| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="./"> |
| <head> |
| <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.io.source_test_utils module — Apache Beam 2.67.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="_static/jquery.js?v=5d32c60e"></script> |
| <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="_static/documentation_options.js?v=959b4fbe"></script> |
| <script src="_static/doctools.js?v=9a2dae69"></script> |
| <script src="_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="_static/js/theme.js"></script> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.io.textio module" href="apache_beam.io.textio.html" /> |
| <link rel="prev" title="apache_beam.io.snowflake module" href="apache_beam.io.snowflake.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| <div class="wy-grid-for-nav"> |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="index.html" class="icon icon-home"> |
| Apache Beam |
| </a> |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="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="Navigation menu"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="apache_beam.io.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.io.html#submodules">Submodules</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.avroio.html">apache_beam.io.avroio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.concat_source.html">apache_beam.io.concat_source module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.debezium.html">apache_beam.io.debezium module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filebasedsink.html">apache_beam.io.filebasedsink module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filebasedsource.html">apache_beam.io.filebasedsource module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.fileio.html">apache_beam.io.fileio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystem.html">apache_beam.io.filesystem module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystemio.html">apache_beam.io.filesystemio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.filesystems.html">apache_beam.io.filesystems module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.hadoopfilesystem.html">apache_beam.io.hadoopfilesystem module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.iobase.html">apache_beam.io.iobase module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.jdbc.html">apache_beam.io.jdbc module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.kafka.html">apache_beam.io.kafka module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.kinesis.html">apache_beam.io.kinesis module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.localfilesystem.html">apache_beam.io.localfilesystem module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.mongodbio.html">apache_beam.io.mongodbio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.parquetio.html">apache_beam.io.parquetio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.range_trackers.html">apache_beam.io.range_trackers module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.requestresponse.html">apache_beam.io.requestresponse module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.restriction_trackers.html">apache_beam.io.restriction_trackers module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.snowflake.html">apache_beam.io.snowflake module</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">apache_beam.io.source_test_utils module</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.read_from_source"><code class="docutils literal notranslate"><span class="pre">read_from_source()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_sources_equal_reference_source"><code class="docutils literal notranslate"><span class="pre">assert_sources_equal_reference_source()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_reentrant_reads_succeed"><code class="docutils literal notranslate"><span class="pre">assert_reentrant_reads_succeed()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_behavior"><code class="docutils literal notranslate"><span class="pre">assert_split_at_fraction_behavior()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_binary"><code class="docutils literal notranslate"><span class="pre">assert_split_at_fraction_binary()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_exhaustive"><code class="docutils literal notranslate"><span class="pre">assert_split_at_fraction_exhaustive()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_fails"><code class="docutils literal notranslate"><span class="pre">assert_split_at_fraction_fails()</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent"><code class="docutils literal notranslate"><span class="pre">assert_split_at_fraction_succeeds_and_consistent()</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.textio.html">apache_beam.io.textio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.tfrecordio.html">apache_beam.io.tfrecordio module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.utils.html">apache_beam.io.utils module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.io.watermark_estimators.html">apache_beam.io.watermark_estimators module</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.testing.html">apache_beam.testing 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> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" > |
| <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="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="breadcrumb-item active">apache_beam.io.source_test_utils module</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="_sources/apache_beam.io.source_test_utils.rst.txt" rel="nofollow"> View page source</a> |
| </li> |
| </ul> |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <section id="module-apache_beam.io.source_test_utils"> |
| <span id="apache-beam-io-source-test-utils-module"></span><h1>apache_beam.io.source_test_utils module<a class="headerlink" href="#module-apache_beam.io.source_test_utils" title="Link to this heading"></a></h1> |
| <p>Helper functions and test harnesses for source implementations.</p> |
| <p>This module contains helper functions and test harnesses for checking |
| correctness of source (a subclass of <code class="docutils literal notranslate"><span class="pre">iobase.BoundedSource</span></code>) and range |
| tracker (a subclass of``iobase.RangeTracker``) implementations.</p> |
| <p>Contains a few lightweight utilities (e.g. reading items from a source such as |
| <code class="docutils literal notranslate"><span class="pre">readFromSource()</span></code>, as well as heavyweight property testing and stress |
| testing harnesses that help getting a large amount of test coverage with few |
| code.</p> |
| <p>Most notable ones are: |
| * <code class="docutils literal notranslate"><span class="pre">assertSourcesEqualReferenceSource()</span></code> helps testing that the data read by |
| the union of sources produced by <code class="docutils literal notranslate"><span class="pre">BoundedSource.split()</span></code> is the same as data |
| read by the original source. |
| * If your source implements dynamic work rebalancing, use the |
| <code class="docutils literal notranslate"><span class="pre">assertSplitAtFraction()</span></code> family of functions - they test behavior of |
| <code class="docutils literal notranslate"><span class="pre">RangeTracker.try_split()</span></code>, in particular, that various consistency |
| properties are respected and the total set of data read by the source is |
| preserved when splits happen. Use <code class="docutils literal notranslate"><span class="pre">assertSplitAtFractionBehavior()</span></code> to test |
| individual cases of <code class="docutils literal notranslate"><span class="pre">RangeTracker.try_split()</span></code> and use |
| <code class="docutils literal notranslate"><span class="pre">assertSplitAtFractionExhaustive()</span></code> as a heavy-weight stress test including |
| concurrency. We strongly recommend to use both.</p> |
| <dl class="simple"> |
| <dt>For example usages, see the unit tests of modules such as</dt><dd><ul class="simple"> |
| <li><p>apache_beam.io.source_test_utils_test.py</p></li> |
| <li><p>apache_beam.io.avroio_test.py</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.read_from_source"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">read_from_source</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stop_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#read_from_source"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.read_from_source" title="Link to this definition"></a></dt> |
| <dd><p>Reads elements from the given <code class="docutils literal notranslate"><span class="pre">`BoundedSource`</span></code>.</p> |
| <p>Only reads elements within the given position range. |
| :param source: <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><code class="xref py py-class docutils literal notranslate"><span class="pre">BoundedSource</span></code></a> implementation. |
| :type source: ~apache_beam.io.iobase.BoundedSource |
| :param start_position: start position for reading. |
| :type start_position: int |
| :param stop_position: stop position for reading. |
| :type stop_position: int</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Returns<span class="colon">:</span></dt> |
| <dd class="field-odd"><p>the set of values read from the sources.</p> |
| </dd> |
| <dt class="field-even">Return type<span class="colon">:</span></dt> |
| <dd class="field-even"><p>List[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)">str</a>]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_sources_equal_reference_source"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_sources_equal_reference_source</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">reference_source_info</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sources_info</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_sources_equal_reference_source"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_sources_equal_reference_source" title="Link to this definition"></a></dt> |
| <dd><p>Tests if a reference source is equal to a given set of sources.</p> |
| <p>Given a reference source (a <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><code class="xref py py-class docutils literal notranslate"><span class="pre">BoundedSource</span></code></a> |
| and a position range) and a list of sources, assert that the union of the |
| records read from the list of sources is equal to the records read from the |
| reference source.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>reference_source_info</strong> (<em>Tuple</em><em>[</em><a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><em>BoundedSource</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>]</em>) – a three-tuple that gives the reference |
| <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><code class="xref py py-class docutils literal notranslate"><span class="pre">BoundedSource</span></code></a>, position to start |
| reading at, and position to stop reading at.</p></li> |
| <li><p><strong>sources_info</strong> (<em>Iterable</em><em>[</em><em>Tuple</em><em>[</em><a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><em>BoundedSource</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>]</em><em>]</em>) – a set of sources. Each source is a three-tuple that is of the same |
| format described above.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#ValueError" title="(in Python v3.13)"><strong>ValueError</strong></a> – if the set of data produced by the reference source |
| and the given set of sources are not equivalent.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_reentrant_reads_succeed"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_reentrant_reads_succeed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_info</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_reentrant_reads_succeed"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_reentrant_reads_succeed" title="Link to this definition"></a></dt> |
| <dd><p>Tests if a given source can be read in a reentrant manner.</p> |
| <p>Assume that given source produces the set of values <code class="docutils literal notranslate"><span class="pre">{v1,</span> <span class="pre">v2,</span> <span class="pre">v3,</span> <span class="pre">...</span> <span class="pre">vn}</span></code>. |
| For <code class="docutils literal notranslate"><span class="pre">i</span></code> in range <code class="docutils literal notranslate"><span class="pre">[1,</span> <span class="pre">n-1]</span></code> this method performs a reentrant read after |
| reading <code class="docutils literal notranslate"><span class="pre">i</span></code> elements and verifies that both the original and reentrant read |
| produce the expected set of values.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>source_info</strong> (<em>Tuple</em><em>[</em><a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><em>BoundedSource</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>, </em><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a><em>]</em>) – a three-tuple that gives the reference |
| <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><code class="xref py py-class docutils literal notranslate"><span class="pre">BoundedSource</span></code></a>, position to start reading |
| at, and a position to stop reading at.</p> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#ValueError" title="(in Python v3.13)"><strong>ValueError</strong></a> – if source is too trivial or reentrant read result |
| in an incorrect read.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_split_at_fraction_behavior"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_split_at_fraction_behavior</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_items_to_read_before_split</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_fraction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_outcome</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_split_at_fraction_behavior"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_behavior" title="Link to this definition"></a></dt> |
| <dd><p>Verifies the behaviour of splitting a source at a given fraction.</p> |
| <p>Asserts that splitting a <a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><code class="xref py py-class docutils literal notranslate"><span class="pre">BoundedSource</span></code></a> either |
| fails after reading <strong>num_items_to_read_before_split</strong> items, or succeeds in |
| a way that is consistent according to |
| <a class="reference internal" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent" title="apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent"><code class="xref py py-func docutils literal notranslate"><span class="pre">assert_split_at_fraction_succeeds_and_consistent()</span></code></a>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source</strong> (<a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><em>BoundedSource</em></a>) – the source to perform |
| dynamic splitting on.</p></li> |
| <li><p><strong>num_items_to_read_before_split</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a>) – number of items to read before |
| splitting.</p></li> |
| <li><p><strong>split_fraction</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><em>float</em></a>) – fraction to split at.</p></li> |
| <li><p><strong>expected_outcome</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><em>int</em></a>) – a value from |
| <code class="xref py py-class docutils literal notranslate"><span class="pre">ExpectedSplitOutcome</span></code>.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns<span class="colon">:</span></dt> |
| <dd class="field-even"><p>a tuple that gives the number of items produced by reading |
| the two ranges produced after dynamic splitting. If splitting did not |
| occur, the first value of the tuple will represent the full set of records |
| read by the source while the second value of the tuple will be <code class="docutils literal notranslate"><span class="pre">-1</span></code>.</p> |
| </dd> |
| <dt class="field-odd">Return type<span class="colon">:</span></dt> |
| <dd class="field-odd"><p>Tuple[<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)">int</a>, <a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)">int</a>]</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_split_at_fraction_binary"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_split_at_fraction_binary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_items</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_items_to_read_before_split</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">left_fraction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">left_result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">right_fraction</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">right_result</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stats</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stop_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_split_at_fraction_binary"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_binary" title="Link to this definition"></a></dt> |
| <dd><p>Performs dynamic work rebalancing for fractions within a given range.</p> |
| <p>Asserts that given a start position, a source can be split at every |
| interesting fraction (halfway between two fractions that differ by at |
| least one item) and the results are consistent if a split succeeds.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source</strong> – source to perform dynamic splitting on.</p></li> |
| <li><p><strong>expected_items</strong> – total set of items expected when reading the source.</p></li> |
| <li><p><strong>num_items_to_read_before_split</strong> – number of items to read before splitting.</p></li> |
| <li><p><strong>left_fraction</strong> – left fraction for binary splitting.</p></li> |
| <li><p><strong>left_result</strong> – result received by splitting at left fraction.</p></li> |
| <li><p><strong>right_fraction</strong> – right fraction for binary splitting.</p></li> |
| <li><p><strong>right_result</strong> – result received by splitting at right fraction.</p></li> |
| <li><p><strong>stats</strong> – a <code class="docutils literal notranslate"><span class="pre">SplitFractionStatistics</span></code> for storing results.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_split_at_fraction_exhaustive"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_split_at_fraction_exhaustive</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">start_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">stop_position</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">perform_multi_threaded_test</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_split_at_fraction_exhaustive"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_exhaustive" title="Link to this definition"></a></dt> |
| <dd><p>Performs and tests dynamic work rebalancing exhaustively.</p> |
| <p>Asserts that for each possible start position, a source can be split at |
| every interesting fraction (halfway between two fractions that differ by at |
| least one item) and the results are consistent if a split succeeds. |
| Verifies multi threaded splitting as well.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source</strong> (<a class="reference internal" href="apache_beam.io.iobase.html#apache_beam.io.iobase.BoundedSource" title="apache_beam.io.iobase.BoundedSource"><em>BoundedSource</em></a>) – the source to perform |
| dynamic splitting on.</p></li> |
| <li><p><strong>perform_multi_threaded_test</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><em>bool</em></a>) – if <a class="reference external" href="https://docs.python.org/3/library/constants.html#True" title="(in Python v3.13)"><code class="xref py py-data docutils literal notranslate"><span class="pre">True</span></code></a> performs a |
| multi-threaded test, otherwise this test is skipped.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><a class="reference external" href="https://docs.python.org/3/library/exceptions.html#ValueError" title="(in Python v3.13)"><strong>ValueError</strong></a> – if the exhaustive splitting test fails.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_split_at_fraction_fails"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_split_at_fraction_fails</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_items_to_read_before_split</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_fraction</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_split_at_fraction_fails"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_fails" title="Link to this definition"></a></dt> |
| <dd><p>Asserts that dynamic work rebalancing at a given fraction fails.</p> |
| <p>Asserts that trying to perform dynamic splitting after reading |
| ‘num_items_to_read_before_split’ items from the source fails.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source</strong> – source to perform dynamic splitting on.</p></li> |
| <li><p><strong>num_items_to_read_before_split</strong> – number of items to read before splitting.</p></li> |
| <li><p><strong>split_fraction</strong> – fraction to split at.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py function"> |
| <dt class="sig sig-object py" id="apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent"> |
| <span class="sig-prename descclassname"><span class="pre">apache_beam.io.source_test_utils.</span></span><span class="sig-name descname"><span class="pre">assert_split_at_fraction_succeeds_and_consistent</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_items_to_read_before_split</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_fraction</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/io/source_test_utils.html#assert_split_at_fraction_succeeds_and_consistent"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.io.source_test_utils.assert_split_at_fraction_succeeds_and_consistent" title="Link to this definition"></a></dt> |
| <dd><p>Verifies some consistency properties of dynamic work rebalancing.</p> |
| <p>Equivalent to the following pseudocode::</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">original_range_tracker</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">getRangeTracker</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">original_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">original_range_tracker</span><span class="p">)</span> |
| <span class="n">items_before_split</span> <span class="o">=</span> <span class="n">read</span> <span class="n">N</span> <span class="n">items</span> <span class="kn">from</span><span class="w"> </span><span class="nn">original_reader</span> |
| <span class="n">suggested_split_position</span> <span class="o">=</span> <span class="n">original_range_tracker</span><span class="o">.</span><span class="n">position_for_fraction</span><span class="p">(</span> |
| <span class="n">split_fraction</span><span class="p">)</span> |
| <span class="n">original_stop_position</span> <span class="o">-</span> <span class="n">original_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">split_position</span><span class="p">,</span> <span class="n">split_fraction</span> <span class="o">=</span> <span class="n">split_result</span> |
| <span class="n">primary_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">original_range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">(),</span> <span class="n">split_position</span><span class="p">)</span> |
| <span class="n">residual_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">split_position</span><span class="p">,</span> |
| <span class="n">original_stop_position</span><span class="p">)</span> |
| |
| <span class="k">assert</span> <span class="n">that</span><span class="p">:</span> <span class="n">items</span> <span class="n">when</span> <span class="n">reading</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">primary_range_tracker</span><span class="p">)</span> <span class="o">==</span> |
| <span class="n">items_before_split</span> <span class="o">+</span> <span class="n">items</span> <span class="kn">from</span><span class="w"> </span><span class="nn">continuing</span> <span class="n">to</span> <span class="n">read</span> <span class="s1">'original_reader'</span> |
| <span class="k">assert</span> <span class="n">that</span><span class="p">:</span> <span class="n">items</span> <span class="n">when</span> <span class="n">reading</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">original_range_tracker</span><span class="p">)</span> <span class="o">=</span> |
| <span class="n">items</span> <span class="n">when</span> <span class="n">reading</span> <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">primary_range_tracker</span><span class="p">)</span> <span class="o">+</span> <span class="n">items</span> <span class="n">when</span> <span class="n">reading</span> |
| <span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">residual_range_tracker</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>source</strong> – source to perform dynamic work rebalancing on.</p></li> |
| <li><p><strong>num_items_to_read_before_split</strong> – number of items to read before splitting.</p></li> |
| <li><p><strong>split_fraction</strong> – fraction to split at.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="apache_beam.io.snowflake.html" class="btn btn-neutral float-left" title="apache_beam.io.snowflake module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="apache_beam.io.textio.html" class="btn btn-neutral float-right" title="apache_beam.io.textio module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |
