blob: f2677e7c08331f356f4adae50229eeb50fbf0a49 [file] [log] [blame]
<!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.operators.mssql_to_hive &mdash; Airflow Documentation</title>
<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 src="../../../_static/js/modernizr.min.js"></script>
</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">
1.10.2
</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 &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../api.html">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="../../../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" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>airflow.operators.mssql_to_hive</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.operators.mssql_to_hive</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># &quot;License&quot;); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">chr</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span>
<span class="kn">import</span> <span class="nn">unicodecsv</span> <span class="k">as</span> <span class="nn">csv</span>
<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span>
<span class="kn">import</span> <span class="nn">pymssql</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.hive_hooks</span> <span class="k">import</span> <span class="n">HiveCliHook</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.mssql_hook</span> <span class="k">import</span> <span class="n">MsSqlHook</span>
<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<div class="viewcode-block" id="MsSqlToHiveTransfer"><a class="viewcode-back" href="../../../code.html#airflow.operators.mssql_to_hive.MsSqlToHiveTransfer">[docs]</a><span class="k">class</span> <span class="nc">MsSqlToHiveTransfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Moves data from Microsoft SQL Server to Hive. The operator runs</span>
<span class="sd"> your query against Microsoft SQL Server, stores the file locally</span>
<span class="sd"> before loading it into a Hive table. If the ``create`` or</span>
<span class="sd"> ``recreate`` arguments are set to ``True``,</span>
<span class="sd"> a ``CREATE TABLE`` and ``DROP TABLE`` statements are generated.</span>
<span class="sd"> Hive data types are inferred from the cursor&#39;s metadata.</span>
<span class="sd"> Note that the table generated in Hive uses ``STORED AS textfile``</span>
<span class="sd"> which isn&#39;t the most efficient serialization format. If a</span>
<span class="sd"> large amount of data is loaded and/or if the table gets</span>
<span class="sd"> queried considerably, you may want to use this operator only to</span>
<span class="sd"> stage the data into a temporary table before loading it into its</span>
<span class="sd"> final destination using a ``HiveOperator``.</span>
<span class="sd"> :param sql: SQL query to execute against the Microsoft SQL Server</span>
<span class="sd"> database. (templated)</span>
<span class="sd"> :type sql: str</span>
<span class="sd"> :param hive_table: target Hive table, use dot notation to target a specific</span>
<span class="sd"> database. (templated)</span>
<span class="sd"> :type hive_table: str</span>
<span class="sd"> :param create: whether to create the table if it doesn&#39;t exist</span>
<span class="sd"> :type create: bool</span>
<span class="sd"> :param recreate: whether to drop and recreate the table at every execution</span>
<span class="sd"> :type recreate: bool</span>
<span class="sd"> :param partition: target partition as a dict of partition columns and</span>
<span class="sd"> values. (templated)</span>
<span class="sd"> :type partition: dict</span>
<span class="sd"> :param delimiter: field delimiter in the file</span>
<span class="sd"> :type delimiter: str</span>
<span class="sd"> :param mssql_conn_id: source Microsoft SQL Server connection</span>
<span class="sd"> :type mssql_conn_id: str</span>
<span class="sd"> :param hive_conn_id: destination hive connection</span>
<span class="sd"> :type hive_conn_id: str</span>
<span class="sd"> :param tblproperties: TBLPROPERTIES of the hive table being created</span>
<span class="sd"> :type tblproperties: dict</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;sql&#39;</span><span class="p">,</span> <span class="s1">&#39;partition&#39;</span><span class="p">,</span> <span class="s1">&#39;hive_table&#39;</span><span class="p">)</span>
<span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.sql&#39;</span><span class="p">,)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#a0e08c&#39;</span>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">sql</span><span class="p">,</span>
<span class="n">hive_table</span><span class="p">,</span>
<span class="n">create</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">recreate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">partition</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="nb">chr</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span>
<span class="n">mssql_conn_id</span><span class="o">=</span><span class="s1">&#39;mssql_default&#39;</span><span class="p">,</span>
<span class="n">hive_cli_conn_id</span><span class="o">=</span><span class="s1">&#39;hive_cli_default&#39;</span><span class="p">,</span>
<span class="n">tblproperties</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">MsSqlToHiveTransfer</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">sql</span> <span class="o">=</span> <span class="n">sql</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_table</span> <span class="o">=</span> <span class="n">hive_table</span>
<span class="bp">self</span><span class="o">.</span><span class="n">partition</span> <span class="o">=</span> <span class="n">partition</span>
<span class="bp">self</span><span class="o">.</span><span class="n">create</span> <span class="o">=</span> <span class="n">create</span>
<span class="bp">self</span><span class="o">.</span><span class="n">recreate</span> <span class="o">=</span> <span class="n">recreate</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span> <span class="o">=</span> <span class="n">delimiter</span>
<span class="bp">self</span><span class="o">.</span><span class="n">mssql_conn_id</span> <span class="o">=</span> <span class="n">mssql_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_cli_conn_id</span> <span class="o">=</span> <span class="n">hive_cli_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">partition</span> <span class="o">=</span> <span class="n">partition</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">tblproperties</span> <span class="o">=</span> <span class="n">tblproperties</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">type_map</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">mssql_type</span><span class="p">):</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">pymssql</span>
<span class="n">d</span> <span class="o">=</span> <span class="p">{</span>
<span class="n">t</span><span class="o">.</span><span class="n">BINARY</span><span class="o">.</span><span class="n">value</span><span class="p">:</span> <span class="s1">&#39;INT&#39;</span><span class="p">,</span>
<span class="n">t</span><span class="o">.</span><span class="n">DECIMAL</span><span class="o">.</span><span class="n">value</span><span class="p">:</span> <span class="s1">&#39;FLOAT&#39;</span><span class="p">,</span>
<span class="n">t</span><span class="o">.</span><span class="n">NUMBER</span><span class="o">.</span><span class="n">value</span><span class="p">:</span> <span class="s1">&#39;INT&#39;</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">return</span> <span class="n">d</span><span class="p">[</span><span class="n">mssql_type</span><span class="p">]</span> <span class="k">if</span> <span class="n">mssql_type</span> <span class="ow">in</span> <span class="n">d</span> <span class="k">else</span> <span class="s1">&#39;STRING&#39;</span>
<span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="n">hive</span> <span class="o">=</span> <span class="n">HiveCliHook</span><span class="p">(</span><span class="n">hive_cli_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hive_cli_conn_id</span><span class="p">)</span>
<span class="n">mssql</span> <span class="o">=</span> <span class="n">MsSqlHook</span><span class="p">(</span><span class="n">mssql_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mssql_conn_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Dumping Microsoft SQL Server query results to local file&quot;</span><span class="p">)</span>
<span class="n">conn</span> <span class="o">=</span> <span class="n">mssql</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="n">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span>
<span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span>
<span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="s2">&quot;w&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">csv_writer</span> <span class="o">=</span> <span class="n">csv</span><span class="o">.</span><span class="n">writer</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;utf-8&#39;</span><span class="p">)</span>
<span class="n">field_dict</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span>
<span class="n">col_count</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span><span class="p">:</span>
<span class="n">col_count</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="n">col_position</span> <span class="o">=</span> <span class="s2">&quot;Column</span><span class="si">{position}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">position</span><span class="o">=</span><span class="n">col_count</span><span class="p">)</span>
<span class="n">field_dict</span><span class="p">[</span><span class="n">col_position</span> <span class="k">if</span> <span class="n">field</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;&#39;</span> <span class="k">else</span> <span class="n">field</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> \
<span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_map</span><span class="p">(</span><span class="n">field</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="n">csv_writer</span><span class="o">.</span><span class="n">writerows</span><span class="p">(</span><span class="n">cursor</span><span class="p">)</span>
<span class="n">f</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span>
<span class="n">cursor</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="n">conn</span><span class="o">.</span><span class="n">close</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">&quot;Loading file into Hive&quot;</span><span class="p">)</span>
<span class="n">hive</span><span class="o">.</span><span class="n">load_file</span><span class="p">(</span>
<span class="n">f</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_table</span><span class="p">,</span>
<span class="n">field_dict</span><span class="o">=</span><span class="n">field_dict</span><span class="p">,</span>
<span class="n">create</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">create</span><span class="p">,</span>
<span class="n">partition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span><span class="p">,</span>
<span class="n">recreate</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">recreate</span><span class="p">,</span>
<span class="n">tblproperties</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">tblproperties</span><span class="p">)</span></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" 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>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>