultdict</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_CacheVersion</span><span class="p">())</span> |
| |
| <div class="viewcode-block" id="FileBasedCacheManager.exists"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.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="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">bool</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_match</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">))</span></div> |
| |
| <span class="k">def</span> <span class="nf">_latest_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="n">timestamp</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_match</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="n">timestamp</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">timestamp</span><span class="p">,</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">last_updated</span><span class="p">(</span><span class="n">path</span><span class="p">))</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_versions</span><span class="p">[</span><span class="s2">"-"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">labels</span><span class="p">)]</span><span class="o">.</span><span class="n">get_version</span><span class="p">(</span><span class="n">timestamp</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <div class="viewcode-block" id="FileBasedCacheManager.read"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.read">[docs]</a> <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[],</span> <span class="o">-</span><span class="mi">1</span> |
| |
| <span class="k">def</span> <span class="nf">_read_helper</span><span class="p">():</span> |
| <span class="n">coder</span> <span class="o">=</span> <span class="n">SafeFastPrimitivesCoder</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_match</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</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="k">yield</span> <span class="n">coder</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span> |
| <span class="n">result</span><span class="p">,</span> <span class="n">version</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">_read_helper</span><span class="p">()),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_latest_version</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span><span class="p">,</span> <span class="n">version</span></div> |
| |
| <div class="viewcode-block" id="FileBasedCacheManager.source"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.source">[docs]</a> <span class="k">def</span> <span class="nf">source</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ReadFromText</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_glob_path</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">),</span> |
| <span class="n">coder</span><span class="o">=</span><span class="n">SafeFastPrimitivesCoder</span><span class="p">())</span><span class="o">.</span><span class="n">_source</span></div> |
| |
| <div class="viewcode-block" id="FileBasedCacheManager.sink"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.sink">[docs]</a> <span class="k">def</span> <span class="nf">sink</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">WriteToText</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">),</span> |
| <span class="n">coder</span><span class="o">=</span><span class="n">SafeFastPrimitivesCoder</span><span class="p">())</span><span class="o">.</span><span class="n">_sink</span></div> |
| |
| <div class="viewcode-block" id="FileBasedCacheManager.cleanup"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.cleanup">[docs]</a> <span class="k">def</span> <span class="nf">cleanup</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span><span class="p">):</span> |
| <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">delete</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span><span class="p">])</span></div> |
| |
| <span class="k">def</span> <span class="nf">_glob_path</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">)</span> <span class="o">+</span> <span class="s1">'-*-of-*'</span> |
| |
| <span class="k">def</span> <span class="nf">_path</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_match</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span> |
| <span class="n">match</span> <span class="o">=</span> <span class="n">filesystems</span><span class="o">.</span><span class="n">FileSystems</span><span class="o">.</span><span class="n">match</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">_glob_path</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">)])</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">match</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">metadata</span><span class="o">.</span><span class="n">path</span> <span class="k">for</span> <span class="n">metadata</span> <span class="ow">in</span> <span class="n">match</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">metadata_list</span><span class="p">]</span> |
| |
| <span class="k">class</span> <span class="nc">_CacheVersion</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""This class keeps track of the timestamp and the corresponding version."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">current_version</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">current_timestamp</span> <span class="o">=</span> <span class="mi">0</span> |
| |
| <span class="k">def</span> <span class="nf">get_version</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">timestamp</span><span class="p">):</span> |
| <span class="sd">"""Updates version if necessary and returns the version number.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> timestamp: (int) unix timestamp when the cache is updated. This value is</span> |
| <span class="sd"> zero if the cache has been evicted or doesn't exist.</span> |
| <span class="sd"> """</span> |
| <span class="c1"># Do not update timestamp if the cache's been evicted.</span> |
| <span class="k">if</span> <span class="n">timestamp</span> <span class="o">!=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">timestamp</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_timestamp</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">timestamp</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">current_timestamp</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">current_version</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_version</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">current_timestamp</span> <span class="o">=</span> <span class="n">timestamp</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">current_version</span></div> |
| |
| |
| <div class="viewcode-block" id="ReadCache"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.ReadCache">[docs]</a><span class="k">class</span> <span class="nc">ReadCache</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A PTransform that reads the PCollections from the cache."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_manager</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span> <span class="o">=</span> <span class="n">cache_manager</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">=</span> <span class="n">label</span> |
| |
| <div class="viewcode-block" id="ReadCache.expand"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.ReadCache.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pbegin</span><span class="p">):</span> |
| <span class="c1"># pylint: disable=expression-not-assigned</span> |
| <span class="k">return</span> <span class="n">pbegin</span> <span class="o">|</span> <span class="s1">'Read'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">Read</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="o">.</span><span class="n">source</span><span class="p">(</span><span class="s1">'full'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_label</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="WriteCache"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.WriteCache">[docs]</a><span class="k">class</span> <span class="nc">WriteCache</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A PTransform that writes the PCollections to the cache."""</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_manager</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">sample_size</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span> <span class="o">=</span> <span class="n">cache_manager</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label</span> <span class="o">=</span> <span class="n">label</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sample</span> <span class="o">=</span> <span class="n">sample</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span> <span class="o">=</span> <span class="n">sample_size</span> |
| |
| <div class="viewcode-block" id="WriteCache.expand"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.WriteCache.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="n">prefix</span> <span class="o">=</span> <span class="s1">'sample'</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample</span> <span class="k">else</span> <span class="s1">'full'</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sample</span><span class="p">:</span> |
| <span class="n">pcoll</span> <span class="o">|=</span> <span class="s1">'Sample'</span> <span class="o">>></span> <span class="p">(</span> |
| <span class="n">combiners</span><span class="o">.</span><span class="n">Sample</span><span class="o">.</span><span class="n">FixedSizeGlobally</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sample_size</span><span class="p">)</span> |
| <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">sample</span><span class="p">:</span> <span class="n">sample</span><span class="p">))</span> |
| <span class="c1"># pylint: disable=expression-not-assigned</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="s1">'Write'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">Write</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="o">.</span><span class="n">sink</span><span class="p">(</span><span class="n">prefix</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_label</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SafeFastPrimitivesCoder"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.SafeFastPrimitivesCoder">[docs]</a><span class="k">class</span> <span class="nc">SafeFastPrimitivesCoder</span><span class="p">(</span><span class="n">coders</span><span class="o">.</span><span class="n">Coder</span><span class="p">):</span> |
| <span class="sd">"""This class add an quote/unquote step to escape special characters."""</span> |
| <span class="c1"># pylint: disable=deprecated-urllib-function</span> |
| |
| <div class="viewcode-block" id="SafeFastPrimitivesCoder.encode"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.SafeFastPrimitivesCoder.encode">[docs]</a> <span class="k">def</span> <span class="nf">encode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">quote</span><span class="p">(</span><span class="n">coders</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">FastPrimitivesCoder</span><span class="p">()</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">value</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="SafeFastPrimitivesCoder.decode"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.SafeFastPrimitivesCoder.decode">[docs]</a> <span class="k">def</span> <span class="nf">decode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">coders</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">FastPrimitivesCoder</span><span class="p">()</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="n">unquote_to_bytes</span><span class="p">(</span><span class="n">value</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> |