blob: 303ebbc795c8e6f30b8f0d043048d722db93e794 [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.benchmarks.nexmark.nexmark_launcher &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.benchmarks.nexmark.nexmark_launcher</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.benchmarks.nexmark.nexmark_launcher</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;Nexmark launcher.</span>
<span class="sd">The Nexmark suite is a series of queries (streaming pipelines) performed</span>
<span class="sd">on a simulation of auction events. The launcher orchestrates the generation</span>
<span class="sd">and parsing of streaming events and the running of queries.</span>
<span class="sd">Model</span>
<span class="sd"> - Person: Author of an auction or a bid.</span>
<span class="sd"> - Auction: Item under auction.</span>
<span class="sd"> - Bid: A bid for an item under auction.</span>
<span class="sd">Events</span>
<span class="sd"> - Create Person</span>
<span class="sd"> - Create Auction</span>
<span class="sd"> - Create Bid</span>
<span class="sd">Queries</span>
<span class="sd"> - Query0: Pass through (send and receive auction events).</span>
<span class="sd">Usage</span>
<span class="sd"> - DirectRunner</span>
<span class="sd"> python nexmark_launcher.py \</span>
<span class="sd"> --query/q &lt;query number&gt; \</span>
<span class="sd"> --project &lt;project id&gt; \</span>
<span class="sd"> --loglevel=DEBUG (optional) \</span>
<span class="sd"> --wait_until_finish_duration &lt;time_in_ms&gt; \</span>
<span class="sd"> --streaming</span>
<span class="sd"> - DataflowRunner</span>
<span class="sd"> python nexmark_launcher.py \</span>
<span class="sd"> --query/q &lt;query number&gt; \</span>
<span class="sd"> --project &lt;project id&gt; \</span>
<span class="sd"> --loglevel=DEBUG (optional) \</span>
<span class="sd"> --wait_until_finish_duration &lt;time_in_ms&gt; \</span>
<span class="sd"> --streaming \</span>
<span class="sd"> --sdk_location &lt;apache_beam tar.gz&gt; \</span>
<span class="sd"> --staging_location=gs://... \</span>
<span class="sd"> --temp_location=gs://</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">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span>
<span class="kn">import</span> <span class="nn">argparse</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">uuid</span>
<span class="kn">from</span> <span class="nn">google.cloud</span> <span class="k">import</span> <span class="n">pubsub</span>
<span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">GoogleCloudOptions</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.options.pipeline_options</span> <span class="k">import</span> <span class="n">SetupOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">StandardOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="k">import</span> <span class="n">TestOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.nexmark_util</span> <span class="k">import</span> <span class="n">Command</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.queries</span> <span class="k">import</span> <span class="n">query0</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.queries</span> <span class="k">import</span> <span class="n">query1</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.queries</span> <span class="k">import</span> <span class="n">query2</span>
<div class="viewcode-block" id="NexmarkLauncher"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher">[docs]</a><span class="k">class</span> <span class="nc">NexmarkLauncher</span><span class="p">(</span><span class="nb">object</span><span class="p">):</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="bp">self</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">uuid</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid</span><span class="o">.</span><span class="n">uuid4</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">topic_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">topic_name</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">uuid</span>
<span class="bp">self</span><span class="o">.</span><span class="n">subscription_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">subscription_name</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">uuid</span>
<span class="n">publish_client</span> <span class="o">=</span> <span class="n">pubsub</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">)</span>
<span class="n">topic</span> <span class="o">=</span> <span class="n">publish_client</span><span class="o">.</span><span class="n">topic</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">topic_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">topic</span><span class="o">.</span><span class="n">exists</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;deleting topic </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">topic_name</span><span class="p">)</span>
<span class="n">topic</span><span class="o">.</span><span class="n">delete</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;creating topic </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">topic_name</span><span class="p">)</span>
<span class="n">topic</span><span class="o">.</span><span class="n">create</span><span class="p">()</span>
<span class="n">sub</span> <span class="o">=</span> <span class="n">topic</span><span class="o">.</span><span class="n">subscription</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">subscription_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">sub</span><span class="o">.</span><span class="n">exists</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;deleting sub </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">topic_name</span><span class="p">)</span>
<span class="n">sub</span><span class="o">.</span><span class="n">delete</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;creating sub </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">topic_name</span><span class="p">)</span>
<span class="n">sub</span><span class="o">.</span><span class="n">create</span><span class="p">()</span>
<div class="viewcode-block" id="NexmarkLauncher.parse_args"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher.parse_args">[docs]</a> <span class="k">def</span> <span class="nf">parse_args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</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;--query&#39;</span><span class="p">,</span> <span class="s1">&#39;-q&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span>
<span class="n">action</span><span class="o">=</span><span class="s1">&#39;append&#39;</span><span class="p">,</span>
<span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">choices</span><span class="o">=</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Query to run&#39;</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;--subscription_name&#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">help</span><span class="o">=</span><span class="s1">&#39;Pub/Sub subscription to read from&#39;</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;--topic_name&#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">help</span><span class="o">=</span><span class="s1">&#39;Pub/Sub topic to read from&#39;</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;--loglevel&#39;</span><span class="p">,</span>
<span class="n">choices</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;DEBUG&#39;</span><span class="p">,</span> <span class="s1">&#39;INFO&#39;</span><span class="p">,</span> <span class="s1">&#39;WARNING&#39;</span><span class="p">,</span>
<span class="s1">&#39;ERROR&#39;</span><span class="p">,</span> <span class="s1">&#39;CRITICAL&#39;</span><span class="p">],</span>
<span class="n">default</span><span class="o">=</span><span class="s1">&#39;INFO&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Set logging level to debug&#39;</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;--input&#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">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Path to the data file containing nexmark events.&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_args</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">logging</span><span class="o">.</span><span class="n">basicConfig</span><span class="p">(</span><span class="n">level</span><span class="o">=</span><span class="nb">getattr</span><span class="p">(</span><span class="n">logging</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">loglevel</span><span class="p">,</span> <span class="kc">None</span><span class="p">),</span>
<span class="nb">format</span><span class="o">=</span><span class="s1">&#39;(</span><span class="si">%(threadName)-10s</span><span class="s1">) </span><span class="si">%(message)s</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipeline_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">pipeline_args</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;args, pipeline_args: </span><span class="si">%s</span><span class="s1">, </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">args</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_args</span><span class="p">)</span>
<span class="c1"># Usage with Dataflow requires a project to be supplied.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">project</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">project</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">project</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">parser</span><span class="o">.</span><span class="n">print_usage</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s1">&#39;: error: argument --project is required&#39;</span><span class="p">)</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="c1"># Pub/Sub is currently available for use only in streaming pipelines.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">streaming</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">streaming</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">streaming</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">parser</span><span class="o">.</span><span class="n">print_usage</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s1">&#39;: error: argument --streaming is required&#39;</span><span class="p">)</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="c1"># wait_until_finish ensures that the streaming job is canceled.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">wait_until_finish_duration</span> <span class="o">=</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">TestOptions</span><span class="p">)</span><span class="o">.</span><span class="n">wait_until_finish_duration</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">wait_until_finish_duration</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">parser</span><span class="o">.</span><span class="n">print_usage</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s1">&#39;: error: argument --wait_until_finish_duration is required&#39;</span><span class="p">)</span> <span class="c1"># pylint: disable=line-too-long</span>
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="c1"># We use the save_main_session option because one or more DoFn&#39;s in this</span>
<span class="c1"># workflow rely on global context (e.g., a module imported at module level).</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">SetupOptions</span><span class="p">)</span><span class="o">.</span><span class="n">save_main_session</span> <span class="o">=</span> <span class="kc">True</span></div>
<div class="viewcode-block" id="NexmarkLauncher.generate_events"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher.generate_events">[docs]</a> <span class="k">def</span> <span class="nf">generate_events</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">publish_client</span> <span class="o">=</span> <span class="n">pubsub</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">)</span>
<span class="n">topic</span> <span class="o">=</span> <span class="n">publish_client</span><span class="o">.</span><span class="n">topic</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">topic_name</span><span class="p">)</span>
<span class="n">sub</span> <span class="o">=</span> <span class="n">topic</span><span class="o">.</span><span class="n">subscription</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">subscription_name</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;Generating auction events to topic </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">topic</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">input</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;gs://&#39;</span><span class="p">):</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.gcsfilesystem</span> <span class="k">import</span> <span class="n">GCSFileSystem</span>
<span class="n">fs</span> <span class="o">=</span> <span class="n">GCSFileSystem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="p">)</span>
<span class="k">with</span> <span class="n">fs</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">input</span><span class="p">)</span> <span class="k">as</span> <span class="n">infile</span><span class="p">:</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">infile</span><span class="p">:</span>
<span class="n">topic</span><span class="o">.</span><span class="n">publish</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">input</span><span class="p">)</span> <span class="k">as</span> <span class="n">infile</span><span class="p">:</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">infile</span><span class="p">:</span>
<span class="n">topic</span><span class="o">.</span><span class="n">publish</span><span class="p">(</span><span class="n">line</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;Finished event generation.&#39;</span><span class="p">)</span>
<span class="c1"># Read from PubSub into a PCollection.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">subscription_name</span><span class="p">:</span>
<span class="n">raw_events</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">|</span> <span class="s1">&#39;ReadPubSub&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ReadFromPubSub</span><span class="p">(</span>
<span class="n">subscription</span><span class="o">=</span><span class="n">sub</span><span class="o">.</span><span class="n">full_name</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">raw_events</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">|</span> <span class="s1">&#39;ReadPubSub&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ReadFromPubSub</span><span class="p">(</span>
<span class="n">topic</span><span class="o">=</span><span class="n">topic</span><span class="o">.</span><span class="n">full_name</span><span class="p">)</span>
<span class="k">return</span> <span class="n">raw_events</span></div>
<div class="viewcode-block" id="NexmarkLauncher.run_query"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher.run_query">[docs]</a> <span class="k">def</span> <span class="nf">run_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">query_args</span><span class="p">,</span> <span class="n">query_errors</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">(</span><span class="n">options</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="p">)</span>
<span class="n">raw_events</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">generate_events</span><span class="p">()</span>
<span class="n">query</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">raw_events</span><span class="p">,</span> <span class="n">query_args</span><span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="n">job_duration</span> <span class="o">=</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">TestOptions</span><span class="p">)</span><span class="o">.</span><span class="n">wait_until_finish_duration</span>
<span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">runner</span> <span class="o">==</span> <span class="s1">&#39;DataflowRunner&#39;</span><span class="p">:</span> <span class="c1"># pylint: disable=line-too-long</span>
<span class="n">result</span><span class="o">.</span><span class="n">wait_until_finish</span><span class="p">(</span><span class="n">duration</span><span class="o">=</span><span class="n">job_duration</span><span class="p">)</span>
<span class="n">result</span><span class="o">.</span><span class="n">cancel</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">result</span><span class="o">.</span><span class="n">wait_until_finish</span><span class="p">()</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">exc</span><span class="p">:</span>
<span class="n">query_errors</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">exc</span><span class="p">))</span>
<span class="k">raise</span></div>
<div class="viewcode-block" id="NexmarkLauncher.cleanup"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher.cleanup">[docs]</a> <span class="k">def</span> <span class="nf">cleanup</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">publish_client</span> <span class="o">=</span> <span class="n">pubsub</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="n">project</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">)</span>
<span class="n">topic</span> <span class="o">=</span> <span class="n">publish_client</span><span class="o">.</span><span class="n">topic</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">topic_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">topic</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="n">topic</span><span class="o">.</span><span class="n">delete</span><span class="p">()</span>
<span class="n">sub</span> <span class="o">=</span> <span class="n">topic</span><span class="o">.</span><span class="n">subscription</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">subscription_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">sub</span><span class="o">.</span><span class="n">exists</span><span class="p">():</span>
<span class="n">sub</span><span class="o">.</span><span class="n">delete</span><span class="p">()</span></div>
<div class="viewcode-block" id="NexmarkLauncher.run"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_launcher.html#apache_beam.testing.benchmarks.nexmark.nexmark_launcher.NexmarkLauncher.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">queries</span> <span class="o">=</span> <span class="p">{</span>
<span class="mi">0</span><span class="p">:</span> <span class="n">query0</span><span class="p">,</span>
<span class="mi">1</span><span class="p">:</span> <span class="n">query1</span><span class="p">,</span>
<span class="mi">2</span><span class="p">:</span> <span class="n">query2</span><span class="p">,</span>
<span class="c1"># TODO(mariagh): Add more queries.</span>
<span class="p">}</span>
<span class="c1"># TODO(mariagh): Move to a config file.</span>
<span class="n">query_args</span> <span class="o">=</span> <span class="p">{</span>
<span class="mi">2</span><span class="p">:</span> <span class="p">{</span>
<span class="s1">&#39;auction_id&#39;</span><span class="p">:</span> <span class="s1">&#39;a1003&#39;</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="n">query_errors</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">query</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parse_args</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;Running query </span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">i</span><span class="p">)</span>
<span class="c1"># The DirectRunner is the default runner, and it needs</span>
<span class="c1"># special handling to cancel streaming jobs.</span>
<span class="n">launch_from_direct_runner</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span>
<span class="n">StandardOptions</span><span class="p">)</span><span class="o">.</span><span class="n">runner</span> <span class="ow">in</span> <span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="s1">&#39;DirectRunner&#39;</span><span class="p">]</span>
<span class="n">query_duration</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">TestOptions</span><span class="p">)</span><span class="o">.</span><span class="n">wait_until_finish_duration</span> <span class="c1"># pylint: disable=line-too-long</span>
<span class="k">if</span> <span class="n">launch_from_direct_runner</span><span class="p">:</span>
<span class="n">command</span> <span class="o">=</span> <span class="n">Command</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">run_query</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">[</span><span class="n">queries</span><span class="p">[</span><span class="n">i</span><span class="p">],</span>
<span class="n">query_args</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">i</span><span class="p">),</span>
<span class="n">query_errors</span><span class="p">])</span>
<span class="n">command</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">timeout</span><span class="o">=</span><span class="n">query_duration</span> <span class="o">//</span> <span class="mi">1000</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="n">queries</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">query_args</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">i</span><span class="p">),</span> <span class="n">query_errors</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">exc</span><span class="p">:</span>
<span class="n">query_errors</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">exc</span><span class="p">)</span>
<span class="k">if</span> <span class="n">query_errors</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">&#39;Query failed with </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">query_errors</span><span class="p">))</span>
<span class="k">else</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;Queries run: </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">args</span><span class="o">.</span><span class="n">query</span><span class="p">)</span></div></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">launcher</span> <span class="o">=</span> <span class="n">NexmarkLauncher</span><span class="p">()</span>
<span class="n">launcher</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="n">launcher</span><span class="o">.</span><span class="n">cleanup</span><span class="p">()</span>
</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>