| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="../../../"> |
| <head> |
| <meta charset="utf-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.io.debezium — Apache Beam 2.67.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="../../../_static/jquery.js?v=5d32c60e"></script> |
| <script src="../../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="../../../_static/documentation_options.js?v=959b4fbe"></script> |
| <script src="../../../_static/doctools.js?v=9a2dae69"></script> |
| <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="../../../_static/js/theme.js"></script> |
| <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 role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="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="Navigation menu"> |
| <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="Mobile navigation menu" > |
| <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="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="../../../index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="../../index.html">Module code</a></li> |
| <li class="breadcrumb-item active">apache_beam.io.debezium</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.debezium</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">""" Unbounded source transform for</span> |
| <span class="sd"> `Debezium <href="https://debezium.io/"/>`_.</span> |
| |
| <span class="sd"> This transform is currently supported by Beam portable</span> |
| <span class="sd"> Flink, Spark, and Dataflow v2 runners.</span> |
| |
| <span class="sd"> **Setup**</span> |
| |
| <span class="sd"> Transform provided in this module is cross-language transform</span> |
| <span class="sd"> implemented in the Beam Java SDK. During the pipeline construction, Python SDK</span> |
| <span class="sd"> will connect to a Java expansion service to expand this transform.</span> |
| <span class="sd"> To facilitate this, a small amount of setup is needed before using this</span> |
| <span class="sd"> transform in a Beam Python pipeline.</span> |
| |
| <span class="sd"> There are several ways to setup cross-language Debezium transform.</span> |
| |
| <span class="sd"> * Option 1: use the default expansion service</span> |
| <span class="sd"> * Option 2: specify a custom expansion service</span> |
| |
| <span class="sd"> See below for details regarding each of these options.</span> |
| |
| <span class="sd"> *Option 1: Use the default expansion service*</span> |
| |
| <span class="sd"> This is the recommended and easiest setup option for using Python Debezium</span> |
| <span class="sd"> transform. This option requires following pre-requisites</span> |
| <span class="sd"> before running the Beam pipeline.</span> |
| |
| <span class="sd"> * Install Java runtime in the computer from where the pipeline is constructed</span> |
| <span class="sd"> and make sure that 'java' command is available.</span> |
| |
| <span class="sd"> In this option, Python SDK will either download (for released Beam version) or</span> |
| <span class="sd"> build (when running from a Beam Git clone) a expansion service jar and use</span> |
| <span class="sd"> that to expand transforms. Currently Debezium transform use the</span> |
| <span class="sd"> 'beam-sdks-java-io-debezium-expansion-service' jar for this purpose.</span> |
| |
| <span class="sd"> *Option 2: specify a custom expansion service*</span> |
| |
| <span class="sd"> In this option, you startup your own expansion service and provide that as</span> |
| <span class="sd"> a parameter when using the transform provided in this module.</span> |
| |
| <span class="sd"> This option requires following pre-requisites before running the Beam</span> |
| <span class="sd"> pipeline.</span> |
| |
| <span class="sd"> * Startup your own expansion service.</span> |
| <span class="sd"> * Update your pipeline to provide the expansion service address when</span> |
| <span class="sd"> initiating Debezium transform provided in this module.</span> |
| |
| <span class="sd"> Flink Users can use the built-in Expansion Service of the Flink Runner's</span> |
| <span class="sd"> Job Server. If you start Flink's Job Server, the expansion service will be</span> |
| <span class="sd"> started on port 8097. For a different address, please set the</span> |
| <span class="sd"> expansion_service parameter.</span> |
| |
| <span class="sd"> **More information**</span> |
| |
| <span class="sd"> For more information regarding cross-language transforms see:</span> |
| <span class="sd"> - https://beam.apache.org/roadmap/portability/</span> |
| |
| <span class="sd"> For more information specific to Flink runner see:</span> |
| <span class="sd"> - https://beam.apache.org/documentation/runners/flink/</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span><span class="w"> </span><span class="nn">json</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">enum</span><span class="w"> </span><span class="kn">import</span> <span class="n">Enum</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">List</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Optional</span> |
| |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam.transforms</span><span class="w"> </span><span class="kn">import</span> <span class="n">Map</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam.transforms</span><span class="w"> </span><span class="kn">import</span> <span class="n">PTransform</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam.transforms.external</span><span class="w"> </span><span class="kn">import</span> <span class="n">BeamJarExpansionService</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam.transforms.external</span><span class="w"> </span><span class="kn">import</span> <span class="n">ExternalTransform</span> |
| <span class="kn">from</span><span class="w"> </span><span class="nn">apache_beam.transforms.external</span><span class="w"> </span><span class="kn">import</span> <span class="n">NamedTupleBasedPayloadBuilder</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'ReadFromDebezium'</span><span class="p">,</span> <span class="s1">'DriverClassName'</span><span class="p">]</span> |
| |
| |
| <span class="k">def</span><span class="w"> </span><span class="nf">default_io_expansion_service</span><span class="p">():</span> |
| <span class="k">return</span> <span class="n">BeamJarExpansionService</span><span class="p">(</span> |
| <span class="s1">'sdks:java:io:debezium:expansion-service:shadowJar'</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="DriverClassName"> |
| <a class="viewcode-back" href="../../../apache_beam.io.debezium.html#apache_beam.io.debezium.DriverClassName">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">DriverClassName</span><span class="p">(</span><span class="n">Enum</span><span class="p">):</span> |
| <span class="n">MYSQL</span> <span class="o">=</span> <span class="s1">'MySQL'</span> |
| <span class="n">POSTGRESQL</span> <span class="o">=</span> <span class="s1">'PostgreSQL'</span> |
| <span class="n">ORACLE</span> <span class="o">=</span> <span class="s1">'Oracle'</span> |
| <span class="n">DB2</span> <span class="o">=</span> <span class="s1">'Db2'</span></div> |
| |
| |
| |
| <span class="n">ReadFromDebeziumSchema</span> <span class="o">=</span> <span class="n">NamedTuple</span><span class="p">(</span> |
| <span class="s1">'ReadFromDebeziumSchema'</span><span class="p">,</span> |
| <span class="p">[(</span><span class="s1">'connector_class'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> <span class="p">(</span><span class="s1">'username'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> <span class="p">(</span><span class="s1">'password'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> |
| <span class="p">(</span><span class="s1">'host'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> <span class="p">(</span><span class="s1">'port'</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span> <span class="p">(</span><span class="s1">'max_number_of_records'</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]),</span> |
| <span class="p">(</span><span class="s1">'connection_properties'</span><span class="p">,</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">])])</span> |
| |
| |
| <div class="viewcode-block" id="ReadFromDebezium"> |
| <a class="viewcode-back" href="../../../apache_beam.io.debezium.html#apache_beam.io.debezium.ReadFromDebezium">[docs]</a> |
| <span class="k">class</span><span class="w"> </span><span class="nc">ReadFromDebezium</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> An external PTransform which reads from Debezium and returns</span> |
| <span class="sd"> a Dictionary for each item in the specified database</span> |
| <span class="sd"> connection.</span> |
| |
| <span class="sd"> Experimental; no backwards compatibility guarantees.</span> |
| <span class="sd"> """</span> |
| <span class="n">URN</span> <span class="o">=</span> <span class="s1">'beam:transform:org.apache.beam:debezium_read:v1'</span> |
| |
| <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">connector_class</span><span class="p">,</span> |
| <span class="n">username</span><span class="p">,</span> |
| <span class="n">password</span><span class="p">,</span> |
| <span class="n">host</span><span class="p">,</span> |
| <span class="n">port</span><span class="p">,</span> |
| <span class="n">max_number_of_records</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">connection_properties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Initializes a read operation from Debezium.</span> |
| |
| <span class="sd"> :param connector_class: name of the jdbc driver class</span> |
| <span class="sd"> :param username: database username</span> |
| <span class="sd"> :param password: database password</span> |
| <span class="sd"> :param host: database host</span> |
| <span class="sd"> :param port: database port</span> |
| <span class="sd"> :param max_number_of_records: maximum number of records</span> |
| <span class="sd"> to be fetched before stop.</span> |
| <span class="sd"> :param connection_properties: properties of the debezium</span> |
| <span class="sd"> connection passed as string</span> |
| <span class="sd"> with with format</span> |
| <span class="sd"> [propertyName=property;]*</span> |
| <span class="sd"> :param expansion_service: The address (host:port)</span> |
| <span class="sd"> of the ExpansionService.</span> |
| <span class="sd"> """</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">params</span> <span class="o">=</span> <span class="n">ReadFromDebeziumSchema</span><span class="p">(</span> |
| <span class="n">connector_class</span><span class="o">=</span><span class="n">connector_class</span><span class="o">.</span><span class="n">value</span><span class="p">,</span> |
| <span class="n">username</span><span class="o">=</span><span class="n">username</span><span class="p">,</span> |
| <span class="n">password</span><span class="o">=</span><span class="n">password</span><span class="p">,</span> |
| <span class="n">host</span><span class="o">=</span><span class="n">host</span><span class="p">,</span> |
| <span class="n">port</span><span class="o">=</span><span class="nb">str</span><span class="p">(</span><span class="n">port</span><span class="p">),</span> |
| <span class="n">max_number_of_records</span><span class="o">=</span><span class="n">max_number_of_records</span><span class="p">,</span> |
| <span class="n">connection_properties</span><span class="o">=</span><span class="n">connection_properties</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span> <span class="ow">or</span> <span class="n">default_io_expansion_service</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="ReadFromDebezium.expand"> |
| <a class="viewcode-back" href="../../../apache_beam.io.debezium.html#apache_beam.io.debezium.ReadFromDebezium.expand">[docs]</a> |
| <span class="k">def</span><span class="w"> </span><span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pbegin</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">pbegin</span> <span class="o">|</span> <span class="n">ExternalTransform</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span> |
| <span class="n">NamedTupleBasedPayloadBuilder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span><span class="p">,</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="nb">str</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'JsonToDict'</span> <span class="o">>></span> <span class="n">Map</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">)</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="nb">dict</span><span class="p">))</span></div> |
| </div> |
| |
| </pre></div> |
| |
| </div> |
| </div> |
| <footer> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |