blob: f432477a441cbe6cb027b1b41b6e628d71e42988 [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.io.external.gcp.pubsub &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.io.external.gcp.pubsub</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.io.external.gcp.pubsub</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="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">typing</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.io.gcp</span> <span class="kn">import</span> <span class="n">pubsub</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">Map</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.external</span> <span class="kn">import</span> <span class="n">ExternalTransform</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms.external</span> <span class="kn">import</span> <span class="n">NamedTupleBasedPayloadBuilder</span>
<span class="n">ReadFromPubsubSchema</span> <span class="o">=</span> <span class="n">typing</span><span class="o">.</span><span class="n">NamedTuple</span><span class="p">(</span>
<span class="s1">&#39;ReadFromPubsubSchema&#39;</span><span class="p">,</span>
<span class="p">[</span>
<span class="p">(</span><span class="s1">&#39;topic&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;subscription&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;id_label&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="p">(</span><span class="s1">&#39;with_attributes&#39;</span><span class="p">,</span> <span class="nb">bool</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;timestamp_attribute&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="p">])</span>
<div class="viewcode-block" id="ReadFromPubSub"><a class="viewcode-back" href="../../../../../apache_beam.io.external.gcp.pubsub.html#apache_beam.io.external.gcp.pubsub.ReadFromPubSub">[docs]</a><span class="k">class</span> <span class="nc">ReadFromPubSub</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An external ``PTransform`` for reading from Cloud Pub/Sub.</span>
<span class="sd"> Experimental; no backwards compatibility guarantees. It requires special</span>
<span class="sd"> preparation of the Java SDK. See https://github.com/apache/beam/issues/19728.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">URN</span> <span class="o">=</span> <span class="s1">&#39;beam:transform:org.apache.beam:pubsub_read:v1&#39;</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">topic</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">subscription</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">id_label</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">with_attributes</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">timestamp_attribute</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initializes ``ReadFromPubSub``.</span>
<span class="sd"> Args:</span>
<span class="sd"> topic: Cloud Pub/Sub topic in the form</span>
<span class="sd"> &quot;projects/&lt;project&gt;/topics/&lt;topic&gt;&quot;. If provided, subscription must be</span>
<span class="sd"> None.</span>
<span class="sd"> subscription: Existing Cloud Pub/Sub subscription to use in the</span>
<span class="sd"> form &quot;projects/&lt;project&gt;/subscriptions/&lt;subscription&gt;&quot;. If not</span>
<span class="sd"> specified, a temporary subscription will be created from the specified</span>
<span class="sd"> topic. If provided, topic must be None.</span>
<span class="sd"> id_label: The attribute on incoming Pub/Sub messages to use as a unique</span>
<span class="sd"> record identifier. When specified, the value of this attribute (which</span>
<span class="sd"> can be any string that uniquely identifies the record) will be used for</span>
<span class="sd"> deduplication of messages. If not provided, we cannot guarantee</span>
<span class="sd"> that no duplicate data will be delivered on the Pub/Sub stream. In this</span>
<span class="sd"> case, deduplication of the stream will be strictly best effort.</span>
<span class="sd"> with_attributes:</span>
<span class="sd"> True - output elements will be</span>
<span class="sd"> :class:`~apache_beam.io.gcp.pubsub.PubsubMessage` objects.</span>
<span class="sd"> False - output elements will be of type ``bytes`` (message</span>
<span class="sd"> data only).</span>
<span class="sd"> timestamp_attribute: Message value to use as element timestamp. If None,</span>
<span class="sd"> uses message publishing time as the timestamp.</span>
<span class="sd"> Timestamp values should be in one of two formats:</span>
<span class="sd"> - A numerical value representing the number of milliseconds since the</span>
<span class="sd"> Unix epoch.</span>
<span class="sd"> - A string in RFC 3339 format, UTC timezone. Example:</span>
<span class="sd"> ``2015-10-29T23:41:41.123Z``. The sub-second component of the</span>
<span class="sd"> timestamp is optional, and digits beyond the first three (i.e., time</span>
<span class="sd"> units smaller than milliseconds) may be ignored.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span> <span class="o">=</span> <span class="n">ReadFromPubsubSchema</span><span class="p">(</span>
<span class="n">topic</span><span class="o">=</span><span class="n">topic</span><span class="p">,</span>
<span class="n">subscription</span><span class="o">=</span><span class="n">subscription</span><span class="p">,</span>
<span class="n">id_label</span><span class="o">=</span><span class="n">id_label</span><span class="p">,</span>
<span class="n">with_attributes</span><span class="o">=</span><span class="n">with_attributes</span><span class="p">,</span>
<span class="n">timestamp_attribute</span><span class="o">=</span><span class="n">timestamp_attribute</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span>
<div class="viewcode-block" id="ReadFromPubSub.expand"><a class="viewcode-back" href="../../../../../apache_beam.io.external.gcp.pubsub.html#apache_beam.io.external.gcp.pubsub.ReadFromPubSub.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">pbegin</span><span class="p">):</span>
<span class="n">pcoll</span> <span class="o">=</span> <span class="n">pbegin</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span>
<span class="n">ExternalTransform</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span>
<span class="n">NamedTupleBasedPayloadBuilder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="p">),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span><span class="p">))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">with_attributes</span><span class="p">:</span>
<span class="n">pcoll</span> <span class="o">=</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="s1">&#39;FromProto&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">Map</span><span class="p">(</span><span class="n">pubsub</span><span class="o">.</span><span class="n">PubsubMessage</span><span class="o">.</span><span class="n">_from_proto_str</span><span class="p">)</span>
<span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span> <span class="o">=</span> <span class="n">pubsub</span><span class="o">.</span><span class="n">PubsubMessage</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span> <span class="o">=</span> <span class="nb">bytes</span>
<span class="k">return</span> <span class="n">pcoll</span></div></div>
<span class="n">WriteToPubsubSchema</span> <span class="o">=</span> <span class="n">typing</span><span class="o">.</span><span class="n">NamedTuple</span><span class="p">(</span>
<span class="s1">&#39;WriteToPubsubSchema&#39;</span><span class="p">,</span>
<span class="p">[</span>
<span class="p">(</span><span class="s1">&#39;topic&#39;</span><span class="p">,</span> <span class="nb">str</span><span class="p">),</span>
<span class="p">(</span><span class="s1">&#39;id_label&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="c1"># this is not implemented yet on the Java side:</span>
<span class="c1"># (&#39;with_attributes&#39;, bool),</span>
<span class="p">(</span><span class="s1">&#39;timestamp_attribute&#39;</span><span class="p">,</span> <span class="n">typing</span><span class="o">.</span><span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]),</span>
<span class="p">])</span>
<div class="viewcode-block" id="WriteToPubSub"><a class="viewcode-back" href="../../../../../apache_beam.io.external.gcp.pubsub.html#apache_beam.io.external.gcp.pubsub.WriteToPubSub">[docs]</a><span class="k">class</span> <span class="nc">WriteToPubSub</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An external ``PTransform`` for writing messages to Cloud Pub/Sub.</span>
<span class="sd"> Experimental; no backwards compatibility guarantees. It requires special</span>
<span class="sd"> preparation of the Java SDK. See https://github.com/apache/beam/issues/19728.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">URN</span> <span class="o">=</span> <span class="s1">&#39;beam:transform:org.apache.beam:pubsub_write:v1&#39;</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">topic</span><span class="p">,</span>
<span class="n">with_attributes</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">id_label</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">timestamp_attribute</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initializes ``WriteToPubSub``.</span>
<span class="sd"> Args:</span>
<span class="sd"> topic: Cloud Pub/Sub topic in the form &quot;/topics/&lt;project&gt;/&lt;topic&gt;&quot;.</span>
<span class="sd"> with_attributes:</span>
<span class="sd"> True - input elements will be</span>
<span class="sd"> :class:`~apache_beam.io.gcp.pubsub.PubsubMessage` objects.</span>
<span class="sd"> False - input elements will be of type ``bytes`` (message</span>
<span class="sd"> data only).</span>
<span class="sd"> id_label: If set, will set an attribute for each Cloud Pub/Sub message</span>
<span class="sd"> with the given name and a unique value. This attribute can then be used</span>
<span class="sd"> in a ReadFromPubSub PTransform to deduplicate messages.</span>
<span class="sd"> timestamp_attribute: If set, will set an attribute for each Cloud Pub/Sub</span>
<span class="sd"> message with the given name and the message&#39;s publish time as the value.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span> <span class="o">=</span> <span class="n">WriteToPubsubSchema</span><span class="p">(</span>
<span class="n">topic</span><span class="o">=</span><span class="n">topic</span><span class="p">,</span>
<span class="n">id_label</span><span class="o">=</span><span class="n">id_label</span><span class="p">,</span>
<span class="c1"># with_attributes=with_attributes,</span>
<span class="n">timestamp_attribute</span><span class="o">=</span><span class="n">timestamp_attribute</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span>
<span class="bp">self</span><span class="o">.</span><span class="n">with_attributes</span> <span class="o">=</span> <span class="n">with_attributes</span>
<div class="viewcode-block" id="WriteToPubSub.expand"><a class="viewcode-back" href="../../../../../apache_beam.io.external.gcp.pubsub.html#apache_beam.io.external.gcp.pubsub.WriteToPubSub.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">pvalue</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">with_attributes</span><span class="p">:</span>
<span class="n">pcoll</span> <span class="o">=</span> <span class="n">pvalue</span> <span class="o">|</span> <span class="s1">&#39;ToProto&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">Map</span><span class="p">(</span><span class="n">pubsub</span><span class="o">.</span><span class="n">WriteToPubSub</span><span class="o">.</span><span class="n">to_proto_str</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pcoll</span> <span class="o">=</span> <span class="n">pvalue</span> <span class="o">|</span> <span class="s1">&#39;ToProto&#39;</span> <span class="o">&gt;&gt;</span> <span class="n">Map</span><span class="p">(</span>
<span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">pubsub</span><span class="o">.</span><span class="n">PubsubMessage</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">_to_proto_str</span><span class="p">())</span>
<span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span> <span class="o">=</span> <span class="nb">bytes</span>
<span class="k">return</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span>
<span class="n">ExternalTransform</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span>
<span class="n">NamedTupleBasedPayloadBuilder</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="p">),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">expansion_service</span><span class="p">))</span></div></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>