blob: 9ab4747885ec1dcb1546a5b4e662f755495d4c9f [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>apache_beam.testing.test_pipeline &mdash; Apache Beam documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="Apache Beam documentation" href="../../../index.html"/>
<link rel="up" title="Module code" href="../../index.html"/>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.internal.html">apache_beam.internal package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.tools.html">apache_beam.tools package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.version.html">apache_beam.version module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.testing.test_pipeline</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.testing.test_pipeline</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="sd">&quot;&quot;&quot;Test Pipeline, a wrapper of Pipeline for test purpose&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span>
<span class="kn">import</span> <span class="nn">argparse</span>
<span class="kn">import</span> <span class="nn">shlex</span>
<span class="kn">from</span> <span class="nn">nose.plugins.skip</span> <span class="k">import</span> <span class="n">SkipTest</span>
<span class="kn">from</span> <span class="nn">apache_beam.internal</span> <span class="k">import</span> <span class="n">pickler</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">PipelineOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.pipeline</span> <span class="k">import</span> <span class="n">Pipeline</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="k">import</span> <span class="n">PipelineState</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">&#39;TestPipeline&#39;</span><span class="p">,</span>
<span class="p">]</span>
<div class="viewcode-block" id="TestPipeline"><a class="viewcode-back" href="../../../apache_beam.testing.test_pipeline.html#apache_beam.testing.test_pipeline.TestPipeline">[docs]</a><span class="k">class</span> <span class="nc">TestPipeline</span><span class="p">(</span><span class="n">Pipeline</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;:class:`TestPipeline` class is used inside of Beam tests that can be</span>
<span class="sd"> configured to run against pipeline runner.</span>
<span class="sd"> It has a functionality to parse arguments from command line and build pipeline</span>
<span class="sd"> options for tests who runs against a pipeline runner and utilizes resources</span>
<span class="sd"> of the pipeline runner. Those test functions are recommended to be tagged by</span>
<span class="sd"> ``@attr(&quot;ValidatesRunner&quot;)`` annotation.</span>
<span class="sd"> In order to configure the test with customized pipeline options from command</span>
<span class="sd"> line, system argument ``--test-pipeline-options`` can be used to obtains a</span>
<span class="sd"> list of pipeline options. If no options specified, default value will be used.</span>
<span class="sd"> For example, use following command line to execute all ValidatesRunner tests::</span>
<span class="sd"> python setup.py nosetests -a ValidatesRunner \\</span>
<span class="sd"> --test-pipeline-options=&quot;--runner=DirectRunner \\</span>
<span class="sd"> --job_name=myJobName \\</span>
<span class="sd"> --num_workers=1&quot;</span>
<span class="sd"> For example, use assert_that for test validation::</span>
<span class="sd"> pipeline = TestPipeline()</span>
<span class="sd"> pcoll = ...</span>
<span class="sd"> assert_that(pcoll, equal_to(...))</span>
<span class="sd"> pipeline.run()</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">runner</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">argv</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">is_integration_test</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">blocking</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize a pipeline object for test.</span>
<span class="sd"> Args:</span>
<span class="sd"> runner (~apache_beam.runners.runner.PipelineRunner): An object of type</span>
<span class="sd"> :class:`~apache_beam.runners.runner.PipelineRunner` that will be used</span>
<span class="sd"> to execute the pipeline. For registered runners, the runner name can be</span>
<span class="sd"> specified, otherwise a runner object must be supplied.</span>
<span class="sd"> options (~apache_beam.options.pipeline_options.PipelineOptions):</span>
<span class="sd"> A configured</span>
<span class="sd"> :class:`~apache_beam.options.pipeline_options.PipelineOptions`</span>
<span class="sd"> object containing arguments that should be used for running the</span>
<span class="sd"> pipeline job.</span>
<span class="sd"> argv (List[str]): A list of arguments (such as :data:`sys.argv`) to be</span>
<span class="sd"> used for building a</span>
<span class="sd"> :class:`~apache_beam.options.pipeline_options.PipelineOptions` object.</span>
<span class="sd"> This will only be used if argument **options** is :data:`None`.</span>
<span class="sd"> is_integration_test (bool): :data:`True` if the test is an integration</span>
<span class="sd"> test, :data:`False` otherwise.</span>
<span class="sd"> blocking (bool): Run method will wait until pipeline execution is</span>
<span class="sd"> completed.</span>
<span class="sd"> Raises:</span>
<span class="sd"> ~exceptions.ValueError: if either the runner or options argument is not</span>
<span class="sd"> of the expected type.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">is_integration_test</span> <span class="o">=</span> <span class="n">is_integration_test</span>
<span class="bp">self</span><span class="o">.</span><span class="n">options_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_parse_test_option_args</span><span class="p">(</span><span class="n">argv</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">blocking</span> <span class="o">=</span> <span class="n">blocking</span>
<span class="k">if</span> <span class="n">options</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">options</span> <span class="o">=</span> <span class="n">PipelineOptions</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">options_list</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">TestPipeline</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">runner</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span>
<div class="viewcode-block" id="TestPipeline.run"><a class="viewcode-back" href="../../../apache_beam.testing.test_pipeline.html#apache_beam.testing.test_pipeline.TestPipeline.run">[docs]</a> <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">test_runner_api</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="n">result</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">TestPipeline</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">test_runner_api</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">blocking</span><span class="p">:</span>
<span class="n">state</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">wait_until_finish</span><span class="p">()</span>
<span class="k">assert</span> <span class="n">state</span> <span class="ow">in</span> <span class="p">(</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">DONE</span><span class="p">,</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">CANCELLED</span><span class="p">),</span> \
<span class="s2">&quot;Pipeline execution failed.&quot;</span>
<span class="k">return</span> <span class="n">result</span></div>
<span class="k">def</span> <span class="nf">_parse_test_option_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">argv</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Parse value of command line argument: --test-pipeline-options to get</span>
<span class="sd"> pipeline options.</span>
<span class="sd"> Args:</span>
<span class="sd"> argv: An iterable of command line arguments to be used. If not specified</span>
<span class="sd"> then sys.argv will be used as input for parsing arguments.</span>
<span class="sd"> Returns:</span>
<span class="sd"> An argument list of options that can be parsed by argparser or directly</span>
<span class="sd"> build a pipeline option.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--test-pipeline-options&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s1">&#39;store&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;only run tests providing service options&#39;</span><span class="p">)</span>
<span class="n">known</span><span class="p">,</span> <span class="n">unused_argv</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_known_args</span><span class="p">(</span><span class="n">argv</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_integration_test</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">known</span><span class="o">.</span><span class="n">test_pipeline_options</span><span class="p">:</span>
<span class="c1"># Skip integration test when argument &#39;--test-pipeline-options&#39; is not</span>
<span class="c1"># specified since nose calls integration tests when runs unit test by</span>
<span class="c1"># &#39;setup.py test&#39;.</span>
<span class="k">raise</span> <span class="n">SkipTest</span><span class="p">(</span><span class="s1">&#39;IT is skipped because --test-pipeline-options &#39;</span>
<span class="s1">&#39;is not specified&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">shlex</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">known</span><span class="o">.</span><span class="n">test_pipeline_options</span><span class="p">)</span> \
<span class="k">if</span> <span class="n">known</span><span class="o">.</span><span class="n">test_pipeline_options</span> <span class="k">else</span> <span class="p">[]</span>
<div class="viewcode-block" id="TestPipeline.get_full_options_as_args"><a class="viewcode-back" href="../../../apache_beam.testing.test_pipeline.html#apache_beam.testing.test_pipeline.TestPipeline.get_full_options_as_args">[docs]</a> <span class="k">def</span> <span class="nf">get_full_options_as_args</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">extra_opts</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Get full pipeline options as an argument list.</span>
<span class="sd"> Append extra pipeline options to existing option list if provided.</span>
<span class="sd"> Test verifier (if contains in extra options) should be pickled before</span>
<span class="sd"> appending, and will be unpickled later in the TestRunner.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">options</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">options_list</span><span class="p">)</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">extra_opts</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">v</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="nb">bool</span><span class="p">)</span> <span class="ow">and</span> <span class="n">v</span><span class="p">:</span>
<span class="n">options</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39;--</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">k</span><span class="p">)</span>
<span class="k">elif</span> <span class="s1">&#39;matcher&#39;</span> <span class="ow">in</span> <span class="n">k</span><span class="p">:</span>
<span class="n">options</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39;--</span><span class="si">%s</span><span class="s1">=</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">pickler</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">v</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">()))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">options</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39;--</span><span class="si">%s</span><span class="s1">=</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">))</span>
<span class="k">return</span> <span class="n">options</span></div>
<div class="viewcode-block" id="TestPipeline.get_option"><a class="viewcode-back" href="../../../apache_beam.testing.test_pipeline.html#apache_beam.testing.test_pipeline.TestPipeline.get_option">[docs]</a> <span class="k">def</span> <span class="nf">get_option</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">opt_name</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Get a pipeline option value by name</span>
<span class="sd"> Args:</span>
<span class="sd"> opt_name: The name of the pipeline option.</span>
<span class="sd"> Returns:</span>
<span class="sd"> None if option is not found in existing option list which is generated</span>
<span class="sd"> by parsing value of argument `test-pipeline-options`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span>
<span class="n">opt_name</span> <span class="o">=</span> <span class="n">opt_name</span><span class="p">[:</span><span class="mi">2</span><span class="p">]</span> <span class="k">if</span> <span class="n">opt_name</span><span class="p">[:</span><span class="mi">2</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;--&#39;</span> <span class="k">else</span> <span class="n">opt_name</span>
<span class="c1"># Option name should start with &#39;--&#39; when it&#39;s used for parsing.</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--&#39;</span> <span class="o">+</span> <span class="n">opt_name</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s1">&#39;store&#39;</span><span class="p">)</span>
<span class="n">known</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_known_args</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">options_list</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">known</span><span class="p">,</span> <span class="n">opt_name</span><span class="p">)</span> <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">known</span><span class="p">,</span> <span class="n">opt_name</span><span class="p">)</span> <span class="k">else</span> <span class="kc">None</span></div></div>
</pre></div>
</div>
<div class="articleComments">
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright .
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.StickyNav.enable();
});
</script>
</body>
</html>