blob: e683d1c46c1960d9775b5ec441a913f1fc8893ae [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.options.capture_limiters &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.options.capture_limiters</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.options.capture_limiters</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 condition how Interactive Beam stops capturing data.</span>
<span class="sd">For internal use only; no backwards-compatibility guarantees.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">threading</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">from</span> <span class="nn">apache_beam.portability.api.beam_interactive_api_pb2</span> <span class="kn">import</span> <span class="n">TestStreamFileHeader</span>
<span class="kn">from</span> <span class="nn">apache_beam.portability.api.beam_interactive_api_pb2</span> <span class="kn">import</span> <span class="n">TestStreamFileRecord</span>
<span class="kn">from</span> <span class="nn">apache_beam.portability.api.beam_runner_api_pb2</span> <span class="kn">import</span> <span class="n">TestStreamPayload</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">interactive_environment</span> <span class="k">as</span> <span class="n">ie</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils.windowed_value</span> <span class="kn">import</span> <span class="n">WindowedValue</span>
<div class="viewcode-block" id="Limiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.Limiter">[docs]</a><span class="k">class</span> <span class="nc">Limiter</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Limits an aspect of the caching layer.&quot;&quot;&quot;</span>
<div class="viewcode-block" id="Limiter.is_triggered"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.Limiter.is_triggered">[docs]</a> <span class="k">def</span> <span class="nf">is_triggered</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># type: () -&gt; bool</span>
<span class="sd">&quot;&quot;&quot;Returns True if the limiter has triggered, and caching should stop.&quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div>
<div class="viewcode-block" id="ElementLimiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.ElementLimiter">[docs]</a><span class="k">class</span> <span class="nc">ElementLimiter</span><span class="p">(</span><span class="n">Limiter</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A `Limiter` that limits reading from cache based on some property of an</span>
<span class="sd"> element.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="ElementLimiter.update"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.ElementLimiter.update">[docs]</a> <span class="k">def</span> <span class="nf">update</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"># type: (Any) -&gt; None</span>
<span class="sd">&quot;&quot;&quot;Update the internal state based on some property of an element.</span>
<span class="sd"> This is executed on every element that is read from cache.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div>
<div class="viewcode-block" id="SizeLimiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.SizeLimiter">[docs]</a><span class="k">class</span> <span class="nc">SizeLimiter</span><span class="p">(</span><span class="n">Limiter</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Limits the cache size to a specified byte limit.&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">size_limit</span> <span class="c1"># type: int</span>
<span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_size_limit</span> <span class="o">=</span> <span class="n">size_limit</span>
<div class="viewcode-block" id="SizeLimiter.is_triggered"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.SizeLimiter.is_triggered">[docs]</a> <span class="k">def</span> <span class="nf">is_triggered</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">total_capture_size</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">track_user_pipelines</span><span class="p">()</span>
<span class="k">for</span> <span class="n">user_pipeline</span> <span class="ow">in</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">tracked_user_pipelines</span><span class="p">:</span>
<span class="n">cache_manager</span> <span class="o">=</span> <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">get_cache_manager</span><span class="p">(</span><span class="n">user_pipeline</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">cache_manager</span><span class="p">,</span> <span class="s1">&#39;capture_size&#39;</span><span class="p">):</span>
<span class="n">total_capture_size</span> <span class="o">+=</span> <span class="n">cache_manager</span><span class="o">.</span><span class="n">capture_size</span>
<span class="k">return</span> <span class="n">total_capture_size</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_size_limit</span></div></div>
<div class="viewcode-block" id="DurationLimiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.DurationLimiter">[docs]</a><span class="k">class</span> <span class="nc">DurationLimiter</span><span class="p">(</span><span class="n">Limiter</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Limits the duration of the capture.&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">duration_limit</span> <span class="c1"># type: datetime.timedelta</span>
<span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_duration_limit</span> <span class="o">=</span> <span class="n">duration_limit</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_timer</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">Timer</span><span class="p">(</span><span class="n">duration_limit</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_trigger</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_timer</span><span class="o">.</span><span class="n">daemon</span> <span class="o">=</span> <span class="kc">True</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_triggered</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_timer</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_trigger</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">_triggered</span> <span class="o">=</span> <span class="kc">True</span>
<div class="viewcode-block" id="DurationLimiter.is_triggered"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.DurationLimiter.is_triggered">[docs]</a> <span class="k">def</span> <span class="nf">is_triggered</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_triggered</span></div></div>
<div class="viewcode-block" id="CountLimiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.CountLimiter">[docs]</a><span class="k">class</span> <span class="nc">CountLimiter</span><span class="p">(</span><span class="n">ElementLimiter</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Limits by counting the number of elements seen.&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">max_count</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_count</span> <span class="o">=</span> <span class="n">max_count</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">=</span> <span class="mi">0</span>
<div class="viewcode-block" id="CountLimiter.update"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.CountLimiter.update">[docs]</a> <span class="k">def</span> <span class="nf">update</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"># A TestStreamFileRecord can contain many elements at once. If e is a file</span>
<span class="c1"># record, then count the number of elements in the bundle.</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">TestStreamFileRecord</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">e</span><span class="o">.</span><span class="n">recorded_event</span><span class="o">.</span><span class="n">element_event</span><span class="p">:</span>
<span class="k">return</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">+=</span> <span class="nb">len</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">recorded_event</span><span class="o">.</span><span class="n">element_event</span><span class="o">.</span><span class="n">elements</span><span class="p">)</span>
<span class="c1"># Otherwise, count everything else but the header of the file since it is</span>
<span class="c1"># not an element.</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">TestStreamFileHeader</span><span class="p">):</span>
<span class="c1"># When elements are DataFrames, we want the output to be constrained by</span>
<span class="c1"># how many rows we have read, not how many DataFrames we have read.</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">WindowedValue</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">value</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">+=</span> <span class="nb">len</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">value</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">+=</span> <span class="mi">1</span></div>
<div class="viewcode-block" id="CountLimiter.is_triggered"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.CountLimiter.is_triggered">[docs]</a> <span class="k">def</span> <span class="nf">is_triggered</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_count</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_count</span></div></div>
<div class="viewcode-block" id="ProcessingTimeLimiter"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.ProcessingTimeLimiter">[docs]</a><span class="k">class</span> <span class="nc">ProcessingTimeLimiter</span><span class="p">(</span><span class="n">ElementLimiter</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Limits by how long the ProcessingTime passed in the element stream.</span>
<span class="sd"> Reads all elements from the timespan [start, start + duration).</span>
<span class="sd"> This measures the duration from the first element in the stream. Each</span>
<span class="sd"> subsequent element has a delta &quot;advance_duration&quot; that moves the internal</span>
<span class="sd"> clock forward. This triggers when the duration from the internal clock and</span>
<span class="sd"> the start exceeds the given duration.</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">max_duration_secs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the ProcessingTimeLimiter.&quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_max_duration_us</span> <span class="o">=</span> <span class="n">max_duration_secs</span> <span class="o">*</span> <span class="mf">1e6</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_us</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cur_time_us</span> <span class="o">=</span> <span class="mi">0</span>
<div class="viewcode-block" id="ProcessingTimeLimiter.update"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.ProcessingTimeLimiter.update">[docs]</a> <span class="k">def</span> <span class="nf">update</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"># Only look at TestStreamFileRecords which hold the processing time.</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">TestStreamPayload</span><span class="o">.</span><span class="n">Event</span><span class="p">):</span>
<span class="k">return</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">e</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;processing_time_event&#39;</span><span class="p">):</span>
<span class="k">return</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_us</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_us</span> <span class="o">=</span> <span class="n">e</span><span class="o">.</span><span class="n">processing_time_event</span><span class="o">.</span><span class="n">advance_duration</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cur_time_us</span> <span class="o">+=</span> <span class="n">e</span><span class="o">.</span><span class="n">processing_time_event</span><span class="o">.</span><span class="n">advance_duration</span></div>
<div class="viewcode-block" id="ProcessingTimeLimiter.is_triggered"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.options.capture_limiters.html#apache_beam.runners.interactive.options.capture_limiters.ProcessingTimeLimiter.is_triggered">[docs]</a> <span class="k">def</span> <span class="nf">is_triggered</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cur_time_us</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_us</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_duration_us</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>