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 16:27:00 UTC
[40/51] [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/hooks/spark_jdbc_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/spark_jdbc_hook.html b/_modules/airflow/contrib/hooks/spark_jdbc_hook.html
new file mode 100644
index 0000000..c22b1e5
--- /dev/null
+++ b/_modules/airflow/contrib/hooks/spark_jdbc_hook.html
@@ -0,0 +1,481 @@
+
+
+<!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.hooks.spark_jdbc_hook — 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.hooks.spark_jdbc_hook</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.hooks.spark_jdbc_hook</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="c1">#</span>
+<span class="kn">import</span> <span class="nn">os</span>
+<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.spark_submit_hook</span> <span class="k">import</span> <span class="n">SparkSubmitHook</span>
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span>
+
+
+<div class="viewcode-block" id="SparkJDBCHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.spark_jdbc_hook.SparkJDBCHook">[docs]</a><span class="k">class</span> <span class="nc">SparkJDBCHook</span><span class="p">(</span><span class="n">SparkSubmitHook</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> This hook extends the SparkSubmitHook specifically for performing data</span>
+<span class="sd"> transfers to/from JDBC-based databases with Apache Spark.</span>
+
+<span class="sd"> :param spark_app_name: Name of the job (default airflow-spark-jdbc)</span>
+<span class="sd"> :type spark_app_name: str</span>
+<span class="sd"> :param spark_conn_id: Connection id as configured in Airflow administration</span>
+<span class="sd"> :type spark_conn_id: str</span>
+<span class="sd"> :param spark_conf: Any additional Spark configuration properties</span>
+<span class="sd"> :type spark_conf: dict</span>
+<span class="sd"> :param spark_py_files: Additional python files used (.zip, .egg, or .py)</span>
+<span class="sd"> :type spark_py_files: str</span>
+<span class="sd"> :param spark_files: Additional files to upload to the container running the job</span>
+<span class="sd"> :type spark_files: str</span>
+<span class="sd"> :param spark_jars: Additional jars to upload and add to the driver and</span>
+<span class="sd"> executor classpath</span>
+<span class="sd"> :type spark_jars: str</span>
+<span class="sd"> :param num_executors: number of executor to run. This should be set so as to manage</span>
+<span class="sd"> the number of connections made with the JDBC database</span>
+<span class="sd"> :type num_executors: int</span>
+<span class="sd"> :param executor_cores: Number of cores per executor</span>
+<span class="sd"> :type executor_cores: int</span>
+<span class="sd"> :param executor_memory: Memory per executor (e.g. 1000M, 2G)</span>
+<span class="sd"> :type executor_memory: str</span>
+<span class="sd"> :param driver_memory: Memory allocated to the driver (e.g. 1000M, 2G)</span>
+<span class="sd"> :type driver_memory: str</span>
+<span class="sd"> :param verbose: Whether to pass the verbose flag to spark-submit for debugging</span>
+<span class="sd"> :type verbose: bool</span>
+<span class="sd"> :param keytab: Full path to the file that contains the keytab</span>
+<span class="sd"> :type keytab: str</span>
+<span class="sd"> :param principal: The name of the kerberos principal used for keytab</span>
+<span class="sd"> :type principal: str</span>
+<span class="sd"> :param cmd_type: Which way the data should flow. 2 possible values:</span>
+<span class="sd"> spark_to_jdbc: data written by spark from metastore to jdbc</span>
+<span class="sd"> jdbc_to_spark: data written by spark from jdbc to metastore</span>
+<span class="sd"> :type cmd_type: str</span>
+<span class="sd"> :param jdbc_table: The name of the JDBC table</span>
+<span class="sd"> :type jdbc_table: str</span>
+<span class="sd"> :param jdbc_conn_id: Connection id used for connection to JDBC database</span>
+<span class="sd"> :type: jdbc_conn_id: str</span>
+<span class="sd"> :param jdbc_driver: Name of the JDBC driver to use for the JDBC connection. This</span>
+<span class="sd"> driver (usually a jar) should be passed in the 'jars' parameter</span>
+<span class="sd"> :type jdbc_driver: str</span>
+<span class="sd"> :param metastore_table: The name of the metastore table,</span>
+<span class="sd"> :type metastore_table: str</span>
+<span class="sd"> :param jdbc_truncate: (spark_to_jdbc only) Whether or not Spark should truncate or</span>
+<span class="sd"> drop and recreate the JDBC table. This only takes effect if</span>
+<span class="sd"> 'save_mode' is set to Overwrite. Also, if the schema is</span>
+<span class="sd"> different, Spark cannot truncate, and will drop and recreate</span>
+<span class="sd"> :type jdbc_truncate: bool</span>
+<span class="sd"> :param save_mode: The Spark save-mode to use (e.g. overwrite, append, etc.)</span>
+<span class="sd"> :type save_mode: str</span>
+<span class="sd"> :param save_format: (jdbc_to_spark-only) The Spark save-format to use (e.g. parquet)</span>
+<span class="sd"> :type save_format: str</span>
+<span class="sd"> :param batch_size: (spark_to_jdbc only) The size of the batch to insert per round</span>
+<span class="sd"> trip to the JDBC database. Defaults to 1000</span>
+<span class="sd"> :type batch_size: int</span>
+<span class="sd"> :param fetch_size: (jdbc_to_spark only) The size of the batch to fetch per round trip</span>
+<span class="sd"> from the JDBC database. Default depends on the JDBC driver</span>
+<span class="sd"> :type fetch_size: int</span>
+<span class="sd"> :param num_partitions: The maximum number of partitions that can be used by Spark</span>
+<span class="sd"> simultaneously, both for spark_to_jdbc and jdbc_to_spark</span>
+<span class="sd"> operations. This will also cap the number of JDBC connections</span>
+<span class="sd"> that can be opened</span>
+<span class="sd"> :type num_partitions: int</span>
+<span class="sd"> :param partition_column: (jdbc_to_spark-only) A numeric column to be used to</span>
+<span class="sd"> partition the metastore table by. If specified, you must</span>
+<span class="sd"> also specify:</span>
+<span class="sd"> num_partitions, lower_bound, upper_bound</span>
+<span class="sd"> :type partition_column: str</span>
+<span class="sd"> :param lower_bound: (jdbc_to_spark-only) Lower bound of the range of the numeric</span>
+<span class="sd"> partition column to fetch. If specified, you must also specify:</span>
+<span class="sd"> num_partitions, partition_column, upper_bound</span>
+<span class="sd"> :type lower_bound: int</span>
+<span class="sd"> :param upper_bound: (jdbc_to_spark-only) Upper bound of the range of the numeric</span>
+<span class="sd"> partition column to fetch. If specified, you must also specify:</span>
+<span class="sd"> num_partitions, partition_column, lower_bound</span>
+<span class="sd"> :type upper_bound: int</span>
+<span class="sd"> :param create_table_column_types: (spark_to_jdbc-only) The database column data types</span>
+<span class="sd"> to use instead of the defaults, when creating the</span>
+<span class="sd"> table. Data type information should be specified in</span>
+<span class="sd"> the same format as CREATE TABLE columns syntax</span>
+<span class="sd"> (e.g: "name CHAR(64), comments VARCHAR(1024)").</span>
+<span class="sd"> The specified types should be valid spark sql data</span>
+<span class="sd"> types.</span>
+<span class="sd"> """</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">spark_app_name</span><span class="o">=</span><span class="s1">'airflow-spark-jdbc'</span><span class="p">,</span>
+ <span class="n">spark_conn_id</span><span class="o">=</span><span class="s1">'spark-default'</span><span class="p">,</span>
+ <span class="n">spark_conf</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">spark_py_files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">spark_files</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">spark_jars</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">num_executors</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">executor_cores</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">executor_memory</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">driver_memory</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">principal</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">keytab</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">cmd_type</span><span class="o">=</span><span class="s1">'spark_to_jdbc'</span><span class="p">,</span>
+ <span class="n">jdbc_table</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">jdbc_conn_id</span><span class="o">=</span><span class="s1">'jdbc-default'</span><span class="p">,</span>
+ <span class="n">jdbc_driver</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">metastore_table</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">jdbc_truncate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">save_mode</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">save_format</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">batch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">fetch_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">num_partitions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">partition_column</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">lower_bound</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">upper_bound</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">create_table_column_types</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">SparkJDBCHook</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">_name</span> <span class="o">=</span> <span class="n">spark_app_name</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_conn_id</span> <span class="o">=</span> <span class="n">spark_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_conf</span> <span class="o">=</span> <span class="n">spark_conf</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_py_files</span> <span class="o">=</span> <span class="n">spark_py_files</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_files</span> <span class="o">=</span> <span class="n">spark_files</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jars</span> <span class="o">=</span> <span class="n">spark_jars</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span> <span class="o">=</span> <span class="n">num_executors</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span> <span class="o">=</span> <span class="n">executor_cores</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span> <span class="o">=</span> <span class="n">executor_memory</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_driver_memory</span> <span class="o">=</span> <span class="n">driver_memory</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="o">=</span> <span class="n">verbose</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span> <span class="o">=</span> <span class="n">keytab</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_principal</span> <span class="o">=</span> <span class="n">principal</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_cmd_type</span> <span class="o">=</span> <span class="n">cmd_type</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_table</span> <span class="o">=</span> <span class="n">jdbc_table</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_conn_id</span> <span class="o">=</span> <span class="n">jdbc_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_driver</span> <span class="o">=</span> <span class="n">jdbc_driver</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_metastore_table</span> <span class="o">=</span> <span class="n">metastore_table</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_truncate</span> <span class="o">=</span> <span class="n">jdbc_truncate</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_save_mode</span> <span class="o">=</span> <span class="n">save_mode</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_save_format</span> <span class="o">=</span> <span class="n">save_format</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_batch_size</span> <span class="o">=</span> <span class="n">batch_size</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_fetch_size</span> <span class="o">=</span> <span class="n">fetch_size</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_num_partitions</span> <span class="o">=</span> <span class="n">num_partitions</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_partition_column</span> <span class="o">=</span> <span class="n">partition_column</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_lower_bound</span> <span class="o">=</span> <span class="n">lower_bound</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_upper_bound</span> <span class="o">=</span> <span class="n">upper_bound</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_create_table_column_types</span> <span class="o">=</span> <span class="n">create_table_column_types</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_resolve_jdbc_connection</span><span class="p">()</span>
+
+ <span class="k">def</span> <span class="nf">_resolve_jdbc_connection</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="n">conn_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'url'</span><span class="p">:</span> <span class="s1">''</span><span class="p">,</span>
+ <span class="s1">'schema'</span><span class="p">:</span> <span class="s1">''</span><span class="p">,</span>
+ <span class="s1">'conn_prefix'</span><span class="p">:</span> <span class="s1">''</span><span class="p">,</span>
+ <span class="s1">'user'</span><span class="p">:</span> <span class="s1">''</span><span class="p">,</span>
+ <span class="s1">'password'</span><span class="p">:</span> <span class="s1">''</span>
+ <span class="p">}</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_conn_id</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">:</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">:</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">host</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'schema'</span><span class="p">]</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">schema</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'user'</span><span class="p">]</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">login</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'password'</span><span class="p">]</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">password</span>
+ <span class="n">extra</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span>
+ <span class="n">conn_data</span><span class="p">[</span><span class="s1">'conn_prefix'</span><span class="p">]</span> <span class="o">=</span> <span class="n">extra</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'conn_prefix'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
+ <span class="k">except</span> <span class="n">AirflowException</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">debug</span><span class="p">(</span>
+ <span class="s2">"Could not load jdbc connection string </span><span class="si">%s</span><span class="s2">, defaulting to </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_conn_id</span><span class="p">,</span> <span class="s2">""</span>
+ <span class="p">)</span>
+ <span class="k">return</span> <span class="n">conn_data</span>
+
+ <span class="k">def</span> <span class="nf">_build_jdbc_application_arguments</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">jdbc_conn</span><span class="p">):</span>
+ <span class="n">arguments</span> <span class="o">=</span> <span class="p">[]</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-cmdType"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cmd_type</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-url'</span><span class="p">,</span> <span class="s2">"</span><span class="si">{0}{1}</span><span class="s2">/</span><span class="si">{2}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+ <span class="n">jdbc_conn</span><span class="p">[</span><span class="s1">'conn_prefix'</span><span class="p">],</span> <span class="n">jdbc_conn</span><span class="p">[</span><span class="s1">'url'</span><span class="p">],</span> <span class="n">jdbc_conn</span><span class="p">[</span><span class="s1">'schema'</span><span class="p">]</span>
+ <span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">[</span><span class="s1">'user'</span><span class="p">]:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-user'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">[</span><span class="s1">'user'</span><span class="p">]]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">[</span><span class="s1">'password'</span><span class="p">]:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-password'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">[</span><span class="s1">'password'</span><span class="p">]]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_metastore_table</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-metastoreTable'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_metastore_table</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_table</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-jdbcTable'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_table</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_truncate</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-jdbcTruncate'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_truncate</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_driver</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-jdbcDriver'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_driver</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_size</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-batchsize'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_batch_size</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fetch_size</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-fetchsize'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_fetch_size</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_partitions</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-numPartitions'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_partitions</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_partition_column</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lower_bound</span> <span class="ow">and</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_upper_bound</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_partitions</span><span class="p">):</span>
+ <span class="c1"># these 3 parameters need to be used all together to take effect.</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-partitionColumn'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_partition_column</span><span class="p">,</span>
+ <span class="s1">'-lowerBound'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lower_bound</span><span class="p">,</span>
+ <span class="s1">'-upperBound'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_upper_bound</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_save_mode</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-saveMode'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_save_mode</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_save_format</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-saveFormat'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_save_format</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_create_table_column_types</span><span class="p">:</span>
+ <span class="n">arguments</span> <span class="o">+=</span> <span class="p">[</span><span class="s1">'-createTableColumnTypes'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_create_table_column_types</span><span class="p">]</span>
+ <span class="k">return</span> <span class="n">arguments</span>
+
+ <span class="k">def</span> <span class="nf">submit_jdbc_job</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_application_args</span> <span class="o">=</span> \
+ <span class="bp">self</span><span class="o">.</span><span class="n">_build_jdbc_application_arguments</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_jdbc_connection</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">submit</span><span class="p">(</span><span class="n">application</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="vm">__file__</span><span class="p">))</span> <span class="o">+</span>
+ <span class="s2">"/spark_jdbc_script.py"</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">pass</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/hooks/spark_sql_hook.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/hooks/spark_sql_hook.html b/_modules/airflow/contrib/hooks/spark_sql_hook.html
new file mode 100644
index 0000000..08d3147
--- /dev/null
+++ b/_modules/airflow/contrib/hooks/spark_sql_hook.html
@@ -0,0 +1,396 @@
+
+
+<!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.hooks.spark_sql_hook — 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.hooks.spark_sql_hook</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.hooks.spark_sql_hook</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="c1">#</span>
+<span class="kn">import</span> <span class="nn">subprocess</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</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.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
+
+
+<div class="viewcode-block" id="SparkSqlHook"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.spark_sql_hook.SparkSqlHook">[docs]</a><span class="k">class</span> <span class="nc">SparkSqlHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> This hook is a wrapper around the spark-sql binary. It requires that the</span>
+<span class="sd"> "spark-sql" binary is in the PATH.</span>
+<span class="sd"> :param sql: The SQL query to execute</span>
+<span class="sd"> :type sql: str</span>
+<span class="sd"> :param conf: arbitrary Spark configuration property</span>
+<span class="sd"> :type conf: str (format: PROP=VALUE)</span>
+<span class="sd"> :param conn_id: connection_id string</span>
+<span class="sd"> :type conn_id: str</span>
+<span class="sd"> :param total_executor_cores: (Standalone & Mesos only) Total cores for all executors (Default: all the available cores on the worker)</span>
+<span class="sd"> :type total_executor_cores: int</span>
+<span class="sd"> :param executor_cores: (Standalone & YARN only) Number of cores per executor (Default: 2)</span>
+<span class="sd"> :type executor_cores: int</span>
+<span class="sd"> :param executor_memory: Memory per executor (e.g. 1000M, 2G) (Default: 1G)</span>
+<span class="sd"> :type executor_memory: str</span>
+<span class="sd"> :param keytab: Full path to the file that contains the keytab</span>
+<span class="sd"> :type keytab: str</span>
+<span class="sd"> :param master: spark://host:port, mesos://host:port, yarn, or local</span>
+<span class="sd"> :type master: str</span>
+<span class="sd"> :param name: Name of the job.</span>
+<span class="sd"> :type name: str</span>
+<span class="sd"> :param num_executors: Number of executors to launch</span>
+<span class="sd"> :type num_executors: int</span>
+<span class="sd"> :param verbose: Whether to pass the verbose flag to spark-sql</span>
+<span class="sd"> :type verbose: bool</span>
+<span class="sd"> :param yarn_queue: The YARN queue to submit to (Default: "default")</span>
+<span class="sd"> :type yarn_queue: str</span>
+<span class="sd"> """</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">sql</span><span class="p">,</span>
+ <span class="n">conf</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">conn_id</span><span class="o">=</span><span class="s1">'spark_sql_default'</span><span class="p">,</span>
+ <span class="n">total_executor_cores</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">executor_cores</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">executor_memory</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">keytab</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">principal</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">master</span><span class="o">=</span><span class="s1">'yarn'</span><span class="p">,</span>
+ <span class="n">name</span><span class="o">=</span><span class="s1">'default-name'</span><span class="p">,</span>
+ <span class="n">num_executors</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
+ <span class="n">yarn_queue</span><span class="o">=</span><span class="s1">'default'</span>
+ <span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_sql</span> <span class="o">=</span> <span class="n">sql</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_conf</span> <span class="o">=</span> <span class="n">conf</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="n">conn_id</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_total_executor_cores</span> <span class="o">=</span> <span class="n">total_executor_cores</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span> <span class="o">=</span> <span class="n">executor_cores</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span> <span class="o">=</span> <span class="n">executor_memory</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span> <span class="o">=</span> <span class="n">keytab</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_principal</span> <span class="o">=</span> <span class="n">principal</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_master</span> <span class="o">=</span> <span class="n">master</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span> <span class="o">=</span> <span class="n">num_executors</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="o">=</span> <span class="n">verbose</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_yarn_queue</span> <span class="o">=</span> <span class="n">yarn_queue</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span> <span class="o">=</span> <span class="kc">None</span>
+
+ <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">pass</span>
+
+ <span class="k">def</span> <span class="nf">_prepare_command</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Construct the spark-sql command to execute. Verbose output is enabled</span>
+<span class="sd"> as default.</span>
+<span class="sd"> :param cmd: command to append to the spark-sql command</span>
+<span class="sd"> :type cmd: str</span>
+<span class="sd"> :return: full command to be executed</span>
+<span class="sd"> """</span>
+ <span class="n">connection_cmd</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"spark-sql"</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conf</span><span class="p">:</span>
+ <span class="k">for</span> <span class="n">conf_el</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conf</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">","</span><span class="p">):</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--conf"</span><span class="p">,</span> <span class="n">conf_el</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_total_executor_cores</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--total-executor-cores"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_total_executor_cores</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--executor-cores"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_executor_cores</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--executor-memory"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_executor_memory</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--keytab"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_keytab</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_principal</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--principal"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_principal</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--num-executors"</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_executors</span><span class="p">)]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sql</span><span class="p">:</span>
+ <span class="n">sql</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sql</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
+ <span class="k">if</span> <span class="n">sql</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">".sql"</span><span class="p">)</span> <span class="ow">or</span> <span class="n">sql</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">".hql"</span><span class="p">):</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-f"</span><span class="p">,</span> <span class="n">sql</span><span class="p">]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-e"</span><span class="p">,</span> <span class="n">sql</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_master</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--master"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_master</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--name"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--verbose"</span><span class="p">]</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_yarn_queue</span><span class="p">:</span>
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--queue"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_yarn_queue</span><span class="p">]</span>
+
+ <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="n">cmd</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Spark-Sql cmd: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">connection_cmd</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">connection_cmd</span>
+
+<div class="viewcode-block" id="SparkSqlHook.run_query"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.hooks.spark_sql_hook.SparkSqlHook.run_query">[docs]</a> <span class="k">def</span> <span class="nf">run_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd</span><span class="o">=</span><span class="s2">""</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"> Remote Popen (actually execute the Spark-sql query)</span>
+
+<span class="sd"> :param cmd: command to remotely execute</span>
+<span class="sd"> :param kwargs: extra arguments to Popen (see subprocess.Popen)</span>
+<span class="sd"> """</span>
+ <span class="n">spark_sql_cmd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_prepare_command</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">spark_sql_cmd</span><span class="p">,</span>
+ <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span>
+ <span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">STDOUT</span><span class="p">,</span>
+ <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+
+ <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">iter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sp</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readline</span><span class="p">,</span> <span class="s1">''</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="n">line</span><span class="p">)</span>
+
+ <span class="n">returncode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span>
+
+ <span class="k">if</span> <span class="n">returncode</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span>
+ <span class="s2">"Cannot execute </span><span class="si">{}</span><span class="s2"> on </span><span class="si">{}</span><span class="s2">. Process exit code: </span><span class="si">{}</span><span class="s2">."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
+ <span class="n">cmd</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_conn</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> <span class="n">returncode</span>
+ <span class="p">)</span>
+ <span class="p">)</span></div>
+
+ <span class="k">def</span> <span class="nf">kill</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span><span class="o">.</span><span class="n">poll</span><span class="p">()</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Killing the Spark-Sql job"</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">_sp</span><span class="o">.</span><span class="n">kill</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