blob: 6b3aaabad3b305e6dc282734943ad25319f0758f [file] [log] [blame]
<!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 &mdash; Apache Beam 2.55.1 documentation</title>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></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/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div class="version">
2.55.1
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<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.dataframe.html">apache_beam.dataframe 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.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="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> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">collections</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">tempfile</span>
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">quote</span>
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">unquote_to_bytes</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="kn">import</span> <span class="n">coders</span>
<span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="kn">import</span> <span class="n">filesystems</span>
<span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="kn">import</span> <span class="n">textio</span>
<span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="kn">import</span> <span class="n">tfrecordio</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">combiners</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="w"> </span><span class="sd">&quot;&quot;&quot;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"> &#39;full&#39; or &#39;sample&#39;) and a cache_label which is a hash of the PCollection</span>
<span class="sd"> derivation.</span>
<span class="sd"> &quot;&quot;&quot;</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="c1"># type (*str) -&gt; bool</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns if the PCollection cache exists.&quot;&quot;&quot;</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="c1"># type (str, *str) -&gt; bool</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns if the given version number is the latest.&quot;&quot;&quot;</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="c1"># type (*str) -&gt; str</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the latest version number of the PCollection cache.&quot;&quot;&quot;</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="o">**</span><span class="n">args</span><span class="p">):</span>
<span class="c1"># type (*str, Dict[str, Any]) -&gt; Tuple[str, Generator[Any]]</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Return the PCollection as a list as well as the version number.</span>
<span class="sd"> Args:</span>
<span class="sd"> *labels: List of labels for PCollection instance.</span>
<span class="sd"> **args: Dict of additional arguments. Currently only &#39;tail&#39; as a boolean.</span>
<span class="sd"> When tail is True, will wait and read new elements until the cache is</span>
<span class="sd"> complete.</span>
<span class="sd"> Returns:</span>
<span class="sd"> A tuple containing an iterator for the items in the PCollection and the</span>
<span class="sd"> 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&#39;s been evicted (thus</span>
<span class="sd"> unavailable =&gt; read() returns version = -1), but it had reached version n</span>
<span class="sd"> before eviction.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
<div class="viewcode-block" id="CacheManager.write"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.write">[docs]</a> <span class="k">def</span> <span class="nf">write</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="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="c1"># type (Any, *str) -&gt; None</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Writes the value to the given cache.</span>
<span class="sd"> Args:</span>
<span class="sd"> value: An encodable (with corresponding PCoder) value</span>
<span class="sd"> *labels: List of labels for PCollection instance</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
<div class="viewcode-block" id="CacheManager.clear"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.clear">[docs]</a> <span class="k">def</span> <span class="nf">clear</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="c1"># type (*str) -&gt; Boolean</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Clears the cache entry of the given labels and returns True on success.</span>
<span class="sd"> Args:</span>
<span class="sd"> value: An encodable (with corresponding PCoder) value</span>
<span class="sd"> *labels: List of labels for PCollection instance</span>
<span class="sd"> &quot;&quot;&quot;</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="c1"># type (*str) -&gt; ptransform.PTransform</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a PTransform that reads the PCollection cache.&quot;&quot;&quot;</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="n">labels</span><span class="p">,</span> <span class="n">is_capture</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="c1"># type (*str, bool) -&gt; ptransform.PTransform</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a PTransform that writes the PCollection cache.</span>
<span class="sd"> TODO(BEAM-10514): Make sure labels will not be converted into an</span>
<span class="sd"> arbitrarily long file path: e.g., windows has a 260 path limit.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
<div class="viewcode-block" id="CacheManager.save_pcoder"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.save_pcoder">[docs]</a> <span class="k">def</span> <span class="nf">save_pcoder</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoder</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="c1"># type (coders.Coder, *str) -&gt; None</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Saves pcoder for given PCollection.</span>
<span class="sd"> Correct reading of PCollection from Cache requires PCoder to be known.</span>
<span class="sd"> This method saves desired PCoder for PCollection that will subsequently</span>
<span class="sd"> be used by sink(...), source(...), and, most importantly, read(...) method.</span>
<span class="sd"> The latter must be able to read a PCollection written by Beam using</span>
<span class="sd"> non-Beam IO.</span>
<span class="sd"> Args:</span>
<span class="sd"> pcoder: A PCoder to be used for reading and writing a PCollection.</span>
<span class="sd"> *labels: List of labels for PCollection instance.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
<div class="viewcode-block" id="CacheManager.load_pcoder"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.load_pcoder">[docs]</a> <span class="k">def</span> <span class="nf">load_pcoder</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="c1"># type (*str) -&gt; coders.Coder</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns previously saved PCoder for reading and writing PCollection.&quot;&quot;&quot;</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="c1"># type () -&gt; None</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Cleans up all the PCollection caches.&quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div>
<div class="viewcode-block" id="CacheManager.size"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.CacheManager.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="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="c1"># type: (*str) -&gt; int</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the size of the PCollection on disk in bytes.&quot;&quot;&quot;</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="w"> </span><span class="sd">&quot;&quot;&quot;Maps PCollections to local temp files for materialization.&quot;&quot;&quot;</span>
<span class="n">_available_formats</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;text&#39;</span><span class="p">:</span> <span class="p">(</span><span class="n">textio</span><span class="o">.</span><span class="n">ReadFromText</span><span class="p">,</span> <span class="n">textio</span><span class="o">.</span><span class="n">WriteToText</span><span class="p">),</span>
<span class="s1">&#39;tfrecord&#39;</span><span class="p">:</span> <span class="p">(</span><span class="n">tfrecordio</span><span class="o">.</span><span class="n">ReadFromTFRecord</span><span class="p">,</span> <span class="n">tfrecordio</span><span class="o">.</span><span class="n">WriteToTFRecord</span><span class="p">)</span>
<span class="p">}</span>
<span class="k">def</span> <span class="fm">__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="n">cache_format</span><span class="o">=</span><span class="s1">&#39;text&#39;</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">cache_dir</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">&#39;ib-&#39;</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">&#39;TEST_TMPDIR&#39;</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>
<span class="bp">self</span><span class="o">.</span><span class="n">cache_format</span> <span class="o">=</span> <span class="n">cache_format</span>
<span class="k">if</span> <span class="n">cache_format</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_available_formats</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Unsupported cache format: &#39;</span><span class="si">%s</span><span class="s2">&#39;.&quot;</span> <span class="o">%</span> <span class="n">cache_format</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_reader_class</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_writer_class</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_available_formats</span><span class="p">[</span>
<span class="n">cache_format</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_default_pcoder</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">SafeFastPrimitivesCoder</span><span class="p">()</span> <span class="k">if</span> <span class="n">cache_format</span> <span class="o">==</span> <span class="s1">&#39;text&#39;</span> <span class="k">else</span> <span class="kc">None</span><span class="p">)</span>
<span class="c1"># List of saved pcoders keyed by PCollection path. It is OK to keep this</span>
<span class="c1"># list in memory because once FileBasedCacheManager object is</span>
<span class="c1"># destroyed/re-created it loses the access to previously written cache</span>
<span class="c1"># objects anyways even if cache_dir already exists. In other words,</span>
<span class="c1"># it is not possible to resume execution of Beam pipeline from the</span>
<span class="c1"># saved cache if FileBasedCacheManager has been reset.</span>
<span class="c1">#</span>
<span class="c1"># However, if we are to implement better cache persistence, one needs</span>
<span class="c1"># to take care of keeping consistency between the cached PCollection</span>
<span class="c1"># and its PCoder type.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_saved_pcoders</span> <span class="o">=</span> <span class="p">{}</span>
<div class="viewcode-block" id="FileBasedCacheManager.size"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.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="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="k">if</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="n">matched_path</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="o">*</span><span class="n">labels</span><span class="p">)</span>
<span class="c1"># if any matched path has a gs:// prefix, it must be cached on GCS</span>
<span class="k">if</span> <span class="s1">&#39;gs://&#39;</span> <span class="ow">in</span> <span class="n">matched_path</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp</span> <span class="kn">import</span> <span class="n">gcsio</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span>
<span class="nb">sum</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">path</span><span class="p">)</span><span class="o">.</span><span class="n">values</span><span class="p">())</span>
<span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">matched_path</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">getsize</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">matched_path</span><span class="p">)</span>
<span class="k">return</span> <span class="mi">0</span></div>
<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">if</span> <span class="n">labels</span> <span class="ow">and</span> <span class="nb">any</span><span class="p">(</span><span class="n">labels</span><span class="p">[</span><span class="mi">1</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>
<span class="k">return</span> <span class="kc">False</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">&quot;-&quot;</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.save_pcoder"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.save_pcoder">[docs]</a> <span class="k">def</span> <span class="nf">save_pcoder</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoder</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_saved_pcoders</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="o">=</span> <span class="n">pcoder</span></div>
<div class="viewcode-block" id="FileBasedCacheManager.load_pcoder"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.load_pcoder">[docs]</a> <span class="k">def</span> <span class="nf">load_pcoder</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">saved_pcoder</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_saved_pcoders</span><span class="o">.</span><span class="n">get</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="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="n">saved_pcoder</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">saved_pcoder</span><span class="p">,</span>
<span class="n">coders</span><span class="o">.</span><span class="n">FastPrimitivesCoder</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_default_pcoder</span>
<span class="k">return</span> <span class="n">saved_pcoder</span></div>
<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="o">**</span><span class="n">args</span><span class="p">):</span>
<span class="c1"># Return an iterator to an empty list if it doesn&#39;t exist.</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="nb">iter</span><span class="p">([]),</span> <span class="o">-</span><span class="mi">1</span>
<span class="c1"># Otherwise, return a generator to the cached PCollection.</span>
<span class="n">source</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">source</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">)</span><span class="o">.</span><span class="n">_source</span>
<span class="n">range_tracker</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">reader</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">)</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>
<span class="k">return</span> <span class="n">reader</span><span class="p">,</span> <span class="n">version</span></div>
<div class="viewcode-block" id="FileBasedCacheManager.write"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.write">[docs]</a> <span class="k">def</span> <span class="nf">write</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">values</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Imitates how a WriteCache transform works without running a pipeline.</span>
<span class="sd"> For testing and cache manager development, not for production usage because</span>
<span class="sd"> the write is not sharded and does not use Beam execution model.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">pcoder</span> <span class="o">=</span> <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">get_coder</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">values</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span>
<span class="c1"># Save the pcoder for the actual labels.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">save_pcoder</span><span class="p">(</span><span class="n">pcoder</span><span class="p">,</span> <span class="o">*</span><span class="n">labels</span><span class="p">)</span>
<span class="n">single_shard_labels</span> <span class="o">=</span> <span class="p">[</span><span class="o">*</span><span class="n">labels</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="s1">&#39;-00000-of-00001&#39;</span><span class="p">]</span>
<span class="c1"># Save the pcoder for the labels that imitates the sharded cache file name</span>
<span class="c1"># suffix.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">save_pcoder</span><span class="p">(</span><span class="n">pcoder</span><span class="p">,</span> <span class="o">*</span><span class="n">single_shard_labels</span><span class="p">)</span>
<span class="c1"># Put a &#39;-%05d-of-%05d&#39; suffix to the cache file.</span>
<span class="n">sink</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sink</span><span class="p">(</span><span class="n">single_shard_labels</span><span class="p">)</span><span class="o">.</span><span class="n">_sink</span>
<span class="n">path</span> <span class="o">=</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="mi">1</span><span class="p">])</span>
<span class="n">writer</span> <span class="o">=</span> <span class="n">sink</span><span class="o">.</span><span class="n">open_writer</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">labels</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">values</span><span class="p">:</span>
<span class="n">writer</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">v</span><span class="p">)</span>
<span class="n">writer</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
<div class="viewcode-block" id="FileBasedCacheManager.clear"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.cache_manager.html#apache_beam.runners.interactive.cache_manager.FileBasedCacheManager.clear">[docs]</a> <span class="k">def</span> <span class="nf">clear</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="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="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">_match</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="kc">True</span>
<span class="k">return</span> <span class="kc">False</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="bp">self</span><span class="o">.</span><span class="n">_reader_class</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="bp">self</span><span class="o">.</span><span class="n">load_pcoder</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">))</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="n">labels</span><span class="p">,</span> <span class="n">is_capture</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_writer_class</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="bp">self</span><span class="o">.</span><span class="n">load_pcoder</span><span class="p">(</span><span class="o">*</span><span class="n">labels</span><span class="p">))</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="bp">self</span><span class="o">.</span><span class="n">_cache_dir</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;gs://&#39;</span><span class="p">):</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp</span> <span class="kn">import</span> <span class="n">gcsfilesystem</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</span>
<span class="n">fs</span> <span class="o">=</span> <span class="n">gcsfilesystem</span><span class="o">.</span><span class="n">GCSFileSystem</span><span class="p">(</span><span class="n">PipelineOptions</span><span class="p">())</span>
<span class="n">fs</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="o">+</span> <span class="s1">&#39;/full/&#39;</span><span class="p">])</span>
<span class="k">elif</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>
<span class="bp">self</span><span class="o">.</span><span class="n">_saved_pcoders</span> <span class="o">=</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">&#39;*-*-of-*&#39;</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="w"> </span><span class="sd">&quot;&quot;&quot;This class keeps track of the timestamp and the corresponding version.&quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__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="w"> </span><span class="sd">&quot;&quot;&quot;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&#39;t exist.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Do not update timestamp if the cache&#39;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">&gt;</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="w"> </span><span class="sd">&quot;&quot;&quot;A PTransform that reads the PCollections from the cache.&quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__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">&#39;Read&#39;</span> <span class="o">&gt;&gt;</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">&#39;full&#39;</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="w"> </span><span class="sd">&quot;&quot;&quot;A PTransform that writes the PCollections to the cache.&quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__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="n">is_capture</span><span class="o">=</span><span class="kc">False</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>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_capture</span> <span class="o">=</span> <span class="n">is_capture</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">&#39;sample&#39;</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">&#39;full&#39;</span>
<span class="c1"># We save pcoder that is necessary for proper reading of</span>
<span class="c1"># cached PCollection. _cache_manager.sink(...) call below</span>
<span class="c1"># should be using this saved pcoder.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="o">.</span><span class="n">save_pcoder</span><span class="p">(</span>
<span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">get_coder</span><span class="p">(</span><span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</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>
<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">&#39;Sample&#39;</span> <span class="o">&gt;&gt;</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">&#39;Write&#39;</span> <span class="o">&gt;&gt;</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="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> <span class="n">is_capture</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_is_capture</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="w"> </span><span class="sd">&quot;&quot;&quot;This class add an quote/unquote step to escape special characters.&quot;&quot;&quot;</span>
<span class="c1"># pylint: disable=bad-option-value</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><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</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>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>