blob: 065e248b553b5a3b7f930dd3fa2c66b0e1f34a19 [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.helper &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.helper</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.helper</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;Cloud Datastore helper functions.</span>
<span class="sd">For internal use only; no backwards-compatibility guarantees.</span>
<span class="sd">&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">import</span> <span class="nn">errno</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">sys</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">socket</span> <span class="k">import</span> <span class="n">error</span> <span class="k">as</span> <span class="n">SocketError</span>
<span class="kn">from</span> <span class="nn">future.builtins</span> <span class="k">import</span> <span class="nb">next</span>
<span class="kn">from</span> <span class="nn">past.builtins</span> <span class="k">import</span> <span class="n">unicode</span>
<span class="c1"># pylint: disable=ungrouped-imports</span>
<span class="kn">from</span> <span class="nn">apache_beam.internal.gcp</span> <span class="k">import</span> <span class="n">auth</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="k">import</span> <span class="n">retry</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">google.cloud.proto.datastore.v1</span> <span class="k">import</span> <span class="n">entity_pb2</span>
<span class="kn">from</span> <span class="nn">google.cloud.proto.datastore.v1</span> <span class="k">import</span> <span class="n">query_pb2</span>
<span class="kn">from</span> <span class="nn">google.rpc</span> <span class="k">import</span> <span class="n">code_pb2</span>
<span class="kn">from</span> <span class="nn">googledatastore</span> <span class="k">import</span> <span class="n">PropertyFilter</span><span class="p">,</span> <span class="n">CompositeFilter</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="kn">from</span> <span class="nn">googledatastore.connection</span> <span class="k">import</span> <span class="n">Datastore</span>
<span class="kn">from</span> <span class="nn">googledatastore.connection</span> <span class="k">import</span> <span class="n">RPCError</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="c1"># pylint: enable=ungrouped-imports</span>
<div class="viewcode-block" id="key_comparator"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.key_comparator">[docs]</a><span class="k">def</span> <span class="nf">key_comparator</span><span class="p">(</span><span class="n">k1</span><span class="p">,</span> <span class="n">k2</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A comparator for Datastore keys.</span>
<span class="sd"> Comparison is only valid for keys in the same partition. The comparison here</span>
<span class="sd"> is between the list of paths for each key.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">k1</span><span class="o">.</span><span class="n">partition_id</span> <span class="o">!=</span> <span class="n">k2</span><span class="o">.</span><span class="n">partition_id</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Cannot compare keys with different partition ids.&#39;</span><span class="p">)</span>
<span class="n">k2_iter</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">k2</span><span class="o">.</span><span class="n">path</span><span class="p">)</span>
<span class="k">for</span> <span class="n">k1_path</span> <span class="ow">in</span> <span class="n">k1</span><span class="o">.</span><span class="n">path</span><span class="p">:</span>
<span class="n">k2_path</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">k2_iter</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">k2_path</span><span class="p">:</span>
<span class="k">return</span> <span class="mi">1</span>
<span class="n">result</span> <span class="o">=</span> <span class="n">compare_path</span><span class="p">(</span><span class="n">k1_path</span><span class="p">,</span> <span class="n">k2_path</span><span class="p">)</span>
<span class="k">if</span> <span class="n">result</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="n">result</span>
<span class="n">k2_path</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">k2_iter</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="n">k2_path</span><span class="p">:</span>
<span class="k">return</span> <span class="o">-</span><span class="mi">1</span>
<span class="k">return</span> <span class="mi">0</span></div>
<div class="viewcode-block" id="compare_path"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.compare_path">[docs]</a><span class="k">def</span> <span class="nf">compare_path</span><span class="p">(</span><span class="n">p1</span><span class="p">,</span> <span class="n">p2</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A comparator for key path.</span>
<span class="sd"> A path has either an `id` or a `name` field defined. The</span>
<span class="sd"> comparison works with the following rules:</span>
<span class="sd"> 1. If one path has `id` defined while the other doesn&#39;t, then the</span>
<span class="sd"> one with `id` defined is considered smaller.</span>
<span class="sd"> 2. If both paths have `id` defined, then their ids are compared.</span>
<span class="sd"> 3. If no `id` is defined for both paths, then their `names` are compared.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">result</span> <span class="o">=</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">kind</span> <span class="o">&gt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">kind</span><span class="p">)</span> <span class="o">-</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">kind</span> <span class="o">&lt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">kind</span><span class="p">)</span>
<span class="k">if</span> <span class="n">result</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="n">result</span>
<span class="k">if</span> <span class="n">p1</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;id&#39;</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">p2</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;id&#39;</span><span class="p">):</span>
<span class="k">return</span> <span class="o">-</span><span class="mi">1</span>
<span class="k">return</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">id</span> <span class="o">&gt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">id</span><span class="p">)</span> <span class="o">-</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">id</span> <span class="o">&lt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">id</span><span class="p">)</span>
<span class="k">if</span> <span class="n">p2</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;id&#39;</span><span class="p">):</span>
<span class="k">return</span> <span class="mi">1</span>
<span class="k">return</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">name</span> <span class="o">&gt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">-</span> <span class="p">(</span><span class="n">p1</span><span class="o">.</span><span class="n">name</span> <span class="o">&lt;</span> <span class="n">p2</span><span class="o">.</span><span class="n">name</span><span class="p">)</span></div>
<div class="viewcode-block" id="get_datastore"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.get_datastore">[docs]</a><span class="k">def</span> <span class="nf">get_datastore</span><span class="p">(</span><span class="n">project</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns a Cloud Datastore client.&quot;&quot;&quot;</span>
<span class="n">credentials</span> <span class="o">=</span> <span class="n">auth</span><span class="o">.</span><span class="n">get_service_credentials</span><span class="p">()</span>
<span class="k">return</span> <span class="n">Datastore</span><span class="p">(</span><span class="n">project</span><span class="p">,</span> <span class="n">credentials</span><span class="p">,</span> <span class="n">host</span><span class="o">=</span><span class="s1">&#39;batch-datastore.googleapis.com&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="make_request"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.make_request">[docs]</a><span class="k">def</span> <span class="nf">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="sd">&quot;&quot;&quot;Make a Cloud Datastore request for the given query.&quot;&quot;&quot;</span>
<span class="n">req</span> <span class="o">=</span> <span class="n">datastore_pb2</span><span class="o">.</span><span class="n">RunQueryRequest</span><span class="p">()</span>
<span class="n">req</span><span class="o">.</span><span class="n">partition_id</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">make_partition</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">req</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
<span class="k">return</span> <span class="n">req</span></div>
<div class="viewcode-block" id="make_partition"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.make_partition">[docs]</a><span class="k">def</span> <span class="nf">make_partition</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="sd">&quot;&quot;&quot;Make a PartitionId for the given project and namespace.&quot;&quot;&quot;</span>
<span class="n">partition</span> <span class="o">=</span> <span class="n">entity_pb2</span><span class="o">.</span><span class="n">PartitionId</span><span class="p">()</span>
<span class="n">partition</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project</span>
<span class="k">if</span> <span class="n">namespace</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">partition</span><span class="o">.</span><span class="n">namespace_id</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="k">return</span> <span class="n">partition</span></div>
<div class="viewcode-block" id="retry_on_rpc_error"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.retry_on_rpc_error">[docs]</a><span class="k">def</span> <span class="nf">retry_on_rpc_error</span><span class="p">(</span><span class="n">exception</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A retry filter for Cloud Datastore RPCErrors.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">RPCError</span><span class="p">):</span>
<span class="n">err_code</span> <span class="o">=</span> <span class="n">exception</span><span class="o">.</span><span class="n">code</span>
<span class="c1"># TODO(BEAM-2156): put these codes in a global list and use that instead.</span>
<span class="k">return</span> <span class="p">(</span><span class="n">err_code</span> <span class="o">==</span> <span class="n">code_pb2</span><span class="o">.</span><span class="n">DEADLINE_EXCEEDED</span> <span class="ow">or</span>
<span class="n">err_code</span> <span class="o">==</span> <span class="n">code_pb2</span><span class="o">.</span><span class="n">UNAVAILABLE</span> <span class="ow">or</span>
<span class="n">err_code</span> <span class="o">==</span> <span class="n">code_pb2</span><span class="o">.</span><span class="n">UNKNOWN</span> <span class="ow">or</span>
<span class="n">err_code</span> <span class="o">==</span> <span class="n">code_pb2</span><span class="o">.</span><span class="n">INTERNAL</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">SocketError</span><span class="p">):</span>
<span class="k">return</span> <span class="p">(</span><span class="n">exception</span><span class="o">.</span><span class="n">errno</span> <span class="o">==</span> <span class="n">errno</span><span class="o">.</span><span class="n">ECONNRESET</span> <span class="ow">or</span>
<span class="n">exception</span><span class="o">.</span><span class="n">errno</span> <span class="o">==</span> <span class="n">errno</span><span class="o">.</span><span class="n">ETIMEDOUT</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="fetch_entities"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.fetch_entities">[docs]</a><span class="k">def</span> <span class="nf">fetch_entities</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;A helper method to fetch entities from Cloud Datastore.</span>
<span class="sd"> Args:</span>
<span class="sd"> project: Project ID</span>
<span class="sd"> namespace: Cloud Datastore namespace</span>
<span class="sd"> query: Query to be read from</span>
<span class="sd"> datastore: Cloud Datastore Client</span>
<span class="sd"> Returns:</span>
<span class="sd"> An iterator of entities.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">QueryIterator</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></div>
<div class="viewcode-block" id="is_key_valid"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.is_key_valid">[docs]</a><span class="k">def</span> <span class="nf">is_key_valid</span><span class="p">(</span><span class="n">key</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns True if a Cloud Datastore key is complete.</span>
<span class="sd"> A key is complete if its last element has either an id or a name.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">key</span><span class="o">.</span><span class="n">path</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">return</span> <span class="n">key</span><span class="o">.</span><span class="n">path</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;id&#39;</span><span class="p">)</span> <span class="ow">or</span> <span class="n">key</span><span class="o">.</span><span class="n">path</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">&#39;name&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="write_mutations"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.write_mutations">[docs]</a><span class="k">def</span> <span class="nf">write_mutations</span><span class="p">(</span><span class="n">datastore</span><span class="p">,</span> <span class="n">project</span><span class="p">,</span> <span class="n">mutations</span><span class="p">,</span> <span class="n">throttler</span><span class="p">,</span>
<span class="n">rpc_stats_callback</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">throttle_delay</span><span class="o">=</span><span class="mi">1</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A helper function to write a batch of mutations to Cloud Datastore.</span>
<span class="sd"> If a commit fails, it will be retried upto 5 times. All mutations in the</span>
<span class="sd"> batch will be committed again, even if the commit was partially successful.</span>
<span class="sd"> If the retry limit is exceeded, the last exception from Cloud Datastore will</span>
<span class="sd"> be raised.</span>
<span class="sd"> Args:</span>
<span class="sd"> datastore: googledatastore.connection.Datastore</span>
<span class="sd"> project: str, project id</span>
<span class="sd"> mutations: list of google.cloud.proto.datastore.v1.datastore_pb2.Mutation</span>
<span class="sd"> rpc_stats_callback: a function to call with arguments `successes` and</span>
<span class="sd"> `failures` and `throttled_secs`; this is called to record successful</span>
<span class="sd"> and failed RPCs to Datastore and time spent waiting for throttling.</span>
<span class="sd"> throttler: AdaptiveThrottler, to use to select requests to be throttled.</span>
<span class="sd"> throttle_delay: float, time in seconds to sleep when throttled.</span>
<span class="sd"> Returns a tuple of:</span>
<span class="sd"> CommitResponse, the response from Datastore;</span>
<span class="sd"> int, the latency of the successful RPC in milliseconds.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">commit_request</span> <span class="o">=</span> <span class="n">datastore_pb2</span><span class="o">.</span><span class="n">CommitRequest</span><span class="p">()</span>
<span class="n">commit_request</span><span class="o">.</span><span class="n">mode</span> <span class="o">=</span> <span class="n">datastore_pb2</span><span class="o">.</span><span class="n">CommitRequest</span><span class="o">.</span><span class="n">NON_TRANSACTIONAL</span>
<span class="n">commit_request</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project</span>
<span class="k">for</span> <span class="n">mutation</span> <span class="ow">in</span> <span class="n">mutations</span><span class="p">:</span>
<span class="n">commit_request</span><span class="o">.</span><span class="n">mutations</span><span class="o">.</span><span class="n">add</span><span class="p">()</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">mutation</span><span class="p">)</span>
<span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry_on_rpc_error</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">commit</span><span class="p">(</span><span class="n">request</span><span class="p">):</span>
<span class="c1"># Client-side throttling.</span>
<span class="k">while</span> <span class="n">throttler</span><span class="o">.</span><span class="n">throttle_request</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="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Delaying request for </span><span class="si">%d</span><span class="s2">s due to previous failures&quot;</span><span class="p">,</span>
<span class="n">throttle_delay</span><span class="p">)</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="n">throttle_delay</span><span class="p">)</span>
<span class="n">rpc_stats_callback</span><span class="p">(</span><span class="n">throttled_secs</span><span class="o">=</span><span class="n">throttle_delay</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">start_time</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="n">response</span> <span class="o">=</span> <span class="n">datastore</span><span class="o">.</span><span class="n">commit</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="n">end_time</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="n">rpc_stats_callback</span><span class="p">(</span><span class="n">successes</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">throttler</span><span class="o">.</span><span class="n">successful_request</span><span class="p">(</span><span class="n">start_time</span><span class="o">*</span><span class="mi">1000</span><span class="p">)</span>
<span class="n">commit_time_ms</span> <span class="o">=</span> <span class="nb">int</span><span class="p">((</span><span class="n">end_time</span><span class="o">-</span><span class="n">start_time</span><span class="p">)</span><span class="o">*</span><span class="mi">1000</span><span class="p">)</span>
<span class="k">return</span> <span class="n">response</span><span class="p">,</span> <span class="n">commit_time_ms</span>
<span class="k">except</span> <span class="p">(</span><span class="n">RPCError</span><span class="p">,</span> <span class="n">SocketError</span><span class="p">):</span>
<span class="k">if</span> <span class="n">rpc_stats_callback</span><span class="p">:</span>
<span class="n">rpc_stats_callback</span><span class="p">(</span><span class="n">errors</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="k">raise</span>
<span class="n">response</span><span class="p">,</span> <span class="n">commit_time_ms</span> <span class="o">=</span> <span class="n">commit</span><span class="p">(</span><span class="n">commit_request</span><span class="p">)</span>
<span class="k">return</span> <span class="n">response</span><span class="p">,</span> <span class="n">commit_time_ms</span></div>
<div class="viewcode-block" id="make_latest_timestamp_query"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.make_latest_timestamp_query">[docs]</a><span class="k">def</span> <span class="nf">make_latest_timestamp_query</span><span class="p">(</span><span class="n">namespace</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Make a Query to fetch the latest timestamp statistics.&quot;&quot;&quot;</span>
<span class="n">query</span> <span class="o">=</span> <span class="n">query_pb2</span><span class="o">.</span><span class="n">Query</span><span class="p">()</span>
<span class="k">if</span> <span class="n">namespace</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">query</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">add</span><span class="p">()</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="s1">&#39;__Stat_Total__&#39;</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">query</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">add</span><span class="p">()</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="s1">&#39;__Stat_Ns_Total__&#39;</span>
<span class="c1"># Descending order of `timestamp`</span>
<span class="n">datastore_helper</span><span class="o">.</span><span class="n">add_property_orders</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="s2">&quot;-timestamp&quot;</span><span class="p">)</span>
<span class="c1"># Only get the latest entity</span>
<span class="n">query</span><span class="o">.</span><span class="n">limit</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">query</span></div>
<div class="viewcode-block" id="make_kind_stats_query"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.make_kind_stats_query">[docs]</a><span class="k">def</span> <span class="nf">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="sd">&quot;&quot;&quot;Make a Query to fetch the latest kind statistics.&quot;&quot;&quot;</span>
<span class="n">kind_stat_query</span> <span class="o">=</span> <span class="n">query_pb2</span><span class="o">.</span><span class="n">Query</span><span class="p">()</span>
<span class="k">if</span> <span class="n">namespace</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">kind_stat_query</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">add</span><span class="p">()</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="s1">&#39;__Stat_Kind__&#39;</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">kind_stat_query</span><span class="o">.</span><span class="n">kind</span><span class="o">.</span><span class="n">add</span><span class="p">()</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="s1">&#39;__Stat_Ns_Kind__&#39;</span>
<span class="n">kind_filter</span> <span class="o">=</span> <span class="n">datastore_helper</span><span class="o">.</span><span class="n">set_property_filter</span><span class="p">(</span>
<span class="n">query_pb2</span><span class="o">.</span><span class="n">Filter</span><span class="p">(),</span> <span class="s1">&#39;kind_name&#39;</span><span class="p">,</span> <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">EQUAL</span><span class="p">,</span>
<span class="n">unicode</span><span class="p">(</span><span class="n">kind</span><span class="p">))</span>
<span class="n">timestamp_filter</span> <span class="o">=</span> <span class="n">datastore_helper</span><span class="o">.</span><span class="n">set_property_filter</span><span class="p">(</span>
<span class="n">query_pb2</span><span class="o">.</span><span class="n">Filter</span><span class="p">(),</span> <span class="s1">&#39;timestamp&#39;</span><span class="p">,</span> <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">EQUAL</span><span class="p">,</span>
<span class="n">latest_timestamp</span><span class="p">)</span>
<span class="n">datastore_helper</span><span class="o">.</span><span class="n">set_composite_filter</span><span class="p">(</span><span class="n">kind_stat_query</span><span class="o">.</span><span class="n">filter</span><span class="p">,</span>
<span class="n">CompositeFilter</span><span class="o">.</span><span class="n">AND</span><span class="p">,</span> <span class="n">kind_filter</span><span class="p">,</span>
<span class="n">timestamp_filter</span><span class="p">)</span>
<span class="k">return</span> <span class="n">kind_stat_query</span></div>
<div class="viewcode-block" id="QueryIterator"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.helper.html#apache_beam.io.gcp.datastore.v1.helper.QueryIterator">[docs]</a><span class="k">class</span> <span class="nc">QueryIterator</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A iterator class for entities of a given query.</span>
<span class="sd"> Entities are read in batches. Retries on failures.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># Maximum number of results to request per query.</span>
<span class="n">_BATCH_SIZE</span> <span class="o">=</span> <span class="mi">500</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="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">datastore</span><span class="p">):</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">_datastore</span> <span class="o">=</span> <span class="n">datastore</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">_namespace</span> <span class="o">=</span> <span class="n">namespace</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_cursor</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_limit</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query</span><span class="o">.</span><span class="n">limit</span><span class="o">.</span><span class="n">value</span> <span class="ow">or</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxsize</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_req</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="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span><span class="n">num_retries</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry_on_rpc_error</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_next_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Fetches the next batch of entities.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_cursor</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_req</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">start_cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start_cursor</span>
<span class="c1"># set batch size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_req</span><span class="o">.</span><span class="n">query</span><span class="o">.</span><span class="n">limit</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_BATCH_SIZE</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_limit</span><span class="p">)</span>
<span class="n">resp</span> <span class="o">=</span> <span class="bp">self</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="bp">self</span><span class="o">.</span><span class="n">_req</span><span class="p">)</span>
<span class="k">return</span> <span class="n">resp</span>
<span class="k">def</span> <span class="nf">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">more_results</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">while</span> <span class="n">more_results</span><span class="p">:</span>
<span class="n">resp</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_next_batch</span><span class="p">()</span>
<span class="k">for</span> <span class="n">entity_result</span> <span class="ow">in</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">yield</span> <span class="n">entity_result</span><span class="o">.</span><span class="n">entity</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_cursor</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">end_cursor</span>
<span class="n">num_results</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</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="bp">self</span><span class="o">.</span><span class="n">_limit</span> <span class="o">-=</span> <span class="n">num_results</span>
<span class="c1"># Check if we need to read more entities.</span>
<span class="c1"># True when query limit hasn&#39;t been satisfied and there are more entities</span>
<span class="c1"># to be read. The latter is true if the response has a status</span>
<span class="c1"># `NOT_FINISHED` or if the number of results read in the previous batch</span>
<span class="c1"># is equal to `_BATCH_SIZE` (all indications that there is more data be</span>
<span class="c1"># read).</span>
<span class="n">more_results</span> <span class="o">=</span> <span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">_limit</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">and</span>
<span class="p">((</span><span class="n">num_results</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_BATCH_SIZE</span><span class="p">)</span> <span class="ow">or</span>
<span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">batch</span><span class="o">.</span><span class="n">more_results</span> <span class="o">==</span>
<span class="n">query_pb2</span><span class="o">.</span><span class="n">QueryResultBatch</span><span class="o">.</span><span class="n">NOT_FINISHED</span><span class="p">)))</span></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>