blob: 0c1843a472993e5d1f63ce995e5933ab07148dcb [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.caching.write_cache &mdash; Apache Beam 2.47.0 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">
2.47.0
</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.caching.write_cache</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.caching.write_cache</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="sd">&quot;&quot;&quot;Module to write cache for PCollections being computed.</span>
<span class="sd">For internal use only; no backward-compatibility guarantees.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</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.portability.api</span> <span class="kn">import</span> <span class="n">beam_runner_api_pb2</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">cache_manager</span> <span class="k">as</span> <span class="n">cache</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.caching.cacheable</span> <span class="kn">import</span> <span class="n">Cacheable</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.caching.reify</span> <span class="kn">import</span> <span class="n">reify_to_cache</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.pipeline_context</span> <span class="kn">import</span> <span class="n">PipelineContext</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.ptransform</span> <span class="kn">import</span> <span class="n">PTransform</span>
<div class="viewcode-block" id="WriteCache"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.write_cache.html#apache_beam.runners.interactive.caching.write_cache.WriteCache">[docs]</a><span class="k">class</span> <span class="nc">WriteCache</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Class that facilitates writing cache for PCollections being computed.</span>
<span class="sd"> &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">pipeline</span><span class="p">:</span> <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">,</span>
<span class="n">context</span><span class="p">:</span> <span class="n">PipelineContext</span><span class="p">,</span>
<span class="n">cache_manager</span><span class="p">:</span> <span class="n">cache</span><span class="o">.</span><span class="n">CacheManager</span><span class="p">,</span>
<span class="n">cacheable</span><span class="p">:</span> <span class="n">Cacheable</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span> <span class="o">=</span> <span class="n">pipeline</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_context</span> <span class="o">=</span> <span class="n">context</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">_cacheable</span> <span class="o">=</span> <span class="n">cacheable</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_key</span> <span class="o">=</span> <span class="n">cacheable</span><span class="o">.</span><span class="n">to_key</span><span class="p">()</span><span class="o">.</span><span class="n">to_str</span><span class="p">()</span>
<div class="viewcode-block" id="WriteCache.write_cache"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.write_cache.html#apache_beam.runners.interactive.caching.write_cache.WriteCache.write_cache">[docs]</a> <span class="k">def</span> <span class="nf">write_cache</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Writes cache for the cacheable PCollection that is being computed.</span>
<span class="sd"> First, it creates a temporary pipeline instance on top of the existing</span>
<span class="sd"> component_id_map from self._pipeline&#39;s context so that both pipelines</span>
<span class="sd"> share the context and have no conflict component ids.</span>
<span class="sd"> Second, it creates a _PCollectionPlaceHolder in the temporary pipeline that</span>
<span class="sd"> mimics the attributes of the cacheable PCollection to be written into cache.</span>
<span class="sd"> It also marks all components in the current temporary pipeline as</span>
<span class="sd"> ignorable when later copying components to self._pipeline.</span>
<span class="sd"> Third, it instantiates a _WriteCacheTransform that uses the</span>
<span class="sd"> _PCollectionPlaceHolder as the input. This adds a subgraph under top level</span>
<span class="sd"> transforms that writes the _PCollectionPlaceHolder into cache.</span>
<span class="sd"> Fourth, it copies components of the subgraph from the temporary pipeline to</span>
<span class="sd"> self._pipeline, skipping components that are ignored in the temporary</span>
<span class="sd"> pipeline and components that are not in the temporary pipeline but presents</span>
<span class="sd"> in the component_id_map of self._pipeline.</span>
<span class="sd"> Last, it replaces inputs of all transforms that consume the</span>
<span class="sd"> _PCollectionPlaceHolder with the cacheable PCollection to be written to</span>
<span class="sd"> cache.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">template</span><span class="p">,</span> <span class="n">write_input_placeholder</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_build_runner_api_template</span><span class="p">()</span>
<span class="n">input_placeholder_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_id</span><span class="p">(</span>
<span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">placeholder_pcoll</span><span class="p">)</span>
<span class="n">input_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_id</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cacheable</span><span class="o">.</span><span class="n">pcoll</span><span class="p">)</span>
<span class="c1"># Copy cache writing subgraph from the template to the pipeline proto.</span>
<span class="k">for</span> <span class="n">pcoll_id</span> <span class="ow">in</span> <span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">pcollections</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">pcoll_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">pcollections</span> <span class="ow">or</span>
<span class="n">pcoll_id</span> <span class="ow">in</span> <span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">ignorable_components</span><span class="o">.</span><span class="n">pcollections</span>
<span class="p">):</span>
<span class="k">continue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">pcollections</span><span class="p">[</span><span class="n">pcoll_id</span><span class="p">]</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span>
<span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">pcollections</span><span class="p">[</span><span class="n">pcoll_id</span><span class="p">])</span>
<span class="k">for</span> <span class="n">coder_id</span> <span class="ow">in</span> <span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">coders</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">coder_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">coders</span> <span class="ow">or</span>
<span class="n">coder_id</span> <span class="ow">in</span> <span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">ignorable_components</span><span class="o">.</span><span class="n">coders</span><span class="p">):</span>
<span class="k">continue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">coders</span><span class="p">[</span><span class="n">coder_id</span><span class="p">]</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span>
<span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">coders</span><span class="p">[</span><span class="n">coder_id</span><span class="p">])</span>
<span class="k">for</span> <span class="n">windowing_strategy_id</span> <span class="ow">in</span> <span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">windowing_strategy_id</span> <span class="ow">in</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">windowing_strategies</span> <span class="ow">or</span>
<span class="n">windowing_strategy_id</span> <span class="ow">in</span>
<span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">ignorable_components</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="p">):</span>
<span class="k">continue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="p">[</span>
<span class="n">windowing_strategy_id</span><span class="p">]</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span>
<span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="p">[</span><span class="n">windowing_strategy_id</span><span class="p">])</span>
<span class="n">template_root_transform_id</span> <span class="o">=</span> <span class="n">template</span><span class="o">.</span><span class="n">root_transform_ids</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">root_transform_id</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">root_transform_ids</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="k">for</span> <span class="n">transform_id</span> <span class="ow">in</span> <span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">transform_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span> <span class="ow">or</span> <span class="n">transform_id</span>
<span class="ow">in</span> <span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">ignorable_components</span><span class="o">.</span><span class="n">transforms</span><span class="p">):</span>
<span class="k">continue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">[</span><span class="n">transform_id</span><span class="p">]</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span>
<span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">[</span><span class="n">transform_id</span><span class="p">])</span>
<span class="k">for</span> <span class="n">top_level_transform</span> <span class="ow">in</span> <span class="n">template</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">[</span>
<span class="n">template_root_transform_id</span><span class="p">]</span><span class="o">.</span><span class="n">subtransforms</span><span class="p">:</span>
<span class="k">if</span> <span class="p">(</span><span class="n">top_level_transform</span> <span class="ow">in</span>
<span class="n">write_input_placeholder</span><span class="o">.</span><span class="n">ignorable_components</span><span class="o">.</span><span class="n">transforms</span><span class="p">):</span>
<span class="k">continue</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="p">[</span>
<span class="n">root_transform_id</span><span class="p">]</span><span class="o">.</span><span class="n">subtransforms</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">top_level_transform</span><span class="p">)</span>
<span class="c1"># Replace all the input pcoll of input_placeholder_id from cache writing</span>
<span class="c1"># with cacheable pcoll of input_id.</span>
<span class="k">for</span> <span class="n">transform</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pipeline</span><span class="o">.</span><span class="n">components</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">inputs</span> <span class="o">=</span> <span class="n">transform</span><span class="o">.</span><span class="n">inputs</span>
<span class="k">if</span> <span class="n">input_placeholder_id</span> <span class="ow">in</span> <span class="n">inputs</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">keys_need_replacement</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
<span class="k">if</span> <span class="n">inputs</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">==</span> <span class="n">input_placeholder_id</span><span class="p">:</span>
<span class="n">keys_need_replacement</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys_need_replacement</span><span class="p">:</span>
<span class="n">inputs</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">input_id</span></div>
<span class="k">def</span> <span class="nf">_build_runner_api_template</span><span class="p">(</span>
<span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">,</span> <span class="s1">&#39;_PCollectionPlaceHolder&#39;</span><span class="p">]:</span>
<span class="n">pph</span> <span class="o">=</span> <span class="n">_PCollectionPlaceHolder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cacheable</span><span class="o">.</span><span class="n">pcoll</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_context</span><span class="p">)</span>
<span class="n">transform</span> <span class="o">=</span> <span class="n">_WriteCacheTransform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key</span><span class="p">)</span>
<span class="n">_</span> <span class="o">=</span> <span class="n">pph</span><span class="o">.</span><span class="n">placeholder_pcoll</span> <span class="o">|</span> <span class="s1">&#39;sink_cache_&#39;</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key</span> <span class="o">&gt;&gt;</span> <span class="n">transform</span>
<span class="k">return</span> <span class="n">pph</span><span class="o">.</span><span class="n">placeholder_pcoll</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">(),</span> <span class="n">pph</span></div>
<span class="k">class</span> <span class="nc">_WriteCacheTransform</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;A composite transform encapsulates writing cache for PCollections.</span>
<span class="sd"> &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">cache</span><span class="o">.</span><span class="n">CacheManager</span><span class="p">,</span> <span class="n">key</span><span class="p">:</span> <span class="nb">str</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">_key</span> <span class="o">=</span> <span class="n">key</span>
<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">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PValue</span><span class="p">:</span>
<span class="k">return</span> <span class="n">reify_to_cache</span><span class="p">(</span>
<span class="n">pcoll</span><span class="o">=</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">cache_key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_key</span><span class="p">,</span> <span class="n">cache_manager</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">_PCollectionPlaceHolder</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;A placeholder as an input to the cache writing transform.</span>
<span class="sd"> &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">pcoll</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">,</span> <span class="n">context</span><span class="p">:</span> <span class="n">PipelineContext</span><span class="p">):</span>
<span class="n">tmp_pipeline</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">()</span>
<span class="n">tmp_pipeline</span><span class="o">.</span><span class="n">component_id_map</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">component_id_map</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_input_placeholder</span> <span class="o">=</span> <span class="n">tmp_pipeline</span> <span class="o">|</span> <span class="s1">&#39;CreatePInput&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">(</span>
<span class="p">[],</span> <span class="n">reshuffle</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">_input_placeholder</span><span class="o">.</span><span class="n">tag</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">tag</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_input_placeholder</span><span class="o">.</span><span class="n">element_type</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_input_placeholder</span><span class="o">.</span><span class="n">is_bounded</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">is_bounded</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_input_placeholder</span><span class="o">.</span><span class="n">_windowing</span> <span class="o">=</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">windowing</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_ignorable_components</span> <span class="o">=</span> <span class="n">tmp_pipeline</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">()</span><span class="o">.</span><span class="n">components</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">placeholder_pcoll</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_placeholder</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">ignorable_components</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">Components</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Subgraph generated by the placeholder that can be ignored in the final</span>
<span class="sd"> pipeline proto.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ignorable_components</span>
</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>