| |
| |
| <!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.bigtableio — 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.bigtableio</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.bigtableio</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">"""BigTable connector</span> |
| |
| <span class="sd">This module implements writing to BigTable tables.</span> |
| <span class="sd">The default mode is to set row data to write to BigTable tables.</span> |
| <span class="sd">The syntax supported is described here:</span> |
| <span class="sd">https://cloud.google.com/bigtable/docs/quickstart-cbt</span> |
| |
| <span class="sd">BigTable connector can be used as main outputs. A main output</span> |
| <span class="sd">(common case) is expected to be massive and will be split into</span> |
| <span class="sd">manageable chunks and processed in parallel. In the example below</span> |
| <span class="sd">we created a list of rows then passed to the GeneratedDirectRows</span> |
| <span class="sd">DoFn to set the Cells and then we call the BigTableWriteFn to insert</span> |
| <span class="sd">those generated rows in the table.</span> |
| |
| <span class="sd"> main_table = (p</span> |
| <span class="sd"> | beam.Create(self._generate())</span> |
| <span class="sd"> | WriteToBigTable(project_id,</span> |
| <span class="sd"> instance_id,</span> |
| <span class="sd"> table_id))</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">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.metrics</span> <span class="k">import</span> <span class="n">Metrics</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.display</span> <span class="k">import</span> <span class="n">DisplayDataItem</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">google.cloud.bigtable</span> <span class="k">import</span> <span class="n">Client</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'WriteToBigTable'</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_BigTableWriteFn</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">""" Creates the connector can call and add_row to the batcher using each</span> |
| <span class="sd"> row in beam pipe line</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> project_id(str): GCP Project ID</span> |
| <span class="sd"> instance_id(str): GCP Instance ID</span> |
| <span class="sd"> table_id(str): GCP Table ID</span> |
| |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="p">,</span> <span class="n">instance_id</span><span class="p">,</span> <span class="n">table_id</span><span class="p">):</span> |
| <span class="sd">""" Constructor of the Write connector of Bigtable</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> project_id(str): GCP Project of to write the Rows</span> |
| <span class="sd"> instance_id(str): GCP Instance to write the Rows</span> |
| <span class="sd"> table_id(str): GCP Table to write the `DirectRows`</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_BigTableWriteFn</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'project_id'</span><span class="p">:</span> <span class="n">project_id</span><span class="p">,</span> |
| <span class="s1">'instance_id'</span><span class="p">:</span> <span class="n">instance_id</span><span class="p">,</span> |
| <span class="s1">'table_id'</span><span class="p">:</span> <span class="n">table_id</span><span class="p">}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batcher</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">written</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">counter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="s1">'Written Row'</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">__getstate__</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">beam_options</span> |
| |
| <span class="k">def</span> <span class="nf">__setstate__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">options</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span> <span class="o">=</span> <span class="n">options</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batcher</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">written</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">counter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="s1">'Written Row'</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">start_bundle</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">client</span> <span class="o">=</span> <span class="n">Client</span><span class="p">(</span><span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'project_id'</span><span class="p">])</span> |
| <span class="n">instance</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">instance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'instance_id'</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="n">instance</span><span class="o">.</span><span class="n">table</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'table_id'</span><span class="p">])</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batcher</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="o">.</span><span class="n">mutations_batcher</span><span class="p">()</span> |
| |
| <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">row</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">written</span><span class="o">.</span><span class="n">inc</span><span class="p">()</span> |
| <span class="c1"># You need to set the timestamp in the cells in this row object,</span> |
| <span class="c1"># when we do a retry we will mutating the same object, but, with this</span> |
| <span class="c1"># we are going to set our cell with new values.</span> |
| <span class="c1"># Example:</span> |
| <span class="c1"># direct_row.set_cell('cf1',</span> |
| <span class="c1"># 'field1',</span> |
| <span class="c1"># 'value1',</span> |
| <span class="c1"># timestamp=datetime.datetime.now())</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batcher</span><span class="o">.</span><span class="n">mutate</span><span class="p">(</span><span class="n">row</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">finish_bundle</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">batcher</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">batcher</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{</span><span class="s1">'projectId'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'project_id'</span><span class="p">],</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Bigtable Project Id'</span><span class="p">),</span> |
| <span class="s1">'instanceId'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'instance_id'</span><span class="p">],</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Bigtable Instance Id'</span><span class="p">),</span> |
| <span class="s1">'tableId'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'table_id'</span><span class="p">],</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Bigtable Table Id'</span><span class="p">)</span> |
| <span class="p">}</span> |
| |
| |
| <div class="viewcode-block" id="WriteToBigTable"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigtableio.html#apache_beam.io.gcp.bigtableio.WriteToBigTable">[docs]</a><span class="k">class</span> <span class="nc">WriteToBigTable</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">""" A transform to write to the Bigtable Table.</span> |
| |
| <span class="sd"> A PTransform that write a list of `DirectRow` into the Bigtable Table</span> |
| |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">project_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">instance_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">""" The PTransform to access the Bigtable Write connector</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> project_id(str): GCP Project of to write the Rows</span> |
| <span class="sd"> instance_id(str): GCP Instance to write the Rows</span> |
| <span class="sd"> table_id(str): GCP Table to write the `DirectRows`</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">WriteToBigTable</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'project_id'</span><span class="p">:</span> <span class="n">project_id</span><span class="p">,</span> |
| <span class="s1">'instance_id'</span><span class="p">:</span> <span class="n">instance_id</span><span class="p">,</span> |
| <span class="s1">'table_id'</span><span class="p">:</span> <span class="n">table_id</span><span class="p">}</span> |
| |
| <div class="viewcode-block" id="WriteToBigTable.expand"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigtableio.html#apache_beam.io.gcp.bigtableio.WriteToBigTable.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pvalue</span><span class="p">):</span> |
| <span class="n">beam_options</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">beam_options</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">pvalue</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">_BigTableWriteFn</span><span class="p">(</span><span class="n">beam_options</span><span class="p">[</span><span class="s1">'project_id'</span><span class="p">],</span> |
| <span class="n">beam_options</span><span class="p">[</span><span class="s1">'instance_id'</span><span class="p">],</span> |
| <span class="n">beam_options</span><span class="p">[</span><span class="s1">'table_id'</span><span class="p">])))</span></div></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> |