blob: f64d4652f36813cfacd1f66244c0ab51325b8b92 [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.reify &mdash; Apache Beam 2.38.0 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">
2.38.0
</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.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>
</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.reify</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.reify</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 for transforms that reifies and unreifies PCollection values with</span>
<span class="sd">window info.</span>
<span class="sd">For internal use only; no backwards-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">Optional</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.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.testing</span> <span class="kn">import</span> <span class="n">test_stream</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.window</span> <span class="kn">import</span> <span class="n">WindowedValue</span>
<span class="n">READ_CACHE</span> <span class="o">=</span> <span class="s1">&#39;ReadCache_&#39;</span>
<span class="n">WRITE_CACHE</span> <span class="o">=</span> <span class="s1">&#39;WriteCache_&#39;</span>
<div class="viewcode-block" id="Reify"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.Reify">[docs]</a><span class="k">class</span> <span class="nc">Reify</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Reifies elements with window info into windowed values.</span>
<span class="sd"> Internally used to capture window info with each element into cache for</span>
<span class="sd"> replayability.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="Reify.process"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.Reify.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">e</span><span class="p">,</span>
<span class="n">w</span><span class="o">=</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">WindowParam</span><span class="p">,</span>
<span class="n">p</span><span class="o">=</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">PaneInfoParam</span><span class="p">,</span>
<span class="n">t</span><span class="o">=</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">TimestampParam</span><span class="p">):</span>
<span class="k">yield</span> <span class="n">test_stream</span><span class="o">.</span><span class="n">WindowedValueHolder</span><span class="p">(</span><span class="n">WindowedValue</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">t</span><span class="p">,</span> <span class="p">[</span><span class="n">w</span><span class="p">],</span> <span class="n">p</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="Unreify"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.Unreify">[docs]</a><span class="k">class</span> <span class="nc">Unreify</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Unreifies elements from windowed values.</span>
<span class="sd"> Cached values are elements with window info. This unpacks the elements.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="Unreify.process"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.Unreify.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">e</span><span class="p">):</span>
<span class="c1"># Row coder was used when encoding windowed values.</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">Row</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="s1">&#39;windowed_value&#39;</span><span class="p">):</span>
<span class="k">yield</span> <span class="n">e</span><span class="o">.</span><span class="n">windowed_value</span></div></div>
<div class="viewcode-block" id="reify_to_cache"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.reify_to_cache">[docs]</a><span class="k">def</span> <span class="nf">reify_to_cache</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">cache_key</span><span class="p">:</span> <span class="nb">str</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">reify_label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">write_cache_label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">is_capture</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</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="sd">&quot;&quot;&quot;Reifies elements into windowed values and write to cache.</span>
<span class="sd"> Args:</span>
<span class="sd"> pcoll: The PCollection to be cached.</span>
<span class="sd"> cache_key: The key of the cache.</span>
<span class="sd"> cache_manager: The cache manager to manage the cache.</span>
<span class="sd"> reify_label: (optional) A transform label for the Reify transform.</span>
<span class="sd"> write_cache_label: (optional) A transform label for the cache-writing</span>
<span class="sd"> transform.</span>
<span class="sd"> is_capture: Whether the cache is capturing a record of recordable sources.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">reify_label</span><span class="p">:</span>
<span class="n">reify_label</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{}{}{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">&#39;ReifyBefore_&#39;</span><span class="p">,</span> <span class="n">WRITE_CACHE</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">write_cache_label</span><span class="p">:</span>
<span class="n">write_cache_label</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{}{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">WRITE_CACHE</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">)</span>
<span class="k">return</span> <span class="p">(</span>
<span class="n">pcoll</span> <span class="o">|</span> <span class="n">reify_label</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">Reify</span><span class="p">())</span>
<span class="o">|</span> <span class="n">write_cache_label</span> <span class="o">&gt;&gt;</span> <span class="n">cache</span><span class="o">.</span><span class="n">WriteCache</span><span class="p">(</span>
<span class="n">cache_manager</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">,</span> <span class="n">is_capture</span><span class="o">=</span><span class="n">is_capture</span><span class="p">))</span></div>
<div class="viewcode-block" id="unreify_from_cache"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.reify.html#apache_beam.runners.interactive.caching.reify.unreify_from_cache">[docs]</a><span class="k">def</span> <span class="nf">unreify_from_cache</span><span class="p">(</span>
<span class="n">pipeline</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">,</span>
<span class="n">cache_key</span><span class="p">:</span> <span class="nb">str</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">element_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">type</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">source_label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
<span class="n">unreify_label</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</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="sd">&quot;&quot;&quot;Reads from cache and unreifies elements from windowed values.</span>
<span class="sd"> pipeline: The pipeline that&#39;s reading from the cache.</span>
<span class="sd"> cache_key: The key of the cache.</span>
<span class="sd"> cache_manager: The cache manager to manage the cache.</span>
<span class="sd"> element_type: (optional) The element type of the PCollection&#39;s elements.</span>
<span class="sd"> source_label: (optional) A transform label for the cache-reading transform.</span>
<span class="sd"> unreify_label: (optional) A transform label for the Unreify transform.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">source_label</span><span class="p">:</span>
<span class="n">source_label</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{}{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">READ_CACHE</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">unreify_label</span><span class="p">:</span>
<span class="n">unreify_label</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{}{}{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s1">&#39;UnreifyAfter_&#39;</span><span class="p">,</span> <span class="n">READ_CACHE</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">)</span>
<span class="n">read_cache</span> <span class="o">=</span> <span class="n">pipeline</span> <span class="o">|</span> <span class="n">source_label</span> <span class="o">&gt;&gt;</span> <span class="n">cache</span><span class="o">.</span><span class="n">ReadCache</span><span class="p">(</span>
<span class="n">cache_manager</span><span class="p">,</span> <span class="n">cache_key</span><span class="p">)</span>
<span class="k">if</span> <span class="n">element_type</span><span class="p">:</span>
<span class="c1"># If the PCollection is schema-aware, explicitly sets the output types.</span>
<span class="k">return</span> <span class="n">read_cache</span> <span class="o">|</span> <span class="n">unreify_label</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span>
<span class="n">Unreify</span><span class="p">())</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">element_type</span><span class="p">)</span>
<span class="k">return</span> <span class="n">read_cache</span> <span class="o">|</span> <span class="n">unreify_label</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">Unreify</span><span class="p">())</span></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>