You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by cr...@apache.org on 2018/01/03 17:48:29 UTC
[29/35] incubator-airflow-site git commit: 1.9.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/operators/bigquery_to_gcs.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/bigquery_to_gcs.html b/_modules/airflow/contrib/operators/bigquery_to_gcs.html
index 97cf815..31355ff 100644
--- a/_modules/airflow/contrib/operators/bigquery_to_gcs.html
+++ b/_modules/airflow/contrib/operators/bigquery_to_gcs.html
@@ -13,6 +13,8 @@
+
+
@@ -30,6 +32,9 @@
+ <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"/>
@@ -40,6 +45,7 @@
<body class="wy-body-for-nav" role="document">
+
<div class="wy-grid-for-nav">
@@ -76,7 +82,10 @@
- <ul>
+
+
+
+ <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>
@@ -90,6 +99,8 @@
<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="../../../../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="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li>
</ul>
@@ -104,8 +115,10 @@
<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>
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../../index.html">Airflow</a>
+
</nav>
@@ -118,19 +131,36 @@
+
+
+
+
+
+
+
+
+
+
<div role="navigation" aria-label="breadcrumbs navigation">
+
<ul class="wy-breadcrumbs">
- <li><a href="../../../../index.html">Docs</a> »</li>
-
+
+ <li><a href="../../../../index.html">Docs</a> »</li>
+
<li><a href="../../../index.html">Module code</a> »</li>
-
- <li>airflow.contrib.operators.bigquery_to_gcs</li>
+
+ <li>airflow.contrib.operators.bigquery_to_gcs</li>
+
+
<li class="wy-breadcrumbs-aside">
-
+
</li>
+
</ul>
+
+
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
@@ -151,65 +181,63 @@
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
-<span class="kn">import</span> <span class="nn">logging</span>
+<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</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.bigquery_hook</span> <span class="kn">import</span> <span class="n">BigQueryHook</span>
-<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span>
-<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
-
-<div class="viewcode-block" id="BigQueryToCloudStorageOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.bigquery_to_gcs.BigQueryToCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryToCloudStorageOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+<div class="viewcode-block" id="BigQueryToCloudStorageOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_to_gcs.BigQueryToCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryToCloudStorageOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Transfers a BigQuery table to a Google Cloud Storage bucket.</span>
+
+<span class="sd"> See here:</span>
+
+<span class="sd"> https://cloud.google.com/bigquery/docs/reference/v2/jobs</span>
+
+<span class="sd"> For more details about these parameters.</span>
+
+<span class="sd"> :param source_project_dataset_table: The dotted</span>
+<span class="sd"> (<project>.|<project>:)<dataset>.<table> BigQuery table to use as the source</span>
+<span class="sd"> data. If <project> is not included, project will be the project defined in</span>
+<span class="sd"> the connection json.</span>
+<span class="sd"> :type source_project_dataset_table: string</span>
+<span class="sd"> :param destination_cloud_storage_uris: The destination Google Cloud</span>
+<span class="sd"> Storage URI (e.g. gs://some-bucket/some-file.txt). Follows</span>
+<span class="sd"> convention defined here:</span>
+<span class="sd"> https://cloud.google.com/bigquery/exporting-data-from-bigquery#exportingmultiple</span>
+<span class="sd"> :type destination_cloud_storage_uris: list</span>
+<span class="sd"> :param compression: Type of compression to use.</span>
+<span class="sd"> :type compression: string</span>
+<span class="sd"> :param export_format: File format to export.</span>
+<span class="sd"> :type field_delimiter: string</span>
+<span class="sd"> :param field_delimiter: The delimiter to use when extracting to a CSV.</span>
+<span class="sd"> :type field_delimiter: string</span>
+<span class="sd"> :param print_header: Whether to print a header for a CSV file extract.</span>
+<span class="sd"> :type print_header: boolean</span>
+<span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span>
+<span class="sd"> :type bigquery_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 must have domain-wide</span>
+<span class="sd"> delegation enabled.</span>
+<span class="sd"> :type delegate_to: string</span>
<span class="sd"> """</span>
- <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'source_project_dataset_table'</span><span class="p">,</span><span class="s1">'destination_cloud_storage_uris'</span><span class="p">,)</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'source_project_dataset_table'</span><span class="p">,</span> <span class="s1">'destination_cloud_storage_uris'</span><span class="p">)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#e4e6f0'</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">source_project_dataset_table</span><span class="p">,</span>
- <span class="n">destination_cloud_storage_uris</span><span class="p">,</span>
- <span class="n">compression</span><span class="o">=</span><span class="s1">'NONE'</span><span class="p">,</span>
- <span class="n">export_format</span><span class="o">=</span><span class="s1">'CSV'</span><span class="p">,</span>
- <span class="n">field_delimiter</span><span class="o">=</span><span class="s1">','</span><span class="p">,</span>
- <span class="n">print_header</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span>
- <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span>
- <span class="n">delegate_to</span><span class="o">=</span><span class="bp">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"> Create a new BigQueryToCloudStorage to move data from BigQuery to</span>
-<span class="sd"> Google Cloud Storage. See here:</span>
-
-<span class="sd"> https://cloud.google.com/bigquery/docs/reference/v2/jobs</span>
-
-<span class="sd"> For more details about these parameters.</span>
-
-<span class="sd"> :param source_project_dataset_table: The dotted (<project>.)<dataset>.<table> BigQuery table to use as the</span>
-<span class="sd"> source data. If <project> is not included, project will be the project defined in the connection json.</span>
-<span class="sd"> :type source_project_dataset_table: string</span>
-<span class="sd"> :param destination_cloud_storage_uris: The destination Google Cloud</span>
-<span class="sd"> Storage URI (e.g. gs://some-bucket/some-file.txt). Follows</span>
-<span class="sd"> convention defined here:</span>
-<span class="sd"> https://cloud.google.com/bigquery/exporting-data-from-bigquery#exportingmultiple</span>
-<span class="sd"> :type destination_cloud_storage_uris: list</span>
-<span class="sd"> :param compression: Type of compression to use.</span>
-<span class="sd"> :type compression: string</span>
-<span class="sd"> :param export_format: File format to export.</span>
-<span class="sd"> :type field_delimiter: string</span>
-<span class="sd"> :param field_delimiter: The delimiter to use when extracting to a CSV.</span>
-<span class="sd"> :type field_delimiter: string</span>
-<span class="sd"> :param print_header: Whether to print a header for a CSV file extract.</span>
-<span class="sd"> :type print_header: boolean</span>
-<span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span>
-<span class="sd"> :type bigquery_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 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">BigQueryToCloudStorageOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
+ <span class="n">source_project_dataset_table</span><span class="p">,</span>
+ <span class="n">destination_cloud_storage_uris</span><span class="p">,</span>
+ <span class="n">compression</span><span class="o">=</span><span class="s1">'NONE'</span><span class="p">,</span>
+ <span class="n">export_format</span><span class="o">=</span><span class="s1">'CSV'</span><span class="p">,</span>
+ <span class="n">field_delimiter</span><span class="o">=</span><span class="s1">','</span><span class="p">,</span>
+ <span class="n">print_header</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+ <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_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="nb">super</span><span class="p">(</span><span class="n">BigQueryToCloudStorageOperator</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">source_project_dataset_table</span> <span class="o">=</span> <span class="n">source_project_dataset_table</span>
<span class="bp">self</span><span class="o">.</span><span class="n">destination_cloud_storage_uris</span> <span class="o">=</span> <span class="n">destination_cloud_storage_uris</span>
<span class="bp">self</span><span class="o">.</span><span class="n">compression</span> <span class="o">=</span> <span class="n">compression</span>
@@ -220,8 +248,11 @@
<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">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing extract of </span><span class="si">%s</span><span class="s1"> into: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_project_dataset_table</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_cloud_storage_uris</span><span class="p">)</span>
- <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_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="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">'Executing extract of </span><span class="si">%s</span><span class="s1"> into: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">source_project_dataset_table</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">destination_cloud_storage_uris</span><span class="p">)</span>
+ <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_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">conn</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="n">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span>
<span class="n">cursor</span><span class="o">.</span><span class="n">run_extract</span><span class="p">(</span>
@@ -234,6 +265,9 @@
</pre></div>
</div>
+ <div class="articleComments">
+
+ </div>
</div>
<footer>
@@ -266,7 +300,8 @@
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
- HAS_SOURCE: true
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/operators/databricks_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/databricks_operator.html b/_modules/airflow/contrib/operators/databricks_operator.html
new file mode 100644
index 0000000..cb38349
--- /dev/null
+++ b/_modules/airflow/contrib/operators/databricks_operator.html
@@ -0,0 +1,487 @@
+
+
+<!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.databricks_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="../../../../configuration.html">Configuration</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="../../../../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="../../../../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.databricks_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.databricks_operator</h1><div class="highlight"><pre>
+<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
+<span class="c1"># you may not use this file except in compliance with the License.</span>
+<span class="c1"># You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
+<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
+<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
+<span class="c1"># See the License for the specific language governing permissions and</span>
+<span class="c1"># limitations under the License.</span>
+<span class="c1">#</span>
+
+<span class="kn">import</span> <span class="nn">six</span>
+<span class="kn">import</span> <span class="nn">time</span>
+
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span>
+<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.databricks_hook</span> <span class="k">import</span> <span class="n">DatabricksHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
+
+
+<div class="viewcode-block" id="DatabricksSubmitRunOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.databricks_operator.DatabricksSubmitRunOperator">[docs]</a><span class="k">class</span> <span class="nc">DatabricksSubmitRunOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Submits an Spark job run to Databricks using the</span>
+<span class="sd"> `api/2.0/jobs/runs/submit</span>
+<span class="sd"> <https://docs.databricks.com/api/latest/jobs.html#runs-submit>`_</span>
+<span class="sd"> API endpoint.</span>
+
+<span class="sd"> There are two ways to instantiate this operator.</span>
+
+<span class="sd"> In the first way, you can take the JSON payload that you typically use</span>
+<span class="sd"> to call the ``api/2.0/jobs/runs/submit`` endpoint and pass it directly</span>
+<span class="sd"> to our ``DatabricksSubmitRunOperator`` through the ``json`` parameter.</span>
+<span class="sd"> For example ::</span>
+<span class="sd"> json = {</span>
+<span class="sd"> 'new_cluster': {</span>
+<span class="sd"> 'spark_version': '2.1.0-db3-scala2.11',</span>
+<span class="sd"> 'num_workers': 2</span>
+<span class="sd"> },</span>
+<span class="sd"> 'notebook_task': {</span>
+<span class="sd"> 'notebook_path': '/Users/airflow@example.com/PrepareData',</span>
+<span class="sd"> },</span>
+<span class="sd"> }</span>
+<span class="sd"> notebook_run = DatabricksSubmitRunOperator(task_id='notebook_run', json=json)</span>
+
+<span class="sd"> Another way to accomplish the same thing is to use the named parameters</span>
+<span class="sd"> of the ``DatabricksSubmitRunOperator`` directly. Note that there is exactly</span>
+<span class="sd"> one named parameter for each top level parameter in the ``runs/submit``</span>
+<span class="sd"> endpoint. In this method, your code would look like this: ::</span>
+<span class="sd"> new_cluster = {</span>
+<span class="sd"> 'spark_version': '2.1.0-db3-scala2.11',</span>
+<span class="sd"> 'num_workers': 2</span>
+<span class="sd"> }</span>
+<span class="sd"> notebook_task = {</span>
+<span class="sd"> 'notebook_path': '/Users/airflow@example.com/PrepareData',</span>
+<span class="sd"> }</span>
+<span class="sd"> notebook_run = DatabricksSubmitRunOperator(</span>
+<span class="sd"> task_id='notebook_run',</span>
+<span class="sd"> new_cluster=new_cluster,</span>
+<span class="sd"> notebook_task=notebook_task)</span>
+
+<span class="sd"> In the case where both the json parameter **AND** the named parameters</span>
+<span class="sd"> are provided, they will be merged together. If there are conflicts during the merge,</span>
+<span class="sd"> the named parameters will take precedence and override the top level ``json`` keys.</span>
+
+<span class="sd"> Currently the named parameters that ``DatabricksSubmitRunOperator`` supports are</span>
+<span class="sd"> - ``spark_jar_task``</span>
+<span class="sd"> - ``notebook_task``</span>
+<span class="sd"> - ``new_cluster``</span>
+<span class="sd"> - ``existing_cluster_id``</span>
+<span class="sd"> - ``libraries``</span>
+<span class="sd"> - ``run_name``</span>
+<span class="sd"> - ``timeout_seconds``</span>
+
+<span class="sd"> :param json: A JSON object containing API parameters which will be passed</span>
+<span class="sd"> directly to the ``api/2.0/jobs/runs/submit`` endpoint. The other named parameters</span>
+<span class="sd"> (i.e. ``spark_jar_task``, ``notebook_task``..) to this operator will</span>
+<span class="sd"> be merged with this json dictionary if they are provided.</span>
+<span class="sd"> If there are conflicts during the merge, the named parameters will</span>
+<span class="sd"> take precedence and override the top level json keys. This field will be</span>
+<span class="sd"> templated.</span>
+
+<span class="sd"> .. seealso::</span>
+<span class="sd"> For more information about templating see :ref:`jinja-templating`.</span>
+<span class="sd"> https://docs.databricks.com/api/latest/jobs.html#runs-submit</span>
+<span class="sd"> :type json: dict</span>
+<span class="sd"> :param spark_jar_task: The main class and parameters for the JAR task. Note that</span>
+<span class="sd"> the actual JAR is specified in the ``libraries``.</span>
+<span class="sd"> *EITHER* ``spark_jar_task`` *OR* ``notebook_task`` should be specified.</span>
+<span class="sd"> This field will be templated.</span>
+
+<span class="sd"> .. seealso::</span>
+<span class="sd"> https://docs.databricks.com/api/latest/jobs.html#jobssparkjartask</span>
+<span class="sd"> :type spark_jar_task: dict</span>
+<span class="sd"> :param notebook_task: The notebook path and parameters for the notebook task.</span>
+<span class="sd"> *EITHER* ``spark_jar_task`` *OR* ``notebook_task`` should be specified.</span>
+<span class="sd"> This field will be templated.</span>
+
+<span class="sd"> .. seealso::</span>
+<span class="sd"> https://docs.databricks.com/api/latest/jobs.html#jobsnotebooktask</span>
+<span class="sd"> :type notebook_task: dict</span>
+<span class="sd"> :param new_cluster: Specs for a new cluster on which this task will be run.</span>
+<span class="sd"> *EITHER* ``new_cluster`` *OR* ``existing_cluster_id`` should be specified.</span>
+<span class="sd"> This field will be templated.</span>
+
+<span class="sd"> .. seealso::</span>
+<span class="sd"> https://docs.databricks.com/api/latest/jobs.html#jobsclusterspecnewcluster</span>
+<span class="sd"> :type new_cluster: dict</span>
+<span class="sd"> :param existing_cluster_id: ID for existing cluster on which to run this task.</span>
+<span class="sd"> *EITHER* ``new_cluster`` *OR* ``existing_cluster_id`` should be specified.</span>
+<span class="sd"> This field will be templated.</span>
+<span class="sd"> :type existing_cluster_id: string</span>
+<span class="sd"> :param libraries: Libraries which this run will use.</span>
+<span class="sd"> This field will be templated.</span>
+
+<span class="sd"> .. seealso::</span>
+<span class="sd"> https://docs.databricks.com/api/latest/libraries.html#managedlibrarieslibrary</span>
+<span class="sd"> :type libraries: list of dicts</span>
+<span class="sd"> :param run_name: The run name used for this task.</span>
+<span class="sd"> By default this will be set to the Airflow ``task_id``. This ``task_id`` is a</span>
+<span class="sd"> required parameter of the superclass ``BaseOperator``.</span>
+<span class="sd"> This field will be templated.</span>
+<span class="sd"> :type run_name: string</span>
+<span class="sd"> :param timeout_seconds: The timeout for this run. By default a value of 0 is used</span>
+<span class="sd"> which means to have no timeout.</span>
+<span class="sd"> This field will be templated.</span>
+<span class="sd"> :type timeout_seconds: int32</span>
+<span class="sd"> :param databricks_conn_id: The name of the Airflow connection to use.</span>
+<span class="sd"> By default and in the common case this will be ``databricks_default``. To use</span>
+<span class="sd"> token based authentication, provide the key ``token`` in the extra field for the</span>
+<span class="sd"> connection.</span>
+<span class="sd"> :type databricks_conn_id: string</span>
+<span class="sd"> :param polling_period_seconds: Controls the rate which we poll for the result of</span>
+<span class="sd"> this run. By default the operator will poll every 30 seconds.</span>
+<span class="sd"> :type polling_period_seconds: int</span>
+<span class="sd"> :param databricks_retry_limit: Amount of times retry if the Databricks backend is</span>
+<span class="sd"> unreachable. Its value must be greater than or equal to 1.</span>
+<span class="sd"> :type databricks_retry_limit: int</span>
+<span class="sd"> """</span>
+ <span class="c1"># Used in airflow.models.BaseOperator</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'json'</span><span class="p">,)</span>
+ <span class="c1"># Databricks brand color (blue) under white text</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#1CB1C2'</span>
+ <span class="n">ui_fgcolor</span> <span class="o">=</span> <span class="s1">'#fff'</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">json</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">spark_jar_task</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">notebook_task</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">new_cluster</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">existing_cluster_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">libraries</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">run_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">timeout_seconds</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">databricks_conn_id</span><span class="o">=</span><span class="s1">'databricks_default'</span><span class="p">,</span>
+ <span class="n">polling_period_seconds</span><span class="o">=</span><span class="mi">30</span><span class="p">,</span>
+ <span class="n">databricks_retry_limit</span><span class="o">=</span><span class="mi">3</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"> Creates a new ``DatabricksSubmitRunOperator``.</span>
+<span class="sd"> """</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">DatabricksSubmitRunOperator</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">kwargs</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span> <span class="o">=</span> <span class="n">json</span> <span class="ow">or</span> <span class="p">{}</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn_id</span> <span class="o">=</span> <span class="n">databricks_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">polling_period_seconds</span> <span class="o">=</span> <span class="n">polling_period_seconds</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">databricks_retry_limit</span> <span class="o">=</span> <span class="n">databricks_retry_limit</span>
+ <span class="k">if</span> <span class="n">spark_jar_task</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'spark_jar_task'</span><span class="p">]</span> <span class="o">=</span> <span class="n">spark_jar_task</span>
+ <span class="k">if</span> <span class="n">notebook_task</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'notebook_task'</span><span class="p">]</span> <span class="o">=</span> <span class="n">notebook_task</span>
+ <span class="k">if</span> <span class="n">new_cluster</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'new_cluster'</span><span class="p">]</span> <span class="o">=</span> <span class="n">new_cluster</span>
+ <span class="k">if</span> <span class="n">existing_cluster_id</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'existing_cluster_id'</span><span class="p">]</span> <span class="o">=</span> <span class="n">existing_cluster_id</span>
+ <span class="k">if</span> <span class="n">libraries</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'libraries'</span><span class="p">]</span> <span class="o">=</span> <span class="n">libraries</span>
+ <span class="k">if</span> <span class="n">run_name</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'run_name'</span><span class="p">]</span> <span class="o">=</span> <span class="n">run_name</span>
+ <span class="k">if</span> <span class="n">timeout_seconds</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'timeout_seconds'</span><span class="p">]</span> <span class="o">=</span> <span class="n">timeout_seconds</span>
+ <span class="k">if</span> <span class="s1">'run_name'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">[</span><span class="s1">'run_name'</span><span class="p">]</span> <span class="o">=</span> <span class="n">run_name</span> <span class="ow">or</span> <span class="n">kwargs</span><span class="p">[</span><span class="s1">'task_id'</span><span class="p">]</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">json</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_deep_string_coerce</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">)</span>
+ <span class="c1"># This variable will be used in case our task gets killed.</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">run_id</span> <span class="o">=</span> <span class="kc">None</span>
+
+ <span class="k">def</span> <span class="nf">_deep_string_coerce</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">content</span><span class="p">,</span> <span class="n">json_path</span><span class="o">=</span><span class="s1">'json'</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Coerces content or all values of content if it is a dict to a string. The</span>
+<span class="sd"> function will throw if content contains non-string or non-numeric types.</span>
+
+<span class="sd"> The reason why we have this function is because the ``self.json`` field must be a dict</span>
+<span class="sd"> with only string values. This is because ``render_template`` will fail for numerical values.</span>
+<span class="sd"> """</span>
+ <span class="n">c</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_deep_string_coerce</span>
+ <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">content</span><span class="p">,</span> <span class="n">six</span><span class="o">.</span><span class="n">string_types</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">content</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">content</span><span class="p">,</span> <span class="n">six</span><span class="o">.</span><span class="n">integer_types</span><span class="o">+</span><span class="p">(</span><span class="nb">float</span><span class="p">,)):</span>
+ <span class="c1"># Databricks can tolerate either numeric or string types in the API backend.</span>
+ <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">content</span><span class="p">)</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">content</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
+ <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="s1">'</span><span class="si">{0}</span><span class="s1">[</span><span class="si">{1}</span><span class="s1">]'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">json_path</span><span class="p">,</span> <span class="n">i</span><span class="p">))</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">e</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">content</span><span class="p">)]</span>
+ <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">content</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
+ <span class="k">return</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">c</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="s1">'</span><span class="si">{0}</span><span class="s1">[</span><span class="si">{1}</span><span class="s1">]'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">json_path</span><span class="p">,</span> <span class="n">k</span><span class="p">))</span>
+ <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="n">content</span><span class="o">.</span><span class="n">items</span><span class="p">())}</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">param_type</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="n">content</span><span class="p">)</span>
+ <span class="n">msg</span> <span class="o">=</span> <span class="s1">'Type </span><span class="si">{0}</span><span class="s1"> used for parameter </span><span class="si">{1}</span><span class="s1"> is not a number or a string'</span> \
+ <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">param_type</span><span class="p">,</span> <span class="n">json_path</span><span class="p">)</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">_log_run_page_url</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">url</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">'View run status, Spark UI, and logs at </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">url</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="k">return</span> <span class="n">DatabricksHook</span><span class="p">(</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">databricks_conn_id</span><span class="p">,</span>
+ <span class="n">retry_limit</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">databricks_retry_limit</span><span class="p">)</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="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">run_id</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">submit_run</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">json</span><span class="p">)</span>
+ <span class="n">run_page_url</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_run_page_url</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">run_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">'Run submitted with run_id: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">run_id</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_log_run_page_url</span><span class="p">(</span><span class="n">run_page_url</span><span class="p">)</span>
+ <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
+ <span class="n">run_state</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_run_state</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">run_id</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">run_state</span><span class="o">.</span><span class="n">is_terminal</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">run_state</span><span class="o">.</span><span class="n">is_successful</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">'</span><span class="si">%s</span><span class="s1"> completed successfully.'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_log_run_page_url</span><span class="p">(</span><span class="n">run_page_url</span><span class="p">)</span>
+ <span class="k">return</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">error_message</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{t}</span><span class="s1"> failed with terminal state: </span><span class="si">{s}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+ <span class="n">t</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span>
+ <span class="n">s</span><span class="o">=</span><span class="n">run_state</span><span class="p">)</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">error_message</span><span class="p">)</span>
+ <span class="k">else</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">'</span><span class="si">%s</span><span class="s1"> in run state: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="n">run_state</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_log_run_page_url</span><span class="p">(</span><span class="n">run_page_url</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">'Sleeping for </span><span class="si">%s</span><span class="s1"> seconds.'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">polling_period_seconds</span><span class="p">)</span>
+ <span class="n">time</span><span class="o">.</span><span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">polling_period_seconds</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">hook</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
+ <span class="n">hook</span><span class="o">.</span><span class="n">cancel_run</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">run_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">'Task: </span><span class="si">%s</span><span class="s1"> with run_id: </span><span class="si">%s</span><span class="s1"> was requested to be cancelled.'</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">run_id</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/28a3eb60/_modules/airflow/contrib/operators/dataflow_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/dataflow_operator.html b/_modules/airflow/contrib/operators/dataflow_operator.html
new file mode 100644
index 0000000..6807e24
--- /dev/null
+++ b/_modules/airflow/contrib/operators/dataflow_operator.html
@@ -0,0 +1,470 @@
+
+
+<!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 — 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="../../../../configuration.html">Configuration</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="../../../../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="../../../../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.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 under the Apache License, Version 2.0 (the "License");</span>
+<span class="c1"># you may not use this file except in compliance with the License.</span>
+<span class="c1"># You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
+<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
+<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
+<span class="c1"># See the License for the specific language governing permissions and</span>
+<span class="c1"># limitations under the License.</span>
+
+<span class="kn">import</span> <span class="nn">copy</span>
+<span class="kn">import</span> <span class="nn">re</span>
+<span class="kn">import</span> <span class="nn">uuid</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.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="../../../../integration.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">"""</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"> It'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"> ```</span>
+<span class="sd"> default_args = {</span>
+<span class="sd"> 'dataflow_default_options': {</span>
+<span class="sd"> 'project': 'my-gcp-project',</span>
+<span class="sd"> 'zone': 'europe-west1-d',</span>
+<span class="sd"> 'stagingLocation': 'gs://my-staging-bucket/staging/'</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 as a file reference with the ``jar``</span>
+<span class="sd"> parameter, the jar needs to be a self executing jar. Use ``options`` to pass on</span>
+<span class="sd"> options to your job.</span>
+
+<span class="sd"> ```</span>
+<span class="sd"> t1 = DataFlowOperation(</span>
+<span class="sd"> task_id='datapflow_example',</span>
+<span class="sd"> jar='{{var.value.gcp_dataflow_base}}pipeline/build/libs/pipeline-example-1.0.jar',</span>
+<span class="sd"> options={</span>
+<span class="sd"> 'autoscalingAlgorithm': 'BASIC',</span>
+<span class="sd"> 'maxNumWorkers': '50',</span>
+<span class="sd"> 'start': '{{ds}}',</span>
+<span class="sd"> 'partitionType': 'DAY'</span>
+<span class="sd"> },</span>
+<span class="sd"> dag=my-dag)</span>
+<span class="sd"> ```</span>
+
+<span class="sd"> Both ``jar`` and ``options`` 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">'options'</span><span class="p">,</span> <span class="s1">'jar'</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">jar</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">'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"> Create a new DataFlowJavaOperator. 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"> 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.</span>
+<span class="sd"> :type jar: string</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: 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 must have</span>
+<span class="sd"> 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">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="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">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="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">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">task_id</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></div>
+
+
+<div class="viewcode-block" id="DataFlowPythonOperator"><a class="viewcode-back" href="../../../../integration.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="n">template_fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'options'</span><span class="p">,</span> <span class="s1">'dataflow_default_options'</span><span class="p">]</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">py_file</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">'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"> Create a new DataFlowPythonOperator. 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"> 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 pipleline file, e.g.,</span>
+<span class="sd"> /some/local/file/path/to/your/python/pipeline/file.py.</span>
+<span class="sd"> :type py_file: string</span>
+<span class="sd"> :param py_options: Additional python options.</span>
+<span class="sd"> :type pyt_options: list of strings, e.g., ["-m", "-v"].</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: 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 must have</span>
+<span class="sd"> 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">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">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">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="sd">"""Execute the python dataflow job."""</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">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">'[A-Z]'</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="s1">'_'</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">task_id</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>
+
+
+<span class="k">class</span> <span class="nc">GoogleCloudBucketHelper</span><span class="p">():</span>
+ <span class="sd">"""GoogleCloudStorageHook helper class to download GCS object."""</span>
+ <span class="n">GCS_PREFIX_LENGTH</span> <span class="o">=</span> <span class="mi">5</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">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="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>
+
+ <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">"""</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: string</span>
+<span class="sd"> :return: The full path of local file.</span>
+<span class="sd"> :type: string</span>
+<span class="sd"> """</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">'gs://'</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 'gs://' prefix and</span>
+ <span class="c1"># then split the remaining by path delimiter '/'.</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">'/'</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">path_components</span> <span class="o"><</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">'Invalid Google Cloud Storage (GCS) object path: </span><span class="si">{}</span><span class="s1">.'</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">'/'</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="s1">'/tmp/dataflow</span><span class="si">{}</span><span class="s1">-</span><span class="si">{}</span><span class="s1">'</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">uuid1</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="n">file_size</span> <span class="o">=</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">file_size</span> <span class="o">></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">'Failed to download Google Cloud Storage GCS object: </span><span class="si">{}</span><span class="s1">'</span>
+ <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_name</span><span class="p">))</span>
+</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