blob: 05764eae27eb02b205a4b07935fb48fb07a4d8a3 [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.v1new.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.v1new.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.v1new.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;</span>
<span class="sd">Cloud Datastore client and test 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">logging</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">uuid</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">range</span>
<span class="kn">from</span> <span class="nn">google.api_core</span> <span class="k">import</span> <span class="n">exceptions</span>
<span class="kn">from</span> <span class="nn">google.cloud</span> <span class="k">import</span> <span class="n">environment_vars</span>
<span class="kn">from</span> <span class="nn">google.cloud.datastore</span> <span class="k">import</span> <span class="n">client</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1new</span> <span class="k">import</span> <span class="n">types</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="kn">from</span> <span class="nn">cachetools.func</span> <span class="k">import</span> <span class="n">ttl_cache</span>
<span class="c1"># https://cloud.google.com/datastore/docs/concepts/errors#error_codes</span>
<span class="n">_RETRYABLE_DATASTORE_ERRORS</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">exceptions</span><span class="o">.</span><span class="n">Aborted</span><span class="p">,</span>
<span class="n">exceptions</span><span class="o">.</span><span class="n">DeadlineExceeded</span><span class="p">,</span>
<span class="n">exceptions</span><span class="o">.</span><span class="n">InternalServerError</span><span class="p">,</span>
<span class="n">exceptions</span><span class="o">.</span><span class="n">ServiceUnavailable</span><span class="p">,</span>
<span class="p">)</span>
<div class="viewcode-block" id="get_client"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.helper.html#apache_beam.io.gcp.datastore.v1new.helper.get_client">[docs]</a><span class="nd">@ttl_cache</span><span class="p">(</span><span class="n">maxsize</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">ttl</span><span class="o">=</span><span class="mi">3600</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">get_client</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;Returns a Cloud Datastore client.&quot;&quot;&quot;</span>
<span class="n">_client</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="n">project</span><span class="o">=</span><span class="n">project</span><span class="p">,</span> <span class="n">namespace</span><span class="o">=</span><span class="n">namespace</span><span class="p">)</span>
<span class="c1"># Avoid overwriting user setting. BEAM-7608</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">environment_vars</span><span class="o">.</span><span class="n">GCD_HOST</span><span class="p">,</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">_client</span><span class="o">.</span><span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://batch-datastore.googleapis.com&#39;</span> <span class="c1"># BEAM-1387</span>
<span class="k">return</span> <span class="n">_client</span></div>
<div class="viewcode-block" id="retry_on_rpc_error"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.helper.html#apache_beam.io.gcp.datastore.v1new.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">return</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">_RETRYABLE_DATASTORE_ERRORS</span><span class="p">)</span></div>
<div class="viewcode-block" id="write_mutations"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.helper.html#apache_beam.io.gcp.datastore.v1new.helper.write_mutations">[docs]</a><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">write_mutations</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">throttler</span><span class="p">,</span> <span class="n">rpc_stats_callback</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 up to 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"> Assumes that the Datastore client library does not perform any retries on</span>
<span class="sd"> commits. It has not been determined how such retries would interact with the</span>
<span class="sd"> retries and throttler used here.</span>
<span class="sd"> See ``google.cloud.datastore_v1.gapic.datastore_client_config`` for</span>
<span class="sd"> retry config.</span>
<span class="sd"> Args:</span>
<span class="sd"> batch: (:class:`~google.cloud.datastore.batch.Batch`) An instance of an</span>
<span class="sd"> in-progress batch.</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: (``apache_beam.io.gcp.datastore.v1.adaptive_throttler.</span>
<span class="sd"> AdaptiveThrottler``)</span>
<span class="sd"> Throttler instance used to select requests to be throttled.</span>
<span class="sd"> throttle_delay: (:class:`float`) time in seconds to sleep when throttled.</span>
<span class="sd"> Returns:</span>
<span class="sd"> (int) The latency of the successful RPC in milliseconds.</span>
<span class="sd"> &quot;&quot;&quot;</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">batch</span><span class="o">.</span><span class="n">commit</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">commit_time_ms</span>
<span class="k">except</span> <span class="ne">Exception</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></div>
<div class="viewcode-block" id="create_entities"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.helper.html#apache_beam.io.gcp.datastore.v1new.helper.create_entities">[docs]</a><span class="k">def</span> <span class="nf">create_entities</span><span class="p">(</span><span class="n">count</span><span class="p">,</span> <span class="n">id_or_name</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Creates a list of entities with random keys.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">id_or_name</span><span class="p">:</span>
<span class="n">ids_or_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">()</span><span class="o">.</span><span class="n">int</span> <span class="o">&amp;</span> <span class="p">((</span><span class="mi">1</span> <span class="o">&lt;&lt;</span> <span class="mi">63</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">count</span><span class="p">)]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">ids_or_names</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">count</span><span class="p">)]</span>
<span class="n">keys</span> <span class="o">=</span> <span class="p">[</span><span class="n">types</span><span class="o">.</span><span class="n">Key</span><span class="p">([</span><span class="s1">&#39;EntityKind&#39;</span><span class="p">,</span> <span class="n">x</span><span class="p">],</span> <span class="n">project</span><span class="o">=</span><span class="s1">&#39;project&#39;</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">ids_or_names</span><span class="p">]</span>
<span class="k">return</span> <span class="p">[</span><span class="n">types</span><span class="o">.</span><span class="n">Entity</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys</span><span class="p">]</span></div>
<div class="viewcode-block" id="create_client_entities"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.helper.html#apache_beam.io.gcp.datastore.v1new.helper.create_client_entities">[docs]</a><span class="k">def</span> <span class="nf">create_client_entities</span><span class="p">(</span><span class="n">count</span><span class="p">,</span> <span class="n">id_or_name</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Creates a list of client-style entities with random keys.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="p">[</span><span class="n">entity</span><span class="o">.</span><span class="n">to_client_entity</span><span class="p">()</span>
<span class="k">for</span> <span class="n">entity</span> <span class="ow">in</span> <span class="n">create_entities</span><span class="p">(</span><span class="n">count</span><span class="p">,</span> <span class="n">id_or_name</span><span class="o">=</span><span class="n">id_or_name</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>