blob: d86168cac796e7e2bb2a376f6a1ccc12fd21a45a [file] [log] [blame]
<!--
Javascript to render AIRFLOW-XXX and PR references in text
as HTML links.
Overrides extrahead block from sphinx_rtd_theme
https://www.sphinx-doc.org/en/master/templating.html
-->
<!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>airflow.contrib.operators.dataflow_operator &mdash; Airflow Documentation</title>
<link rel="shortcut icon" href="../../../../_static/pin_32.png"/>
<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 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="stylesheet" href="../../../../_static/graphviz.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script>
document.addEventListener('DOMContentLoaded', function() {
var el = document.getElementById('changelog');
if (el !== null ) {
// [AIRFLOW-...]
el.innerHTML = el.innerHTML.replace(
/\[(AIRFLOW-[\d]+)\]/g,
`<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>`
);
// (#...)
el.innerHTML = el.innerHTML.replace(
/\(#([\d]+)\)/g,
`<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>`
);
};
})
</script>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-140539454-1']);
_gaq.push(['_trackPageview']);
</script>
<style>
.example-header {
position: relative;
background: #9AAA7A;
padding: 8px 16px;
margin-bottom: 0;
}
.example-header--with-button {
padding-right: 166px;
}
.example-header:after{
content: '';
display: table;
clear: both;
}
.example-title {
display:block;
padding: 4px;
margin-right: 16px;
color: white;
overflow-x: auto;
}
.example-header-button {
top: 8px;
right: 16px;
position: absolute;
}
.example-header + .highlight-python {
margin-top: 0 !important;
}
.viewcode-button {
display: inline-block;
padding: 8px 16px;
border: 0;
margin: 0;
outline: 0;
border-radius: 2px;
-webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3);
box-shadow: 0 3px 6px 0 rgba(0,0,0,.3);
color: #404040;
background-color: #e7e7e7;
cursor: pointer;
font-size: 16px;
font-weight: 500;
line-height: 1;
text-decoration: none;
text-overflow: ellipsis;
overflow: hidden;
text-transform: uppercase;
-webkit-transition: background-color .2s;
transition: background-color .2s;
vertical-align: middle;
white-space: nowrap;
}
.viewcode-button:visited {
color: #404040;
}
.viewcode-button:hover, .viewcode-button:focus {
color: #404040;
background-color: #d6d6d6;
}
</style>
</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"> Airflow
</a>
<div class="version">
1.10.6
</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="../../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</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">Airflow</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><a href="../operators.html">airflow.contrib.operators</a> &raquo;</li>
<li>airflow.contrib.operators.dataflow_operator</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 airflow.contrib.operators.dataflow_operator</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># &quot;License&quot;); you may not use this file except in compliance</span>
<span class="c1"># with 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,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">uuid</span>
<span class="kn">import</span> <span class="nn">copy</span>
<span class="kn">import</span> <span class="nn">tempfile</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcs_hook</span> <span class="k">import</span> <span class="n">GoogleCloudStorageHook</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_dataflow_hook</span> <span class="k">import</span> <span class="n">DataFlowHook</span>
<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.version</span> <span class="k">import</span> <span class="n">version</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<div class="viewcode-block" id="DataFlowJavaOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowJavaOperator">[docs]</a><span class="k">class</span> <span class="nc">DataFlowJavaOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Start a Java Cloud DataFlow batch job. The parameters of the operation</span>
<span class="sd"> will be passed to the job.</span>
<span class="sd"> **Example**: ::</span>
<span class="sd"> default_args = {</span>
<span class="sd"> &#39;owner&#39;: &#39;Airflow&#39;,</span>
<span class="sd"> &#39;depends_on_past&#39;: False,</span>
<span class="sd"> &#39;start_date&#39;:</span>
<span class="sd"> (2016, 8, 1),</span>
<span class="sd"> &#39;email&#39;: [&#39;alex@vanboxel.be&#39;],</span>
<span class="sd"> &#39;email_on_failure&#39;: False,</span>
<span class="sd"> &#39;email_on_retry&#39;: False,</span>
<span class="sd"> &#39;retries&#39;: 1,</span>
<span class="sd"> &#39;retry_delay&#39;: timedelta(minutes=30),</span>
<span class="sd"> &#39;dataflow_default_options&#39;: {</span>
<span class="sd"> &#39;project&#39;: &#39;my-gcp-project&#39;,</span>
<span class="sd"> &#39;zone&#39;: &#39;us-central1-f&#39;,</span>
<span class="sd"> &#39;stagingLocation&#39;: &#39;gs://bucket/tmp/dataflow/staging/&#39;,</span>
<span class="sd"> }</span>
<span class="sd"> }</span>
<span class="sd"> dag = DAG(&#39;test-dag&#39;, default_args=default_args)</span>
<span class="sd"> task = DataFlowJavaOperator(</span>
<span class="sd"> gcp_conn_id=&#39;gcp_default&#39;,</span>
<span class="sd"> task_id=&#39;normalize-cal&#39;,</span>
<span class="sd"> jar=&#39;{{var.value.gcp_dataflow_base}}pipeline-ingress-cal-normalize-1.0.jar&#39;,</span>
<span class="sd"> options={</span>
<span class="sd"> &#39;autoscalingAlgorithm&#39;: &#39;BASIC&#39;,</span>
<span class="sd"> &#39;maxNumWorkers&#39;: &#39;50&#39;,</span>
<span class="sd"> &#39;start&#39;: &#39;{{ds}}&#39;,</span>
<span class="sd"> &#39;partitionType&#39;: &#39;DAY&#39;</span>
<span class="sd"> },</span>
<span class="sd"> dag=dag)</span>
<span class="sd"> .. seealso::</span>
<span class="sd"> For more detail on job submission have a look at the reference:</span>
<span class="sd"> https://cloud.google.com/dataflow/pipelines/specifying-exec-params</span>
<span class="sd"> :param jar: The reference to a self executing DataFlow jar (templated).</span>
<span class="sd"> :type jar: str</span>
<span class="sd"> :param job_name: The &#39;jobName&#39; to use when executing the DataFlow job</span>
<span class="sd"> (templated). This ends up being set in the pipeline options, so any entry</span>
<span class="sd"> with key ``&#39;jobName&#39;`` in ``options`` will be overwritten.</span>
<span class="sd"> :type job_name: str</span>
<span class="sd"> :param dataflow_default_options: Map of default job options.</span>
<span class="sd"> :type dataflow_default_options: dict</span>
<span class="sd"> :param options: Map of job specific options.</span>
<span class="sd"> :type options: dict</span>
<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud</span>
<span class="sd"> Platform.</span>
<span class="sd"> :type gcp_conn_id: str</span>
<span class="sd"> :param delegate_to: The account to impersonate, if any.</span>
<span class="sd"> For this to work, the service account making the request must have</span>
<span class="sd"> domain-wide delegation enabled.</span>
<span class="sd"> :type delegate_to: str</span>
<span class="sd"> :param poll_sleep: The time in seconds to sleep between polling Google</span>
<span class="sd"> Cloud Platform for the dataflow job status while the job is in the</span>
<span class="sd"> JOB_STATE_RUNNING state.</span>
<span class="sd"> :type poll_sleep: int</span>
<span class="sd"> :param job_class: The name of the dataflow job class to be executed, it</span>
<span class="sd"> is often not the main class configured in the dataflow jar file.</span>
<span class="sd"> :type job_class: str</span>
<span class="sd"> ``jar``, ``options``, and ``job_name`` are templated so you can use variables in them.</span>
<span class="sd"> Note that both</span>
<span class="sd"> ``dataflow_default_options`` and ``options`` will be merged to specify pipeline</span>
<span class="sd"> execution parameter, and ``dataflow_default_options`` is expected to save</span>
<span class="sd"> high-level options, for instances, project and zone information, which</span>
<span class="sd"> apply to all dataflow operators in the DAG.</span>
<span class="sd"> It&#39;s a good practice to define dataflow_* parameters in the default_args of the dag</span>
<span class="sd"> like the project, zone and staging location.</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> default_args = {</span>
<span class="sd"> &#39;dataflow_default_options&#39;: {</span>
<span class="sd"> &#39;project&#39;: &#39;my-gcp-project&#39;,</span>
<span class="sd"> &#39;zone&#39;: &#39;europe-west1-d&#39;,</span>
<span class="sd"> &#39;stagingLocation&#39;: &#39;gs://my-staging-bucket/staging/&#39;</span>
<span class="sd"> }</span>
<span class="sd"> }</span>
<span class="sd"> You need to pass the path to your dataflow as a file reference with the ``jar``</span>
<span class="sd"> parameter, the jar needs to be a self executing jar (see documentation here:</span>
<span class="sd"> https://beam.apache.org/documentation/runners/dataflow/#self-executing-jar).</span>
<span class="sd"> Use ``options`` to pass on options to your job.</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> t1 = DataFlowJavaOperator(</span>
<span class="sd"> task_id=&#39;datapflow_example&#39;,</span>
<span class="sd"> jar=&#39;{{var.value.gcp_dataflow_base}}pipeline/build/libs/pipeline-example-1.0.jar&#39;,</span>
<span class="sd"> options={</span>
<span class="sd"> &#39;autoscalingAlgorithm&#39;: &#39;BASIC&#39;,</span>
<span class="sd"> &#39;maxNumWorkers&#39;: &#39;50&#39;,</span>
<span class="sd"> &#39;start&#39;: &#39;{{ds}}&#39;,</span>
<span class="sd"> &#39;partitionType&#39;: &#39;DAY&#39;,</span>
<span class="sd"> &#39;labels&#39;: {&#39;foo&#39; : &#39;bar&#39;}</span>
<span class="sd"> },</span>
<span class="sd"> gcp_conn_id=&#39;gcp-airflow-service-account&#39;,</span>
<span class="sd"> dag=my-dag)</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="DataFlowJavaOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowJavaOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;options&#39;</span><span class="p">,</span> <span class="s1">&#39;jar&#39;</span><span class="p">,</span> <span class="s1">&#39;job_name&#39;</span><span class="p">]</span></div>
<div class="viewcode-block" id="DataFlowJavaOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowJavaOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#0273d4&#39;</span></div>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">jar</span><span class="p">,</span>
<span class="n">job_name</span><span class="o">=</span><span class="s1">&#39;{{task.task_id}}&#39;</span><span class="p">,</span>
<span class="n">dataflow_default_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="n">job_class</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataFlowJavaOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">dataflow_default_options</span> <span class="o">=</span> <span class="n">dataflow_default_options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="n">options</span> <span class="o">=</span> <span class="n">options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="n">options</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="s1">&#39;labels&#39;</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">update</span><span class="p">(</span>
<span class="p">{</span><span class="s1">&#39;airflow-version&#39;</span><span class="p">:</span> <span class="s1">&#39;v&#39;</span> <span class="o">+</span> <span class="n">version</span><span class="o">.</span><span class="n">replace</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><span class="o">.</span><span class="n">replace</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>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span>
<span class="bp">self</span><span class="o">.</span><span class="n">jar</span> <span class="o">=</span> <span class="n">jar</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span> <span class="o">=</span> <span class="n">dataflow_default_options</span>
<span class="bp">self</span><span class="o">.</span><span class="n">options</span> <span class="o">=</span> <span class="n">options</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_class</span> <span class="o">=</span> <span class="n">job_class</span>
<div class="viewcode-block" id="DataFlowJavaOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowJavaOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="n">bucket_helper</span> <span class="o">=</span> <span class="n">GoogleCloudBucketHelper</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">jar</span> <span class="o">=</span> <span class="n">bucket_helper</span><span class="o">.</span><span class="n">google_cloud_to_local</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">jar</span><span class="p">)</span>
<span class="n">hook</span> <span class="o">=</span> <span class="n">DataFlowHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span>
<span class="n">dataflow_options</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span><span class="p">)</span>
<span class="n">dataflow_options</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="p">)</span>
<span class="n">hook</span><span class="o">.</span><span class="n">start_java_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">,</span> <span class="n">dataflow_options</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">jar</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_class</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="DataflowTemplateOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataflowTemplateOperator">[docs]</a><span class="k">class</span> <span class="nc">DataflowTemplateOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Start a Templated Cloud DataFlow batch job. The parameters of the operation</span>
<span class="sd"> will be passed to the job.</span>
<span class="sd"> :param template: The reference to the DataFlow template.</span>
<span class="sd"> :type template: str</span>
<span class="sd"> :param job_name: The &#39;jobName&#39; to use when executing the DataFlow template</span>
<span class="sd"> (templated).</span>
<span class="sd"> :param dataflow_default_options: Map of default job environment options.</span>
<span class="sd"> :type dataflow_default_options: dict</span>
<span class="sd"> :param parameters: Map of job specific parameters for the template.</span>
<span class="sd"> :type parameters: dict</span>
<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud</span>
<span class="sd"> Platform.</span>
<span class="sd"> :type gcp_conn_id: str</span>
<span class="sd"> :param delegate_to: The account to impersonate, if any.</span>
<span class="sd"> For this to work, the service account making the request must have</span>
<span class="sd"> domain-wide delegation enabled.</span>
<span class="sd"> :type delegate_to: str</span>
<span class="sd"> :param poll_sleep: The time in seconds to sleep between polling Google</span>
<span class="sd"> Cloud Platform for the dataflow job status while the job is in the</span>
<span class="sd"> JOB_STATE_RUNNING state.</span>
<span class="sd"> :type poll_sleep: int</span>
<span class="sd"> It&#39;s a good practice to define dataflow_* parameters in the default_args of the dag</span>
<span class="sd"> like the project, zone and staging location.</span>
<span class="sd"> .. seealso::</span>
<span class="sd"> https://cloud.google.com/dataflow/docs/reference/rest/v1b3/LaunchTemplateParameters</span>
<span class="sd"> https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> default_args = {</span>
<span class="sd"> &#39;dataflow_default_options&#39;: {</span>
<span class="sd"> &#39;project&#39;: &#39;my-gcp-project&#39;,</span>
<span class="sd"> &#39;region&#39;: &#39;europe-west1&#39;,</span>
<span class="sd"> &#39;zone&#39;: &#39;europe-west1-d&#39;,</span>
<span class="sd"> &#39;tempLocation&#39;: &#39;gs://my-staging-bucket/staging/&#39;,</span>
<span class="sd"> }</span>
<span class="sd"> }</span>
<span class="sd"> }</span>
<span class="sd"> You need to pass the path to your dataflow template as a file reference with the</span>
<span class="sd"> ``template`` parameter. Use ``parameters`` to pass on parameters to your job.</span>
<span class="sd"> Use ``environment`` to pass on runtime environment variables to your job.</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> t1 = DataflowTemplateOperator(</span>
<span class="sd"> task_id=&#39;datapflow_example&#39;,</span>
<span class="sd"> template=&#39;{{var.value.gcp_dataflow_base}}&#39;,</span>
<span class="sd"> parameters={</span>
<span class="sd"> &#39;inputFile&#39;: &quot;gs://bucket/input/my_input.txt&quot;,</span>
<span class="sd"> &#39;outputFile&#39;: &quot;gs://bucket/output/my_output.txt&quot;</span>
<span class="sd"> },</span>
<span class="sd"> gcp_conn_id=&#39;gcp-airflow-service-account&#39;,</span>
<span class="sd"> dag=my-dag)</span>
<span class="sd"> ``template``, ``dataflow_default_options``, ``parameters``, and ``job_name`` are</span>
<span class="sd"> templated so you can use variables in them.</span>
<span class="sd"> Note that ``dataflow_default_options`` is expected to save high-level options</span>
<span class="sd"> for project information, which apply to all dataflow operators in the DAG.</span>
<span class="sd"> .. seealso::</span>
<span class="sd"> https://cloud.google.com/dataflow/docs/reference/rest/v1b3</span>
<span class="sd"> /LaunchTemplateParameters</span>
<span class="sd"> https://cloud.google.com/dataflow/docs/reference/rest/v1b3/RuntimeEnvironment</span>
<span class="sd"> For more detail on job template execution have a look at the reference:</span>
<span class="sd"> https://cloud.google.com/dataflow/docs/templates/executing-templates</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="DataflowTemplateOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataflowTemplateOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;parameters&#39;</span><span class="p">,</span> <span class="s1">&#39;dataflow_default_options&#39;</span><span class="p">,</span> <span class="s1">&#39;template&#39;</span><span class="p">,</span> <span class="s1">&#39;job_name&#39;</span><span class="p">]</span></div>
<div class="viewcode-block" id="DataflowTemplateOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataflowTemplateOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#0273d4&#39;</span></div>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">template</span><span class="p">,</span>
<span class="n">job_name</span><span class="o">=</span><span class="s1">&#39;{{task.task_id}}&#39;</span><span class="p">,</span>
<span class="n">dataflow_default_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataflowTemplateOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">dataflow_default_options</span> <span class="o">=</span> <span class="n">dataflow_default_options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="n">parameters</span> <span class="o">=</span> <span class="n">parameters</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span> <span class="o">=</span> <span class="n">dataflow_default_options</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<span class="bp">self</span><span class="o">.</span><span class="n">template</span> <span class="o">=</span> <span class="n">template</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">parameters</span>
<div class="viewcode-block" id="DataflowTemplateOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataflowTemplateOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="n">hook</span> <span class="o">=</span> <span class="n">DataFlowHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span>
<span class="n">hook</span><span class="o">.</span><span class="n">start_template_dataflow</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">template</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="DataFlowPythonOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowPythonOperator">[docs]</a><span class="k">class</span> <span class="nc">DataFlowPythonOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Launching Cloud Dataflow jobs written in python. Note that both</span>
<span class="sd"> dataflow_default_options and options will be merged to specify pipeline</span>
<span class="sd"> execution parameter, and dataflow_default_options is expected to save</span>
<span class="sd"> high-level options, for instances, project and zone information, which</span>
<span class="sd"> apply to all dataflow operators in the DAG.</span>
<span class="sd"> .. seealso::</span>
<span class="sd"> For more detail on job submission have a look at the reference:</span>
<span class="sd"> https://cloud.google.com/dataflow/pipelines/specifying-exec-params</span>
<span class="sd"> :param py_file: Reference to the python dataflow pipeline file.py, e.g.,</span>
<span class="sd"> /some/local/file/path/to/your/python/pipeline/file. (templated)</span>
<span class="sd"> :type py_file: str</span>
<span class="sd"> :param job_name: The &#39;job_name&#39; to use when executing the DataFlow job</span>
<span class="sd"> (templated). This ends up being set in the pipeline options, so any entry</span>
<span class="sd"> with key ``&#39;jobName&#39;`` or ``&#39;job_name&#39;`` in ``options`` will be overwritten.</span>
<span class="sd"> :type job_name: str</span>
<span class="sd"> :param py_options: Additional python options, e.g., [&quot;-m&quot;, &quot;-v&quot;].</span>
<span class="sd"> :type pyt_options: list[str]</span>
<span class="sd"> :param dataflow_default_options: Map of default job options.</span>
<span class="sd"> :type dataflow_default_options: dict</span>
<span class="sd"> :param options: Map of job specific options.</span>
<span class="sd"> :type options: dict</span>
<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to Google Cloud</span>
<span class="sd"> Platform.</span>
<span class="sd"> :type gcp_conn_id: str</span>
<span class="sd"> :param delegate_to: The account to impersonate, if any.</span>
<span class="sd"> For this to work, the service account making the request must have</span>
<span class="sd"> domain-wide delegation enabled.</span>
<span class="sd"> :type delegate_to: str</span>
<span class="sd"> :param poll_sleep: The time in seconds to sleep between polling Google</span>
<span class="sd"> Cloud Platform for the dataflow job status while the job is in the</span>
<span class="sd"> JOB_STATE_RUNNING state.</span>
<span class="sd"> :type poll_sleep: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="DataFlowPythonOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowPythonOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;options&#39;</span><span class="p">,</span> <span class="s1">&#39;dataflow_default_options&#39;</span><span class="p">,</span> <span class="s1">&#39;job_name&#39;</span><span class="p">,</span> <span class="s1">&#39;py_file&#39;</span><span class="p">]</span></div>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">py_file</span><span class="p">,</span>
<span class="n">job_name</span><span class="o">=</span><span class="s1">&#39;{{task.task_id}}&#39;</span><span class="p">,</span>
<span class="n">py_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">dataflow_default_options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">options</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DataFlowPythonOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">py_file</span> <span class="o">=</span> <span class="n">py_file</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_name</span> <span class="o">=</span> <span class="n">job_name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">py_options</span> <span class="o">=</span> <span class="n">py_options</span> <span class="ow">or</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span> <span class="o">=</span> <span class="n">dataflow_default_options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">options</span> <span class="o">=</span> <span class="n">options</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="s1">&#39;labels&#39;</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">update</span><span class="p">(</span>
<span class="p">{</span><span class="s1">&#39;airflow-version&#39;</span><span class="p">:</span> <span class="s1">&#39;v&#39;</span> <span class="o">+</span> <span class="n">version</span><span class="o">.</span><span class="n">replace</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><span class="o">.</span><span class="n">replace</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>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span>
<span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span> <span class="o">=</span> <span class="n">poll_sleep</span>
<div class="viewcode-block" id="DataFlowPythonOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.DataFlowPythonOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Execute the python dataflow job.&quot;&quot;&quot;</span>
<span class="n">bucket_helper</span> <span class="o">=</span> <span class="n">GoogleCloudBucketHelper</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">py_file</span> <span class="o">=</span> <span class="n">bucket_helper</span><span class="o">.</span><span class="n">google_cloud_to_local</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">py_file</span><span class="p">)</span>
<span class="n">hook</span> <span class="o">=</span> <span class="n">DataFlowHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">gcp_conn_id</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">,</span>
<span class="n">poll_sleep</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">poll_sleep</span><span class="p">)</span>
<span class="n">dataflow_options</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dataflow_default_options</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
<span class="n">dataflow_options</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="p">)</span>
<span class="c1"># Convert argument names from lowerCamelCase to snake case.</span>
<span class="n">camel_to_snake</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">name</span><span class="p">:</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span>
<span class="sa">r</span><span class="s1">&#39;[A-Z]&#39;</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="s1">&#39;_&#39;</span> <span class="o">+</span> <span class="n">x</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">lower</span><span class="p">(),</span> <span class="n">name</span><span class="p">)</span>
<span class="n">formatted_options</span> <span class="o">=</span> <span class="p">{</span><span class="n">camel_to_snake</span><span class="p">(</span><span class="n">key</span><span class="p">):</span> <span class="n">dataflow_options</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">dataflow_options</span><span class="p">}</span>
<span class="n">hook</span><span class="o">.</span><span class="n">start_python_dataflow</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_name</span><span class="p">,</span> <span class="n">formatted_options</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">py_file</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">py_options</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="GoogleCloudBucketHelper"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.GoogleCloudBucketHelper">[docs]</a><span class="k">class</span> <span class="nc">GoogleCloudBucketHelper</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;GoogleCloudStorageHook helper class to download GCS object.&quot;&quot;&quot;</span>
<div class="viewcode-block" id="GoogleCloudBucketHelper.GCS_PREFIX_LENGTH"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.GoogleCloudBucketHelper.GCS_PREFIX_LENGTH">[docs]</a> <span class="n">GCS_PREFIX_LENGTH</span> <span class="o">=</span> <span class="mi">5</span></div>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">&#39;google_cloud_default&#39;</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_gcs_hook</span> <span class="o">=</span> <span class="n">GoogleCloudStorageHook</span><span class="p">(</span><span class="n">gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="p">)</span>
<div class="viewcode-block" id="GoogleCloudBucketHelper.google_cloud_to_local"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dataflow_operator/index.html#airflow.contrib.operators.dataflow_operator.GoogleCloudBucketHelper.google_cloud_to_local">[docs]</a> <span class="k">def</span> <span class="nf">google_cloud_to_local</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_name</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Checks whether the file specified by file_name is stored in Google Cloud</span>
<span class="sd"> Storage (GCS), if so, downloads the file and saves it locally. The full</span>
<span class="sd"> path of the saved file will be returned. Otherwise the local file_name</span>
<span class="sd"> will be returned immediately.</span>
<span class="sd"> :param file_name: The full path of input file.</span>
<span class="sd"> :type file_name: str</span>
<span class="sd"> :return: The full path of local file.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">file_name</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="k">return</span> <span class="n">file_name</span>
<span class="c1"># Extracts bucket_id and object_id by first removing &#39;gs://&#39; prefix and</span>
<span class="c1"># then split the remaining by path delimiter &#39;/&#39;.</span>
<span class="n">path_components</span> <span class="o">=</span> <span class="n">file_name</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">GCS_PREFIX_LENGTH</span><span class="p">:]</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="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">path_components</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span>
<span class="s1">&#39;Invalid Google Cloud Storage (GCS) object path: </span><span class="si">{}</span><span class="s1">&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_name</span><span class="p">))</span>
<span class="n">bucket_id</span> <span class="o">=</span> <span class="n">path_components</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">object_id</span> <span class="o">=</span> <span class="s1">&#39;/&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">path_components</span><span class="p">[</span><span class="mi">1</span><span class="p">:])</span>
<span class="n">local_file</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
<span class="n">tempfile</span><span class="o">.</span><span class="n">gettempdir</span><span class="p">(),</span>
<span class="s1">&#39;dataflow</span><span class="si">{}</span><span class="s1">-</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</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="mi">8</span><span class="p">],</span> <span class="n">path_components</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_gcs_hook</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">bucket_id</span><span class="p">,</span> <span class="n">object_id</span><span class="p">,</span> <span class="n">local_file</span><span class="p">)</span>
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">stat</span><span class="p">(</span><span class="n">local_file</span><span class="p">)</span><span class="o">.</span><span class="n">st_size</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="n">local_file</span>
<span class="k">raise</span> <span class="ne">Exception</span><span class="p">(</span>
<span class="s1">&#39;Failed to download Google Cloud Storage (GCS) object: </span><span class="si">{}</span><span class="s1">&#39;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_name</span><span class="p">))</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</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>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../../privacy_notice.html">Privacy Policy</a>
for more details.
<script type="text/javascript">
(function() {
var ga = document.createElement('script');
ga.src = ('https:' == document.location.protocol ?
'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
ga.setAttribute('async', 'true');
var nodes = document.documentElement.childNodes;
var i = -1;
var node;
do {
i++;
node = nodes[i]
} while(node.nodeType !== Node.ELEMENT_NODE);
node.appendChild(ga);
})();
</script>
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>