| |
| |
| <!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.spanner 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.avroio module" href="apache_beam.io.avroio.html" /> |
| <link rel="prev" title="apache_beam.io.gcp.resource_identifiers module" href="apache_beam.io.gcp.resource_identifiers.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.dataframe.html">apache_beam.dataframe 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.azure.html">apache_beam.io.azure 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"><a class="reference internal" href="apache_beam.io.gcp.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4 current"><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>apache_beam.io.gcp.spanner module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.io.gcp.spanner.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.spanner"> |
| <span id="apache-beam-io-gcp-spanner-module"></span><h1>apache_beam.io.gcp.spanner module<a class="headerlink" href="#module-apache_beam.io.gcp.spanner" title="Permalink to this headline">¶</a></h1> |
| <p>PTransforms for supporting Spanner in Python pipelines.</p> |
| <p>These transforms are currently supported by Beam portable |
| Flink and Spark runners.</p> |
| <p><strong>Setup</strong></p> |
| <p>Transforms provided in this module are cross-language transforms |
| implemented in the Beam Java SDK. During the pipeline construction, Python SDK |
| will connect to a Java expansion service to expand these transforms. |
| To facilitate this, a small amount of setup is needed before using these |
| transforms in a Beam Python pipeline.</p> |
| <p>There are several ways to setup cross-language Spanner transforms.</p> |
| <ul class="simple"> |
| <li>Option 1: use the default expansion service</li> |
| <li>Option 2: specify a custom expansion service</li> |
| </ul> |
| <p>See below for details regarding each of these options.</p> |
| <p><em>Option 1: Use the default expansion service</em></p> |
| <p>This is the recommended and easiest setup option for using Python Spanner |
| transforms. This option is only available for Beam 2.26.0 and later.</p> |
| <p>This option requires following pre-requisites before running the Beam |
| pipeline.</p> |
| <ul class="simple"> |
| <li>Install Java runtime in the computer from where the pipeline is constructed |
| and make sure that ‘java’ command is available.</li> |
| </ul> |
| <p>In this option, Python SDK will either download (for released Beam version) or |
| build (when running from a Beam Git clone) a expansion service jar and use |
| that to expand transforms. Currently Spanner transforms use the |
| ‘beam-sdks-java-io-google-cloud-platform-expansion-service’ jar for this |
| purpose.</p> |
| <p><em>Option 2: specify a custom expansion service</em></p> |
| <p>In this option, you startup your own expansion service and provide that as |
| a parameter when using the transforms provided in this module.</p> |
| <p>This option requires following pre-requisites before running the Beam |
| pipeline.</p> |
| <ul class="simple"> |
| <li>Startup your own expansion service.</li> |
| <li>Update your pipeline to provide the expansion service address when |
| initiating Spanner transforms provided in this module.</li> |
| </ul> |
| <p>Flink Users can use the built-in Expansion Service of the Flink Runner’s |
| Job Server. If you start Flink’s Job Server, the expansion service will be |
| started on port 8097. For a different address, please set the |
| expansion_service parameter.</p> |
| <p><strong>More information</strong></p> |
| <p>For more information regarding cross-language transforms see: |
| - <a class="reference external" href="https://beam.apache.org/roadmap/portability/">https://beam.apache.org/roadmap/portability/</a></p> |
| <p>For more information specific to Flink runner see: |
| - <a class="reference external" href="https://beam.apache.org/documentation/runners/flink/">https://beam.apache.org/documentation/runners/flink/</a></p> |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">TimeUnit</code><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#TimeUnit"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/enum.html#enum.Enum" title="(in Python v3.9)"><code class="xref py py-class docutils literal notranslate"><span class="pre">enum.Enum</span></code></a></p> |
| <p>An enumeration.</p> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.NANOSECONDS"> |
| <code class="descname">NANOSECONDS</code><em class="property"> = 1</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.NANOSECONDS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.MICROSECONDS"> |
| <code class="descname">MICROSECONDS</code><em class="property"> = 2</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.MICROSECONDS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.MILLISECONDS"> |
| <code class="descname">MILLISECONDS</code><em class="property"> = 3</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.MILLISECONDS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.SECONDS"> |
| <code class="descname">SECONDS</code><em class="property"> = 4</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.SECONDS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.HOURS"> |
| <code class="descname">HOURS</code><em class="property"> = 5</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.HOURS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimeUnit.DAYS"> |
| <code class="descname">DAYS</code><em class="property"> = 6</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimeUnit.DAYS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">TimestampBoundMode</code><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#TimestampBoundMode"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/enum.html#enum.Enum" title="(in Python v3.9)"><code class="xref py py-class docutils literal notranslate"><span class="pre">enum.Enum</span></code></a></p> |
| <p>An enumeration.</p> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode.MAX_STALENESS"> |
| <code class="descname">MAX_STALENESS</code><em class="property"> = 1</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode.MAX_STALENESS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode.EXACT_STALENESS"> |
| <code class="descname">EXACT_STALENESS</code><em class="property"> = 2</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode.EXACT_STALENESS" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode.READ_TIMESTAMP"> |
| <code class="descname">READ_TIMESTAMP</code><em class="property"> = 3</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode.READ_TIMESTAMP" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode.MIN_READ_TIMESTAMP"> |
| <code class="descname">MIN_READ_TIMESTAMP</code><em class="property"> = 4</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode.MIN_READ_TIMESTAMP" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.TimestampBoundMode.STRONG"> |
| <code class="descname">STRONG</code><em class="property"> = 5</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.TimestampBoundMode.STRONG" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.ReadFromSpanner"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">ReadFromSpanner</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>row_type=None</em>, <em>sql=None</em>, <em>table=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>batching=None</em>, <em>timestamp_bound_mode=None</em>, <em>read_timestamp=None</em>, <em>staleness=None</em>, <em>time_unit=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#ReadFromSpanner"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.ReadFromSpanner" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which reads from the specified Spanner instance’s database.</p> |
| <p>This transform required type of the row it has to return to provide the |
| schema. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleRow</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="n">ReadFromSpanner</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance_id'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'your_database_id'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">row_type</span><span class="o">=</span><span class="n">ExampleRow</span><span class="p">,</span> |
| <span class="n">query</span><span class="o">=</span><span class="s1">'SELECT * FROM some_table'</span><span class="p">,</span> |
| <span class="n">timestamp_bound_mode</span><span class="o">=</span><span class="n">TimestampBoundMode</span><span class="o">.</span><span class="n">MAX_STALENESS</span><span class="p">,</span> |
| <span class="n">staleness</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> |
| <span class="n">time_unit</span><span class="o">=</span><span class="n">TimeUnit</span><span class="o">.</span><span class="n">HOURS</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="n">ExampleRow</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes a read operation from Spanner.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>row_type</strong> – Row type that fits the given query or table. Passed as |
| NamedTuple, e.g. NamedTuple(‘name’, [(‘row_name’, unicode)])</li> |
| <li><strong>sql</strong> – An sql query to execute. It’s results must fit the |
| provided row_type. Don’t use when table is set.</li> |
| <li><strong>table</strong> – A spanner table. When provided all columns from row_type |
| will be selected to query. Don’t use when query is set.</li> |
| <li><strong>batching</strong> – By default Batch API is used to read data from Cloud |
| Spanner. It is useful to disable batching when the underlying query |
| is not root-partitionable.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>timestamp_bound_mode</strong> – Defines how Cloud Spanner will choose a |
| timestamp for a read-only transaction or a single read/query. |
| Passed as TimestampBoundMode enum. Possible values: |
| STRONG: A timestamp bound that will perform reads and queries at a |
| timestamp where all previously committed transactions are visible. |
| READ_TIMESTAMP: Returns a timestamp bound that will perform reads |
| and queries at the given timestamp. |
| MIN_READ_TIMESTAMP: Returns a timestamp bound that will perform reads |
| and queries at a timestamp chosen to be at least given timestamp value. |
| EXACT_STALENESS: Returns a timestamp bound that will perform reads and |
| queries at an exact staleness. The timestamp is chosen soon after the |
| read is started. |
| MAX_STALENESS: Returns a timestamp bound that will perform reads and |
| queries at a timestamp chosen to be at most time_unit stale.</li> |
| <li><strong>read_timestamp</strong> – Timestamp in string. Use only when |
| timestamp_bound_mode is set to READ_TIMESTAMP or MIN_READ_TIMESTAMP.</li> |
| <li><strong>staleness</strong> – Staleness value as int. Use only when |
| timestamp_bound_mode is set to EXACT_STALENESS or MAX_STALENESS. |
| time_unit has to be set along with this param.</li> |
| <li><strong>time_unit</strong> – Time unit for staleness_value passed as TimeUnit enum. |
| Possible values: NANOSECONDS, MICROSECONDS, MILLISECONDS, SECONDS, |
| HOURS, DAYS.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.ReadFromSpanner.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:read:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.ReadFromSpanner.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerDelete"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">SpannerDelete</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>table</em>, <em>max_batch_size_bytes=None</em>, <em>max_number_mutations=None</em>, <em>max_number_rows=None</em>, <em>grouping_factor=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>commit_deadline=None</em>, <em>max_cumulative_backoff=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#SpannerDelete"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerDelete" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which writes delete mutations to the specified Spanner |
| table.</p> |
| <p>This transform receives rows defined as NamedTuple. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleKey</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleKey</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="s1">'Impulse'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Impulse</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'Generate'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_rows</span><span class="p">))</span> |
| <span class="o">|</span> <span class="s1">'To row'</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="k">lambda</span> <span class="n">n</span><span class="p">:</span> <span class="n">ExampleKey</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">ExampleKey</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'Write to Spanner'</span> <span class="o">>></span> <span class="n">SpannerDelete</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'existing_database'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'your_table'</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes a delete operation to a Spanner table.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>table</strong> – Specifies the Cloud Spanner table.</li> |
| <li><strong>max_batch_size_bytes</strong> – Specifies the batch size limit (max number of |
| bytes mutated per batch). Default value is 1048576 bytes = 1MB.</li> |
| <li><strong>max_number_mutations</strong> – Specifies the cell mutation limit (maximum |
| number of mutated cells per batch). Default value is 5000.</li> |
| <li><strong>max_number_rows</strong> – Specifies the row mutation limit (maximum number of |
| mutated rows per batch). Default value is 500.</li> |
| <li><strong>grouping_factor</strong> – Specifies the multiple of max mutation (in terms |
| of both bytes per batch and cells per batch) that is used to select a |
| set of mutations to sort by key for batching. This sort uses local |
| memory on the workers, so using large values can cause out of memory |
| errors. Default value is 1000.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>commit_deadline</strong> – Specifies the deadline for the Commit API call. |
| Default is 15 secs. DEADLINE_EXCEEDED errors will prompt a backoff/retry |
| until the value of commit_deadline is reached. DEADLINE_EXCEEDED errors |
| are ar reported with logging and counters. Pass seconds as value.</li> |
| <li><strong>max_cumulative_backoff</strong> – Specifies the maximum cumulative backoff |
| time when retrying after DEADLINE_EXCEEDED errors. Default is 900s |
| (15min). If the mutations still have not been written after this time, |
| they are treated as a failure, and handled according to the setting of |
| failure_mode. Pass seconds as value.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerDelete.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:delete:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerDelete.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerInsert"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">SpannerInsert</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>table</em>, <em>max_batch_size_bytes=None</em>, <em>max_number_mutations=None</em>, <em>max_number_rows=None</em>, <em>grouping_factor=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>commit_deadline=None</em>, <em>max_cumulative_backoff=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#SpannerInsert"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerInsert" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which writes insert mutations to the specified Spanner |
| table.</p> |
| <p>This transform receives rows defined as NamedTuple. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleRow</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="s1">'Impulse'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Impulse</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'Generate'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_rows</span><span class="p">))</span> |
| <span class="o">|</span> <span class="s1">'To row'</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="k">lambda</span> <span class="n">n</span><span class="p">:</span> <span class="n">ExampleRow</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'Write to Spanner'</span> <span class="o">>></span> <span class="n">SpannerInsert</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'existing_database'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'your_table'</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes an insert operation to a Spanner table.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>table</strong> – Specifies the Cloud Spanner table.</li> |
| <li><strong>max_batch_size_bytes</strong> – Specifies the batch size limit (max number of |
| bytes mutated per batch). Default value is 1048576 bytes = 1MB.</li> |
| <li><strong>max_number_mutations</strong> – Specifies the cell mutation limit (maximum |
| number of mutated cells per batch). Default value is 5000.</li> |
| <li><strong>max_number_rows</strong> – Specifies the row mutation limit (maximum number of |
| mutated rows per batch). Default value is 500.</li> |
| <li><strong>grouping_factor</strong> – Specifies the multiple of max mutation (in terms |
| of both bytes per batch and cells per batch) that is used to select a |
| set of mutations to sort by key for batching. This sort uses local |
| memory on the workers, so using large values can cause out of memory |
| errors. Default value is 1000.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>commit_deadline</strong> – Specifies the deadline for the Commit API call. |
| Default is 15 secs. DEADLINE_EXCEEDED errors will prompt a backoff/retry |
| until the value of commit_deadline is reached. DEADLINE_EXCEEDED errors |
| are ar reported with logging and counters. Pass seconds as value.</li> |
| <li><strong>max_cumulative_backoff</strong> – Specifies the maximum cumulative backoff |
| time when retrying after DEADLINE_EXCEEDED errors. Default is 900s |
| (15min). If the mutations still have not been written after this time, |
| they are treated as a failure, and handled according to the setting of |
| failure_mode. Pass seconds as value.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerInsert.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:insert:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerInsert.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerReplace"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">SpannerReplace</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>table</em>, <em>max_batch_size_bytes=None</em>, <em>max_number_mutations=None</em>, <em>max_number_rows=None</em>, <em>grouping_factor=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>commit_deadline=None</em>, <em>max_cumulative_backoff=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#SpannerReplace"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerReplace" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which writes replace mutations to the specified Spanner |
| table.</p> |
| <p>This transform receives rows defined as NamedTuple. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleRow</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="s1">'Impulse'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Impulse</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'Generate'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_rows</span><span class="p">))</span> |
| <span class="o">|</span> <span class="s1">'To row'</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="k">lambda</span> <span class="n">n</span><span class="p">:</span> <span class="n">ExampleRow</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'Write to Spanner'</span> <span class="o">>></span> <span class="n">SpannerReplace</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'existing_database'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'your_table'</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes a replace operation to a Spanner table.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>table</strong> – Specifies the Cloud Spanner table.</li> |
| <li><strong>max_batch_size_bytes</strong> – Specifies the batch size limit (max number of |
| bytes mutated per batch). Default value is 1048576 bytes = 1MB.</li> |
| <li><strong>max_number_mutations</strong> – Specifies the cell mutation limit (maximum |
| number of mutated cells per batch). Default value is 5000.</li> |
| <li><strong>max_number_rows</strong> – Specifies the row mutation limit (maximum number of |
| mutated rows per batch). Default value is 500.</li> |
| <li><strong>grouping_factor</strong> – Specifies the multiple of max mutation (in terms |
| of both bytes per batch and cells per batch) that is used to select a |
| set of mutations to sort by key for batching. This sort uses local |
| memory on the workers, so using large values can cause out of memory |
| errors. Default value is 1000.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>commit_deadline</strong> – Specifies the deadline for the Commit API call. |
| Default is 15 secs. DEADLINE_EXCEEDED errors will prompt a backoff/retry |
| until the value of commit_deadline is reached. DEADLINE_EXCEEDED errors |
| are ar reported with logging and counters. Pass seconds as value.</li> |
| <li><strong>max_cumulative_backoff</strong> – Specifies the maximum cumulative backoff |
| time when retrying after DEADLINE_EXCEEDED errors. Default is 900s |
| (15min). If the mutations still have not been written after this time, |
| they are treated as a failure, and handled according to the setting of |
| failure_mode. Pass seconds as value.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerReplace.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:replace:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerReplace.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerInsertOrUpdate"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">SpannerInsertOrUpdate</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>table</em>, <em>max_batch_size_bytes=None</em>, <em>max_number_mutations=None</em>, <em>max_number_rows=None</em>, <em>grouping_factor=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>commit_deadline=None</em>, <em>max_cumulative_backoff=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#SpannerInsertOrUpdate"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerInsertOrUpdate" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which writes insert-or-update mutations to the specified Spanner |
| table.</p> |
| <p>This transform receives rows defined as NamedTuple. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleRow</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="s1">'Impulse'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Impulse</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'Generate'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_rows</span><span class="p">))</span> |
| <span class="o">|</span> <span class="s1">'To row'</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="k">lambda</span> <span class="n">n</span><span class="p">:</span> <span class="n">ExampleRow</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'Write to Spanner'</span> <span class="o">>></span> <span class="n">SpannerInsertOrUpdate</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'existing_database'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'your_table'</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes an insert-or-update operation to a Spanner table.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>table</strong> – Specifies the Cloud Spanner table.</li> |
| <li><strong>max_batch_size_bytes</strong> – Specifies the batch size limit (max number of |
| bytes mutated per batch). Default value is 1048576 bytes = 1MB.</li> |
| <li><strong>max_number_mutations</strong> – Specifies the cell mutation limit (maximum |
| number of mutated cells per batch). Default value is 5000.</li> |
| <li><strong>max_number_rows</strong> – Specifies the row mutation limit (maximum number of |
| mutated rows per batch). Default value is 500.</li> |
| <li><strong>grouping_factor</strong> – Specifies the multiple of max mutation (in terms |
| of both bytes per batch and cells per batch) that is used to select a |
| set of mutations to sort by key for batching. This sort uses local |
| memory on the workers, so using large values can cause out of memory |
| errors. Default value is 1000.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>commit_deadline</strong> – Specifies the deadline for the Commit API call. |
| Default is 15 secs. DEADLINE_EXCEEDED errors will prompt a backoff/retry |
| until the value of commit_deadline is reached. DEADLINE_EXCEEDED errors |
| are ar reported with logging and counters. Pass seconds as value.</li> |
| <li><strong>max_cumulative_backoff</strong> – Specifies the maximum cumulative backoff |
| time when retrying after DEADLINE_EXCEEDED errors. Default is 900s |
| (15min). If the mutations still have not been written after this time, |
| they are treated as a failure, and handled according to the setting of |
| failure_mode. Pass seconds as value.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerInsertOrUpdate.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:insert_or_update:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerInsertOrUpdate.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerUpdate"> |
| <em class="property">class </em><code class="descclassname">apache_beam.io.gcp.spanner.</code><code class="descname">SpannerUpdate</code><span class="sig-paren">(</span><em>project_id</em>, <em>instance_id</em>, <em>database_id</em>, <em>table</em>, <em>max_batch_size_bytes=None</em>, <em>max_number_mutations=None</em>, <em>max_number_rows=None</em>, <em>grouping_factor=None</em>, <em>host=None</em>, <em>emulator_host=None</em>, <em>commit_deadline=None</em>, <em>max_cumulative_backoff=None</em>, <em>expansion_service=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/gcp/spanner.html#SpannerUpdate"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerUpdate" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform" title="apache_beam.transforms.external.ExternalTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.external.ExternalTransform</span></code></a></p> |
| <p>A PTransform which writes update mutations to the specified Spanner |
| table.</p> |
| <p>This transform receives rows defined as NamedTuple. Example:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">NamedTuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">coders</span> |
| |
| <span class="k">class</span> <span class="nc">ExampleRow</span><span class="p">(</span><span class="n">NamedTuple</span><span class="p">):</span> |
| <span class="nb">id</span><span class="p">:</span> <span class="nb">int</span> |
| <span class="n">name</span><span class="p">:</span> <span class="n">unicode</span> |
| |
| <span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">,</span> <span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">Pipeline</span><span class="p">()</span> <span class="k">as</span> <span class="n">p</span><span class="p">:</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">p</span> |
| <span class="o">|</span> <span class="s1">'Impulse'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">Impulse</span><span class="p">()</span> |
| <span class="o">|</span> <span class="s1">'Generate'</span> <span class="o">>></span> <span class="n">beam</span><span class="o">.</span><span class="n">FlatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_rows</span><span class="p">))</span> |
| <span class="o">|</span> <span class="s1">'To row'</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="k">lambda</span> <span class="n">n</span><span class="p">:</span> <span class="n">ExampleRow</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">ExampleRow</span><span class="p">)</span> |
| <span class="o">|</span> <span class="s1">'Write to Spanner'</span> <span class="o">>></span> <span class="n">SpannerUpdate</span><span class="p">(</span> |
| <span class="n">instance_id</span><span class="o">=</span><span class="s1">'your_instance'</span><span class="p">,</span> |
| <span class="n">database_id</span><span class="o">=</span><span class="s1">'existing_database'</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="s1">'your_project_id'</span><span class="p">,</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'your_table'</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p>Experimental; no backwards compatibility guarantees.</p> |
| <p>Initializes an update operation to a Spanner table.</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>project_id</strong> – Specifies the Cloud Spanner project.</li> |
| <li><strong>instance_id</strong> – Specifies the Cloud Spanner instance.</li> |
| <li><strong>database_id</strong> – Specifies the Cloud Spanner database.</li> |
| <li><strong>table</strong> – Specifies the Cloud Spanner table.</li> |
| <li><strong>max_batch_size_bytes</strong> – Specifies the batch size limit (max number of |
| bytes mutated per batch). Default value is 1048576 bytes = 1MB.</li> |
| <li><strong>max_number_mutations</strong> – Specifies the cell mutation limit (maximum |
| number of mutated cells per batch). Default value is 5000.</li> |
| <li><strong>max_number_rows</strong> – Specifies the row mutation limit (maximum number of |
| mutated rows per batch). Default value is 500.</li> |
| <li><strong>grouping_factor</strong> – Specifies the multiple of max mutation (in terms |
| of both bytes per batch and cells per batch) that is used to select a |
| set of mutations to sort by key for batching. This sort uses local |
| memory on the workers, so using large values can cause out of memory |
| errors. Default value is 1000.</li> |
| <li><strong>host</strong> – Specifies the Cloud Spanner host.</li> |
| <li><strong>emulator_host</strong> – Specifies Spanner emulator host.</li> |
| <li><strong>commit_deadline</strong> – Specifies the deadline for the Commit API call. |
| Default is 15 secs. DEADLINE_EXCEEDED errors will prompt a backoff/retry |
| until the value of commit_deadline is reached. DEADLINE_EXCEEDED errors |
| are ar reported with logging and counters. Pass seconds as value.</li> |
| <li><strong>max_cumulative_backoff</strong> – Specifies the maximum cumulative backoff |
| time when retrying after DEADLINE_EXCEEDED errors. Default is 900s |
| (15min). If the mutations still have not been written after this time, |
| they are treated as a failure, and handled according to the setting of |
| failure_mode. Pass seconds as value.</li> |
| <li><strong>expansion_service</strong> – The address (host:port) of the ExpansionService.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="attribute"> |
| <dt id="apache_beam.io.gcp.spanner.SpannerUpdate.URN"> |
| <code class="descname">URN</code><em class="property"> = 'beam:external:java:spanner:update:v1'</em><a class="headerlink" href="#apache_beam.io.gcp.spanner.SpannerUpdate.URN" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="apache_beam.io.avroio.html" class="btn btn-neutral float-right" title="apache_beam.io.avroio module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.io.gcp.resource_identifiers.html" class="btn btn-neutral float-left" title="apache_beam.io.gcp.resource_identifiers 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> |