| |
| |
| <!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.query_splitter — 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> »</li> |
| |
| <li><a href="../../../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.gcp.datastore.v1.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.v1.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 "License"); 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 "AS IS" 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">"""Implements a Cloud Datastore query splitter."""</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| |
| <span class="kn">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">builtins</span> <span class="k">import</span> <span class="nb">round</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.io.gcp.datastore.v1</span> <span class="k">import</span> <span class="n">helper</span> |
| |
| <span class="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">query_pb2</span> |
| <span class="kn">from</span> <span class="nn">google.cloud.proto.datastore.v1.query_pb2</span> <span class="k">import</span> <span class="n">PropertyFilter</span> |
| <span class="kn">from</span> <span class="nn">google.cloud.proto.datastore.v1.query_pb2</span> <span class="k">import</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="n">UNSUPPORTED_OPERATORS</span> <span class="o">=</span> <span class="p">[</span><span class="n">PropertyFilter</span><span class="o">.</span><span class="n">LESS_THAN</span><span class="p">,</span> |
| <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">LESS_THAN_OR_EQUAL</span><span class="p">,</span> |
| <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">GREATER_THAN</span><span class="p">,</span> |
| <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">GREATER_THAN_OR_EQUAL</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="n">UNSUPPORTED_OPERATORS</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="c1"># pylint: enable=wrong-import-order, wrong-import-position</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'get_splits'</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| <span class="n">SCATTER_PROPERTY_NAME</span> <span class="o">=</span> <span class="s1">'__scatter__'</span> |
| <span class="n">KEY_PROPERTY_NAME</span> <span class="o">=</span> <span class="s1">'__key__'</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="get_splits"><a class="viewcode-back" href="../../../../../../apache_beam.io.gcp.datastore.v1.query_splitter.html#apache_beam.io.gcp.datastore.v1.query_splitter.get_splits">[docs]</a><span class="k">def</span> <span class="nf">get_splits</span><span class="p">(</span><span class="n">datastore</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">partition</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""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"> datastore: 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"> partition: the partition the query is running in.</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"> """</span> |
| |
| <span class="c1"># Validate that the number of splits is not out of bounds.</span> |
| <span class="k">if</span> <span class="n">num_splits</span> <span class="o"><</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'The number of splits must be greater than 0.'</span><span class="p">)</span> |
| |
| <span class="k">if</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="p">[</span><span class="n">query</span><span class="p">]</span> |
| |
| <span class="n">_validate_query</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">scatter_keys</span> <span class="o">=</span> <span class="n">_get_scatter_keys</span><span class="p">(</span><span class="n">datastore</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">partition</span><span class="p">)</span> |
| <span class="n">last_key</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">for</span> <span class="n">next_key</span> <span class="ow">in</span> <span class="n">_get_split_key</span><span class="p">(</span><span class="n">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_key</span><span class="p">,</span> <span class="n">next_key</span><span class="p">,</span> <span class="n">query</span><span class="p">))</span> |
| <span class="n">last_key</span> <span class="o">=</span> <span class="n">next_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_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_query</span><span class="p">(</span><span class="n">query</span><span class="p">):</span> |
| <span class="sd">""" Verifies that the given query can be properly scattered."""</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="o">.</span><span class="n">kind</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Query must have exactly one kind.'</span><span class="p">)</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="ne">ValueError</span><span class="p">(</span><span class="s1">'Query cannot have any sort orders.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">'limit'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Query cannot have a limit set.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">offset</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Query cannot have an offset set.'</span><span class="p">)</span> |
| |
| <span class="n">_validate_filter</span><span class="p">(</span><span class="n">query</span><span class="o">.</span><span class="n">filter</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_validate_filter</span><span class="p">(</span><span class="nb">filter</span><span class="p">):</span> |
| <span class="sd">"""Validates that we only have allowable filters.</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"> """</span> |
| |
| <span class="k">if</span> <span class="nb">filter</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">'composite_filter'</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">sub_filter</span> <span class="ow">in</span> <span class="nb">filter</span><span class="o">.</span><span class="n">composite_filter</span><span class="o">.</span><span class="n">filters</span><span class="p">:</span> |
| <span class="n">_validate_filter</span><span class="p">(</span><span class="n">sub_filter</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">filter</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">'property_filter'</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">filter</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">op</span> <span class="ow">in</span> <span class="n">UNSUPPORTED_OPERATORS</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Query cannot have any inequality filters.'</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">pass</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">"""Creates a scatter query from the given user query."""</span> |
| |
| <span class="n">scatter_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">for</span> <span class="n">kind</span> <span class="ow">in</span> <span class="n">query</span><span class="o">.</span><span class="n">kind</span><span class="p">:</span> |
| <span class="n">scatter_kind</span> <span class="o">=</span> <span class="n">scatter_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="n">scatter_kind</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">kind</span><span class="p">)</span> |
| |
| <span class="c1"># ascending order</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">scatter_query</span><span class="p">,</span> <span class="n">SCATTER_PROPERTY_NAME</span><span class="p">)</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">scatter_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="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">datastore_helper</span><span class="o">.</span><span class="n">add_projection</span><span class="p">(</span><span class="n">scatter_query</span><span class="p">,</span> <span class="n">KEY_PROPERTY_NAME</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">scatter_query</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_get_scatter_keys</span><span class="p">(</span><span class="n">datastore</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">partition</span><span class="p">):</span> |
| <span class="sd">"""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"> numSplits: the number of desired splits.</span> |
| <span class="sd"> query: the user query.</span> |
| <span class="sd"> partition: the partition to run the query in.</span> |
| <span class="sd"> datastore: the client to datastore containing the data.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A list of scatter keys returned by Datastore.</span> |
| <span class="sd"> """</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">key_splits</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</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="k">if</span> <span class="n">partition</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">partition</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">scatter_point_query</span><span class="p">)</span> |
| |
| <span class="n">resp</span> <span class="o">=</span> <span class="n">datastore</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="n">req</span><span class="p">)</span> |
| <span class="k">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="n">key_splits</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">entity_result</span><span class="o">.</span><span class="n">entity</span><span class="o">.</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="k">if</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> |
| <span class="k">break</span> |
| |
| <span class="n">scatter_point_query</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">scatter_point_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">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="n">key_splits</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">helper</span><span class="o">.</span><span class="n">key_comparator</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">key_splits</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_get_split_key</span><span class="p">(</span><span class="n">keys</span><span class="p">,</span> <span class="n">num_splits</span><span class="p">):</span> |
| <span class="sd">"""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"> 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"> """</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">keys</span> <span class="ow">or</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">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="k">return</span> <span class="n">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 "fractional" keys per split get</span> |
| <span class="c1"># distributed throughout the splits and don'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">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_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_keys</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">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_keys</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_create_split</span><span class="p">(</span><span class="n">last_key</span><span class="p">,</span> <span class="n">next_key</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span> |
| <span class="sd">"""Create a new {@link Query} given the query and range..</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> last_key: the previous key. If null then assumed to be the beginning.</span> |
| <span class="sd"> next_key: the next key. If null then assumed to be the end.</span> |
| <span class="sd"> query: the desired query.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A split query with fetches entities in the range [last_key, next_key)</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="n">last_key</span> <span class="ow">or</span> <span class="n">next_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_pb2</span><span class="o">.</span><span class="n">Query</span><span class="p">()</span> |
| <span class="n">split_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="n">composite_filter</span> <span class="o">=</span> <span class="n">split_query</span><span class="o">.</span><span class="n">filter</span><span class="o">.</span><span class="n">composite_filter</span> |
| <span class="n">composite_filter</span><span class="o">.</span><span class="n">op</span> <span class="o">=</span> <span class="n">CompositeFilter</span><span class="o">.</span><span class="n">AND</span> |
| |
| <span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">HasField</span><span class="p">(</span><span class="s1">'filter'</span><span class="p">):</span> |
| <span class="n">composite_filter</span><span class="o">.</span><span class="n">filters</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">query</span><span class="o">.</span><span class="n">filter</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">last_key</span><span class="p">:</span> |
| <span class="n">lower_bound</span> <span class="o">=</span> <span class="n">composite_filter</span><span class="o">.</span><span class="n">filters</span><span class="o">.</span><span class="n">add</span><span class="p">()</span> |
| <span class="n">lower_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">property</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">KEY_PROPERTY_NAME</span> |
| <span class="n">lower_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">op</span> <span class="o">=</span> <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">GREATER_THAN_OR_EQUAL</span> |
| <span class="n">lower_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">key_value</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">last_key</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">next_key</span><span class="p">:</span> |
| <span class="n">upper_bound</span> <span class="o">=</span> <span class="n">composite_filter</span><span class="o">.</span><span class="n">filters</span><span class="o">.</span><span class="n">add</span><span class="p">()</span> |
| <span class="n">upper_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">property</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">KEY_PROPERTY_NAME</span> |
| <span class="n">upper_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">op</span> <span class="o">=</span> <span class="n">PropertyFilter</span><span class="o">.</span><span class="n">LESS_THAN</span> |
| <span class="n">upper_bound</span><span class="o">.</span><span class="n">property_filter</span><span class="o">.</span><span class="n">value</span><span class="o">.</span><span class="n">key_value</span><span class="o">.</span><span class="n">CopyFrom</span><span class="p">(</span><span class="n">next_key</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">split_query</span> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright . |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/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> |