You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/27 16:26:46 UTC
[26/51] [partial] incubator-airflow-site git commit: 1.10.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/pubsub_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/pubsub_operator.html b/_modules/airflow/contrib/operators/pubsub_operator.html
new file mode 100644
index 0000000..99a540f
--- /dev/null
+++ b/_modules/airflow/contrib/operators/pubsub_operator.html
@@ -0,0 +1,669 @@
+
+
+<!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.pubsub_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../../index.html"/>
+ <link rel="up" title="Module code" href="../../../index.html"/>
+
+
+ <script src="../../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../../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</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & 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">Experimental Rest API</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="../../../../lineage.html">Lineage</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="../../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">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> »</li>
+
+ <li><a href="../../../index.html">Module code</a> »</li>
+
+ <li>airflow.contrib.operators.pubsub_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.pubsub_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"># "License"); 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"># "AS IS" 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">from</span> <span class="nn">airflow.contrib.hooks.gcp_pubsub_hook</span> <span class="k">import</span> <span class="n">PubSubHook</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.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="PubSubTopicCreateOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.pubsub_operator.PubSubTopicCreateOperator">[docs]</a><span class="k">class</span> <span class="nc">PubSubTopicCreateOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""Create a PubSub topic.</span>
+
+<span class="sd"> By default, if the topic already exists, this operator will</span>
+<span class="sd"> not cause the DAG to fail. ::</span>
+
+<span class="sd"> with DAG('successful DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubTopicCreateOperator(project='my-project',</span>
+<span class="sd"> topic='my_new_topic')</span>
+<span class="sd"> >> PubSubTopicCreateOperator(project='my-project',</span>
+<span class="sd"> topic='my_new_topic')</span>
+<span class="sd"> )</span>
+
+<span class="sd"> The operator can be configured to fail if the topic already exists. ::</span>
+
+<span class="sd"> with DAG('failing DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubTopicCreateOperator(project='my-project',</span>
+<span class="sd"> topic='my_new_topic')</span>
+<span class="sd"> >> PubSubTopicCreateOperator(project='my-project',</span>
+<span class="sd"> topic='my_new_topic',</span>
+<span class="sd"> fail_if_exists=True)</span>
+<span class="sd"> )</span>
+
+<span class="sd"> Both ``project`` and ``topic`` are templated so you can use</span>
+<span class="sd"> variables in them.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'project'</span><span class="p">,</span> <span class="s1">'topic'</span><span class="p">]</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span>
+
+ <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">project</span><span class="p">,</span>
+ <span class="n">topic</span><span class="p">,</span>
+ <span class="n">fail_if_exists</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</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="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="sd">"""</span>
+<span class="sd"> :param project: the GCP project ID where the topic will be created</span>
+<span class="sd"> :type project: string</span>
+<span class="sd"> :param topic: the topic to create. Do not include the</span>
+<span class="sd"> full topic path. In other words, instead of</span>
+<span class="sd"> ``projects/{project}/topics/{topic}``, provide only</span>
+<span class="sd"> ``{topic}``. (templated)</span>
+<span class="sd"> :type topic: string</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to</span>
+<span class="sd"> Google Cloud Platform.</span>
+<span class="sd"> :type gcp_conn_id: string</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</span>
+<span class="sd"> must have domain-wide delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PubSubTopicCreateOperator</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">project</span> <span class="o">=</span> <span class="n">project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">topic</span> <span class="o">=</span> <span class="n">topic</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fail_if_exists</span> <span class="o">=</span> <span class="n">fail_if_exists</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="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">PubSubHook</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">hook</span><span class="o">.</span><span class="n">create_topic</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">topic</span><span class="p">,</span>
+ <span class="n">fail_if_exists</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">fail_if_exists</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PubSubSubscriptionCreateOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.pubsub_operator.PubSubSubscriptionCreateOperator">[docs]</a><span class="k">class</span> <span class="nc">PubSubSubscriptionCreateOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""Create a PubSub subscription.</span>
+
+<span class="sd"> By default, the subscription will be created in ``topic_project``. If</span>
+<span class="sd"> ``subscription_project`` is specified and the GCP credentials allow, the</span>
+<span class="sd"> Subscription can be created in a different project from its topic.</span>
+
+<span class="sd"> By default, if the subscription already exists, this operator will</span>
+<span class="sd"> not cause the DAG to fail. However, the topic must exist in the project. ::</span>
+
+<span class="sd"> with DAG('successful DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubSubscriptionCreateOperator(</span>
+<span class="sd"> topic_project='my-project', topic='my-topic',</span>
+<span class="sd"> subscription='my-subscription')</span>
+<span class="sd"> >> PubSubSubscriptionCreateOperator(</span>
+<span class="sd"> topic_project='my-project', topic='my-topic',</span>
+<span class="sd"> subscription='my-subscription')</span>
+<span class="sd"> )</span>
+
+<span class="sd"> The operator can be configured to fail if the subscription already exists.</span>
+<span class="sd"> ::</span>
+
+<span class="sd"> with DAG('failing DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubSubscriptionCreateOperator(</span>
+<span class="sd"> topic_project='my-project', topic='my-topic',</span>
+<span class="sd"> subscription='my-subscription')</span>
+<span class="sd"> >> PubSubSubscriptionCreateOperator(</span>
+<span class="sd"> topic_project='my-project', topic='my-topic',</span>
+<span class="sd"> subscription='my-subscription', fail_if_exists=True)</span>
+<span class="sd"> )</span>
+
+<span class="sd"> Finally, subscription is not required. If not passed, the operator will</span>
+<span class="sd"> generated a universally unique identifier for the subscription's name. ::</span>
+
+<span class="sd"> with DAG('DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag >> PubSubSubscriptionCreateOperator(</span>
+<span class="sd"> topic_project='my-project', topic='my-topic')</span>
+<span class="sd"> )</span>
+
+<span class="sd"> ``topic_project``, ``topic``, ``subscription``, and</span>
+<span class="sd"> ``subscription`` are templated so you can use variables in them.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'topic_project'</span><span class="p">,</span> <span class="s1">'topic'</span><span class="p">,</span> <span class="s1">'subscription'</span><span class="p">,</span>
+ <span class="s1">'subscription_project'</span><span class="p">]</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span>
+
+ <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">topic_project</span><span class="p">,</span>
+ <span class="n">topic</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">subscription_project</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">ack_deadline_secs</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span>
+ <span class="n">fail_if_exists</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</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="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="sd">"""</span>
+<span class="sd"> :param topic_project: the GCP project ID where the topic exists</span>
+<span class="sd"> :type topic_project: string</span>
+<span class="sd"> :param topic: the topic to create. Do not include the</span>
+<span class="sd"> full topic path. In other words, instead of</span>
+<span class="sd"> ``projects/{project}/topics/{topic}``, provide only</span>
+<span class="sd"> ``{topic}``. (templated)</span>
+<span class="sd"> :type topic: string</span>
+<span class="sd"> :param subscription: the Pub/Sub subscription name. If empty, a random</span>
+<span class="sd"> name will be generated using the uuid module</span>
+<span class="sd"> :type subscription: string</span>
+<span class="sd"> :param subscription_project: the GCP project ID where the subscription</span>
+<span class="sd"> will be created. If empty, ``topic_project`` will be used.</span>
+<span class="sd"> :type subscription_project: string</span>
+<span class="sd"> :param ack_deadline_secs: Number of seconds that a subscriber has to</span>
+<span class="sd"> acknowledge each message pulled from the subscription</span>
+<span class="sd"> :type ack_deadline_secs: int</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to</span>
+<span class="sd"> Google Cloud Platform.</span>
+<span class="sd"> :type gcp_conn_id: string</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</span>
+<span class="sd"> must have domain-wide delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PubSubSubscriptionCreateOperator</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">topic_project</span> <span class="o">=</span> <span class="n">topic_project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">topic</span> <span class="o">=</span> <span class="n">topic</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">subscription</span> <span class="o">=</span> <span class="n">subscription</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">subscription_project</span> <span class="o">=</span> <span class="n">subscription_project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">ack_deadline_secs</span> <span class="o">=</span> <span class="n">ack_deadline_secs</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fail_if_exists</span> <span class="o">=</span> <span class="n">fail_if_exists</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="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">PubSubHook</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="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_subscription</span><span class="p">(</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">topic_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">topic</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">subscription</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">subscription_project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">ack_deadline_secs</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fail_if_exists</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PubSubTopicDeleteOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.pubsub_operator.PubSubTopicDeleteOperator">[docs]</a><span class="k">class</span> <span class="nc">PubSubTopicDeleteOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""Delete a PubSub topic.</span>
+
+<span class="sd"> By default, if the topic does not exist, this operator will</span>
+<span class="sd"> not cause the DAG to fail. ::</span>
+
+<span class="sd"> with DAG('successful DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubTopicDeleteOperator(project='my-project',</span>
+<span class="sd"> topic='non_existing_topic')</span>
+<span class="sd"> )</span>
+
+<span class="sd"> The operator can be configured to fail if the topic does not exist. ::</span>
+
+<span class="sd"> with DAG('failing DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubTopicCreateOperator(project='my-project',</span>
+<span class="sd"> topic='non_existing_topic',</span>
+<span class="sd"> fail_if_not_exists=True)</span>
+<span class="sd"> )</span>
+
+<span class="sd"> Both ``project`` and ``topic`` are templated so you can use</span>
+<span class="sd"> variables in them.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'project'</span><span class="p">,</span> <span class="s1">'topic'</span><span class="p">]</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#cb4335'</span>
+
+ <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">project</span><span class="p">,</span>
+ <span class="n">topic</span><span class="p">,</span>
+ <span class="n">fail_if_not_exists</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</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="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="sd">"""</span>
+<span class="sd"> :param project: the GCP project ID in which to work (templated)</span>
+<span class="sd"> :type project: string</span>
+<span class="sd"> :param topic: the topic to delete. Do not include the</span>
+<span class="sd"> full topic path. In other words, instead of</span>
+<span class="sd"> ``projects/{project}/topics/{topic}``, provide only</span>
+<span class="sd"> ``{topic}``. (templated)</span>
+<span class="sd"> :type topic: string</span>
+<span class="sd"> :param fail_if_not_exists: If True and the topic does not exist, fail</span>
+<span class="sd"> the task</span>
+<span class="sd"> :type fail_if_not_exists: bool</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to</span>
+<span class="sd"> Google Cloud Platform.</span>
+<span class="sd"> :type gcp_conn_id: string</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</span>
+<span class="sd"> must have domain-wide delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PubSubTopicDeleteOperator</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">project</span> <span class="o">=</span> <span class="n">project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">topic</span> <span class="o">=</span> <span class="n">topic</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fail_if_not_exists</span> <span class="o">=</span> <span class="n">fail_if_not_exists</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="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">PubSubHook</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">hook</span><span class="o">.</span><span class="n">delete_topic</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">topic</span><span class="p">,</span>
+ <span class="n">fail_if_not_exists</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">fail_if_not_exists</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PubSubSubscriptionDeleteOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.pubsub_operator.PubSubSubscriptionDeleteOperator">[docs]</a><span class="k">class</span> <span class="nc">PubSubSubscriptionDeleteOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""Delete a PubSub subscription.</span>
+
+<span class="sd"> By default, if the subscription does not exist, this operator will</span>
+<span class="sd"> not cause the DAG to fail. ::</span>
+
+<span class="sd"> with DAG('successful DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubSubscriptionDeleteOperator(project='my-project',</span>
+<span class="sd"> subscription='non-existing')</span>
+<span class="sd"> )</span>
+
+<span class="sd"> The operator can be configured to fail if the subscription already exists.</span>
+
+<span class="sd"> ::</span>
+
+<span class="sd"> with DAG('failing DAG') as dag:</span>
+<span class="sd"> (</span>
+<span class="sd"> dag</span>
+<span class="sd"> >> PubSubSubscriptionDeleteOperator(</span>
+<span class="sd"> project='my-project', subscription='non-existing',</span>
+<span class="sd"> fail_if_not_exists=True)</span>
+<span class="sd"> )</span>
+
+<span class="sd"> ``project``, and ``subscription`` are templated so you can use</span>
+<span class="sd"> variables in them.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'project'</span><span class="p">,</span> <span class="s1">'subscription'</span><span class="p">]</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#cb4335'</span>
+
+ <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">project</span><span class="p">,</span>
+ <span class="n">subscription</span><span class="p">,</span>
+ <span class="n">fail_if_not_exists</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</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="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="sd">"""</span>
+<span class="sd"> :param project: the GCP project ID in which to work (templated)</span>
+<span class="sd"> :type project: string</span>
+<span class="sd"> :param subscription: the subscription to delete. Do not include the</span>
+<span class="sd"> full subscription path. In other words, instead of</span>
+<span class="sd"> ``projects/{project}/subscription/{subscription}``, provide only</span>
+<span class="sd"> ``{subscription}``. (templated)</span>
+<span class="sd"> :type subscription: string</span>
+<span class="sd"> :param fail_if_not_exists: If True and the subscription does not exist,</span>
+<span class="sd"> fail the task</span>
+<span class="sd"> :type fail_if_not_exists: bool</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to</span>
+<span class="sd"> Google Cloud Platform.</span>
+<span class="sd"> :type gcp_conn_id: string</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</span>
+<span class="sd"> must have domain-wide delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PubSubSubscriptionDeleteOperator</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">project</span> <span class="o">=</span> <span class="n">project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">subscription</span> <span class="o">=</span> <span class="n">subscription</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">fail_if_not_exists</span> <span class="o">=</span> <span class="n">fail_if_not_exists</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="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">PubSubHook</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">hook</span><span class="o">.</span><span class="n">delete_subscription</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">subscription</span><span class="p">,</span>
+ <span class="n">fail_if_not_exists</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">fail_if_not_exists</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PubSubPublishOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.pubsub_operator.PubSubPublishOperator">[docs]</a><span class="k">class</span> <span class="nc">PubSubPublishOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""Publish messages to a PubSub topic.</span>
+
+<span class="sd"> Each Task publishes all provided messages to the same topic</span>
+<span class="sd"> in a single GCP project. If the topic does not exist, this</span>
+<span class="sd"> task will fail. ::</span>
+
+<span class="sd"> from base64 import b64encode as b64e</span>
+
+<span class="sd"> m1 = {'data': b64e('Hello, World!'),</span>
+<span class="sd"> 'attributes': {'type': 'greeting'}</span>
+<span class="sd"> }</span>
+<span class="sd"> m2 = {'data': b64e('Knock, knock')}</span>
+<span class="sd"> m3 = {'attributes': {'foo': ''}}</span>
+
+<span class="sd"> t1 = PubSubPublishOperator(</span>
+<span class="sd"> project='my-project',topic='my_topic',</span>
+<span class="sd"> messages=[m1, m2, m3],</span>
+<span class="sd"> create_topic=True,</span>
+<span class="sd"> dag=dag)</span>
+
+<span class="sd"> ``project`` , ``topic``, and ``messages`` are templated so you can use</span>
+<span class="sd"> variables in them.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'project'</span><span class="p">,</span> <span class="s1">'topic'</span><span class="p">,</span> <span class="s1">'messages'</span><span class="p">]</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#0273d4'</span>
+
+ <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">project</span><span class="p">,</span>
+ <span class="n">topic</span><span class="p">,</span>
+ <span class="n">messages</span><span class="p">,</span>
+ <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</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="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="sd">"""</span>
+<span class="sd"> :param project: the GCP project ID in which to work (templated)</span>
+<span class="sd"> :type project: string</span>
+<span class="sd"> :param topic: the topic to which to publish. Do not include the</span>
+<span class="sd"> full topic path. In other words, instead of</span>
+<span class="sd"> ``projects/{project}/topics/{topic}``, provide only</span>
+<span class="sd"> ``{topic}``. (templated)</span>
+<span class="sd"> :type topic: string</span>
+<span class="sd"> :param messages: a list of messages to be published to the</span>
+<span class="sd"> topic. Each message is a dict with one or more of the</span>
+<span class="sd"> following keys-value mappings:</span>
+<span class="sd"> * 'data': a base64-encoded string</span>
+<span class="sd"> * 'attributes': {'key1': 'value1', ...}</span>
+<span class="sd"> Each message must contain at least a non-empty 'data' value</span>
+<span class="sd"> or an attribute dict with at least one key. See</span>
+<span class="sd"> https://cloud.google.com/pubsub/docs/reference/rest/v1/PubsubMessage</span>
+<span class="sd"> (templated)</span>
+<span class="sd"> :type messages: list</span>
+<span class="sd"> :param gcp_conn_id: The connection ID to use connecting to</span>
+<span class="sd"> Google Cloud Platform.</span>
+<span class="sd"> :type gcp_conn_id: string</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</span>
+<span class="sd"> must have domain-wide delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PubSubPublishOperator</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">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">project</span> <span class="o">=</span> <span class="n">project</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">topic</span> <span class="o">=</span> <span class="n">topic</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">messages</span> <span class="o">=</span> <span class="n">messages</span>
+
+ <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">PubSubHook</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">hook</span><span class="o">.</span><span class="n">publish</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">project</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">topic</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">messages</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </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/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../../_static/doctools.js"></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/qubole_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/qubole_operator.html b/_modules/airflow/contrib/operators/qubole_operator.html
new file mode 100644
index 0000000..b14626b
--- /dev/null
+++ b/_modules/airflow/contrib/operators/qubole_operator.html
@@ -0,0 +1,411 @@
+
+
+<!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.qubole_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../../index.html"/>
+ <link rel="up" title="Module code" href="../../../index.html"/>
+
+
+ <script src="../../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../../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</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & 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">Experimental Rest API</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="../../../../lineage.html">Lineage</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="../../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">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> »</li>
+
+ <li><a href="../../../index.html">Module code</a> »</li>
+
+ <li>airflow.contrib.operators.qubole_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.qubole_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"># "License"); 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"># "AS IS" 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">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.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
+<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.qubole_hook</span> <span class="k">import</span> <span class="n">QuboleHook</span>
+
+
+<div class="viewcode-block" id="QuboleOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.qubole_operator.QuboleOperator">[docs]</a><span class="k">class</span> <span class="nc">QuboleOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Execute tasks (commands) on QDS (https://qubole.com).</span>
+
+<span class="sd"> :param qubole_conn_id: Connection id which consists of qds auth_token</span>
+<span class="sd"> :type qubole_conn_id: str</span>
+
+<span class="sd"> kwargs:</span>
+<span class="sd"> :command_type: type of command to be executed, e.g. hivecmd, shellcmd, hadoopcmd</span>
+<span class="sd"> :tags: array of tags to be assigned with the command</span>
+<span class="sd"> :cluster_label: cluster label on which the command will be executed</span>
+<span class="sd"> :name: name to be given to command</span>
+<span class="sd"> :notify: whether to send email on command completion or not (default is False)</span>
+
+<span class="sd"> **Arguments specific to command types**</span>
+
+<span class="sd"> hivecmd:</span>
+<span class="sd"> :query: inline query statement</span>
+<span class="sd"> :script_location: s3 location containing query statement</span>
+<span class="sd"> :sample_size: size of sample in bytes on which to run query</span>
+<span class="sd"> :macros: macro values which were used in query</span>
+<span class="sd"> prestocmd:</span>
+<span class="sd"> :query: inline query statement</span>
+<span class="sd"> :script_location: s3 location containing query statement</span>
+<span class="sd"> :macros: macro values which were used in query</span>
+<span class="sd"> hadoopcmd:</span>
+<span class="sd"> :sub_commnad: must be one these ["jar", "s3distcp", "streaming"] followed by</span>
+<span class="sd"> 1 or more args</span>
+<span class="sd"> shellcmd:</span>
+<span class="sd"> :script: inline command with args</span>
+<span class="sd"> :script_location: s3 location containing query statement</span>
+<span class="sd"> :files: list of files in s3 bucket as file1,file2 format. These files will be</span>
+<span class="sd"> copied into the working directory where the qubole command is being</span>
+<span class="sd"> executed.</span>
+<span class="sd"> :archives: list of archives in s3 bucket as archive1,archive2 format. These</span>
+<span class="sd"> will be unarchived intothe working directory where the qubole command is</span>
+<span class="sd"> being executed</span>
+<span class="sd"> :parameters: any extra args which need to be passed to script (only when</span>
+<span class="sd"> script_location is supplied)</span>
+<span class="sd"> pigcmd:</span>
+<span class="sd"> :script: inline query statement (latin_statements)</span>
+<span class="sd"> :script_location: s3 location containing pig query</span>
+<span class="sd"> :parameters: any extra args which need to be passed to script (only when</span>
+<span class="sd"> script_location is supplied</span>
+<span class="sd"> sparkcmd:</span>
+<span class="sd"> :program: the complete Spark Program in Scala, SQL, Command, R, or Python</span>
+<span class="sd"> :cmdline: spark-submit command line, all required information must be specify</span>
+<span class="sd"> in cmdline itself.</span>
+<span class="sd"> :sql: inline sql query</span>
+<span class="sd"> :script_location: s3 location containing query statement</span>
+<span class="sd"> :language: language of the program, Scala, SQL, Command, R, or Python</span>
+<span class="sd"> :app_id: ID of an Spark job server app</span>
+<span class="sd"> :arguments: spark-submit command line arguments</span>
+<span class="sd"> :user_program_arguments: arguments that the user program takes in</span>
+<span class="sd"> :macros: macro values which were used in query</span>
+<span class="sd"> dbtapquerycmd:</span>
+<span class="sd"> :db_tap_id: data store ID of the target database, in Qubole.</span>
+<span class="sd"> :query: inline query statement</span>
+<span class="sd"> :macros: macro values which were used in query</span>
+<span class="sd"> dbexportcmd:</span>
+<span class="sd"> :mode: 1 (simple), 2 (advance)</span>
+<span class="sd"> :hive_table: Name of the hive table</span>
+<span class="sd"> :partition_spec: partition specification for Hive table.</span>
+<span class="sd"> :dbtap_id: data store ID of the target database, in Qubole.</span>
+<span class="sd"> :db_table: name of the db table</span>
+<span class="sd"> :db_update_mode: allowinsert or updateonly</span>
+<span class="sd"> :db_update_keys: columns used to determine the uniqueness of rows</span>
+<span class="sd"> :export_dir: HDFS/S3 location from which data will be exported.</span>
+<span class="sd"> :fields_terminated_by: hex of the char used as column separator in the dataset</span>
+<span class="sd"> dbimportcmd:</span>
+<span class="sd"> :mode: 1 (simple), 2 (advance)</span>
+<span class="sd"> :hive_table: Name of the hive table</span>
+<span class="sd"> :dbtap_id: data store ID of the target database, in Qubole.</span>
+<span class="sd"> :db_table: name of the db table</span>
+<span class="sd"> :where_clause: where clause, if any</span>
+<span class="sd"> :parallelism: number of parallel db connections to use for extracting data</span>
+<span class="sd"> :extract_query: SQL query to extract data from db. $CONDITIONS must be part</span>
+<span class="sd"> of the where clause.</span>
+<span class="sd"> :boundary_query: Query to be used get range of row IDs to be extracted</span>
+<span class="sd"> :split_column: Column used as row ID to split data into ranges (mode 2)</span>
+
+<span class="sd"> .. note:: Following fields are template-supported : ``query``, ``script_location``,</span>
+<span class="sd"> ``sub_command``, ``script``, ``files``, ``archives``, ``program``, ``cmdline``,</span>
+<span class="sd"> ``sql``, ``where_clause``, ``extract_query``, ``boundary_query``, ``macros``,</span>
+<span class="sd"> ``tags``, ``name``, ``parameters``, ``dbtap_id``, ``hive_table``, ``db_table``,</span>
+<span class="sd"> ``split_column``, ``note_id``, ``db_update_keys``, ``export_dir``,</span>
+<span class="sd"> ``partition_spec``, ``qubole_conn_id``, ``arguments``, ``user_program_arguments``.</span>
+<span class="sd"> You can also use ``.txt`` files for template driven use cases.</span>
+
+<span class="sd"> .. note:: In QuboleOperator there is a default handler for task failures and retries,</span>
+<span class="sd"> which generally kills the command running at QDS for the corresponding task</span>
+<span class="sd"> instance. You can override this behavior by providing your own failure and retry</span>
+<span class="sd"> handler in task definition.</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'query'</span><span class="p">,</span> <span class="s1">'script_location'</span><span class="p">,</span> <span class="s1">'sub_command'</span><span class="p">,</span> <span class="s1">'script'</span><span class="p">,</span> <span class="s1">'files'</span><span class="p">,</span>
+ <span class="s1">'archives'</span><span class="p">,</span> <span class="s1">'program'</span><span class="p">,</span> <span class="s1">'cmdline'</span><span class="p">,</span> <span class="s1">'sql'</span><span class="p">,</span> <span class="s1">'where_clause'</span><span class="p">,</span> <span class="s1">'tags'</span><span class="p">,</span>
+ <span class="s1">'extract_query'</span><span class="p">,</span> <span class="s1">'boundary_query'</span><span class="p">,</span> <span class="s1">'macros'</span><span class="p">,</span> <span class="s1">'name'</span><span class="p">,</span> <span class="s1">'parameters'</span><span class="p">,</span>
+ <span class="s1">'dbtap_id'</span><span class="p">,</span> <span class="s1">'hive_table'</span><span class="p">,</span> <span class="s1">'db_table'</span><span class="p">,</span> <span class="s1">'split_column'</span><span class="p">,</span> <span class="s1">'note_id'</span><span class="p">,</span>
+ <span class="s1">'db_update_keys'</span><span class="p">,</span> <span class="s1">'export_dir'</span><span class="p">,</span> <span class="s1">'partition_spec'</span><span class="p">,</span> <span class="s1">'qubole_conn_id'</span><span class="p">,</span>
+ <span class="s1">'arguments'</span><span class="p">,</span> <span class="s1">'user_program_arguments'</span><span class="p">)</span>
+
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.txt'</span><span class="p">,)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#3064A1'</span>
+ <span class="n">ui_fgcolor</span> <span class="o">=</span> <span class="s1">'#fff'</span>
+
+ <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">qubole_conn_id</span><span class="o">=</span><span class="s2">"qubole_default"</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">args</span> <span class="o">=</span> <span class="n">args</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span> <span class="o">=</span> <span class="n">kwargs</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">[</span><span class="s1">'qubole_conn_id'</span><span class="p">]</span> <span class="o">=</span> <span class="n">qubole_conn_id</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">QuboleOperator</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">on_failure_callback</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">on_failure_callback</span> <span class="o">=</span> <span class="n">QuboleHook</span><span class="o">.</span><span class="n">handle_failure_retry</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">on_retry_callback</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">on_retry_callback</span> <span class="o">=</span> <span class="n">QuboleHook</span><span class="o">.</span><span class="n">handle_failure_retry</span>
+
+ <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="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">context</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">on_kill</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ti</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">get_hook</span><span class="p">()</span><span class="o">.</span><span class="n">kill</span><span class="p">(</span><span class="n">ti</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">get_results</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ti</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">fp</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">inline</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">delim</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">fetch</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_results</span><span class="p">(</span><span class="n">ti</span><span class="p">,</span> <span class="n">fp</span><span class="p">,</span> <span class="n">inline</span><span class="p">,</span> <span class="n">delim</span><span class="p">,</span> <span class="n">fetch</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">get_log</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ti</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_log</span><span class="p">(</span><span class="n">ti</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">get_jobs_id</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ti</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_jobs_id</span><span class="p">(</span><span class="n">ti</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">get_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="c1"># Reinitiating the hook, as some template fields might have changed</span>
+ <span class="k">return</span> <span class="n">QuboleHook</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="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">QuboleOperator</span><span class="o">.</span><span class="n">template_fields</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">[</span><span class="n">name</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="s1">''</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="nb">object</span><span class="o">.</span><span class="fm">__getattribute__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">__setattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">QuboleOperator</span><span class="o">.</span><span class="n">template_fields</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="nb">object</span><span class="o">.</span><span class="fm">__setattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </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/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../../_static/doctools.js"></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/s3_list_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/s3_list_operator.html b/_modules/airflow/contrib/operators/s3_list_operator.html
new file mode 100644
index 0000000..531f835
--- /dev/null
+++ b/_modules/airflow/contrib/operators/s3_list_operator.html
@@ -0,0 +1,317 @@
+
+
+<!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.s3_list_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="index" title="Index"
+ href="../../../../genindex.html"/>
+ <link rel="search" title="Search" href="../../../../search.html"/>
+ <link rel="top" title="Airflow Documentation" href="../../../../index.html"/>
+ <link rel="up" title="Module code" href="../../../index.html"/>
+
+
+ <script src="../../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../../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</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & 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">Experimental Rest API</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="../../../../lineage.html">Lineage</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="../../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">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> »</li>
+
+ <li><a href="../../../index.html">Module code</a> »</li>
+
+ <li>airflow.contrib.operators.s3_list_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.s3_list_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"># "License"); 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"># "AS IS" 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">from</span> <span class="nn">airflow.hooks.S3_hook</span> <span class="k">import</span> <span class="n">S3Hook</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.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="S3ListOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.s3_list_operator.S3ListOperator">[docs]</a><span class="k">class</span> <span class="nc">S3ListOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> List all objects from the bucket with the given string prefix in name.</span>
+
+<span class="sd"> This operator returns a python list with the name of objects which can be</span>
+<span class="sd"> used by `xcom` in the downstream task.</span>
+
+<span class="sd"> :param bucket: The S3 bucket where to find the objects.</span>
+<span class="sd"> :type bucket: string</span>
+<span class="sd"> :param prefix: Prefix string to filters the objects whose name begin with</span>
+<span class="sd"> such prefix</span>
+<span class="sd"> :type prefix: string</span>
+<span class="sd"> :param delimiter: the delimiter marks key hierarchy.</span>
+<span class="sd"> :type delimiter: string</span>
+<span class="sd"> :param aws_conn_id: The connection ID to use when connecting to S3 storage.</span>
+<span class="sd"> :type aws_conn_id: string</span>
+
+<span class="sd"> **Example**:</span>
+<span class="sd"> The following operator would list all the files</span>
+<span class="sd"> (excluding subfolders) from the S3</span>
+<span class="sd"> ``customers/2018/04/`` key in the ``data`` bucket. ::</span>
+
+<span class="sd"> s3_file = S3ListOperator(</span>
+<span class="sd"> task_id='list_3s_files',</span>
+<span class="sd"> bucket='data',</span>
+<span class="sd"> prefix='customers/2018/04/',</span>
+<span class="sd"> delimiter='/',</span>
+<span class="sd"> aws_conn_id='aws_customers_conn'</span>
+<span class="sd"> )</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'bucket'</span><span class="p">,</span> <span class="s1">'prefix'</span><span class="p">,</span> <span class="s1">'delimiter'</span><span class="p">)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#ffd700'</span>
+
+ <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">bucket</span><span class="p">,</span>
+ <span class="n">prefix</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span>
+ <span class="n">delimiter</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span>
+ <span class="n">aws_conn_id</span><span class="o">=</span><span class="s1">'aws_default'</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">S3ListOperator</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">bucket</span> <span class="o">=</span> <span class="n">bucket</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">prefix</span> <span class="o">=</span> <span class="n">prefix</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span> <span class="o">=</span> <span class="n">delimiter</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span> <span class="o">=</span> <span class="n">aws_conn_id</span>
+
+ <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">S3Hook</span><span class="p">(</span><span class="n">aws_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span><span class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Getting the list of files from bucket: </span><span class="si">{0}</span><span class="s1"> in prefix: </span><span class="si">{1}</span><span class="s1"> (Delimiter </span><span class="si">{2}</span><span class="s1">)'</span><span class="o">.</span>
+ <span class="nb">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span><span class="p">))</span>
+
+ <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">list_keys</span><span class="p">(</span>
+ <span class="n">bucket_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket</span><span class="p">,</span>
+ <span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span>
+ <span class="n">delimiter</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ <div class="articleComments">
+
+ </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/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../../',
+ VERSION:'',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../../_static/doctools.js"></script>
+
+
+
+
+
+ <script type="text/javascript" src="../../../../_static/js/theme.js"></script>
+
+
+
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.StickyNav.enable();
+ });
+ </script>
+
+
+</body>
+</html>
\ No newline at end of file