pydoc/2.38.0/_modules/apache_beam/io/gcp/datastore/v1new/query_splitter.html - beam-site - Git at Google



 <!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.query_splitter &mdash; Apache Beam 2.38.0 documentation</title>


   <script type="text/javascript" src="../../../../../../_static/js/modernizr.min.js"></script>


       <script type="text/javascript" id="documentation_options" data-url_root="../../../../../../" src="../../../../../../_static/documentation_options.js"></script>
         <script type="text/javascript" src="../../../../../../_static/jquery.js"></script>
         <script type="text/javascript" src="../../../../../../_static/underscore.js"></script>
         <script type="text/javascript" src="../../../../../../_static/doctools.js"></script>
         <script type="text/javascript" src="../../../../../../_static/language_data.js"></script>
         <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>

     <script type="text/javascript" src="../../../../../../_static/js/theme.js"></script>


   <link rel="stylesheet" href="../../../../../../_static/css/theme.css" type="text/css" />
   <link rel="stylesheet" href="../../../../../../_static/pygments.css" type="text/css" />
     <link rel="index" title="Index" href="../../../../../../genindex.html" />
     <link rel="search" title="Search" href="../../../../../../search.html" />
 </head>

 <body class="wy-body-for-nav">


   <div class="wy-grid-for-nav">

     <nav data-toggle="wy-nav-shift" class="wy-nav-side">
       <div class="wy-side-scroll">
         <div class="wy-side-nav-search" >


             <a href="../../../../../../index.html" class="icon icon-home"> Apache Beam


           </a>


               <div class="version">
                 2.38.0
               </div>


 <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.dataframe.html">apache_beam.dataframe 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.ml.html">apache_beam.ml package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../../../apache_beam.options.html">apache_beam.options package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../../../apache_beam.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>
 </ul>


         </div>
       </div>
     </nav>

     <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">


       <nav class="wy-nav-top" aria-label="top navigation">

           <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
           <a href="../../../../../../index.html">Apache Beam</a>

       </nav>


       <div class="wy-nav-content">

         <div class="rst-content">


 <div role="navigation" aria-label="breadcrumbs navigation">

   <ul class="wy-breadcrumbs">

       <li><a href="../../../../../../index.html">Docs</a> &raquo;</li>

           <li><a href="../../../../../index.html">Module code</a> &raquo;</li>

       <li>apache_beam.io.gcp.datastore.v1new.query_splitter</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.query_splitter</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">Implements a Cloud Datastore query splitter.</span>

 <span class="sd">For internal use only. No backwards compatibility guarantees.</span>
 <span class="sd">&quot;&quot;&quot;</span>
 <span class="c1"># pytype: skip-file</span>

 <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1new</span> <span class="kn">import</span> <span class="n">types</span>
 <span class="kn">from</span> <span class="nn">apache_beam.options.value_provider</span> <span class="kn">import</span> <span class="n">ValueProvider</span>

 <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;QuerySplitterError&#39;</span><span class="p">,</span> <span class="s1">&#39;SplitNotPossibleError&#39;</span><span class="p">,</span> <span class="s1">&#39;get_splits&#39;</span><span class="p">]</span>

 <span class="n">SCATTER_PROPERTY_NAME</span> <span class="o">=</span> <span class="s1">&#39;__scatter__&#39;</span>
 <span class="n">KEY_PROPERTY_NAME</span> <span class="o">=</span> <span class="s1">&#39;__key__&#39;</span>
 <span class="c1"># The number of keys to sample for each split.</span>
 <span class="n">KEYS_PER_SPLIT</span> <span class="o">=</span> <span class="mi">32</span>


 <div class="viewcode-block" id="QuerySplitterError"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.query_splitter.html#apache_beam.io.gcp.datastore.v1new.query_splitter.QuerySplitterError">[docs]</a><span class="k">class</span> <span class="nc">QuerySplitterError</span><span class="p">(</span><span class="ne">Exception</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Top-level error type.&quot;&quot;&quot;</span></div>


 <div class="viewcode-block" id="SplitNotPossibleError"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.query_splitter.html#apache_beam.io.gcp.datastore.v1new.query_splitter.SplitNotPossibleError">[docs]</a><span class="k">class</span> <span class="nc">SplitNotPossibleError</span><span class="p">(</span><span class="n">QuerySplitterError</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Raised when some parameter of the query does not allow splitting.&quot;&quot;&quot;</span></div>


 <div class="viewcode-block" id="get_splits"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1new.query_splitter.html#apache_beam.io.gcp.datastore.v1new.query_splitter.get_splits">[docs]</a><span class="k">def</span> <span class="nf">get_splits</span><span class="p">(</span><span class="n">client</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Returns a list of sharded queries for the given Cloud Datastore query.</span>

 <span class="sd">  This will create up to the desired number of splits, however it may return</span>
 <span class="sd">  less splits if the desired number of splits is unavailable. This will happen</span>
 <span class="sd">  if the number of split points provided by the underlying Datastore is less</span>
 <span class="sd">  than the desired number, which will occur if the number of results for the</span>
 <span class="sd">  query is too small.</span>

 <span class="sd">  This implementation of the QuerySplitter uses the __scatter__ property to</span>
 <span class="sd">  gather random split points for a query.</span>

 <span class="sd">  Note: This implementation is derived from the java query splitter in</span>
 <span class="sd">  https://github.com/GoogleCloudPlatform/google-cloud-datastore/blob/master/java/datastore/src/main/java/com/google/datastore/v1/client/QuerySplitterImpl.java</span>

 <span class="sd">  Args:</span>
 <span class="sd">    client: the datastore client.</span>
 <span class="sd">    query: the query to split.</span>
 <span class="sd">    num_splits: the desired number of splits.</span>

 <span class="sd">  Returns:</span>
 <span class="sd">    A list of split queries, of a max length of `num_splits`</span>

 <span class="sd">  Raises:</span>
 <span class="sd">    QuerySplitterError: if split could not be performed owing to query or split</span>
 <span class="sd">      parameters.</span>
 <span class="sd">  &quot;&quot;&quot;</span>
   <span class="k">if</span> <span class="n">num_splits</span> <span class="o">&lt;=</span> <span class="mi">1</span><span class="p">:</span>
     <span class="k">raise</span> <span class="n">SplitNotPossibleError</span><span class="p">(</span><span class="s1">&#39;num_splits must be &gt; 1, got: </span><span class="si">%d</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">num_splits</span><span class="p">)</span>
   <span class="n">validate_split</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>

   <span class="n">splits</span> <span class="o">=</span> <span class="p">[]</span>
   <span class="n">client_scatter_keys</span> <span class="o">=</span> <span class="n">_get_scatter_keys</span><span class="p">(</span><span class="n">client</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">)</span>
   <span class="n">last_client_key</span> <span class="o">=</span> <span class="kc">None</span>
   <span class="k">for</span> <span class="n">next_client_key</span> <span class="ow">in</span> <span class="n">_get_split_key</span><span class="p">(</span><span class="n">client_scatter_keys</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
     <span class="n">splits</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_create_split</span><span class="p">(</span><span class="n">last_client_key</span><span class="p">,</span> <span class="n">next_client_key</span><span class="p">,</span> <span class="n">query</span><span class="p">))</span>
     <span class="n">last_client_key</span> <span class="o">=</span> <span class="n">next_client_key</span>

   <span class="n">splits</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_create_split</span><span class="p">(</span><span class="n">last_client_key</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">query</span><span class="p">))</span>
   <span class="k">return</span> <span class="n">splits</span></div>


 <span class="k">def</span> <span class="nf">validate_split</span><span class="p">(</span><span class="n">query</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">  Verifies that the given query can be properly scattered.</span>

 <span class="sd">  Note that equality and ancestor filters are allowed, however they may result</span>
 <span class="sd">  in inefficient sharding.</span>

 <span class="sd">  Raises:</span>
 <span class="sd">    QuerySplitterError if split could not be performed owing to query</span>
 <span class="sd">      parameters.</span>
 <span class="sd">  &quot;&quot;&quot;</span>
   <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">order</span><span class="p">:</span>
     <span class="k">raise</span> <span class="n">SplitNotPossibleError</span><span class="p">(</span><span class="s1">&#39;Query cannot have any sort orders.&#39;</span><span class="p">)</span>

   <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">limit</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
     <span class="k">raise</span> <span class="n">SplitNotPossibleError</span><span class="p">(</span><span class="s1">&#39;Query cannot have a limit set.&#39;</span><span class="p">)</span>

   <span class="k">for</span> <span class="nb">filter</span> <span class="ow">in</span> <span class="n">query</span><span class="o">.</span><span class="n">filters</span><span class="p">:</span>
     <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="nb">filter</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">ValueProvider</span><span class="p">):</span>
       <span class="n">filter_operator</span> <span class="o">=</span> <span class="nb">filter</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
     <span class="k">else</span><span class="p">:</span>
       <span class="n">filter_operator</span> <span class="o">=</span> <span class="nb">filter</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
     <span class="k">if</span> <span class="n">filter_operator</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;&lt;&#39;</span><span class="p">,</span> <span class="s1">&#39;&lt;=&#39;</span><span class="p">,</span> <span class="s1">&#39;&gt;&#39;</span><span class="p">,</span> <span class="s1">&#39;&gt;=&#39;</span><span class="p">]:</span>
       <span class="k">raise</span> <span class="n">SplitNotPossibleError</span><span class="p">(</span><span class="s1">&#39;Query cannot have any inequality filters.&#39;</span><span class="p">)</span>


 <span class="k">def</span> <span class="nf">_create_scatter_query</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Creates a scatter query from the given user query.&quot;&quot;&quot;</span>
   <span class="c1"># There is a split containing entities before and after each scatter entity:</span>
   <span class="c1"># ||---*------*------*------*------*------*------*---||  * = scatter entity</span>
   <span class="c1"># If we represent each split as a region before a scatter entity, there is an</span>
   <span class="c1"># extra region following the last scatter point. Thus, we do not need the</span>
   <span class="c1"># scatter entity for the last region.</span>
   <span class="n">limit</span> <span class="o">=</span> <span class="p">(</span><span class="n">num_splits</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">KEYS_PER_SPLIT</span>
   <span class="n">scatter_query</span> <span class="o">=</span> <span class="n">types</span><span class="o">.</span><span class="n">Query</span><span class="p">(</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="n">project</span><span class="o">=</span><span class="n">query</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">query</span><span class="o">.</span><span class="n">namespace</span><span class="p">,</span>
       <span class="n">order</span><span class="o">=</span><span class="p">[</span><span class="n">SCATTER_PROPERTY_NAME</span><span class="p">],</span>
       <span class="n">projection</span><span class="o">=</span><span class="p">[</span><span class="n">KEY_PROPERTY_NAME</span><span class="p">],</span>
       <span class="n">limit</span><span class="o">=</span><span class="n">limit</span><span class="p">)</span>
   <span class="k">return</span> <span class="n">scatter_query</span>


 <span class="k">class</span> <span class="nc">IdOrName</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Represents an ID or name of a Datastore key,</span>

 <span class="sd">   Implements sort ordering: by ID, then by name, keys with IDs before those</span>
 <span class="sd">   with names.</span>
 <span class="sd">   &quot;&quot;&quot;</span>
   <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">id_or_name</span><span class="p">):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">id_or_name</span> <span class="o">=</span> <span class="n">id_or_name</span>
     <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">id_or_name</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">id</span> <span class="o">=</span> <span class="kc">None</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">id_or_name</span>
     <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">id_or_name</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">id</span> <span class="o">=</span> <span class="n">id_or_name</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="kc">None</span>
     <span class="k">else</span><span class="p">:</span>
       <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">&#39;Unexpected type of id_or_name: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">id_or_name</span><span class="p">)</span>

   <span class="k">def</span> <span class="fm">__lt__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">):</span>
     <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">IdOrName</span><span class="p">):</span>
       <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__lt__</span><span class="p">(</span><span class="n">other</span><span class="p">)</span>

     <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">id</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="k">if</span> <span class="n">other</span><span class="o">.</span><span class="n">id</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
         <span class="k">return</span> <span class="kc">True</span>
       <span class="k">else</span><span class="p">:</span>
         <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">id</span> <span class="o">&lt;</span> <span class="n">other</span><span class="o">.</span><span class="n">id</span>

     <span class="k">if</span> <span class="n">other</span><span class="o">.</span><span class="n">id</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="k">return</span> <span class="kc">False</span>

     <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">&lt;</span> <span class="n">other</span><span class="o">.</span><span class="n">name</span>

   <span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">):</span>
     <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">IdOrName</span><span class="p">):</span>
       <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__eq__</span><span class="p">(</span><span class="n">other</span><span class="p">)</span>
     <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">id</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">id</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">name</span>

   <span class="k">def</span> <span class="fm">__hash__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
     <span class="k">return</span> <span class="nb">hash</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">other</span><span class="p">))</span>


 <span class="k">def</span> <span class="nf">client_key_sort_key</span><span class="p">(</span><span class="n">client_key</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Key function for sorting lists of ``google.cloud.datastore.key.Key``.&quot;&quot;&quot;</span>
   <span class="n">sort_key</span> <span class="o">=</span> <span class="p">[</span><span class="n">client_key</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="n">client_key</span><span class="o">.</span><span class="n">namespace</span> <span class="ow">or</span> <span class="s1">&#39;&#39;</span><span class="p">]</span>
   <span class="c1"># A key path is made up of (kind, id_or_name) pairs. The last pair might be</span>
   <span class="c1"># missing an id_or_name.</span>
   <span class="n">flat_path</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">client_key</span><span class="o">.</span><span class="n">flat_path</span><span class="p">)</span>
   <span class="k">while</span> <span class="n">flat_path</span><span class="p">:</span>
     <span class="n">sort_key</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">flat_path</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</span><span class="p">))</span>  <span class="c1"># kind</span>
     <span class="k">if</span> <span class="n">flat_path</span><span class="p">:</span>
       <span class="n">sort_key</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">IdOrName</span><span class="p">(</span><span class="n">flat_path</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</span><span class="p">)))</span>

   <span class="k">return</span> <span class="n">sort_key</span>


 <span class="k">def</span> <span class="nf">_get_scatter_keys</span><span class="p">(</span><span class="n">client</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Gets a list of split keys given a desired number of splits.</span>

 <span class="sd">  This list will contain multiple split keys for each split. Only a single split</span>
 <span class="sd">  key will be chosen as the split point, however providing multiple keys allows</span>
 <span class="sd">  for more uniform sharding.</span>

 <span class="sd">  Args:</span>
 <span class="sd">    client: the client to datastore containing the data.</span>
 <span class="sd">    query: the user query.</span>
 <span class="sd">    num_splits: the number of desired splits.</span>

 <span class="sd">  Returns:</span>
 <span class="sd">    A list of scatter keys returned by Datastore.</span>
 <span class="sd">  &quot;&quot;&quot;</span>
   <span class="n">scatter_point_query</span> <span class="o">=</span> <span class="n">_create_scatter_query</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">)</span>
   <span class="n">client_query</span> <span class="o">=</span> <span class="n">scatter_point_query</span><span class="o">.</span><span class="n">_to_client_query</span><span class="p">(</span><span class="n">client</span><span class="p">)</span>
   <span class="n">client_key_splits</span> <span class="o">=</span> <span class="p">[</span>
       <span class="n">client_entity</span><span class="o">.</span><span class="n">key</span> <span class="k">for</span> <span class="n">client_entity</span> <span class="ow">in</span> <span class="n">client_query</span><span class="o">.</span><span class="n">fetch</span><span class="p">(</span>
           <span class="n">client</span><span class="o">=</span><span class="n">client</span><span class="p">,</span> <span class="n">limit</span><span class="o">=</span><span class="n">scatter_point_query</span><span class="o">.</span><span class="n">limit</span><span class="p">)</span>
   <span class="p">]</span>
   <span class="n">client_key_splits</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">client_key_sort_key</span><span class="p">)</span>
   <span class="k">return</span> <span class="n">client_key_splits</span>


 <span class="k">def</span> <span class="nf">_get_split_key</span><span class="p">(</span><span class="n">client_keys</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Given a list of keys and a number of splits find the keys to split on.</span>

 <span class="sd">  Args:</span>
 <span class="sd">    client_keys: the list of keys.</span>
 <span class="sd">    num_splits: the number of splits.</span>

 <span class="sd">  Returns:</span>
 <span class="sd">    A list of keys to split on.</span>

 <span class="sd">  &quot;&quot;&quot;</span>

   <span class="c1"># If the number of keys is less than the number of splits, we are limited</span>
   <span class="c1"># in the number of splits we can make.</span>
   <span class="k">if</span> <span class="ow">not</span> <span class="n">client_keys</span> <span class="ow">or</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">client_keys</span><span class="p">)</span> <span class="o">&lt;</span> <span class="p">(</span><span class="n">num_splits</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)):</span>
     <span class="k">return</span> <span class="n">client_keys</span>

   <span class="c1"># Calculate the number of keys per split. This should be KEYS_PER_SPLIT,</span>
   <span class="c1"># but may be less if there are not KEYS_PER_SPLIT * (numSplits - 1) scatter</span>
   <span class="c1"># entities.</span>
   <span class="c1">#</span>
   <span class="c1"># Consider the following dataset, where - represents an entity and</span>
   <span class="c1"># * represents an entity that is returned as a scatter entity:</span>
   <span class="c1"># ||---*-----*----*-----*-----*------*----*----||</span>
   <span class="c1"># If we want 4 splits in this data, the optimal split would look like:</span>
   <span class="c1"># ||---*-----*----*-----*-----*------*----*----||</span>
   <span class="c1">#            |          |            |</span>
   <span class="c1"># The scatter keys in the last region are not useful to us, so we never</span>
   <span class="c1"># request them:</span>
   <span class="c1"># ||---*-----*----*-----*-----*------*---------||</span>
   <span class="c1">#            |          |            |</span>
   <span class="c1"># With 6 scatter keys we want to set scatter points at indexes: 1, 3, 5.</span>
   <span class="c1">#</span>
   <span class="c1"># We keep this as a float so that any &quot;fractional&quot; keys per split get</span>
   <span class="c1"># distributed throughout the splits and don&#39;t make the last split</span>
   <span class="c1"># significantly larger than the rest.</span>

   <span class="n">num_keys_per_split</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="mf">1.0</span><span class="p">,</span> <span class="nb">float</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">client_keys</span><span class="p">))</span> <span class="o">/</span> <span class="p">(</span><span class="n">num_splits</span> <span class="o">-</span> <span class="mi">1</span><span class="p">))</span>

   <span class="n">split_client_keys</span> <span class="o">=</span> <span class="p">[]</span>

   <span class="c1"># Grab the last sample for each split, otherwise the first split will be too</span>
   <span class="c1"># small.</span>
   <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span>
     <span class="n">split_index</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">i</span> <span class="o">*</span> <span class="n">num_keys_per_split</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span>
     <span class="n">split_client_keys</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">client_keys</span><span class="p">[</span><span class="n">split_index</span><span class="p">])</span>

   <span class="k">return</span> <span class="n">split_client_keys</span>


 <span class="k">def</span> <span class="nf">_create_split</span><span class="p">(</span><span class="n">last_client_key</span><span class="p">,</span> <span class="n">next_client_key</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
   <span class="sd">&quot;&quot;&quot;Create a new {@link Query} given the query and range.</span>

 <span class="sd">  Args:</span>
 <span class="sd">    last_client_key: the previous key. If null then assumed to be the beginning.</span>
 <span class="sd">    next_client_key: the next key. If null then assumed to be the end.</span>
 <span class="sd">    query: query to base the split query on.</span>

 <span class="sd">  Returns:</span>
 <span class="sd">    A split query with fetches entities in the range [last_key, next_client_key)</span>
 <span class="sd">  &quot;&quot;&quot;</span>
   <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">last_client_key</span> <span class="ow">or</span> <span class="n">next_client_key</span><span class="p">):</span>
     <span class="k">return</span> <span class="n">query</span>

   <span class="n">split_query</span> <span class="o">=</span> <span class="n">query</span><span class="o">.</span><span class="n">clone</span><span class="p">()</span>
   <span class="c1"># Copy filters and possible convert the default empty tuple to empty list.</span>
   <span class="n">filters</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">split_query</span><span class="o">.</span><span class="n">filters</span><span class="p">)</span>

   <span class="k">if</span> <span class="n">last_client_key</span><span class="p">:</span>
     <span class="n">filters</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">KEY_PROPERTY_NAME</span><span class="p">,</span> <span class="s1">&#39;&gt;=&#39;</span><span class="p">,</span> <span class="n">last_client_key</span><span class="p">))</span>
   <span class="k">if</span> <span class="n">next_client_key</span><span class="p">:</span>
     <span class="n">filters</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">KEY_PROPERTY_NAME</span><span class="p">,</span> <span class="s1">&#39;&lt;&#39;</span><span class="p">,</span> <span class="n">next_client_key</span><span class="p">))</span>

   <span class="n">split_query</span><span class="o">.</span><span class="n">filters</span> <span class="o">=</span> <span class="n">filters</span>
   <span class="k">return</span> <span class="n">split_query</span>
 </pre></div>

            </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/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.

 </footer>

         </div>
       </div>

     </section>

   </div>


   <script type="text/javascript">
       jQuery(function () {
           SphinxRtdTheme.Navigation.enable(true);
       });
   </script>


 </body>
 </html>