| |
| |
| |
| |
| <!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.sqoop_hook — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </style> |
| <!-- Matomo --> |
| <script> |
| var _paq = window._paq = window._paq || []; |
| _paq.push(['disableCookies']); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '13']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo --> |
| </head> |
| |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.3 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</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="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">API Reference</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li><a href="../hooks.html">airflow.contrib.hooks</a> »</li> |
| |
| <li>airflow.contrib.hooks.sqoop_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.sqoop_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="sd">"""</span> |
| <span class="sd">This module contains a sqoop 1.x hook</span> |
| <span class="sd">"""</span> |
| <span class="kn">import</span> <span class="nn">subprocess</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.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span> |
| <span class="kn">from</span> <span class="nn">copy</span> <span class="k">import</span> <span class="n">deepcopy</span> |
| |
| |
| <div class="viewcode-block" id="SqoopHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook">[docs]</a><span class="k">class</span> <span class="nc">SqoopHook</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 sqoop 1 binary. To be able to use the hook</span> |
| <span class="sd"> it is required that "sqoop" is in the PATH.</span> |
| |
| <span class="sd"> Additional arguments that can be passed via the 'extra' JSON field of the</span> |
| <span class="sd"> sqoop connection:</span> |
| |
| <span class="sd"> * ``job_tracker``: Job tracker local|jobtracker:port.</span> |
| <span class="sd"> * ``namenode``: Namenode.</span> |
| <span class="sd"> * ``lib_jars``: Comma separated jar files to include in the classpath.</span> |
| <span class="sd"> * ``files``: Comma separated files to be copied to the map reduce cluster.</span> |
| <span class="sd"> * ``archives``: Comma separated archives to be unarchived on the compute</span> |
| <span class="sd"> machines.</span> |
| <span class="sd"> * ``password_file``: Path to file containing the password.</span> |
| |
| <span class="sd"> :param conn_id: Reference to the sqoop connection.</span> |
| <span class="sd"> :type conn_id: str</span> |
| <span class="sd"> :param verbose: Set sqoop to verbose.</span> |
| <span class="sd"> :type verbose: bool</span> |
| <span class="sd"> :param num_mappers: Number of map tasks to import in parallel.</span> |
| <span class="sd"> :type num_mappers: int</span> |
| <span class="sd"> :param properties: Properties to set via the -D argument</span> |
| <span class="sd"> :type properties: dict</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">conn_id</span><span class="o">=</span><span class="s1">'sqoop_default'</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">num_mappers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">hcatalog_database</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">hcatalog_table</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">properties</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="c1"># No mutable types in the default parameters</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="n">connection_parameters</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">job_tracker</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'job_tracker'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">namenode</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'namenode'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">libjars</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'libjars'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">files</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'files'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">archives</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'archives'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">password_file</span> <span class="o">=</span> <span class="n">connection_parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'password_file'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_database</span> <span class="o">=</span> <span class="n">hcatalog_database</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_table</span> <span class="o">=</span> <span class="n">hcatalog_table</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">num_mappers</span> <span class="o">=</span> <span class="n">num_mappers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">properties</span> <span class="o">=</span> <span class="n">properties</span> <span class="ow">or</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">"Using connection to: </span><span class="si">{}</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="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="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">port</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">schema</span> |
| <span class="p">)</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="SqoopHook.get_conn"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.get_conn">[docs]</a> <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">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook.cmd_mask_password"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.cmd_mask_password">[docs]</a> <span class="k">def</span> <span class="nf">cmd_mask_password</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cmd_orig</span><span class="p">):</span> |
| <span class="n">cmd</span> <span class="o">=</span> <span class="n">deepcopy</span><span class="p">(</span><span class="n">cmd_orig</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">password_index</span> <span class="o">=</span> <span class="n">cmd</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s1">'--password'</span><span class="p">)</span> |
| <span class="n">cmd</span><span class="p">[</span><span class="n">password_index</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'MASKED'</span> |
| <span class="k">except</span> <span class="ne">ValueError</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">"No password in sqoop cmd"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">cmd</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook.Popen"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.Popen">[docs]</a> <span class="k">def</span> <span class="nf">Popen</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="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Remote Popen</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"> :return: handle to subprocess</span> |
| <span class="sd"> """</span> |
| <span class="n">masked_cmd</span> <span class="o">=</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cmd_mask_password</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Executing command: </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">masked_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">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="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="o">.</span><span class="n">strip</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">wait</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">"Command exited with return code </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">sp</span><span class="o">.</span><span class="n">returncode</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="o">.</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">"Sqoop command failed: </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">masked_cmd</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook._prepare_command"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook._prepare_command">[docs]</a> <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">export</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="n">sqoop_cmd_type</span> <span class="o">=</span> <span class="s2">"export"</span> <span class="k">if</span> <span class="n">export</span> <span class="k">else</span> <span class="s2">"import"</span> |
| <span class="n">connection_cmd</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"sqoop"</span><span class="p">,</span> <span class="n">sqoop_cmd_type</span><span class="p">]</span> |
| |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">properties</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-D"</span><span class="p">,</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">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)]</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">namenode</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-fs"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">namenode</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_tracker</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-jt"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_tracker</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">libjars</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-libjars"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">libjars</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-files"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">archives</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"-archives"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">archives</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--username"</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">login</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--password"</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">password</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">password_file</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--password-file"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">password_file</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">num_mappers</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--num-mappers"</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_mappers</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_database</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--hcatalog-database"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_database</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_table</span><span class="p">:</span> |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--hcatalog-table"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hcatalog_table</span><span class="p">]</span> |
| |
| <span class="n">connection_cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--connect"</span><span class="p">,</span> <span class="s2">"</span><span class="si">{}</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="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="bp">self</span><span class="o">.</span><span class="n">conn</span><span class="o">.</span><span class="n">port</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">schema</span> |
| <span class="p">)]</span> |
| |
| <span class="k">return</span> <span class="n">connection_cmd</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <div class="viewcode-block" id="SqoopHook._get_export_format_argument"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook._get_export_format_argument">[docs]</a> <span class="k">def</span> <span class="nf">_get_export_format_argument</span><span class="p">(</span><span class="n">file_type</span><span class="o">=</span><span class="s1">'text'</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">file_type</span> <span class="o">==</span> <span class="s2">"avro"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="s2">"--as-avrodatafile"</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">file_type</span> <span class="o">==</span> <span class="s2">"sequence"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="s2">"--as-sequencefile"</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">file_type</span> <span class="o">==</span> <span class="s2">"parquet"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="s2">"--as-parquetfile"</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">file_type</span> <span class="o">==</span> <span class="s2">"text"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="s2">"--as-textfile"</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"Argument file_type should be 'avro', "</span></div> |
| <span class="s2">"'sequence', 'parquet' or 'text'."</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="SqoopHook._import_cmd"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook._import_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_import_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">target_dir</span><span class="p">,</span> <span class="n">append</span><span class="p">,</span> <span class="n">file_type</span><span class="p">,</span> <span class="n">split_by</span><span class="p">,</span> <span class="n">direct</span><span class="p">,</span> |
| <span class="n">driver</span><span class="p">,</span> <span class="n">extra_import_options</span><span class="p">):</span> |
| |
| <span class="n">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">export</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">target_dir</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--target-dir"</span><span class="p">,</span> <span class="n">target_dir</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">append</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--append"</span><span class="p">]</span> |
| |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_export_format_argument</span><span class="p">(</span><span class="n">file_type</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">split_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--split-by"</span><span class="p">,</span> <span class="n">split_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">direct</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--direct"</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">driver</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--driver"</span><span class="p">,</span> <span class="n">driver</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">extra_import_options</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">extra_import_options</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</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="n">key</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">value</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)]</span> |
| |
| <span class="k">return</span> <span class="n">cmd</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook.import_table"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.import_table">[docs]</a> <span class="k">def</span> <span class="nf">import_table</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">target_dir</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">append</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">file_type</span><span class="o">=</span><span class="s2">"text"</span><span class="p">,</span> |
| <span class="n">columns</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">split_by</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">where</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">direct</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">driver</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">extra_import_options</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Imports table from remote location to target dir. Arguments are</span> |
| <span class="sd"> copies of direct sqoop command line arguments</span> |
| |
| <span class="sd"> :param table: Table to read</span> |
| <span class="sd"> :param target_dir: HDFS destination dir</span> |
| <span class="sd"> :param append: Append data to an existing dataset in HDFS</span> |
| <span class="sd"> :param file_type: "avro", "sequence", "text" or "parquet".</span> |
| <span class="sd"> Imports data to into the specified format. Defaults to text.</span> |
| <span class="sd"> :param columns: <col,col,col…> Columns to import from table</span> |
| <span class="sd"> :param split_by: Column of the table used to split work units</span> |
| <span class="sd"> :param where: WHERE clause to use during import</span> |
| <span class="sd"> :param direct: Use direct connector if exists for the database</span> |
| <span class="sd"> :param driver: Manually specify JDBC driver class to use</span> |
| <span class="sd"> :param extra_import_options: Extra import options to pass as dict.</span> |
| <span class="sd"> If a key doesn't have a value, just pass an empty string to it.</span> |
| <span class="sd"> Don't include prefix of -- for sqoop options.</span> |
| <span class="sd"> """</span> |
| <span class="n">cmd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_import_cmd</span><span class="p">(</span><span class="n">target_dir</span><span class="p">,</span> <span class="n">append</span><span class="p">,</span> <span class="n">file_type</span><span class="p">,</span> <span class="n">split_by</span><span class="p">,</span> <span class="n">direct</span><span class="p">,</span> |
| <span class="n">driver</span><span class="p">,</span> <span class="n">extra_import_options</span><span class="p">)</span> |
| |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--table"</span><span class="p">,</span> <span class="n">table</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">columns</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--columns"</span><span class="p">,</span> <span class="n">columns</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">where</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--where"</span><span class="p">,</span> <span class="n">where</span><span class="p">]</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook.import_query"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.import_query">[docs]</a> <span class="k">def</span> <span class="nf">import_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">query</span><span class="p">,</span> <span class="n">target_dir</span><span class="p">,</span> <span class="n">append</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">file_type</span><span class="o">=</span><span class="s2">"text"</span><span class="p">,</span> |
| <span class="n">split_by</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">direct</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">driver</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">extra_import_options</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Imports a specific query from the rdbms to hdfs</span> |
| |
| <span class="sd"> :param query: Free format query to run</span> |
| <span class="sd"> :param target_dir: HDFS destination dir</span> |
| <span class="sd"> :param append: Append data to an existing dataset in HDFS</span> |
| <span class="sd"> :param file_type: "avro", "sequence", "text" or "parquet"</span> |
| <span class="sd"> Imports data to hdfs into the specified format. Defaults to text.</span> |
| <span class="sd"> :param split_by: Column of the table used to split work units</span> |
| <span class="sd"> :param direct: Use direct import fast path</span> |
| <span class="sd"> :param driver: Manually specify JDBC driver class to use</span> |
| <span class="sd"> :param extra_import_options: Extra import options to pass as dict.</span> |
| <span class="sd"> If a key doesn't have a value, just pass an empty string to it.</span> |
| <span class="sd"> Don't include prefix of -- for sqoop options.</span> |
| <span class="sd"> """</span> |
| <span class="n">cmd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_import_cmd</span><span class="p">(</span><span class="n">target_dir</span><span class="p">,</span> <span class="n">append</span><span class="p">,</span> <span class="n">file_type</span><span class="p">,</span> <span class="n">split_by</span><span class="p">,</span> <span class="n">direct</span><span class="p">,</span> |
| <span class="n">driver</span><span class="p">,</span> <span class="n">extra_import_options</span><span class="p">)</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--query"</span><span class="p">,</span> <span class="n">query</span><span class="p">]</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook._export_cmd"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook._export_cmd">[docs]</a> <span class="k">def</span> <span class="nf">_export_cmd</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">export_dir</span><span class="p">,</span> <span class="n">input_null_string</span><span class="p">,</span> |
| <span class="n">input_null_non_string</span><span class="p">,</span> <span class="n">staging_table</span><span class="p">,</span> <span class="n">clear_staging_table</span><span class="p">,</span> |
| <span class="n">enclosed_by</span><span class="p">,</span> <span class="n">escaped_by</span><span class="p">,</span> <span class="n">input_fields_terminated_by</span><span class="p">,</span> |
| <span class="n">input_lines_terminated_by</span><span class="p">,</span> <span class="n">input_optionally_enclosed_by</span><span class="p">,</span> |
| <span class="n">batch</span><span class="p">,</span> <span class="n">relaxed_isolation</span><span class="p">,</span> <span class="n">extra_export_options</span><span class="p">):</span> |
| |
| <span class="n">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">export</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">input_null_string</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--input-null-string"</span><span class="p">,</span> <span class="n">input_null_string</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">input_null_non_string</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--input-null-non-string"</span><span class="p">,</span> <span class="n">input_null_non_string</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">staging_table</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--staging-table"</span><span class="p">,</span> <span class="n">staging_table</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">clear_staging_table</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--clear-staging-table"</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">enclosed_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--enclosed-by"</span><span class="p">,</span> <span class="n">enclosed_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">escaped_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--escaped-by"</span><span class="p">,</span> <span class="n">escaped_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">input_fields_terminated_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--input-fields-terminated-by"</span><span class="p">,</span> <span class="n">input_fields_terminated_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">input_lines_terminated_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--input-lines-terminated-by"</span><span class="p">,</span> <span class="n">input_lines_terminated_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">input_optionally_enclosed_by</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--input-optionally-enclosed-by"</span><span class="p">,</span> |
| <span class="n">input_optionally_enclosed_by</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">batch</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--batch"</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">relaxed_isolation</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--relaxed-isolation"</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">export_dir</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--export-dir"</span><span class="p">,</span> <span class="n">export_dir</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">extra_export_options</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">extra_export_options</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</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="n">key</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">value</span><span class="p">:</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)]</span> |
| |
| <span class="c1"># The required option</span> |
| <span class="n">cmd</span> <span class="o">+=</span> <span class="p">[</span><span class="s2">"--table"</span><span class="p">,</span> <span class="n">table</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="n">cmd</span></div> |
| |
| <div class="viewcode-block" id="SqoopHook.export_table"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/sqoop_hook/index.html#airflow.contrib.hooks.sqoop_hook.SqoopHook.export_table">[docs]</a> <span class="k">def</span> <span class="nf">export_table</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">export_dir</span><span class="p">,</span> <span class="n">input_null_string</span><span class="p">,</span> |
| <span class="n">input_null_non_string</span><span class="p">,</span> <span class="n">staging_table</span><span class="p">,</span> |
| <span class="n">clear_staging_table</span><span class="p">,</span> <span class="n">enclosed_by</span><span class="p">,</span> |
| <span class="n">escaped_by</span><span class="p">,</span> <span class="n">input_fields_terminated_by</span><span class="p">,</span> |
| <span class="n">input_lines_terminated_by</span><span class="p">,</span> |
| <span class="n">input_optionally_enclosed_by</span><span class="p">,</span> <span class="n">batch</span><span class="p">,</span> |
| <span class="n">relaxed_isolation</span><span class="p">,</span> <span class="n">extra_export_options</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Exports Hive table to remote location. Arguments are copies of direct</span> |
| <span class="sd"> sqoop command line Arguments</span> |
| |
| <span class="sd"> :param table: Table remote destination</span> |
| <span class="sd"> :param export_dir: Hive table to export</span> |
| <span class="sd"> :param input_null_string: The string to be interpreted as null for</span> |
| <span class="sd"> string columns</span> |
| <span class="sd"> :param input_null_non_string: The string to be interpreted as null</span> |
| <span class="sd"> for non-string columns</span> |
| <span class="sd"> :param staging_table: The table in which data will be staged before</span> |
| <span class="sd"> being inserted into the destination table</span> |
| <span class="sd"> :param clear_staging_table: Indicate that any data present in the</span> |
| <span class="sd"> staging table can be deleted</span> |
| <span class="sd"> :param enclosed_by: Sets a required field enclosing character</span> |
| <span class="sd"> :param escaped_by: Sets the escape character</span> |
| <span class="sd"> :param input_fields_terminated_by: Sets the field separator character</span> |
| <span class="sd"> :param input_lines_terminated_by: Sets the end-of-line character</span> |
| <span class="sd"> :param input_optionally_enclosed_by: Sets a field enclosing character</span> |
| <span class="sd"> :param batch: Use batch mode for underlying statement execution</span> |
| <span class="sd"> :param relaxed_isolation: Transaction isolation to read uncommitted</span> |
| <span class="sd"> for the mappers</span> |
| <span class="sd"> :param extra_export_options: Extra export options to pass as dict.</span> |
| <span class="sd"> If a key doesn't have a value, just pass an empty string to it.</span> |
| <span class="sd"> Don't include prefix of -- for sqoop options.</span> |
| <span class="sd"> """</span> |
| <span class="n">cmd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_export_cmd</span><span class="p">(</span><span class="n">table</span><span class="p">,</span> <span class="n">export_dir</span><span class="p">,</span> <span class="n">input_null_string</span><span class="p">,</span> |
| <span class="n">input_null_non_string</span><span class="p">,</span> <span class="n">staging_table</span><span class="p">,</span> |
| <span class="n">clear_staging_table</span><span class="p">,</span> <span class="n">enclosed_by</span><span class="p">,</span> <span class="n">escaped_by</span><span class="p">,</span> |
| <span class="n">input_fields_terminated_by</span><span class="p">,</span> |
| <span class="n">input_lines_terminated_by</span><span class="p">,</span> |
| <span class="n">input_optionally_enclosed_by</span><span class="p">,</span> <span class="n">batch</span><span class="p">,</span> |
| <span class="n">relaxed_isolation</span><span class="p">,</span> <span class="n">extra_export_options</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |