| |
| |
| <!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.io.gcp.pubsub_it_pipeline — Apache Beam documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| |
| |
| |
| |
| |
| <link rel="index" title="Index" |
| href="../../../../genindex.html"/> |
| <link rel="search" title="Search" href="../../../../search.html"/> |
| <link rel="top" title="Apache Beam documentation" href="../../../../index.html"/> |
| <link rel="up" title="Module code" href="../../../index.html"/> |
| |
| |
| <script src="../../../../_static/js/modernizr.min.js"></script> |
| |
| </head> |
| |
| <body class="wy-body-for-nav" role="document"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search"> |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.internal.html">apache_beam.internal package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.tools.html">apache_beam.tools package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.version.html">apache_beam.version module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| |
| <div class="wy-nav-content"> |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.gcp.pubsub_it_pipeline</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.io.gcp.pubsub_it_pipeline</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| <span class="sd">"""</span> |
| <span class="sd">Test pipeline for use by pubsub_integration_test.</span> |
| <span class="sd">"""</span> |
| |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| |
| <span class="kn">import</span> <span class="nn">argparse</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.options.pipeline_options</span> <span class="k">import</span> <span class="n">PipelineOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">SetupOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">StandardOptions</span> |
| |
| |
| <div class="viewcode-block" id="run_pipeline"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.pubsub_it_pipeline.html#apache_beam.io.gcp.pubsub_it_pipeline.run_pipeline">[docs]</a><span class="k">def</span> <span class="nf">run_pipeline</span><span class="p">(</span><span class="n">argv</span><span class="p">,</span> <span class="n">with_attributes</span><span class="p">,</span> <span class="n">id_label</span><span class="p">,</span> <span class="n">timestamp_attribute</span><span class="p">):</span> |
| <span class="sd">"""Build and run the pipeline."""</span> |
| |
| <span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span> |
| <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
| <span class="s1">'--output_topic'</span><span class="p">,</span> <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span><span class="s1">'Output PubSub topic of the form '</span> |
| <span class="s1">'"projects/<PROJECT>/topic/<TOPIC>".'</span><span class="p">))</span> |
| <span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span> |
| <span class="s1">'--input_subscription'</span><span class="p">,</span> <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span><span class="s1">'Input PubSub subscription of the form '</span> |
| <span class="s1">'"projects/<PROJECT>/subscriptions/<SUBSCRIPTION>."'</span><span class="p">))</span> |
| <span class="n">known_args</span><span class="p">,</span> <span class="n">pipeline_args</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_known_args</span><span class="p">(</span><span class="n">argv</span><span class="p">)</span> |
| |
| <span class="c1"># We use the save_main_session option because one or more DoFn's in this</span> |
| <span class="c1"># workflow rely on global context (e.g., a module imported at module level).</span> |
| <span class="n">pipeline_options</span> <span class="o">=</span> <span class="n">PipelineOptions</span><span class="p">(</span><span class="n">pipeline_args</span><span class="p">)</span> |
| <span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">SetupOptions</span><span class="p">)</span><span class="o">.</span><span class="n">save_main_session</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">streaming</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">p</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">options</span><span class="o">=</span><span class="n">pipeline_options</span><span class="p">)</span> |
| <span class="n">runner_name</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">runner</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span> |
| |
| <span class="c1"># Read from PubSub into a PCollection.</span> |
| <span class="k">if</span> <span class="n">runner_name</span> <span class="o">==</span> <span class="s1">'TestDirectRunner'</span><span class="p">:</span> |
| <span class="n">messages</span> <span class="o">=</span> <span class="n">p</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ReadFromPubSub</span><span class="p">(</span> |
| <span class="n">subscription</span><span class="o">=</span><span class="n">known_args</span><span class="o">.</span><span class="n">input_subscription</span><span class="p">,</span> |
| <span class="n">with_attributes</span><span class="o">=</span><span class="n">with_attributes</span><span class="p">,</span> |
| <span class="n">timestamp_attribute</span><span class="o">=</span><span class="n">timestamp_attribute</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">messages</span> <span class="o">=</span> <span class="n">p</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ReadFromPubSub</span><span class="p">(</span> |
| <span class="n">subscription</span><span class="o">=</span><span class="n">known_args</span><span class="o">.</span><span class="n">input_subscription</span><span class="p">,</span> |
| <span class="n">id_label</span><span class="o">=</span><span class="n">id_label</span><span class="p">,</span> |
| <span class="n">with_attributes</span><span class="o">=</span><span class="n">with_attributes</span><span class="p">,</span> |
| <span class="n">timestamp_attribute</span><span class="o">=</span><span class="n">timestamp_attribute</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">add_attribute</span><span class="p">(</span><span class="n">msg</span><span class="p">,</span> <span class="n">timestamp</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="n">msg</span><span class="o">.</span><span class="n">data</span> <span class="o">+=</span> <span class="s1">'-seen'</span> |
| <span class="n">msg</span><span class="o">.</span><span class="n">attributes</span><span class="p">[</span><span class="s1">'processed'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'IT'</span> |
| <span class="k">if</span> <span class="n">timestamp_attribute</span> <span class="ow">in</span> <span class="n">msg</span><span class="o">.</span><span class="n">attributes</span><span class="p">:</span> |
| <span class="n">msg</span><span class="o">.</span><span class="n">attributes</span><span class="p">[</span><span class="n">timestamp_attribute</span> <span class="o">+</span> <span class="s1">'_out'</span><span class="p">]</span> <span class="o">=</span> <span class="n">timestamp</span><span class="o">.</span><span class="n">to_rfc3339</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">msg</span> |
| |
| <span class="k">def</span> <span class="nf">modify_data</span><span class="p">(</span><span class="n">data</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">data</span> <span class="o">+</span> <span class="s1">'-seen'</span> |
| |
| <span class="k">if</span> <span class="n">with_attributes</span><span class="p">:</span> |
| <span class="n">output</span> <span class="o">=</span> <span class="n">messages</span> <span class="o">|</span> <span class="s1">'add_attribute'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">add_attribute</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">output</span> <span class="o">=</span> <span class="n">messages</span> <span class="o">|</span> <span class="s1">'modify_data'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">modify_data</span><span class="p">)</span> |
| |
| <span class="c1"># Write to PubSub.</span> |
| <span class="k">if</span> <span class="n">runner_name</span> <span class="o">==</span> <span class="s1">'TestDirectRunner'</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="n">output</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">WriteToPubSub</span><span class="p">(</span><span class="n">known_args</span><span class="o">.</span><span class="n">output_topic</span><span class="p">,</span> |
| <span class="n">with_attributes</span><span class="o">=</span><span class="n">with_attributes</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="n">output</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">WriteToPubSub</span><span class="p">(</span><span class="n">known_args</span><span class="o">.</span><span class="n">output_topic</span><span class="p">,</span> |
| <span class="n">id_label</span><span class="o">=</span><span class="n">id_label</span><span class="p">,</span> |
| <span class="n">with_attributes</span><span class="o">=</span><span class="n">with_attributes</span><span class="p">,</span> |
| <span class="n">timestamp_attribute</span><span class="o">=</span><span class="n">timestamp_attribute</span><span class="p">)</span> |
| |
| <span class="n">result</span> <span class="o">=</span> <span class="n">p</span><span class="o">.</span><span class="n">run</span><span class="p">()</span> |
| <span class="n">result</span><span class="o">.</span><span class="n">wait_until_finish</span><span class="p">()</span></div> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright . |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| |
| |
| <script type="text/javascript"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT:'../../../../', |
| VERSION:'', |
| COLLAPSE_INDEX:false, |
| FILE_SUFFIX:'.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.StickyNav.enable(); |
| }); |
| </script> |
| |
| |
| </body> |
| </html> |