| |
| |
| <!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.source_test_utils — 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.source_test_utils</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.source_test_utils</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">"""Helper functions and test harnesses for source implementations.</span> |
| |
| <span class="sd">This module contains helper functions and test harnesses for checking</span> |
| <span class="sd">correctness of source (a subclass of ``iobase.BoundedSource``) and range</span> |
| <span class="sd">tracker (a subclass of``iobase.RangeTracker``) implementations.</span> |
| |
| <span class="sd">Contains a few lightweight utilities (e.g. reading items from a source such as</span> |
| <span class="sd">``readFromSource()``, as well as heavyweight property testing and stress</span> |
| <span class="sd">testing harnesses that help getting a large amount of test coverage with few</span> |
| <span class="sd">code.</span> |
| |
| <span class="sd">Most notable ones are:</span> |
| <span class="sd">* ``assertSourcesEqualReferenceSource()`` helps testing that the data read by</span> |
| <span class="sd">the union of sources produced by ``BoundedSource.split()`` is the same as data</span> |
| <span class="sd">read by the original source.</span> |
| <span class="sd">* If your source implements dynamic work rebalancing, use the</span> |
| <span class="sd">``assertSplitAtFraction()`` family of functions - they test behavior of</span> |
| <span class="sd">``RangeTracker.try_split()``, in particular, that various consistency</span> |
| <span class="sd">properties are respected and the total set of data read by the source is</span> |
| <span class="sd">preserved when splits happen. Use ``assertSplitAtFractionBehavior()`` to test</span> |
| <span class="sd">individual cases of ``RangeTracker.try_split()`` and use</span> |
| <span class="sd">``assertSplitAtFractionExhaustive()`` as a heavy-weight stress test including</span> |
| <span class="sd">concurrency. We strongly recommend to use both.</span> |
| |
| <span class="sd">For example usages, see the unit tests of modules such as</span> |
| <span class="sd"> * apache_beam.io.source_test_utils_test.py</span> |
| <span class="sd"> * apache_beam.io.avroio_test.py</span> |
| <span class="sd">"""</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">import</span> <span class="nn">weakref</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">next</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">range</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">namedtuple</span> |
| <span class="kn">from</span> <span class="nn">multiprocessing.pool</span> <span class="k">import</span> <span class="n">ThreadPool</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="k">import</span> <span class="n">iobase</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'read_from_source'</span><span class="p">,</span> |
| <span class="s1">'assert_sources_equal_reference_source'</span><span class="p">,</span> |
| <span class="s1">'assert_reentrant_reads_succeed'</span><span class="p">,</span> |
| <span class="s1">'assert_split_at_fraction_behavior'</span><span class="p">,</span> |
| <span class="s1">'assert_split_at_fraction_binary'</span><span class="p">,</span> |
| <span class="s1">'assert_split_at_fraction_exhaustive'</span><span class="p">,</span> |
| <span class="s1">'assert_split_at_fraction_fails'</span><span class="p">,</span> |
| <span class="s1">'assert_split_at_fraction_succeeds_and_consistent'</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">ExpectedSplitOutcome</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="n">MUST_SUCCEED_AND_BE_CONSISTENT</span> <span class="o">=</span> <span class="mi">1</span> |
| <span class="n">MUST_FAIL</span> <span class="o">=</span> <span class="mi">2</span> |
| <span class="n">MUST_BE_CONSISTENT_IF_SUCCEEDS</span> <span class="o">=</span> <span class="mi">3</span> |
| |
| |
| <span class="n">SplitAtFractionResult</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span> |
| <span class="s1">'SplitAtFractionResult'</span><span class="p">,</span> <span class="s1">'num_primary_items num_residual_items'</span><span class="p">)</span> |
| |
| <span class="n">SplitFractionStatistics</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span> |
| <span class="s1">'SplitFractionStatistics'</span><span class="p">,</span> |
| <span class="s1">'successful_fractions non_trivial_fractions'</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="read_from_source"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.read_from_source">[docs]</a><span class="k">def</span> <span class="nf">read_from_source</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Reads elements from the given ```BoundedSource```.</span> |
| |
| <span class="sd"> Only reads elements within the given position range.</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> source (~apache_beam.io.iobase.BoundedSource):</span> |
| <span class="sd"> :class:`~apache_beam.io.iobase.BoundedSource` implementation.</span> |
| <span class="sd"> start_position (int): start position for reading.</span> |
| <span class="sd"> stop_position (int): stop position for reading.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> List[str]: the set of values read from the sources.</span> |
| <span class="sd"> """</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">range_tracker</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span><span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">,</span> <span class="n">iobase</span><span class="o">.</span><span class="n">RangeTracker</span><span class="p">)</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">reader</span><span class="p">:</span> |
| <span class="n">values</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">values</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_ThreadPool</span><span class="p">(</span><span class="n">threads</span><span class="p">):</span> |
| <span class="c1"># ThreadPool crashes in old versions of Python (< 2.7.5) if created from a</span> |
| <span class="c1"># child thread. (http://bugs.python.org/issue10015)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">threading</span><span class="o">.</span><span class="n">current_thread</span><span class="p">(),</span> <span class="s1">'_children'</span><span class="p">):</span> |
| <span class="n">threading</span><span class="o">.</span><span class="n">current_thread</span><span class="p">()</span><span class="o">.</span><span class="n">_children</span> <span class="o">=</span> <span class="n">weakref</span><span class="o">.</span><span class="n">WeakKeyDictionary</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">ThreadPool</span><span class="p">(</span><span class="n">threads</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="assert_sources_equal_reference_source"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_sources_equal_reference_source">[docs]</a><span class="k">def</span> <span class="nf">assert_sources_equal_reference_source</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">,</span> <span class="n">sources_info</span><span class="p">):</span> |
| <span class="sd">"""Tests if a reference source is equal to a given set of sources.</span> |
| |
| <span class="sd"> Given a reference source (a :class:`~apache_beam.io.iobase.BoundedSource`</span> |
| <span class="sd"> and a position range) and a list of sources, assert that the union of the</span> |
| <span class="sd"> records read from the list of sources is equal to the records read from the</span> |
| <span class="sd"> reference source.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> reference_source_info\</span> |
| <span class="sd"> (Tuple[~apache_beam.io.iobase.BoundedSource, int, int]):</span> |
| <span class="sd"> a three-tuple that gives the reference</span> |
| <span class="sd"> :class:`~apache_beam.io.iobase.BoundedSource`, position to start</span> |
| <span class="sd"> reading at, and position to stop reading at.</span> |
| <span class="sd"> sources_info\</span> |
| <span class="sd"> (Iterable[Tuple[~apache_beam.io.iobase.BoundedSource, int, int]]):</span> |
| <span class="sd"> a set of sources. Each source is a three-tuple that is of the same</span> |
| <span class="sd"> format described above.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ~exceptions.ValueError: if the set of data produced by the reference source</span> |
| <span class="sd"> and the given set of sources are not equivalent.</span> |
| |
| <span class="sd"> """</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span> <span class="ow">and</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span> <span class="ow">and</span> |
| <span class="nb">isinstance</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">iobase</span><span class="o">.</span><span class="n">BoundedSource</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'reference_source_info must a three-tuple where first'</span> |
| <span class="s1">'item of the tuple gives a '</span> |
| <span class="s1">'iobase.BoundedSource. Received: </span><span class="si">%r</span><span class="s1">'</span> |
| <span class="o">%</span> <span class="n">reference_source_info</span><span class="p">)</span> |
| <span class="n">reference_records</span> <span class="o">=</span> <span class="n">read_from_source</span><span class="p">(</span> |
| <span class="o">*</span><span class="n">reference_source_info</span><span class="p">)</span> |
| |
| <span class="n">source_records</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">source_info</span> <span class="ow">in</span> <span class="n">sources_info</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">source_info</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_info</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">source_info</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span> <span class="ow">and</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">source_info</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span> <span class="ow">and</span> |
| <span class="nb">isinstance</span><span class="p">(</span><span class="n">source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">iobase</span><span class="o">.</span><span class="n">BoundedSource</span><span class="p">)):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'source_info must a three tuple where first'</span> |
| <span class="s1">'item of the tuple gives a '</span> |
| <span class="s1">'iobase.BoundedSource. Received: </span><span class="si">%r</span><span class="s1">'</span> |
| <span class="o">%</span> <span class="n">source_info</span><span class="p">)</span> |
| <span class="k">if</span> <span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">())</span> <span class="o">!=</span> |
| <span class="nb">type</span><span class="p">(</span><span class="n">source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">())):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Reference source </span><span class="si">%r</span><span class="s1"> and the source </span><span class="si">%r</span><span class="s1"> must use the same coder. '</span> |
| <span class="s1">'They are using </span><span class="si">%r</span><span class="s1"> and </span><span class="si">%r</span><span class="s1"> respectively instead.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">reference_source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> |
| <span class="nb">type</span><span class="p">(</span><span class="n">reference_source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">()),</span> |
| <span class="nb">type</span><span class="p">(</span><span class="n">source_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">())))</span> |
| <span class="n">source_records</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">read_from_source</span><span class="p">(</span><span class="o">*</span><span class="n">source_info</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">reference_records</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_records</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Reference source must produce the same number of records as the '</span> |
| <span class="s1">'list of sources. Number of records were </span><span class="si">%d</span><span class="s1"> and </span><span class="si">%d</span><span class="s1"> instead.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">reference_records</span><span class="p">),</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_records</span><span class="p">)))</span> |
| |
| <span class="k">if</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">reference_records</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">source_records</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Reference source and provided list of sources must produce the '</span> |
| <span class="s1">'same set of records.'</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="assert_reentrant_reads_succeed"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_reentrant_reads_succeed">[docs]</a><span class="k">def</span> <span class="nf">assert_reentrant_reads_succeed</span><span class="p">(</span><span class="n">source_info</span><span class="p">):</span> |
| <span class="sd">"""Tests if a given source can be read in a reentrant manner.</span> |
| |
| <span class="sd"> Assume that given source produces the set of values ``{v1, v2, v3, ... vn}``.</span> |
| <span class="sd"> For ``i`` in range ``[1, n-1]`` this method performs a reentrant read after</span> |
| <span class="sd"> reading ``i`` elements and verifies that both the original and reentrant read</span> |
| <span class="sd"> produce the expected set of values.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source_info (Tuple[~apache_beam.io.iobase.BoundedSource, int, int]):</span> |
| <span class="sd"> a three-tuple that gives the reference</span> |
| <span class="sd"> :class:`~apache_beam.io.iobase.BoundedSource`, position to start reading</span> |
| <span class="sd"> at, and a position to stop reading at.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ~exceptions.ValueError: if source is too trivial or reentrant read result</span> |
| <span class="sd"> in an incorrect read.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span> <span class="o">=</span> <span class="n">source_info</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">iobase</span><span class="o">.</span><span class="n">BoundedSource</span><span class="p">)</span> |
| |
| <span class="n">expected_values</span> <span class="o">=</span> <span class="p">[</span><span class="n">val</span> <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span> |
| <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">))]</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">expected_values</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Source is too trivial since it produces only </span><span class="si">%d</span><span class="s1"> '</span> |
| <span class="s1">'values. Please give a source that reads at least 2 '</span> |
| <span class="s1">'values.'</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">expected_values</span><span class="p">))</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="nb">len</span><span class="p">(</span><span class="n">expected_values</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="n">read_iter</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span> |
| <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">))</span> |
| <span class="n">original_read</span> <span class="o">=</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">i</span><span class="p">):</span> |
| <span class="n">original_read</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">next</span><span class="p">(</span><span class="n">read_iter</span><span class="p">))</span> |
| |
| <span class="c1"># Reentrant read</span> |
| <span class="n">reentrant_read</span> <span class="o">=</span> <span class="p">[</span><span class="n">val</span> <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span> |
| <span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span><span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">))]</span> |
| |
| <span class="c1"># Continuing original read.</span> |
| <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">read_iter</span><span class="p">:</span> |
| <span class="n">original_read</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">val</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">original_read</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">expected_values</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Source did not produce expected values when '</span> |
| <span class="s1">'performing a reentrant read after reading </span><span class="si">%d</span><span class="s1"> values. '</span> |
| <span class="s1">'Expected </span><span class="si">%r</span><span class="s1"> received </span><span class="si">%r</span><span class="s1">.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">expected_values</span><span class="p">,</span> <span class="n">original_read</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">reentrant_read</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">expected_values</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'A reentrant read of source after reading </span><span class="si">%d</span><span class="s1"> values '</span> |
| <span class="s1">'did not produce expected values. Expected </span><span class="si">%r</span><span class="s1"> '</span> |
| <span class="s1">'received </span><span class="si">%r</span><span class="s1">.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">expected_values</span><span class="p">,</span> <span class="n">reentrant_read</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="assert_split_at_fraction_behavior"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_split_at_fraction_behavior">[docs]</a><span class="k">def</span> <span class="nf">assert_split_at_fraction_behavior</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">split_fraction</span><span class="p">,</span> <span class="n">expected_outcome</span><span class="p">):</span> |
| <span class="sd">"""Verifies the behaviour of splitting a source at a given fraction.</span> |
| |
| <span class="sd"> Asserts that splitting a :class:`~apache_beam.io.iobase.BoundedSource` either</span> |
| <span class="sd"> fails after reading **num_items_to_read_before_split** items, or succeeds in</span> |
| <span class="sd"> a way that is consistent according to</span> |
| <span class="sd"> :func:`assert_split_at_fraction_succeeds_and_consistent()`.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source (~apache_beam.io.iobase.BoundedSource): the source to perform</span> |
| <span class="sd"> dynamic splitting on.</span> |
| <span class="sd"> num_items_to_read_before_split (int): number of items to read before</span> |
| <span class="sd"> splitting.</span> |
| <span class="sd"> split_fraction (float): fraction to split at.</span> |
| <span class="sd"> expected_outcome (int): a value from</span> |
| <span class="sd"> :class:`~apache_beam.io.source_test_utils.ExpectedSplitOutcome`.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> Tuple[int, int]: a tuple that gives the number of items produced by reading</span> |
| <span class="sd"> the two ranges produced after dynamic splitting. If splitting did not</span> |
| <span class="sd"> occur, the first value of the tuple will represent the full set of records</span> |
| <span class="sd"> read by the source while the second value of the tuple will be ``-1``.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">iobase</span><span class="o">.</span><span class="n">BoundedSource</span><span class="p">)</span> |
| <span class="n">expected_items</span> <span class="o">=</span> <span class="n">read_from_source</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">,</span> |
| <span class="n">expected_outcome</span><span class="p">)</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">split_fraction</span><span class="p">,</span> <span class="n">expected_outcome</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| |
| <span class="n">range_tracker</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span><span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">,</span> <span class="n">iobase</span><span class="o">.</span><span class="n">RangeTracker</span><span class="p">)</span> |
| <span class="n">current_items</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">)</span> |
| <span class="c1"># Reading 'num_items_to_read_before_split' items.</span> |
| <span class="n">reader_iter</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">reader</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">num_items_to_read_before_split</span><span class="p">):</span> |
| <span class="n">current_items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">next</span><span class="p">(</span><span class="n">reader_iter</span><span class="p">))</span> |
| |
| <span class="n">suggested_split_position</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">position_at_fraction</span><span class="p">(</span> |
| <span class="n">split_fraction</span><span class="p">)</span> |
| |
| <span class="n">stop_position_before_split</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> |
| <span class="n">split_result</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">try_split</span><span class="p">(</span><span class="n">suggested_split_position</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">split_result</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="nb">len</span><span class="p">(</span><span class="n">split_result</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">2</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Split result must be a tuple that contains split '</span> |
| <span class="s1">'position and split fraction. Received: </span><span class="si">%r</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">split_result</span><span class="p">,))</span> |
| |
| <span class="k">if</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> <span class="o">!=</span> <span class="n">split_result</span><span class="p">[</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">'After a successful split, the stop position of the '</span> |
| <span class="s1">'RangeTracker must be the same as the returned split '</span> |
| <span class="s1">'position. Observed </span><span class="si">%r</span><span class="s1"> and </span><span class="si">%r</span><span class="s1"> which are different.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> <span class="o">%</span> <span class="p">(</span><span class="n">split_result</span><span class="p">[</span><span class="mi">0</span><span class="p">],)))</span> |
| |
| <span class="k">if</span> <span class="n">split_fraction</span> <span class="o"><</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">split_fraction</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">'Split fraction must be within the range [0,1]'</span><span class="p">,</span> |
| <span class="s1">'Observed split fraction was </span><span class="si">%r</span><span class="s1">.'</span> <span class="o">%</span> <span class="p">(</span><span class="n">split_result</span><span class="p">[</span><span class="mi">1</span><span class="p">],))</span> |
| |
| <span class="n">stop_position_after_split</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">split_result</span> <span class="ow">and</span> <span class="n">stop_position_after_split</span> <span class="o">==</span> <span class="n">stop_position_before_split</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Stop position </span><span class="si">%r</span><span class="s1"> did not change after a successful '</span> |
| <span class="s1">'split of source </span><span class="si">%r</span><span class="s1"> at fraction </span><span class="si">%r</span><span class="s1">.'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">stop_position_before_split</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="n">expected_outcome</span> <span class="o">==</span> <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_SUCCEED_AND_BE_CONSISTENT</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">split_result</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Expected split of source </span><span class="si">%r</span><span class="s1"> at fraction </span><span class="si">%r</span><span class="s1"> to be '</span> |
| <span class="s1">'successful after reading </span><span class="si">%d</span><span class="s1"> elements. But '</span> |
| <span class="s1">'the split failed.'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">))</span> |
| <span class="k">elif</span> <span class="n">expected_outcome</span> <span class="o">==</span> <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_FAIL</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">split_result</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Expected split of source </span><span class="si">%r</span><span class="s1"> at fraction </span><span class="si">%r</span><span class="s1"> after '</span> |
| <span class="s1">'reading </span><span class="si">%d</span><span class="s1"> elements to fail. But splitting '</span> |
| <span class="s1">'succeeded with result </span><span class="si">%r</span><span class="s1">.'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">split_result</span><span class="p">))</span> |
| |
| <span class="k">elif</span> <span class="p">(</span><span class="n">expected_outcome</span> <span class="o">!=</span> |
| <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_BE_CONSISTENT_IF_SUCCEEDS</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unknown type of expected outcome: </span><span class="si">%r</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="n">expected_outcome</span><span class="p">)</span> |
| <span class="n">current_items</span><span class="o">.</span><span class="n">extend</span><span class="p">([</span><span class="n">value</span> <span class="k">for</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">reader_iter</span><span class="p">])</span> |
| |
| <span class="n">residual_range</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">split_result</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">stop_position_before_split</span><span class="p">)</span> <span class="k">if</span> <span class="n">split_result</span> <span class="k">else</span> <span class="kc">None</span> |
| |
| <span class="k">return</span> <span class="n">_verify_single_split_fraction_result</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">current_items</span><span class="p">,</span> |
| <span class="n">split_result</span><span class="p">,</span> |
| <span class="p">(</span><span class="n">range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">(),</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()),</span> |
| <span class="n">residual_range</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_range_to_str</span><span class="p">(</span><span class="n">start</span><span class="p">,</span> <span class="n">stop</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'['</span> <span class="o">+</span> <span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">start</span><span class="p">)</span> <span class="o">+</span> <span class="s1">','</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">stop</span><span class="p">)</span> <span class="o">+</span> <span class="s1">')'</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_verify_single_split_fraction_result</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">current_items</span><span class="p">,</span> <span class="n">split_successful</span><span class="p">,</span> <span class="n">primary_range</span><span class="p">,</span> |
| <span class="n">residual_range</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">):</span> |
| |
| <span class="k">assert</span> <span class="n">primary_range</span> |
| <span class="n">primary_items</span> <span class="o">=</span> <span class="n">read_from_source</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="o">*</span><span class="n">primary_range</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">split_successful</span><span class="p">:</span> |
| <span class="c1"># For unsuccessful splits, residual_range should be None.</span> |
| <span class="k">assert</span> <span class="ow">not</span> <span class="n">residual_range</span> |
| |
| <span class="n">residual_items</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">read_from_source</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="o">*</span><span class="n">residual_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">split_successful</span> <span class="k">else</span> <span class="p">[])</span> |
| |
| <span class="n">total_items</span> <span class="o">=</span> <span class="n">primary_items</span> <span class="o">+</span> <span class="n">residual_items</span> |
| |
| <span class="k">if</span> <span class="n">current_items</span> <span class="o">!=</span> <span class="n">primary_items</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Current source </span><span class="si">%r</span><span class="s1"> and a source created using the '</span> |
| <span class="s1">'range of the primary source </span><span class="si">%r</span><span class="s1"> determined '</span> |
| <span class="s1">'by performing dynamic work rebalancing at fraction '</span> |
| <span class="s1">'</span><span class="si">%r</span><span class="s1"> produced different values. Expected '</span> |
| <span class="s1">'these sources to produce the same list of values.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">source</span><span class="p">,</span> |
| <span class="n">_range_to_str</span><span class="p">(</span><span class="o">*</span><span class="n">primary_range</span><span class="p">),</span> |
| <span class="n">split_fraction</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">expected_items</span> <span class="o">!=</span> <span class="n">total_items</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Items obtained by reading the source </span><span class="si">%r</span><span class="s1"> for primary '</span> |
| <span class="s1">'and residual ranges </span><span class="si">%s</span><span class="s1"> and </span><span class="si">%s</span><span class="s1"> did not produce the '</span> |
| <span class="s1">'expected list of values.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">source</span><span class="p">,</span> |
| <span class="n">_range_to_str</span><span class="p">(</span><span class="o">*</span><span class="n">primary_range</span><span class="p">),</span> |
| <span class="n">_range_to_str</span><span class="p">(</span><span class="o">*</span><span class="n">residual_range</span><span class="p">)))</span> |
| |
| <span class="n">result</span> <span class="o">=</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">primary_items</span><span class="p">),</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">residual_items</span><span class="p">)</span> <span class="k">if</span> <span class="n">split_successful</span> <span class="k">else</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| |
| <div class="viewcode-block" id="assert_split_at_fraction_succeeds_and_consistent"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent">[docs]</a><span class="k">def</span> <span class="nf">assert_split_at_fraction_succeeds_and_consistent</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">):</span> |
| <span class="sd">"""Verifies some consistency properties of dynamic work rebalancing.</span> |
| |
| <span class="sd"> Equivalent to the following pseudocode:::</span> |
| |
| <span class="sd"> original_range_tracker = source.getRangeTracker(None, None)</span> |
| <span class="sd"> original_reader = source.read(original_range_tracker)</span> |
| <span class="sd"> items_before_split = read N items from original_reader</span> |
| <span class="sd"> suggested_split_position = original_range_tracker.position_for_fraction(</span> |
| <span class="sd"> split_fraction)</span> |
| <span class="sd"> original_stop_position - original_range_tracker.stop_position()</span> |
| <span class="sd"> split_result = range_tracker.try_split()</span> |
| <span class="sd"> split_position, split_fraction = split_result</span> |
| <span class="sd"> primary_range_tracker = source.get_range_tracker(</span> |
| <span class="sd"> original_range_tracker.start_position(), split_position)</span> |
| <span class="sd"> residual_range_tracker = source.get_range_tracker(split_position,</span> |
| <span class="sd"> original_stop_position)</span> |
| |
| <span class="sd"> assert that: items when reading source.read(primary_range_tracker) ==</span> |
| <span class="sd"> items_before_split + items from continuing to read 'original_reader'</span> |
| <span class="sd"> assert that: items when reading source.read(original_range_tracker) =</span> |
| <span class="sd"> items when reading source.read(primary_range_tracker) + items when reading</span> |
| <span class="sd"> source.read(residual_range_tracker)</span> |
| |
| <span class="sd"> Args:</span> |
| |
| <span class="sd"> source: source to perform dynamic work rebalancing on.</span> |
| <span class="sd"> num_items_to_read_before_split: number of items to read before splitting.</span> |
| <span class="sd"> split_fraction: fraction to split at.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">,</span> |
| <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_SUCCEED_AND_BE_CONSISTENT</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="assert_split_at_fraction_fails"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_split_at_fraction_fails">[docs]</a><span class="k">def</span> <span class="nf">assert_split_at_fraction_fails</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">split_fraction</span><span class="p">):</span> |
| <span class="sd">"""Asserts that dynamic work rebalancing at a given fraction fails.</span> |
| |
| <span class="sd"> Asserts that trying to perform dynamic splitting after reading</span> |
| <span class="sd"> 'num_items_to_read_before_split' items from the source fails.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source: source to perform dynamic splitting on.</span> |
| <span class="sd"> num_items_to_read_before_split: number of items to read before splitting.</span> |
| <span class="sd"> split_fraction: fraction to split at.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">,</span> |
| <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_FAIL</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="assert_split_at_fraction_binary"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_split_at_fraction_binary">[docs]</a><span class="k">def</span> <span class="nf">assert_split_at_fraction_binary</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">left_fraction</span><span class="p">,</span> |
| <span class="n">left_result</span><span class="p">,</span> <span class="n">right_fraction</span><span class="p">,</span> <span class="n">right_result</span><span class="p">,</span> <span class="n">stats</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Performs dynamic work rebalancing for fractions within a given range.</span> |
| |
| <span class="sd"> Asserts that given a start position, a source can be split at every</span> |
| <span class="sd"> interesting fraction (halfway between two fractions that differ by at</span> |
| <span class="sd"> least one item) and the results are consistent if a split succeeds.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source: source to perform dynamic splitting on.</span> |
| <span class="sd"> expected_items: total set of items expected when reading the source.</span> |
| <span class="sd"> num_items_to_read_before_split: number of items to read before splitting.</span> |
| <span class="sd"> left_fraction: left fraction for binary splitting.</span> |
| <span class="sd"> left_result: result received by splitting at left fraction.</span> |
| <span class="sd"> right_fraction: right fraction for binary splitting.</span> |
| <span class="sd"> right_result: result received by splitting at right fraction.</span> |
| <span class="sd"> stats: a ``SplitFractionStatistics`` for storing results.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">right_fraction</span> <span class="o">></span> <span class="n">left_fraction</span> |
| |
| <span class="k">if</span> <span class="n">right_fraction</span> <span class="o">-</span> <span class="n">left_fraction</span> <span class="o"><</span> <span class="mf">0.001</span><span class="p">:</span> |
| <span class="c1"># This prevents infinite recursion.</span> |
| <span class="k">return</span> |
| |
| <span class="n">middle_fraction</span> <span class="o">=</span> <span class="p">(</span><span class="n">left_fraction</span> <span class="o">+</span> <span class="n">right_fraction</span><span class="p">)</span> <span class="o">/</span> <span class="mi">2</span> |
| |
| <span class="k">if</span> <span class="n">left_result</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">left_result</span> <span class="o">=</span> <span class="n">_assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">left_fraction</span><span class="p">,</span> |
| <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_BE_CONSISTENT_IF_SUCCEEDS</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">right_result</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">right_result</span> <span class="o">=</span> <span class="n">_assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">right_fraction</span><span class="p">,</span> <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_BE_CONSISTENT_IF_SUCCEEDS</span><span class="p">)</span> |
| |
| <span class="n">middle_result</span> <span class="o">=</span> <span class="n">_assert_split_at_fraction_behavior</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">middle_fraction</span><span class="p">,</span> |
| <span class="n">ExpectedSplitOutcome</span><span class="o">.</span><span class="n">MUST_BE_CONSISTENT_IF_SUCCEEDS</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">middle_result</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">!=</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="n">stats</span><span class="o">.</span><span class="n">successful_fractions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">middle_fraction</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">middle_result</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">stats</span><span class="o">.</span><span class="n">non_trivial_fractions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">middle_fraction</span><span class="p">)</span> |
| |
| <span class="c1"># Two split results are equivalent if primary and residual ranges of them</span> |
| <span class="c1"># produce the same number of records (simply checking the size of primary</span> |
| <span class="c1"># enough since the total number of records is constant).</span> |
| |
| <span class="k">if</span> <span class="n">left_result</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">!=</span> <span class="n">middle_result</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">assert_split_at_fraction_binary</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> <span class="n">left_fraction</span><span class="p">,</span> |
| <span class="n">left_result</span><span class="p">,</span> <span class="n">middle_fraction</span><span class="p">,</span> <span class="n">middle_result</span><span class="p">,</span> <span class="n">stats</span><span class="p">)</span> |
| |
| <span class="c1"># We special case right_fraction=1.0 since that could fail due to being out</span> |
| <span class="c1"># of range. (even if a dynamic split fails at 'middle_fraction' and at</span> |
| <span class="c1"># fraction 1.0, there might be fractions in range ('middle_fraction', 1.0)</span> |
| <span class="c1"># where dynamic splitting succeeds).</span> |
| <span class="k">if</span> <span class="n">right_fraction</span> <span class="o">==</span> <span class="mf">1.0</span> <span class="ow">or</span> <span class="n">middle_result</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">!=</span> <span class="n">right_result</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">assert_split_at_fraction_binary</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_split</span><span class="p">,</span> |
| <span class="n">middle_fraction</span><span class="p">,</span> <span class="n">middle_result</span><span class="p">,</span> <span class="n">right_fraction</span><span class="p">,</span> <span class="n">right_result</span><span class="p">,</span> <span class="n">stats</span><span class="p">)</span></div> |
| |
| |
| <span class="n">MAX_CONCURRENT_SPLITTING_TRIALS_PER_ITEM</span> <span class="o">=</span> <span class="mi">100</span> |
| <span class="n">MAX_CONCURRENT_SPLITTING_TRIALS_TOTAL</span> <span class="o">=</span> <span class="mi">1000</span> |
| |
| |
| <div class="viewcode-block" id="assert_split_at_fraction_exhaustive"><a class="viewcode-back" href="../../../apache_beam.io.source_test_utils.html#apache_beam.io.source_test_utils.assert_split_at_fraction_exhaustive">[docs]</a><span class="k">def</span> <span class="nf">assert_split_at_fraction_exhaustive</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">perform_multi_threaded_test</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="sd">"""Performs and tests dynamic work rebalancing exhaustively.</span> |
| |
| <span class="sd"> Asserts that for each possible start position, a source can be split at</span> |
| <span class="sd"> every interesting fraction (halfway between two fractions that differ by at</span> |
| <span class="sd"> least one item) and the results are consistent if a split succeeds.</span> |
| <span class="sd"> Verifies multi threaded splitting as well.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> source (~apache_beam.io.iobase.BoundedSource): the source to perform</span> |
| <span class="sd"> dynamic splitting on.</span> |
| <span class="sd"> perform_multi_threaded_test (bool): if :data:`True` performs a</span> |
| <span class="sd"> multi-threaded test, otherwise this test is skipped.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ~exceptions.ValueError: if the exhaustive splitting test fails.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">expected_items</span> <span class="o">=</span> <span class="n">read_from_source</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">expected_items</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Source </span><span class="si">%r</span><span class="s1"> is empty.'</span> <span class="o">%</span> <span class="n">source</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">expected_items</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">'Source </span><span class="si">%r</span><span class="s1"> only reads a single item.'</span> <span class="o">%</span> <span class="n">source</span><span class="p">)</span> |
| |
| <span class="n">all_non_trivial_fractions</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="n">any_successful_fractions</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="n">any_non_trivial_fractions</span> <span class="o">=</span> <span class="kc">False</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="nb">len</span><span class="p">(</span><span class="n">expected_items</span><span class="p">)):</span> |
| <span class="n">stats</span> <span class="o">=</span> <span class="n">SplitFractionStatistics</span><span class="p">([],</span> <span class="p">[])</span> |
| |
| <span class="n">assert_split_at_fraction_binary</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">stats</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">stats</span><span class="o">.</span><span class="n">successful_fractions</span><span class="p">:</span> |
| <span class="n">any_successful_fractions</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">if</span> <span class="n">stats</span><span class="o">.</span><span class="n">non_trivial_fractions</span><span class="p">:</span> |
| <span class="n">any_non_trivial_fractions</span> <span class="o">=</span> <span class="kc">True</span> |
| |
| <span class="n">all_non_trivial_fractions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">stats</span><span class="o">.</span><span class="n">non_trivial_fractions</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">any_successful_fractions</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'SplitAtFraction test completed vacuously: no '</span> |
| <span class="s1">'successful split fractions found'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">any_non_trivial_fractions</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'SplitAtFraction test completed vacuously: no non-trivial split '</span> |
| <span class="s1">'fractions found'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">perform_multi_threaded_test</span><span class="p">:</span> |
| <span class="k">return</span> |
| |
| <span class="n">num_total_trials</span> <span class="o">=</span> <span class="mi">0</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="nb">len</span><span class="p">(</span><span class="n">expected_items</span><span class="p">)):</span> |
| <span class="n">non_trivial_fractions</span> <span class="o">=</span> <span class="p">[</span><span class="mf">2.0</span><span class="p">]</span> <span class="c1"># 2.0 is larger than any valid fraction.</span> |
| <span class="n">non_trivial_fractions</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">all_non_trivial_fractions</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> |
| <span class="n">min_non_trivial_fraction</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">non_trivial_fractions</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">min_non_trivial_fraction</span> <span class="o">==</span> <span class="mf">2.0</span><span class="p">:</span> |
| <span class="c1"># This will not happen all the time. Otherwise previous test will fail</span> |
| <span class="c1"># due to vacuousness.</span> |
| <span class="k">continue</span> |
| |
| <span class="n">num_trials</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">have_success</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="n">have_failure</span> <span class="o">=</span> <span class="kc">False</span> |
| |
| <span class="n">thread_pool</span> <span class="o">=</span> <span class="n">_ThreadPool</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="n">num_trials</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="p">(</span><span class="n">num_trials</span> <span class="o">></span> |
| <span class="n">MAX_CONCURRENT_SPLITTING_TRIALS_PER_ITEM</span><span class="p">):</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span> |
| <span class="s1">'After </span><span class="si">%d</span><span class="s1"> concurrent splitting trials at item #</span><span class="si">%d</span><span class="s1">, observed '</span> |
| <span class="s1">'only </span><span class="si">%s</span><span class="s1">, giving up on this item'</span><span class="p">,</span> |
| <span class="n">num_trials</span><span class="p">,</span> |
| <span class="n">i</span><span class="p">,</span> |
| <span class="s1">'success'</span> <span class="k">if</span> <span class="n">have_success</span> <span class="k">else</span> <span class="s1">'failure'</span> |
| <span class="p">)</span> |
| <span class="k">break</span> |
| |
| <span class="k">if</span> <span class="n">_assert_split_at_fraction_concurrent</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">i</span><span class="p">,</span> <span class="n">min_non_trivial_fraction</span><span class="p">,</span> <span class="n">thread_pool</span><span class="p">):</span> |
| <span class="n">have_success</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">have_failure</span> <span class="o">=</span> <span class="kc">True</span> |
| |
| <span class="k">if</span> <span class="n">have_success</span> <span class="ow">and</span> <span class="n">have_failure</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'</span><span class="si">%d</span><span class="s1"> trials to observe both success and failure of '</span> |
| <span class="s1">'concurrent splitting at item #</span><span class="si">%d</span><span class="s1">'</span><span class="p">,</span> <span class="n">num_trials</span><span class="p">,</span> <span class="n">i</span><span class="p">)</span> |
| <span class="k">break</span> |
| <span class="k">finally</span><span class="p">:</span> |
| <span class="n">thread_pool</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> |
| |
| <span class="n">num_total_trials</span> <span class="o">+=</span> <span class="n">num_trials</span> |
| |
| <span class="k">if</span> <span class="n">num_total_trials</span> <span class="o">></span> <span class="n">MAX_CONCURRENT_SPLITTING_TRIALS_TOTAL</span><span class="p">:</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'After </span><span class="si">%d</span><span class="s1"> total concurrent splitting trials, considered '</span> |
| <span class="s1">'only </span><span class="si">%d</span><span class="s1"> items, giving up.'</span><span class="p">,</span> <span class="n">num_total_trials</span><span class="p">,</span> <span class="n">i</span><span class="p">)</span> |
| <span class="k">break</span> |
| |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'</span><span class="si">%d</span><span class="s1"> total concurrent splitting trials for </span><span class="si">%d</span><span class="s1"> items'</span><span class="p">,</span> |
| <span class="n">num_total_trials</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">expected_items</span><span class="p">))</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_assert_split_at_fraction_concurrent</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">num_items_to_read_before_splitting</span><span class="p">,</span> |
| <span class="n">split_fraction</span><span class="p">,</span> <span class="n">thread_pool</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| |
| <span class="n">range_tracker</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">stop_position_before_split</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">range_tracker</span><span class="p">)</span> |
| <span class="n">reader_iter</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">reader</span><span class="p">)</span> |
| |
| <span class="n">current_items</span> <span class="o">=</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">num_items_to_read_before_splitting</span><span class="p">):</span> |
| <span class="n">current_items</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">next</span><span class="p">(</span><span class="n">reader_iter</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">read_or_split</span><span class="p">(</span><span class="n">test_params</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">test_params</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">val</span> <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">test_params</span><span class="p">[</span><span class="mi">1</span><span class="p">]]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">position</span> <span class="o">=</span> <span class="n">test_params</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">position_at_fraction</span><span class="p">(</span><span class="n">test_params</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">test_params</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">try_split</span><span class="p">(</span><span class="n">position</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <span class="n">inputs</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">pool</span> <span class="o">=</span> <span class="n">thread_pool</span> <span class="k">if</span> <span class="n">thread_pool</span> <span class="k">else</span> <span class="n">_ThreadPool</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">inputs</span><span class="o">.</span><span class="n">append</span><span class="p">([</span><span class="kc">True</span><span class="p">,</span> <span class="n">reader_iter</span><span class="p">])</span> |
| <span class="n">inputs</span><span class="o">.</span><span class="n">append</span><span class="p">([</span><span class="kc">False</span><span class="p">,</span> <span class="n">range_tracker</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">])</span> |
| |
| <span class="n">results</span> <span class="o">=</span> <span class="n">pool</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">read_or_split</span><span class="p">,</span> <span class="n">inputs</span><span class="p">)</span> |
| <span class="k">finally</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">thread_pool</span><span class="p">:</span> |
| <span class="n">pool</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> |
| |
| <span class="n">current_items</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">results</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="n">primary_range</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">(),</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">())</span> |
| |
| <span class="n">split_result</span> <span class="o">=</span> <span class="n">results</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="n">residual_range</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">split_result</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">stop_position_before_split</span><span class="p">)</span> <span class="k">if</span> <span class="n">split_result</span> <span class="k">else</span> <span class="kc">None</span> |
| |
| <span class="n">res</span> <span class="o">=</span> <span class="n">_verify_single_split_fraction_result</span><span class="p">(</span> |
| <span class="n">source</span><span class="p">,</span> <span class="n">expected_items</span><span class="p">,</span> <span class="n">current_items</span><span class="p">,</span> <span class="n">split_result</span><span class="p">,</span> |
| <span class="n">primary_range</span><span class="p">,</span> <span class="n">residual_range</span><span class="p">,</span> <span class="n">split_fraction</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">res</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">></span> <span class="mi">0</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> |
