Google Git
Sign in
apache / beam-site / refs/heads/updates_release_2.8.0 / . / pydoc / 2.8.0 / _modules / apache_beam / io / gcp / datastore / v1 / datastoreio.html
blob: 7d51c70ae40e537209c7f5d66198ff45a667eeea [file] [log] [blame]
<!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.v1.datastoreio &mdash; 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> &raquo;</li>
<li><a href="../../../../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.io.gcp.datastore.v1.datastoreio</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.datastore.v1.datastoreio</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">&quot;&quot;&quot;A connector for reading from and writing to Google Cloud Datastore&quot;&quot;&quot;</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">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">round</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1</span> <span class="k">import</span> <span class="n">helper</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1</span> <span class="k">import</span> <span class="n">query_splitter</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1</span> <span class="k">import</span> <span class="n">util</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1.adaptive_throttler</span> <span class="k">import</span> <span class="n">AdaptiveThrottler</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics.metric</span> <span class="k">import</span> <span class="n">Metrics</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">Create</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">DoFn</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">FlatMap</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">GroupByKey</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">Map</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">ParDo</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">PTransform</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.util</span> <span class="k">import</span> <span class="n">Values</span>
<span class="c1"># Protect against environments where datastore library is not available.</span>
<span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">google.cloud.proto.datastore.v1</span> <span class="k">import</span> <span class="n">datastore_pb2</span>
<span class="kn">from</span> <span class="nn">googledatastore</span> <span class="k">import</span> <span class="n">helper</span> <span class="k">as</span> <span class="n">datastore_helper</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="c1"># pylint: enable=wrong-import-order, wrong-import-position</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;ReadFromDatastore&#39;</span><span class="p">,</span> <span class="s1">&#39;WriteToDatastore&#39;</span><span class="p">,</span> <span class="s1">&#39;DeleteFromDatastore&#39;</span><span class="p">]</span>
<div class="viewcode-block" id="ReadFromDatastore"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore">[docs]</a><span class="k">class</span> <span class="nc">ReadFromDatastore</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``PTransform`` for reading from Google Cloud Datastore.</span>
<span class="sd"> To read a ``PCollection[Entity]`` from a Cloud Datastore ``Query``, use</span>
<span class="sd"> ``ReadFromDatastore`` transform by providing a `project` id and a `query` to</span>
<span class="sd"> read from. You can optionally provide a `namespace` and/or specify how many</span>
<span class="sd"> splits you want for the query through `num_splits` option.</span>
<span class="sd"> Note: Normally, a runner will read from Cloud Datastore in parallel across</span>
<span class="sd"> many workers. However, when the `query` is configured with a `limit` or if the</span>
<span class="sd"> query contains inequality filters like `GREATER_THAN, LESS_THAN` etc., then</span>
<span class="sd"> all the returned results will be read by a single worker in order to ensure</span>
<span class="sd"> correct data. Since data is read from a single worker, this could have</span>
<span class="sd"> significant impact on the performance of the job.</span>
<span class="sd"> The semantics for the query splitting is defined below:</span>
<span class="sd"> 1. If `num_splits` is equal to 0, then the number of splits will be chosen</span>
<span class="sd"> dynamically at runtime based on the query data size.</span>
<span class="sd"> 2. Any value of `num_splits` greater than</span>
<span class="sd"> `ReadFromDatastore._NUM_QUERY_SPLITS_MAX` will be capped at that value.</span>
<span class="sd"> 3. If the `query` has a user limit set, or contains inequality filters, then</span>
<span class="sd"> `num_splits` will be ignored and no split will be performed.</span>
<span class="sd"> 4. Under certain cases Cloud Datastore is unable to split query to the</span>
<span class="sd"> requested number of splits. In such cases we just use whatever the Cloud</span>
<span class="sd"> Datastore returns.</span>
<span class="sd"> See https://developers.google.com/datastore/ for more details on Google Cloud</span>
<span class="sd"> Datastore.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># An upper bound on the number of splits for a query.</span>
<span class="n">_NUM_QUERY_SPLITS_MAX</span> <span class="o">=</span> <span class="mi">50000</span>
<span class="c1"># A lower bound on the number of splits for a query. This is to ensure that</span>
<span class="c1"># we parellelize the query even when Datastore statistics are not available.</span>
<span class="n">_NUM_QUERY_SPLITS_MIN</span> <span class="o">=</span> <span class="mi">12</span>
<span class="c1"># Default bundle size of 64MB.</span>
<span class="n">_DEFAULT_BUNDLE_SIZE_BYTES</span> <span class="o">=</span> <span class="mi">64</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</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</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">namespace</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_splits</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the `ReadFromDatastore` transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> project: The ID of the project to read from.</span>
<span class="sd"> query: Cloud Datastore query to be read from.</span>
<span class="sd"> namespace: An optional namespace.</span>
<span class="sd"> num_splits: Number of splits for the query.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Import here to avoid adding the dependency for local running scenarios.</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span>
<span class="kn">from</span> <span class="nn">apitools.base</span> <span class="k">import</span> <span class="n">py</span> <span class="c1"># pylint: disable=unused-variable</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span>
<span class="s1">&#39;Google Cloud IO not available, &#39;</span>
<span class="s1">&#39;please install apache_beam[gcp]&#39;</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;datastoreio read transform is experimental.&#39;</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ReadFromDatastore</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="k">if</span> <span class="ow">not</span> <span class="n">project</span><span class="p">:</span>
<span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Project cannot be empty&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">query</span><span class="p">:</span>
<span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Query cannot be empty&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">num_splits</span> <span class="o">&lt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;num_splits must be greater than or equal 0&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span> <span class="o">=</span> <span class="n">project</span>
<span class="c1"># using _namespace conflicts with DisplayData._namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_query</span> <span class="o">=</span> <span class="n">query</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span> <span class="o">=</span> <span class="n">num_splits</span>
<div class="viewcode-block" id="ReadFromDatastore.expand"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.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">pcoll</span><span class="p">):</span>
<span class="c1"># This is a composite transform involves the following:</span>
<span class="c1"># 1. Create a singleton of the user provided `query` and apply a ``ParDo``</span>
<span class="c1"># that splits the query into `num_splits` and assign each split query a</span>
<span class="c1"># unique `int` as the key. The resulting output is of the type</span>
<span class="c1"># ``PCollection[(int, Query)]``.</span>
<span class="c1">#</span>
<span class="c1"># If the value of `num_splits` is less than or equal to 0, then the</span>
<span class="c1"># number of splits will be computed dynamically based on the size of the</span>
<span class="c1"># data for the `query`.</span>
<span class="c1">#</span>
<span class="c1"># 2. The resulting ``PCollection`` is sharded using a ``GroupByKey``</span>
<span class="c1"># operation. The queries are extracted from the (int, Iterable[Query]) and</span>
<span class="c1"># flattened to output a ``PCollection[Query]``.</span>
<span class="c1">#</span>
<span class="c1"># 3. In the third step, a ``ParDo`` reads entities for each query and</span>
<span class="c1"># outputs a ``PCollection[Entity]``.</span>
<span class="n">queries</span> <span class="o">=</span> <span class="p">(</span><span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span>
<span class="o">|</span> <span class="s1">&#39;UserQuery&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">Create</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="p">])</span>
<span class="o">|</span> <span class="s1">&#39;SplitQuery&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">ParDo</span><span class="p">(</span><span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">SplitQueryFn</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span><span class="p">)))</span>
<span class="n">sharded_queries</span> <span class="o">=</span> <span class="p">(</span><span class="n">queries</span>
<span class="o">|</span> <span class="n">GroupByKey</span><span class="p">()</span>
<span class="o">|</span> <span class="n">Values</span><span class="p">()</span>
<span class="o">|</span> <span class="s1">&#39;Flatten&#39;</span> <span class="o">&gt;&gt;</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="n">x</span><span class="p">))</span>
<span class="n">entities</span> <span class="o">=</span> <span class="n">sharded_queries</span> <span class="o">|</span> <span class="s1">&#39;Read&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">ParDo</span><span class="p">(</span>
<span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">ReadFn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span><span class="p">))</span>
<span class="k">return</span> <span class="n">entities</span></div>
<div class="viewcode-block" id="ReadFromDatastore.display_data"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.display_data">[docs]</a> <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="n">disp_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;project&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span>
<span class="s1">&#39;query&#39;</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="p">),</span>
<span class="s1">&#39;num_splits&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span><span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">disp_data</span><span class="p">[</span><span class="s1">&#39;namespace&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span>
<span class="k">return</span> <span class="n">disp_data</span></div>
<div class="viewcode-block" id="ReadFromDatastore.SplitQueryFn"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.SplitQueryFn">[docs]</a> <span class="k">class</span> <span class="nc">SplitQueryFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A `DoFn` that splits a given query into multiple sub-queries.&quot;&quot;&quot;</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</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">SplitQueryFn</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">_datastore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span> <span class="o">=</span> <span class="n">project</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_query</span> <span class="o">=</span> <span class="n">query</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span> <span class="o">=</span> <span class="n">num_splits</span>
<div class="viewcode-block" id="ReadFromDatastore.SplitQueryFn.start_bundle"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.SplitQueryFn.start_bundle">[docs]</a> <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="bp">self</span><span class="o">.</span><span class="n">_datastore</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">get_datastore</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">)</span></div>
<div class="viewcode-block" id="ReadFromDatastore.SplitQueryFn.process"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.SplitQueryFn.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="c1"># distinct key to be used to group query splits.</span>
<span class="n">key</span> <span class="o">=</span> <span class="mi">1</span>
<span class="c1"># If query has a user set limit, then the query cannot be split.</span>
<span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;limit&#39;</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[(</span><span class="n">key</span><span class="p">,</span> <span class="n">query</span><span class="p">)]</span>
<span class="c1"># Compute the estimated numSplits if not specified by the user.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">estimated_num_splits</span> <span class="o">=</span> <span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">get_estimated_num_splits</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">estimated_num_splits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Splitting the query into </span><span class="si">%d</span><span class="s2"> splits&quot;</span><span class="p">,</span> <span class="n">estimated_num_splits</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">query_splits</span> <span class="o">=</span> <span class="n">query_splitter</span><span class="o">.</span><span class="n">get_splits</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">estimated_num_splits</span><span class="p">,</span>
<span class="n">helper</span><span class="o">.</span><span class="n">make_partition</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span><span class="p">))</span>
<span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">&quot;Unable to parallelize the given query: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span>
<span class="n">exc_info</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">query_splits</span> <span class="o">=</span> <span class="p">[</span><span class="n">query</span><span class="p">]</span>
<span class="n">sharded_query_splits</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">split_query</span> <span class="ow">in</span> <span class="n">query_splits</span><span class="p">:</span>
<span class="n">sharded_query_splits</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">key</span><span class="p">,</span> <span class="n">split_query</span><span class="p">))</span>
<span class="n">key</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">sharded_query_splits</span></div>
<div class="viewcode-block" id="ReadFromDatastore.SplitQueryFn.display_data"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.SplitQueryFn.display_data">[docs]</a> <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="n">disp_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;project&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span>
<span class="s1">&#39;query&#39;</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="p">),</span>
<span class="s1">&#39;num_splits&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_splits</span><span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">disp_data</span><span class="p">[</span><span class="s1">&#39;namespace&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span>
<span class="k">return</span> <span class="n">disp_data</span></div></div>
<div class="viewcode-block" id="ReadFromDatastore.ReadFn"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.ReadFn">[docs]</a> <span class="k">class</span> <span class="nc">ReadFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A DoFn that reads entities from Cloud Datastore, for a given query.&quot;&quot;&quot;</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</span><span class="p">,</span> <span class="n">namespace</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">ReadFn</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">_project</span> <span class="o">=</span> <span class="n">project</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="ReadFromDatastore.ReadFn.start_bundle"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.ReadFn.start_bundle">[docs]</a> <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="bp">self</span><span class="o">.</span><span class="n">_datastore</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">get_datastore</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">)</span></div>
<div class="viewcode-block" id="ReadFromDatastore.ReadFn.process"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.ReadFn.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="c1"># Returns an iterator of entities that reads in batches.</span>
<span class="n">entities</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">fetch_entities</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span><span class="p">,</span>
<span class="n">query</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span><span class="p">)</span>
<span class="k">return</span> <span class="n">entities</span></div>
<div class="viewcode-block" id="ReadFromDatastore.ReadFn.display_data"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.ReadFn.display_data">[docs]</a> <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="n">disp_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;project&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">disp_data</span><span class="p">[</span><span class="s1">&#39;namespace&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_datastore_namespace</span>
<span class="k">return</span> <span class="n">disp_data</span></div></div>
<div class="viewcode-block" id="ReadFromDatastore.query_latest_statistics_timestamp"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.query_latest_statistics_timestamp">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">query_latest_statistics_timestamp</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">datastore</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Fetches the latest timestamp of statistics from Cloud Datastore.</span>
<span class="sd"> Cloud Datastore system tables with statistics are periodically updated.</span>
<span class="sd"> This method fethes the latest timestamp (in microseconds) of statistics</span>
<span class="sd"> update using the `__Stat_Total__` table.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">query</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">make_latest_timestamp_query</span><span class="p">(</span><span class="n">namespace</span><span class="p">)</span>
<span class="n">req</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">make_request</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">query</span><span class="p">)</span>
<span class="n">resp</span> <span class="o">=</span> <span class="n">datastore</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="n">req</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">batch</span><span class="o">.</span><span class="n">entity_results</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Datastore total statistics unavailable.&quot;</span><span class="p">)</span>
<span class="n">entity</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">batch</span><span class="o">.</span><span class="n">entity_results</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">entity</span>
<span class="k">return</span> <span class="n">datastore_helper</span><span class="o">.</span><span class="n">micros_from_timestamp</span><span class="p">(</span>
<span class="n">entity</span><span class="o">.</span><span class="n">properties</span><span class="p">[</span><span class="s1">&#39;timestamp&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">timestamp_value</span><span class="p">)</span></div>
<div class="viewcode-block" id="ReadFromDatastore.get_estimated_size_bytes"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.get_estimated_size_bytes">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">get_estimated_size_bytes</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">datastore</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Get the estimated size of the data returned by the given query.</span>
<span class="sd"> Cloud Datastore provides no way to get a good estimate of how large the</span>
<span class="sd"> result of a query is going to be. Hence we use the __Stat_Kind__ system</span>
<span class="sd"> table to get size of the entire kind as an approximate estimate, assuming</span>
<span class="sd"> exactly 1 kind is specified in the query.</span>
<span class="sd"> See https://cloud.google.com/datastore/docs/concepts/stats.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">kind</span> <span class="o">=</span> <span class="n">query</span><span class="o">.</span><span class="n">kind</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">name</span>
<span class="n">latest_timestamp</span> <span class="o">=</span> <span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">query_latest_statistics_timestamp</span><span class="p">(</span>
<span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">datastore</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">&#39;Latest stats timestamp for kind </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">kind</span><span class="p">,</span> <span class="n">latest_timestamp</span><span class="p">)</span>
<span class="n">kind_stats_query</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">helper</span><span class="o">.</span><span class="n">make_kind_stats_query</span><span class="p">(</span><span class="n">namespace</span><span class="p">,</span> <span class="n">kind</span><span class="p">,</span> <span class="n">latest_timestamp</span><span class="p">))</span>
<span class="n">req</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">make_request</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">kind_stats_query</span><span class="p">)</span>
<span class="n">resp</span> <span class="o">=</span> <span class="n">datastore</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="n">req</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">batch</span><span class="o">.</span><span class="n">entity_results</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Datastore statistics for kind </span><span class="si">%s</span><span class="s2"> unavailable&quot;</span> <span class="o">%</span> <span class="n">kind</span><span class="p">)</span>
<span class="n">entity</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">batch</span><span class="o">.</span><span class="n">entity_results</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">entity</span>
<span class="k">return</span> <span class="n">datastore_helper</span><span class="o">.</span><span class="n">get_value</span><span class="p">(</span><span class="n">entity</span><span class="o">.</span><span class="n">properties</span><span class="p">[</span><span class="s1">&#39;entity_bytes&#39;</span><span class="p">])</span></div>
<div class="viewcode-block" id="ReadFromDatastore.get_estimated_num_splits"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.ReadFromDatastore.get_estimated_num_splits">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">get_estimated_num_splits</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">datastore</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Computes the number of splits to be performed on the given query.&quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">estimated_size_bytes</span> <span class="o">=</span> <span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">get_estimated_size_bytes</span><span class="p">(</span>
<span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">datastore</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">&#39;Estimated size bytes for query: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">estimated_size_bytes</span><span class="p">)</span>
<span class="n">num_splits</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">min</span><span class="p">(</span><span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">_NUM_QUERY_SPLITS_MAX</span><span class="p">,</span> <span class="nb">round</span><span class="p">(</span>
<span class="p">(</span><span class="nb">float</span><span class="p">(</span><span class="n">estimated_size_bytes</span><span class="p">)</span> <span class="o">/</span>
<span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">_DEFAULT_BUNDLE_SIZE_BYTES</span><span class="p">))))</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;Failed to fetch estimated size bytes: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="c1"># Fallback in case estimated size is unavailable.</span>
<span class="n">num_splits</span> <span class="o">=</span> <span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">_NUM_QUERY_SPLITS_MIN</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span><span class="n">num_splits</span><span class="p">,</span> <span class="n">ReadFromDatastore</span><span class="o">.</span><span class="n">_NUM_QUERY_SPLITS_MIN</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">_Mutate</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``PTransform`` that writes mutations to Cloud Datastore.</span>
<span class="sd"> Only idempotent Datastore mutation operations (upsert and delete) are</span>
<span class="sd"> supported, as the commits are retried when failures occur.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">_WRITE_BATCH_INITIAL_SIZE</span> <span class="o">=</span> <span class="mi">200</span>
<span class="c1"># Max allowed Datastore writes per batch, and max bytes per batch.</span>
<span class="c1"># Note that the max bytes per batch set here is lower than the 10MB limit</span>
<span class="c1"># actually enforced by the API, to leave space for the CommitRequest wrapper</span>
<span class="c1"># around the mutations.</span>
<span class="n">_WRITE_BATCH_MAX_SIZE</span> <span class="o">=</span> <span class="mi">500</span>
<span class="n">_WRITE_BATCH_MAX_BYTES_SIZE</span> <span class="o">=</span> <span class="mi">9000000</span>
<span class="n">_WRITE_BATCH_MIN_SIZE</span> <span class="o">=</span> <span class="mi">10</span>
<span class="n">_WRITE_BATCH_TARGET_LATENCY_MS</span> <span class="o">=</span> <span class="mi">5000</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</span><span class="p">,</span> <span class="n">mutation_fn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initializes a Mutate transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> project: The Project ID</span>
<span class="sd"> mutation_fn: A function that converts `entities` or `keys` to</span>
<span class="sd"> `mutations`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span> <span class="o">=</span> <span class="n">project</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutation_fn</span> <span class="o">=</span> <span class="n">mutation_fn</span>
<span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;datastoreio write transform is experimental.&#39;</span><span class="p">)</span>
<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">pcoll</span><span class="p">):</span>
<span class="k">return</span> <span class="p">(</span><span class="n">pcoll</span>
<span class="o">|</span> <span class="s1">&#39;Convert to Mutation&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">Map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_mutation_fn</span><span class="p">)</span>
<span class="o">|</span> <span class="s1">&#39;Write Mutation to Datastore&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">ParDo</span><span class="p">(</span><span class="n">_Mutate</span><span class="o">.</span><span class="n">DatastoreWriteFn</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">)))</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">&#39;project&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span>
<span class="s1">&#39;mutation_fn&#39;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mutation_fn</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">}</span>
<span class="k">class</span> <span class="nc">_DynamicBatchSizer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Determines request sizes for future Datastore RPCS.&quot;&quot;&quot;</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="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span> <span class="o">=</span> <span class="n">util</span><span class="o">.</span><span class="n">MovingSum</span><span class="p">(</span><span class="n">window_ms</span><span class="o">=</span><span class="mi">120000</span><span class="p">,</span>
<span class="n">bucket_ms</span><span class="o">=</span><span class="mi">10000</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_batch_size</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns the recommended size for datastore RPCs at this time.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">has_data</span><span class="p">(</span><span class="n">now</span><span class="p">):</span>
<span class="k">return</span> <span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_INITIAL_SIZE</span>
<span class="n">recent_mean_latency_ms</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="n">now</span><span class="p">))</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span><span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_MIN_SIZE</span><span class="p">,</span>
<span class="nb">min</span><span class="p">(</span><span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_MAX_SIZE</span><span class="p">,</span>
<span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_TARGET_LATENCY_MS</span>
<span class="o">//</span> <span class="nb">max</span><span class="p">(</span><span class="n">recent_mean_latency_ms</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="p">))</span>
<span class="k">def</span> <span class="nf">report_latency</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">now</span><span class="p">,</span> <span class="n">latency_ms</span><span class="p">,</span> <span class="n">num_mutations</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Reports the latency of an RPC to Datastore.</span>
<span class="sd"> Args:</span>
<span class="sd"> now: double, completion time of the RPC as seconds since the epoch.</span>
<span class="sd"> latency_ms: double, the observed latency in milliseconds for this RPC.</span>
<span class="sd"> num_mutations: int, number of mutations contained in the RPC.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_commit_time_per_entity_ms</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">now</span><span class="p">,</span> <span class="n">latency_ms</span> <span class="o">/</span> <span class="n">num_mutations</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">DatastoreWriteFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``DoFn`` that write mutations to Datastore.</span>
<span class="sd"> Mutations are written in batches, where the maximum batch size is</span>
<span class="sd"> `_Mutate._WRITE_BATCH_SIZE`.</span>
<span class="sd"> Commits are non-transactional. If a commit fails because of a conflict over</span>
<span class="sd"> an entity group, the commit will be retried. This means that the mutation</span>
<span class="sd"> should be idempotent (`upsert` and `delete` mutations) to prevent duplicate</span>
<span class="sd"> data or errors.</span>
<span class="sd"> &quot;&quot;&quot;</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</span><span class="p">,</span> <span class="n">fixed_batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Args:</span>
<span class="sd"> project: str, the cloud project id.</span>
<span class="sd"> fixed_batch_size: int, for testing only, this forces all batches of</span>
<span class="sd"> writes to be a fixed size, for easier unittesting.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_project</span> <span class="o">=</span> <span class="n">project</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_fixed_batch_size</span> <span class="o">=</span> <span class="n">fixed_batch_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rpc_successes</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="n">_Mutate</span><span class="o">.</span><span class="n">DatastoreWriteFn</span><span class="p">,</span> <span class="s2">&quot;datastoreRpcSuccesses&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rpc_errors</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="n">_Mutate</span><span class="o">.</span><span class="n">DatastoreWriteFn</span><span class="p">,</span> <span class="s2">&quot;datastoreRpcErrors&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_throttled_secs</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="n">_Mutate</span><span class="o">.</span><span class="n">DatastoreWriteFn</span><span class="p">,</span> <span class="s2">&quot;cumulativeThrottlingSeconds&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_throttler</span> <span class="o">=</span> <span class="n">AdaptiveThrottler</span><span class="p">(</span><span class="n">window_ms</span><span class="o">=</span><span class="mi">120000</span><span class="p">,</span> <span class="n">bucket_ms</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span>
<span class="n">overload_ratio</span><span class="o">=</span><span class="mf">1.25</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_update_rpc_stats</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">successes</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">errors</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">throttled_secs</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rpc_successes</span><span class="o">.</span><span class="n">inc</span><span class="p">(</span><span class="n">successes</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rpc_errors</span><span class="o">.</span><span class="n">inc</span><span class="p">(</span><span class="n">errors</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_throttled_secs</span><span class="o">.</span><span class="n">inc</span><span class="p">(</span><span class="n">throttled_secs</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="bp">self</span><span class="o">.</span><span class="n">_mutations</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutations_size</span> <span class="o">=</span> <span class="mi">0</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">get_datastore</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fixed_batch_size</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_target_batch_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fixed_batch_size</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batch_sizer</span> <span class="o">=</span> <span class="n">_Mutate</span><span class="o">.</span><span class="n">_DynamicBatchSizer</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_target_batch_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_sizer</span><span class="o">.</span><span class="n">get_batch_size</span><span class="p">(</span>
<span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span><span class="o">*</span><span class="mi">1000</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">element</span><span class="p">):</span>
<span class="n">size</span> <span class="o">=</span> <span class="n">element</span><span class="o">.</span><span class="n">ByteSize</span><span class="p">()</span>
<span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span> <span class="ow">and</span>
<span class="n">size</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mutations_size</span> <span class="o">&gt;</span> <span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_MAX_BYTES_SIZE</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">element</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutations_size</span> <span class="o">+=</span> <span class="n">size</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_target_batch_size</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_flush_batch</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_flush_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># Flush the current batch of mutations to Cloud Datastore.</span>
<span class="n">_</span><span class="p">,</span> <span class="n">latency_ms</span> <span class="o">=</span> <span class="n">helper</span><span class="o">.</span><span class="n">write_mutations</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_datastore</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_throttler</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_rpc_stats</span><span class="p">,</span>
<span class="n">throttle_delay</span><span class="o">=</span><span class="n">_Mutate</span><span class="o">.</span><span class="n">_WRITE_BATCH_TARGET_LATENCY_MS</span><span class="o">//</span><span class="mi">1000</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;Successfully wrote </span><span class="si">%d</span><span class="s2"> mutations in </span><span class="si">%d</span><span class="s2">ms.&quot;</span><span class="p">,</span>
<span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="p">),</span> <span class="n">latency_ms</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fixed_batch_size</span><span class="p">:</span>
<span class="n">now</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span><span class="o">*</span><span class="mi">1000</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batch_sizer</span><span class="o">.</span><span class="n">report_latency</span><span class="p">(</span><span class="n">now</span><span class="p">,</span> <span class="n">latency_ms</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_target_batch_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_sizer</span><span class="o">.</span><span class="n">get_batch_size</span><span class="p">(</span><span class="n">now</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutations</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mutations_size</span> <span class="o">=</span> <span class="mi">0</span>
<div class="viewcode-block" id="WriteToDatastore"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.WriteToDatastore">[docs]</a><span class="k">class</span> <span class="nc">WriteToDatastore</span><span class="p">(</span><span class="n">_Mutate</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``PTransform`` to write a ``PCollection[Entity]`` to Cloud Datastore.&quot;&quot;&quot;</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</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the `WriteToDatastore` transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> project: The ID of the project to write to.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Import here to avoid adding the dependency for local running scenarios.</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span>
<span class="kn">from</span> <span class="nn">apitools.base</span> <span class="k">import</span> <span class="n">py</span> <span class="c1"># pylint: disable=unused-variable</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span>
<span class="s1">&#39;Google Cloud IO not available, &#39;</span>
<span class="s1">&#39;please install apache_beam[gcp]&#39;</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">WriteToDatastore</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="n">project</span><span class="p">,</span> <span class="n">WriteToDatastore</span><span class="o">.</span><span class="n">to_upsert_mutation</span><span class="p">)</span>
<div class="viewcode-block" id="WriteToDatastore.to_upsert_mutation"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.WriteToDatastore.to_upsert_mutation">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">to_upsert_mutation</span><span class="p">(</span><span class="n">entity</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">helper</span><span class="o">.</span><span class="n">is_key_valid</span><span class="p">(</span><span class="n">entity</span><span class="o">.</span><span class="n">key</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Entities to be written to the Cloud Datastore must &#39;</span>
<span class="s1">&#39;have complete keys:</span><span class="se">\n</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">entity</span><span class="p">)</span>
<span class="n">mutation</span> <span class="o">=</span> <span class="n">datastore_pb2</span><span class="o">.</span><span class="n">Mutation</span><span class="p">()</span>
<span class="n">mutation</span><span class="o">.</span><span class="n">upsert</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">entity</span><span class="p">)</span>
<span class="k">return</span> <span class="n">mutation</span></div></div>
<div class="viewcode-block" id="DeleteFromDatastore"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.DeleteFromDatastore">[docs]</a><span class="k">class</span> <span class="nc">DeleteFromDatastore</span><span class="p">(</span><span class="n">_Mutate</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``PTransform`` to delete a ``PCollection[Key]`` from Cloud Datastore.&quot;&quot;&quot;</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</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the `DeleteFromDatastore` transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> project: The ID of the project from which the entities will be deleted.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DeleteFromDatastore</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="n">project</span><span class="p">,</span> <span class="n">DeleteFromDatastore</span><span class="o">.</span><span class="n">to_delete_mutation</span><span class="p">)</span>
<div class="viewcode-block" id="DeleteFromDatastore.to_delete_mutation"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.datastoreio.html#apache_beam.io.gcp.datastore.v1.datastoreio.DeleteFromDatastore.to_delete_mutation">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">to_delete_mutation</span><span class="p">(</span><span class="n">key</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">helper</span><span class="o">.</span><span class="n">is_key_valid</span><span class="p">(</span><span class="n">key</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Keys to be deleted from the Cloud Datastore must be &#39;</span>
<span class="s1">&#39;complete:</span><span class="se">\n</span><span class="si">%s</span><span class="s1">&quot;, key&#39;</span><span class="p">)</span>
<span class="n">mutation</span> <span class="o">=</span> <span class="n">datastore_pb2</span><span class="o">.</span><span class="n">Mutation</span><span class="p">()</span>
<span class="n">mutation</span><span class="o">.</span><span class="n">delete</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="k">return</span> <span class="n">mutation</span></div></div>
</pre></div>
</div>
<div class="articleComments">
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; 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>