blob: 97737d46b60aa5379f7d14a519f57cf5a3db6bb5 [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.pipeline_verifiers &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.pipeline_verifiers</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.pipeline_verifiers</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;End-to-end test result verifiers</span>
<span class="sd">A set of verifiers that are used in end-to-end tests to verify state/output</span>
<span class="sd">of test pipeline job. Customized verifier should extend</span>
<span class="sd">`hamcrest.core.base_matcher.BaseMatcher` and override _matches.</span>
<span class="sd">&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">logging</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">from</span> <span class="nn">hamcrest.core.base_matcher</span> <span class="k">import</span> <span class="n">BaseMatcher</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystems</span> <span class="k">import</span> <span class="n">FileSystems</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="kn">from</span> <span class="nn">apache_beam.testing</span> <span class="k">import</span> <span class="n">test_utils</span> <span class="k">as</span> <span class="n">utils</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="k">import</span> <span class="n">retry</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">&#39;PipelineStateMatcher&#39;</span><span class="p">,</span>
<span class="s1">&#39;FileChecksumMatcher&#39;</span><span class="p">,</span>
<span class="s1">&#39;retry_on_io_error_and_server_error&#39;</span><span class="p">,</span>
<span class="p">]</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">apitools.base.py.exceptions</span> <span class="k">import</span> <span class="n">HttpError</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="n">HttpError</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">MAX_RETRIES</span> <span class="o">=</span> <span class="mi">4</span>
<div class="viewcode-block" id="PipelineStateMatcher"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.PipelineStateMatcher">[docs]</a><span class="k">class</span> <span class="nc">PipelineStateMatcher</span><span class="p">(</span><span class="n">BaseMatcher</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Matcher that verify pipeline job terminated in expected state</span>
<span class="sd"> Matcher compares the actual pipeline terminate state with expected.</span>
<span class="sd"> By default, `PipelineState.DONE` is used as expected state.</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">expected_state</span><span class="o">=</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">DONE</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expected_state</span> <span class="o">=</span> <span class="n">expected_state</span>
<span class="k">def</span> <span class="nf">_matches</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pipeline_result</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pipeline_result</span><span class="o">.</span><span class="n">state</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">expected_state</span>
<div class="viewcode-block" id="PipelineStateMatcher.describe_to"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.PipelineStateMatcher.describe_to">[docs]</a> <span class="k">def</span> <span class="nf">describe_to</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">description</span><span class="p">):</span>
<span class="n">description</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="s2">&quot;Test pipeline expected terminated in state: &quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">expected_state</span><span class="p">)</span></div>
<div class="viewcode-block" id="PipelineStateMatcher.describe_mismatch"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.PipelineStateMatcher.describe_mismatch">[docs]</a> <span class="k">def</span> <span class="nf">describe_mismatch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pipeline_result</span><span class="p">,</span> <span class="n">mismatch_description</span><span class="p">):</span>
<span class="n">mismatch_description</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="s2">&quot;Test pipeline job terminated in state: &quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="n">pipeline_result</span><span class="o">.</span><span class="n">state</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="retry_on_io_error_and_server_error"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.retry_on_io_error_and_server_error">[docs]</a><span class="k">def</span> <span class="nf">retry_on_io_error_and_server_error</span><span class="p">(</span><span class="n">exception</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Filter allowing retries on file I/O errors and service error.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="ne">IOError</span><span class="p">)</span> <span class="ow">or</span> \
<span class="p">(</span><span class="n">HttpError</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">exception</span><span class="p">,</span> <span class="n">HttpError</span><span class="p">))</span></div>
<div class="viewcode-block" id="FileChecksumMatcher"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.FileChecksumMatcher">[docs]</a><span class="k">class</span> <span class="nc">FileChecksumMatcher</span><span class="p">(</span><span class="n">BaseMatcher</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Matcher that verifies file(s) content by comparing file checksum.</span>
<span class="sd"> Use apache_beam.io.filebasedsink to fetch file(s) from given path.</span>
<span class="sd"> File checksum is a hash string computed from content of file(s).</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">file_path</span><span class="p">,</span> <span class="n">expected_checksum</span><span class="p">,</span> <span class="n">sleep_secs</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize a FileChecksumMatcher object</span>
<span class="sd"> Args:</span>
<span class="sd"> file_path : A string that is the full path of output file. This path</span>
<span class="sd"> can contain globs.</span>
<span class="sd"> expected_checksum : A hash string that is computed from expected</span>
<span class="sd"> result.</span>
<span class="sd"> sleep_secs : Number of seconds to wait before verification start.</span>
<span class="sd"> Extra time are given to make sure output files are ready on FS.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">sleep_secs</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">isinstance</span><span class="p">(</span><span class="n">sleep_secs</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sleep_secs</span> <span class="o">=</span> <span class="n">sleep_secs</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Sleep seconds, if received, must be int. &#39;</span>
<span class="s1">&#39;But received: </span><span class="si">%r</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">sleep_secs</span><span class="p">,</span>
<span class="nb">type</span><span class="p">(</span><span class="n">sleep_secs</span><span class="p">)))</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sleep_secs</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_path</span> <span class="o">=</span> <span class="n">file_path</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expected_checksum</span> <span class="o">=</span> <span class="n">expected_checksum</span>
<span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">num_retries</span><span class="o">=</span><span class="n">MAX_RETRIES</span><span class="p">,</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry_on_io_error_and_server_error</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_read_with_retry</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Read path with retry if I/O failed&quot;&quot;&quot;</span>
<span class="n">read_lines</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">match_result</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">match</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">file_path</span><span class="p">])[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">matched_path</span> <span class="o">=</span> <span class="p">[</span><span class="n">f</span><span class="o">.</span><span class="n">path</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">match_result</span><span class="o">.</span><span class="n">metadata_list</span><span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">matched_path</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="s1">&#39;No such file or directory: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_path</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">&#39;Find </span><span class="si">%d</span><span class="s1"> files in </span><span class="si">%s</span><span class="s1">: </span><span class="se">\n</span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="nb">len</span><span class="p">(</span><span class="n">matched_path</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_path</span><span class="p">,</span> <span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">matched_path</span><span class="p">))</span>
<span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">matched_path</span><span class="p">:</span>
<span class="k">with</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s1">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">f</span><span class="p">:</span>
<span class="n">read_lines</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
<span class="k">return</span> <span class="n">read_lines</span>
<span class="k">def</span> <span class="nf">_matches</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">sleep_secs</span><span class="p">:</span>
<span class="c1"># Wait to have output file ready on FS</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">&#39;Wait </span><span class="si">%d</span><span class="s1"> seconds...&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sleep_secs</span><span class="p">)</span>
<span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sleep_secs</span><span class="p">)</span>
<span class="c1"># Read from given file(s) path</span>
<span class="n">read_lines</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_read_with_retry</span><span class="p">()</span>
<span class="c1"># Compute checksum</span>
<span class="bp">self</span><span class="o">.</span><span class="n">checksum</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">compute_hash</span><span class="p">(</span><span class="n">read_lines</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">&#39;Read from given path </span><span class="si">%s</span><span class="s1">, </span><span class="si">%d</span><span class="s1"> lines, checksum: </span><span class="si">%s</span><span class="s1">.&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_path</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">read_lines</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">checksum</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">checksum</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">expected_checksum</span>
<div class="viewcode-block" id="FileChecksumMatcher.describe_to"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.FileChecksumMatcher.describe_to">[docs]</a> <span class="k">def</span> <span class="nf">describe_to</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">description</span><span class="p">):</span>
<span class="n">description</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="s2">&quot;Expected checksum is &quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">expected_checksum</span><span class="p">)</span></div>
<div class="viewcode-block" id="FileChecksumMatcher.describe_mismatch"><a class="viewcode-back" href="../../../apache_beam.testing.pipeline_verifiers.html#apache_beam.testing.pipeline_verifiers.FileChecksumMatcher.describe_mismatch">[docs]</a> <span class="k">def</span> <span class="nf">describe_mismatch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pipeline_result</span><span class="p">,</span> <span class="n">mismatch_description</span><span class="p">):</span>
<span class="n">mismatch_description</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="s2">&quot;Actual checksum is &quot;</span><span class="p">)</span> \
<span class="o">.</span><span class="n">append_text</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">checksum</span><span class="p">)</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>