| |
| |
| <!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.datastore.v1new.datastoreio module — Apache Beam 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 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" /> |
| <link rel="next" title="apache_beam.io.gcp.datastore.v1new.helper module" href="apache_beam.io.gcp.datastore.v1new.helper.html" /> |
| <link rel="prev" title="apache_beam.io.gcp.datastore.v1new.datastore_write_it_pipeline module" href="apache_beam.io.gcp.datastore.v1new.datastore_write_it_pipeline.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" /> |
| <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 class="current"> |
| <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 current"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.io.html#subpackages">Subpackages</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.aws.html">apache_beam.io.aws package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.external.html">apache_beam.io.external package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.flink.html">apache_beam.io.flink package</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="apache_beam.io.gcp.html">apache_beam.io.gcp package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.io.gcp.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="apache_beam.io.gcp.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="apache_beam.io.html#submodules">Submodules</a></li> |
| </ul> |
| </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.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" 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="apache_beam.io.html">apache_beam.io package</a> »</li> |
| |
| <li><a href="apache_beam.io.gcp.html">apache_beam.io.gcp package</a> »</li> |
| |
| <li><a href="apache_beam.io.gcp.datastore.html">apache_beam.io.gcp.datastore package</a> »</li> |
| |
| <li><a href="apache_beam.io.gcp.datastore.v1new.html">apache_beam.io.gcp.datastore.v1new package</a> »</li> |
| |
| <li>apache_beam.io.gcp.datastore.v1new.datastoreio module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.io.gcp.datastore.v1new.datastoreio.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="module-apache_beam.io.gcp.datastore.v1new.datastoreio"> |
| <span id="apache-beam-io-gcp-datastore-v1new-datastoreio-module"></span><h1>apache_beam.io.gcp.datastore.v1new.datastoreio module<a class="headerlink" href="#module-apache_beam.io.gcp.datastore.v1new.datastoreio" title="Permalink to this headline">¶</a></h1> |
| <p>A connector for reading from and writing to Google Cloud Datastore.</p> |
| <p>Please use this module for Datastore I/O since |
| <code class="docutils literal notranslate"><span class="pre">apache_beam.io.gcp.datastore.v1.datastoreio</span></code> will be deprecated in the |
| next Beam major release.</p> |
| <p>This module uses the newer google-cloud-datastore package. Its API was different |
| enough to require extensive changes to this and associated modules.</p> |
| <p>This module is experimental, no backwards compatibility guarantees.</p> |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.datastore.v1new.datastoreio.</code><code class="descname">ReadFromDatastore</code><span class="sig-paren">(</span><em>query</em>, <em>num_splits=0</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/datastore/v1new/datastoreio.html#ReadFromDatastore"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.ptransform.html#apache_beam.transforms.ptransform.PTransform" title="apache_beam.transforms.ptransform.PTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.ptransform.PTransform</span></code></a></p> |
| <p>A <code class="docutils literal notranslate"><span class="pre">PTransform</span></code> for querying Google Cloud Datastore.</p> |
| <p>To read a <code class="docutils literal notranslate"><span class="pre">PCollection[Entity]</span></code> from a Cloud Datastore <code class="docutils literal notranslate"><span class="pre">Query</span></code>, use |
| the <code class="docutils literal notranslate"><span class="pre">ReadFromDatastore</span></code> transform by providing a <cite>query</cite> to |
| read from. The project and optional namespace are set in the query. |
| The query will be split into multiple queries to allow for parallelism. The |
| degree of parallelism is automatically determined, but can be overridden by |
| setting <cite>num_splits</cite> to a value of 1 or greater.</p> |
| <p>Note: Normally, a runner will read from Cloud Datastore in parallel across |
| many workers. However, when the <cite>query</cite> is configured with a <cite>limit</cite> or if the |
| query contains inequality filters like <cite>GREATER_THAN, LESS_THAN</cite> etc., then |
| all the returned results will be read by a single worker in order to ensure |
| correct data. Since data is read from a single worker, this could have |
| significant impact on the performance of the job. Using a |
| <a class="reference internal" href="apache_beam.transforms.util.html#apache_beam.transforms.util.Reshuffle" title="apache_beam.transforms.util.Reshuffle"><code class="xref py py-class docutils literal notranslate"><span class="pre">Reshuffle</span></code></a> transform after the read in |
| this case might be beneficial for parallelizing work across workers.</p> |
| <dl class="docutils"> |
| <dt>The semantics for query splitting is defined below:</dt> |
| <dd><p class="first">1. If <cite>num_splits</cite> is equal to 0, then the number of splits will be chosen |
| dynamically at runtime based on the query data size.</p> |
| <p>2. Any value of <cite>num_splits</cite> greater than |
| <cite>ReadFromDatastore._NUM_QUERY_SPLITS_MAX</cite> will be capped at that value.</p> |
| <p>3. If the <cite>query</cite> has a user limit set, or contains inequality filters, then |
| <cite>num_splits</cite> will be ignored and no split will be performed.</p> |
| <p class="last">4. Under certain cases Cloud Datastore is unable to split query to the |
| requested number of splits. In such cases we just use whatever Cloud |
| Datastore returns.</p> |
| </dd> |
| </dl> |
| <p>See <a class="reference external" href="https://developers.google.com/datastore/">https://developers.google.com/datastore/</a> for more details on Google Cloud |
| Datastore.</p> |
| <p>Initialize the <cite>ReadFromDatastore</cite> transform.</p> |
| <p>This transform outputs elements of type |
| <a class="reference internal" href="apache_beam.io.gcp.datastore.v1new.types.html#apache_beam.io.gcp.datastore.v1new.types.Entity" title="apache_beam.io.gcp.datastore.v1new.types.Entity"><code class="xref py py-class docutils literal notranslate"><span class="pre">Entity</span></code></a>.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>query</strong> – (<a class="reference internal" href="apache_beam.io.gcp.datastore.v1new.types.html#apache_beam.io.gcp.datastore.v1new.types.Query" title="apache_beam.io.gcp.datastore.v1new.types.Query"><code class="xref py py-class docutils literal notranslate"><span class="pre">Query</span></code></a>) query |
| used to fetch entities.</li> |
| <li><strong>num_splits</strong> – (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">int</span></code></a>) (optional) Number of splits for the query.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore.expand"> |
| <code class="descname">expand</code><span class="sig-paren">(</span><em>pcoll</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/datastore/v1new/datastoreio.html#ReadFromDatastore.expand"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore.expand" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore.display_data"> |
| <code class="descname">display_data</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/datastore/v1new/datastoreio.html#ReadFromDatastore.display_data"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.datastore.v1new.datastoreio.ReadFromDatastore.display_data" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.datastore.v1new.datastoreio.WriteToDatastore"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.datastore.v1new.datastoreio.</code><code class="descname">WriteToDatastore</code><span class="sig-paren">(</span><em>project</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/datastore/v1new/datastoreio.html#WriteToDatastore"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.datastore.v1new.datastoreio.WriteToDatastore" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.io.gcp.datastore.v1new.datastoreio._Mutate</span></code></p> |
| <p>Writes elements of type |
| <a class="reference internal" href="apache_beam.io.gcp.datastore.v1new.types.html#apache_beam.io.gcp.datastore.v1new.types.Entity" title="apache_beam.io.gcp.datastore.v1new.types.Entity"><code class="xref py py-class docutils literal notranslate"><span class="pre">Entity</span></code></a> to Cloud Datastore.</p> |
| <p>Entity keys must be complete. The <code class="docutils literal notranslate"><span class="pre">project</span></code> field in each key must match the |
| project ID passed to this transform. If <code class="docutils literal notranslate"><span class="pre">project</span></code> field in entity or |
| property key is empty then it is filled with the project ID passed to this |
| transform.</p> |
| <p>Initialize the <cite>WriteToDatastore</cite> transform.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>project</strong> – (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>) The ID of the project to write entities to.</td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.datastore.v1new.datastoreio.DeleteFromDatastore"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.datastore.v1new.datastoreio.</code><code class="descname">DeleteFromDatastore</code><span class="sig-paren">(</span><em>project</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/datastore/v1new/datastoreio.html#DeleteFromDatastore"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.datastore.v1new.datastoreio.DeleteFromDatastore" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.io.gcp.datastore.v1new.datastoreio._Mutate</span></code></p> |
| <p>Deletes elements matching input |
| <a class="reference internal" href="apache_beam.io.gcp.datastore.v1new.types.html#apache_beam.io.gcp.datastore.v1new.types.Key" title="apache_beam.io.gcp.datastore.v1new.types.Key"><code class="xref py py-class docutils literal notranslate"><span class="pre">Key</span></code></a> elements from Cloud |
| Datastore.</p> |
| <p>Keys must be complete. The <code class="docutils literal notranslate"><span class="pre">project</span></code> field in each key must match the |
| project ID passed to this transform. If <code class="docutils literal notranslate"><span class="pre">project</span></code> field in key is empty then |
| it is filled with the project ID passed to this transform.</p> |
| <p>Initialize the <cite>DeleteFromDatastore</cite> transform.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>project</strong> – (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>) The ID of the project from which the entities will |
| be deleted.</td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="apache_beam.io.gcp.datastore.v1new.helper.html" class="btn btn-neutral float-right" title="apache_beam.io.gcp.datastore.v1new.helper module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.io.gcp.datastore.v1new.datastore_write_it_pipeline.html" class="btn btn-neutral float-left" title="apache_beam.io.gcp.datastore.v1new.datastore_write_it_pipeline module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <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> |