| |
| |
| <!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.bigquery_io_read_pipeline — 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> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.gcp.bigquery_io_read_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.bigquery_io_read_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">"""A Dataflow job that counts the number of rows in a BQ table.</span> |
| |
| <span class="sd"> Can be configured to simulate slow reading for a given number of rows.</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span> <span class="nn">argparse</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">random</span> |
| <span class="kn">import</span> <span class="nn">time</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.io.gcp.bigquery</span> <span class="kn">import</span> <span class="n">ReadFromBigQuery</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">GoogleCloudOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.testing.test_pipeline</span> <span class="kn">import</span> <span class="n">TestPipeline</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.testing.util</span> <span class="kn">import</span> <span class="n">assert_that</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.testing.util</span> <span class="kn">import</span> <span class="n">equal_to</span> |
| |
| |
| <div class="viewcode-block" id="RowToStringWithSlowDown"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_io_read_pipeline.html#apache_beam.io.gcp.bigquery_io_read_pipeline.RowToStringWithSlowDown">[docs]</a><span class="k">class</span> <span class="nc">RowToStringWithSlowDown</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span> |
| <div class="viewcode-block" id="RowToStringWithSlowDown.process"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_io_read_pipeline.html#apache_beam.io.gcp.bigquery_io_read_pipeline.RowToStringWithSlowDown.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">element</span><span class="p">,</span> <span class="n">num_slow</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="k">if</span> <span class="n">num_slow</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="p">[</span><span class="s1">'row'</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">rand</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">()</span> <span class="o">*</span> <span class="mi">100</span> |
| <span class="k">if</span> <span class="n">rand</span> <span class="o"><</span> <span class="n">num_slow</span><span class="p">:</span> |
| <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="mf">0.01</span><span class="p">)</span> |
| <span class="k">yield</span> <span class="p">[</span><span class="s1">'slow_row'</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="p">[</span><span class="s1">'row'</span><span class="p">]</span></div></div> |
| |
| |
| <div class="viewcode-block" id="run"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_io_read_pipeline.html#apache_beam.io.gcp.bigquery_io_read_pipeline.run">[docs]</a><span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="n">argv</span><span class="o">=</span><span class="kc">None</span><span class="p">):</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">'--input_table'</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="s1">'Input table to process.'</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">'--num_records'</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="s1">'The expected number of records'</span><span class="p">,</span> |
| <span class="nb">type</span><span class="o">=</span><span class="nb">int</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">'--num_slow'</span><span class="p">,</span> |
| <span class="n">default</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span> |
| <span class="s1">'Percentage of rows that will be slow. '</span> |
| <span class="s1">'Must be in the range [0, 100)'</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">'--beam_bq_source'</span><span class="p">,</span> |
| <span class="n">default</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="nb">type</span><span class="o">=</span><span class="nb">bool</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span> |
| <span class="s1">'Whether to use the new ReadFromBigQuery'</span> |
| <span class="s1">' transform, or the BigQuerySource.'</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="n">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="k">with</span> <span class="n">TestPipeline</span><span class="p">(</span><span class="n">options</span><span class="o">=</span><span class="n">options</span><span class="p">)</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">known_args</span><span class="o">.</span><span class="n">beam_bq_source</span><span class="p">:</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">ReadFromBigQuery</span><span class="p">(</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'</span><span class="si">%s</span><span class="s1">:</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="n">known_args</span><span class="o">.</span><span class="n">input_table</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">reader</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">Read</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">BigQuerySource</span><span class="p">(</span><span class="n">known_args</span><span class="o">.</span><span class="n">input_table</span><span class="p">))</span> |
| |
| <span class="c1"># pylint: disable=expression-not-assigned</span> |
| <span class="n">count</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> <span class="o">|</span> <span class="s1">'read'</span> <span class="o">>></span> <span class="n">reader</span> |
| <span class="o">|</span> <span class="s1">'row to string'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span> |
| <span class="n">RowToStringWithSlowDown</span><span class="p">(),</span> <span class="n">num_slow</span><span class="o">=</span><span class="n">known_args</span><span class="o">.</span><span class="n">num_slow</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'count'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">combiners</span><span class="o">.</span><span class="n">Count</span><span class="o">.</span><span class="n">Globally</span><span class="p">())</span> |
| |
| <span class="n">assert_that</span><span class="p">(</span><span class="n">count</span><span class="p">,</span> <span class="n">equal_to</span><span class="p">([</span><span class="n">known_args</span><span class="o">.</span><span class="n">num_records</span><span class="p">]))</span></div> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">()</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span> |
| <span class="n">run</span><span class="p">()</span> |
| </pre></div> |
| |
| </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/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> |