blob: 13eda17c85f870db9ee744e59e7a24b402a11f0c [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_util &mdash; Apache Beam 2.47.0 documentation</title>
<script type="text/javascript" src="../../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../../" src="../../../../../_static/documentation_options.js"></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/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../../search.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 class="version">
2.47.0
</div>
<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.dataframe.html">apache_beam.dataframe 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.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="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_util</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_util</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;Utilities for the Nexmark suite.</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. This util includes:</span>
<span class="sd"> - A Command class used to terminate the streaming jobs</span>
<span class="sd"> launched in nexmark_launcher.py by the DirectRunner.</span>
<span class="sd"> - A ParseEventFn DoFn to parse events received from PubSub.</span>
<span class="sd">Usage:</span>
<span class="sd">To run a process for a certain duration, define in the code:</span>
<span class="sd"> command = Command(process_to_terminate, args)</span>
<span class="sd"> command.run(timeout=duration)</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">threading</span>
<span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics</span> <span class="kn">import</span> <span class="n">MetricsFilter</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="kn">import</span> <span class="n">PipelineResult</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.models</span> <span class="kn">import</span> <span class="n">auction_bid</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.models</span> <span class="kn">import</span> <span class="n">nexmark_model</span>
<span class="kn">from</span> <span class="nn">apache_beam.testing.benchmarks.nexmark.models.field_name</span> <span class="kn">import</span> <span class="n">FieldNames</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">window</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils.timestamp</span> <span class="kn">import</span> <span class="n">Timestamp</span>
<span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span>
<div class="viewcode-block" id="Command"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.Command">[docs]</a><span class="k">class</span> <span class="nc">Command</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cmd</span> <span class="o">=</span> <span class="n">cmd</span>
<span class="bp">self</span><span class="o">.</span><span class="n">args</span> <span class="o">=</span> <span class="n">args</span>
<div class="viewcode-block" id="Command.run"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.Command.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">timeout</span><span class="p">):</span>
<span class="k">def</span> <span class="nf">thread_target</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;Starting thread for </span><span class="si">%d</span><span class="s1"> seconds: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">timeout</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">cmd</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cmd</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">)</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s1">&#39;</span><span class="si">%d</span><span class="s1"> seconds elapsed. Thread (</span><span class="si">%s</span><span class="s1">) finished.&#39;</span><span class="p">,</span>
<span class="n">timeout</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cmd</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span>
<span class="n">thread</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">Thread</span><span class="p">(</span><span class="n">target</span><span class="o">=</span><span class="n">thread_target</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;Thread-timeout&#39;</span><span class="p">)</span>
<span class="n">thread</span><span class="o">.</span><span class="n">daemon</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">thread</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
<span class="n">thread</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">timeout</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="setup_coder"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.setup_coder">[docs]</a><span class="k">def</span> <span class="nf">setup_coder</span><span class="p">():</span>
<span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span>
<span class="n">nexmark_model</span><span class="o">.</span><span class="n">Auction</span><span class="p">,</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">AuctionCoder</span><span class="p">)</span>
<span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span>
<span class="n">nexmark_model</span><span class="o">.</span><span class="n">Person</span><span class="p">,</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">PersonCoder</span><span class="p">)</span>
<span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">nexmark_model</span><span class="o">.</span><span class="n">Bid</span><span class="p">,</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">BidCoder</span><span class="p">)</span>
<span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span>
<span class="n">auction_bid</span><span class="o">.</span><span class="n">AuctionBid</span><span class="p">,</span> <span class="n">auction_bid</span><span class="o">.</span><span class="n">AuctionBidCoder</span><span class="p">)</span></div>
<div class="viewcode-block" id="ParseEventFn"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.ParseEventFn">[docs]</a><span class="k">class</span> <span class="nc">ParseEventFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Original parser for parsing raw events info into a Python objects.</span>
<span class="sd"> Each event line has the following format:</span>
<span class="sd"> person: &lt;id starting with &#39;p&#39;&gt;,name,email,credit_card,city, \</span>
<span class="sd"> state,timestamp,extra</span>
<span class="sd"> auction: &lt;id starting with &#39;a&#39;&gt;,item_name, description,initial_bid, \</span>
<span class="sd"> reserve_price,timestamp,expires,seller,category,extra</span>
<span class="sd"> bid: &lt;auction starting with &#39;b&#39;&gt;,bidder,price,timestamp,extra</span>
<span class="sd"> For example:</span>
<span class="sd"> &#39;p12345,maria,maria@maria.com,1234-5678-9012-3456, \</span>
<span class="sd"> sunnyvale,CA,1528098831536&#39;</span>
<span class="sd"> &#39;a12345,car67,2012 hyundai elantra,15000,20000, \</span>
<span class="sd"> 1528098831536,20180630,maria,vehicle&#39;</span>
<span class="sd"> &#39;b12345,maria,20000,1528098831536&#39;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="ParseEventFn.process"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.ParseEventFn.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">elem</span><span class="p">):</span>
<span class="n">model_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;p&#39;</span><span class="p">:</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Person</span><span class="p">,</span>
<span class="s1">&#39;a&#39;</span><span class="p">:</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Auction</span><span class="p">,</span>
<span class="s1">&#39;b&#39;</span><span class="p">:</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Bid</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">row</span> <span class="o">=</span> <span class="n">elem</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;,&#39;</span><span class="p">)</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">model_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">elem</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">model</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Invalid event: </span><span class="si">%s</span><span class="s1">.&#39;</span> <span class="o">%</span> <span class="n">row</span><span class="p">)</span>
<span class="n">event</span> <span class="o">=</span> <span class="n">model</span><span class="p">(</span><span class="o">*</span><span class="n">row</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;Parsed event: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">event</span><span class="p">)</span>
<span class="k">yield</span> <span class="n">event</span></div></div>
<div class="viewcode-block" id="ParseJsonEventFn"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.ParseJsonEventFn">[docs]</a><span class="k">class</span> <span class="nc">ParseJsonEventFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Parses the raw event info into a Python objects.</span>
<span class="sd"> Each event line has the following format:</span>
<span class="sd"> person: {id,name,email,credit_card,city, \</span>
<span class="sd"> state,timestamp,extra}</span>
<span class="sd"> auction: {id,item_name, description,initial_bid, \</span>
<span class="sd"> reserve_price,timestamp,expires,seller,category,extra}</span>
<span class="sd"> bid: {auction,bidder,price,timestamp,extra}</span>
<span class="sd"> For example:</span>
<span class="sd"> {&quot;id&quot;:1000,&quot;name&quot;:&quot;Peter Jones&quot;,&quot;emailAddress&quot;:&quot;nhd@xcat.com&quot;,\</span>
<span class="sd"> &quot;creditCard&quot;:&quot;7241 7320 9143 4888&quot;,&quot;city&quot;:&quot;Portland&quot;,&quot;state&quot;:&quot;WY&quot;,\</span>
<span class="sd"> &quot;dateTime&quot;:1528098831026,\&quot;extra&quot;:&quot;WN_HS_bnpVQ\\[[&quot;}</span>
<span class="sd"> {&quot;id&quot;:1000,&quot;itemName&quot;:&quot;wkx mgee&quot;,&quot;description&quot;:&quot;eszpqxtdxrvwmmywkmogoahf&quot;,\</span>
<span class="sd"> &quot;initialBid&quot;:28873,&quot;reserve&quot;:29448,&quot;dateTime&quot;:1528098831036,\</span>
<span class="sd"> &quot;expires&quot;:1528098840451,&quot;seller&quot;:1000,&quot;category&quot;:13,&quot;extra&quot;:&quot;zcuupiz&quot;}</span>
<span class="sd"> {&quot;auction&quot;:1000,&quot;bidder&quot;:1001,&quot;price&quot;:32530001,&quot;dateTime&quot;:1528098831066,\</span>
<span class="sd"> &quot;extra&quot;:&quot;fdiysaV^]NLVsbolvyqwgticfdrwdyiyofWPYTOuwogvszlxjrcNOORM&quot;}</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="ParseJsonEventFn.process"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.ParseJsonEventFn.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">elem</span><span class="p">):</span>
<span class="n">json_dict</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">elem</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">])</span> <span class="ow">is</span> <span class="nb">dict</span><span class="p">:</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">]</span> <span class="o">=</span> <span class="n">json_dict</span><span class="p">[</span>
<span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">][</span><span class="s1">&#39;millis&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="n">FieldNames</span><span class="o">.</span><span class="n">NAME</span> <span class="ow">in</span> <span class="n">json_dict</span><span class="p">:</span>
<span class="k">yield</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Person</span><span class="p">(</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">ID</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">NAME</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EMAIL_ADDRESS</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">CREDIT_CARD</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">CITY</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">STATE</span><span class="p">],</span>
<span class="n">millis_to_timestamp</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">]),</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXTRA</span><span class="p">])</span>
<span class="k">elif</span> <span class="n">FieldNames</span><span class="o">.</span><span class="n">ITEM_NAME</span> <span class="ow">in</span> <span class="n">json_dict</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXPIRES</span><span class="p">])</span> <span class="ow">is</span> <span class="nb">dict</span><span class="p">:</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXPIRES</span><span class="p">]</span> <span class="o">=</span> <span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXPIRES</span><span class="p">][</span><span class="s1">&#39;millis&#39;</span><span class="p">]</span>
<span class="k">yield</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Auction</span><span class="p">(</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">ID</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">ITEM_NAME</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DESCRIPTION</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">INITIAL_BID</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">RESERVE</span><span class="p">],</span>
<span class="n">millis_to_timestamp</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">]),</span>
<span class="n">millis_to_timestamp</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXPIRES</span><span class="p">]),</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">SELLER</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">CATEGORY</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXTRA</span><span class="p">])</span>
<span class="k">elif</span> <span class="n">FieldNames</span><span class="o">.</span><span class="n">AUCTION</span> <span class="ow">in</span> <span class="n">json_dict</span><span class="p">:</span>
<span class="k">yield</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Bid</span><span class="p">(</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">AUCTION</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">BIDDER</span><span class="p">],</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">PRICE</span><span class="p">],</span>
<span class="n">millis_to_timestamp</span><span class="p">(</span><span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">DATE_TIME</span><span class="p">]),</span>
<span class="n">json_dict</span><span class="p">[</span><span class="n">FieldNames</span><span class="o">.</span><span class="n">EXTRA</span><span class="p">])</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;Invalid event: </span><span class="si">%s</span><span class="s1">.&#39;</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">json_dict</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="CountAndLog"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.CountAndLog">[docs]</a><span class="k">class</span> <span class="nc">CountAndLog</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span>
<div class="viewcode-block" id="CountAndLog.expand"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.CountAndLog.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span>
<span class="k">return</span> <span class="p">(</span>
<span class="n">pcoll</span>
<span class="o">|</span> <span class="s1">&#39;window&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">WindowInto</span><span class="p">(</span><span class="n">window</span><span class="o">.</span><span class="n">GlobalWindows</span><span class="p">())</span>
<span class="o">|</span> <span class="s2">&quot;Count&quot;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">combiners</span><span class="o">.</span><span class="n">Count</span><span class="o">.</span><span class="n">Globally</span><span class="p">()</span>
<span class="o">|</span> <span class="s2">&quot;Log&quot;</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="n">log_count_info</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="log_count_info"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.log_count_info">[docs]</a><span class="k">def</span> <span class="nf">log_count_info</span><span class="p">(</span><span class="n">count</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;Query resulted in </span><span class="si">%d</span><span class="s1"> results&#39;</span><span class="p">,</span> <span class="n">count</span><span class="p">)</span>
<span class="k">return</span> <span class="n">count</span></div>
<div class="viewcode-block" id="display"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.display">[docs]</a><span class="k">def</span> <span class="nf">display</span><span class="p">(</span><span class="n">elm</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="n">elm</span><span class="p">)</span>
<span class="k">return</span> <span class="n">elm</span></div>
<div class="viewcode-block" id="model_to_json"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.model_to_json">[docs]</a><span class="k">def</span> <span class="nf">model_to_json</span><span class="p">(</span><span class="n">model</span><span class="p">):</span>
<span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">construct_json_dict</span><span class="p">(</span><span class="n">model</span><span class="p">),</span> <span class="n">separators</span><span class="o">=</span><span class="p">(</span><span class="s1">&#39;,&#39;</span><span class="p">,</span> <span class="s1">&#39;:&#39;</span><span class="p">))</span></div>
<div class="viewcode-block" id="construct_json_dict"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.construct_json_dict">[docs]</a><span class="k">def</span> <span class="nf">construct_json_dict</span><span class="p">(</span><span class="n">model</span><span class="p">):</span>
<span class="k">return</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">unnest_to_json</span><span class="p">(</span><span class="n">v</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">model</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span></div>
<div class="viewcode-block" id="unnest_to_json"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.unnest_to_json">[docs]</a><span class="k">def</span> <span class="nf">unnest_to_json</span><span class="p">(</span><span class="n">cand</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cand</span><span class="p">,</span> <span class="n">Timestamp</span><span class="p">):</span>
<span class="k">return</span> <span class="n">cand</span><span class="o">.</span><span class="n">micros</span> <span class="o">//</span> <span class="mi">1000</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span>
<span class="n">cand</span><span class="p">,</span> <span class="p">(</span><span class="n">nexmark_model</span><span class="o">.</span><span class="n">Auction</span><span class="p">,</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Bid</span><span class="p">,</span> <span class="n">nexmark_model</span><span class="o">.</span><span class="n">Person</span><span class="p">)):</span>
<span class="k">return</span> <span class="n">construct_json_dict</span><span class="p">(</span><span class="n">cand</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">cand</span></div>
<div class="viewcode-block" id="millis_to_timestamp"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.millis_to_timestamp">[docs]</a><span class="k">def</span> <span class="nf">millis_to_timestamp</span><span class="p">(</span><span class="n">millis</span><span class="p">):</span>
<span class="c1"># type: (int) -&gt; Timestamp</span>
<span class="n">micro_second</span> <span class="o">=</span> <span class="n">millis</span> <span class="o">*</span> <span class="mi">1000</span>
<span class="k">return</span> <span class="n">Timestamp</span><span class="p">(</span><span class="n">micros</span><span class="o">=</span><span class="n">micro_second</span><span class="p">)</span></div>
<div class="viewcode-block" id="get_counter_metric"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.get_counter_metric">[docs]</a><span class="k">def</span> <span class="nf">get_counter_metric</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
<span class="c1"># type: (PipelineResult, str, str) -&gt; int</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> get specific counter metric from pipeline result</span>
<span class="sd"> Args:</span>
<span class="sd"> result: the PipelineResult which metrics are read from</span>
<span class="sd"> namespace: a string representing the namespace of wanted metric</span>
<span class="sd"> name: a string representing the name of the wanted metric</span>
<span class="sd"> Returns:</span>
<span class="sd"> the result of the wanted metric if it exist, else -1</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">metrics</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">metrics</span><span class="p">()</span><span class="o">.</span><span class="n">query</span><span class="p">(</span>
<span class="n">MetricsFilter</span><span class="p">()</span><span class="o">.</span><span class="n">with_namespace</span><span class="p">(</span><span class="n">namespace</span><span class="p">)</span><span class="o">.</span><span class="n">with_name</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
<span class="n">counters</span> <span class="o">=</span> <span class="n">metrics</span><span class="p">[</span><span class="s1">&#39;counters&#39;</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">counters</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span>
<span class="s1">&#39;</span><span class="si">%d</span><span class="s1"> instead of one metric result matches name: </span><span class="si">%s</span><span class="s1"> in namespace </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">counters</span><span class="p">),</span> <span class="n">name</span><span class="p">,</span> <span class="n">namespace</span><span class="p">))</span>
<span class="k">return</span> <span class="n">counters</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">result</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">counters</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="k">else</span> <span class="o">-</span><span class="mi">1</span></div>
<div class="viewcode-block" id="get_start_time_metric"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.get_start_time_metric">[docs]</a><span class="k">def</span> <span class="nf">get_start_time_metric</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
<span class="c1"># type: (PipelineResult, str, str) -&gt; int</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> get the start time out of all times recorded by the specified distribution</span>
<span class="sd"> metric</span>
<span class="sd"> Args:</span>
<span class="sd"> result: the PipelineResult which metrics are read from</span>
<span class="sd"> namespace: a string representing the namespace of wanted metric</span>
<span class="sd"> name: a string representing the name of the wanted metric</span>
<span class="sd"> Returns:</span>
<span class="sd"> the smallest time in the metric or -1 if it doesn&#39;t exist</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">distributions</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">metrics</span><span class="p">()</span><span class="o">.</span><span class="n">query</span><span class="p">(</span>
<span class="n">MetricsFilter</span><span class="p">()</span><span class="o">.</span><span class="n">with_namespace</span><span class="p">(</span><span class="n">namespace</span><span class="p">)</span><span class="o">.</span><span class="n">with_name</span><span class="p">(</span>
<span class="n">name</span><span class="p">))[</span><span class="s1">&#39;distributions&#39;</span><span class="p">]</span>
<span class="n">min_list</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">m</span><span class="p">:</span> <span class="n">m</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">min</span><span class="p">,</span> <span class="n">distributions</span><span class="p">))</span>
<span class="k">return</span> <span class="nb">min</span><span class="p">(</span><span class="n">min_list</span><span class="p">)</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">min_list</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="k">else</span> <span class="o">-</span><span class="mi">1</span></div>
<div class="viewcode-block" id="get_end_time_metric"><a class="viewcode-back" href="../../../../../apache_beam.testing.benchmarks.nexmark.nexmark_util.html#apache_beam.testing.benchmarks.nexmark.nexmark_util.get_end_time_metric">[docs]</a><span class="k">def</span> <span class="nf">get_end_time_metric</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">namespace</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
<span class="c1"># type: (PipelineResult, str, str) -&gt; int</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> get the end time out of all times recorded by the specified distribution</span>
<span class="sd"> metric</span>
<span class="sd"> Args:</span>
<span class="sd"> result: the PipelineResult which metrics are read from</span>
<span class="sd"> namespace: a string representing the namespace of wanted metric</span>
<span class="sd"> name: a string representing the name of the wanted metric</span>
<span class="sd"> Returns:</span>
<span class="sd"> the largest time in the metric or -1 if it doesn&#39;t exist</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">distributions</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">metrics</span><span class="p">()</span><span class="o">.</span><span class="n">query</span><span class="p">(</span>
<span class="n">MetricsFilter</span><span class="p">()</span><span class="o">.</span><span class="n">with_namespace</span><span class="p">(</span><span class="n">namespace</span><span class="p">)</span><span class="o">.</span><span class="n">with_name</span><span class="p">(</span>
<span class="n">name</span><span class="p">))[</span><span class="s1">&#39;distributions&#39;</span><span class="p">]</span>
<span class="n">max_list</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">m</span><span class="p">:</span> <span class="n">m</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">max</span><span class="p">,</span> <span class="n">distributions</span><span class="p">))</span>
<span class="k">return</span> <span class="nb">max</span><span class="p">(</span><span class="n">max_list</span><span class="p">)</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">max_list</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="k">else</span> <span class="o">-</span><span class="mi">1</span></div>
</pre></div>
</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/rtfd/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">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>