You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ma...@apache.org on 2016/06/05 05:24:12 UTC
[22/34] incubator-airflow-site git commit: Initial commit
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/9e19165c/_modules/mysql_operator.html
----------------------------------------------------------------------
diff --git a/_modules/mysql_operator.html b/_modules/mysql_operator.html
new file mode 100644
index 0000000..2cb0a09
--- /dev/null
+++ b/_modules/mysql_operator.html
@@ -0,0 +1,240 @@
+
+
+<!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>mysql_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="top" title="Airflow Documentation" href="../index.html"/>
+ <link rel="up" title="Module code" href="index.html"/>
+
+
+ <script src="../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../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>mysql_operator</li>
+ <li class="wy-breadcrumbs-aside">
+
+
+
+ </li>
+ </ul>
+ <hr/>
+</div>
+ <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
+ <div itemprop="articleBody">
+
+ <h1>Source code for mysql_operator</h1><div class="highlight"><pre>
+<span></span><span class="kn">import</span> <span class="nn">logging</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">MySqlHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="MySqlOperator"><a class="viewcode-back" href="../code.html#airflow.operators.MySqlOperator">[docs]</a><span class="k">class</span> <span class="nc">MySqlOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Executes sql code in a specific MySQL database</span>
+
+<span class="sd"> :param mysql_conn_id: reference to a specific mysql database</span>
+<span class="sd"> :type mysql_conn_id: string</span>
+<span class="sd"> :param sql: the sql code to be executed</span>
+<span class="sd"> :type sql: Can receive a str representing a sql statement,</span>
+<span class="sd"> a list of str (sql statements), or reference to a template file.</span>
+<span class="sd"> Template reference are recognized by str ending in '.sql'</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#ededed'</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">mysql_conn_id</span><span class="o">=</span><span class="s1">'mysql_default'</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">autocommit</span><span class="o">=</span><span class="bp">False</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">MySqlOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span> <span class="o">=</span> <span class="n">mysql_conn_id</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">autocommit</span> <span class="o">=</span> <span class="n">autocommit</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">parameters</span>
+
+ <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing: '</span> <span class="o">+</span> <span class="nb">str</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="n">hook</span> <span class="o">=</span> <span class="n">MySqlHook</span><span class="p">(</span><span class="n">mysql_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span><span class="p">)</span>
+ <span class="n">hook</span><span class="o">.</span><span class="n">run</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="n">autocommit</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">autocommit</span><span class="p">,</span>
+ <span class="n">parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">parameters</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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/9e19165c/_modules/mysql_to_hive.html
----------------------------------------------------------------------
diff --git a/_modules/mysql_to_hive.html b/_modules/mysql_to_hive.html
new file mode 100644
index 0000000..19ecd32
--- /dev/null
+++ b/_modules/mysql_to_hive.html
@@ -0,0 +1,316 @@
+
+
+<!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>mysql_to_hive — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="top" title="Airflow Documentation" href="../index.html"/>
+ <link rel="up" title="Module code" href="index.html"/>
+
+
+ <script src="../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../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>mysql_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 mysql_to_hive</h1><div class="highlight"><pre>
+<span></span><span class="kn">from</span> <span class="nn">builtins</span> <span class="kn">import</span> <span class="nb">chr</span>
+<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">OrderedDict</span>
+<span class="kn">import</span> <span class="nn">unicodecsv</span> <span class="kn">as</span> <span class="nn">csv</span>
+<span class="kn">import</span> <span class="nn">logging</span>
+<span class="kn">from</span> <span class="nn">tempfile</span> <span class="kn">import</span> <span class="n">NamedTemporaryFile</span>
+<span class="kn">import</span> <span class="nn">MySQLdb</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">HiveCliHook</span><span class="p">,</span> <span class="n">MySqlHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="MySqlToHiveTransfer"><a class="viewcode-back" href="../code.html#airflow.operators.MySqlToHiveTransfer">[docs]</a><span class="k">class</span> <span class="nc">MySqlToHiveTransfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Moves data from MySql to Hive. The operator runs your query against</span>
+<span class="sd"> MySQL, stores the file locally before loading it into a Hive table.</span>
+<span class="sd"> If the ``create`` or ``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's metadata. Note that the</span>
+<span class="sd"> table generated in Hive uses ``STORED AS textfile``</span>
+<span class="sd"> which isn'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 MySQL database</span>
+<span class="sd"> :type sql: str</span>
+<span class="sd"> :param hive_table: target Hive table, use dot notation to target a</span>
+<span class="sd"> specific database</span>
+<span class="sd"> :type hive_table: str</span>
+<span class="sd"> :param create: whether to create the table if it doesn't exist</span>
+<span class="sd"> :type create: bool</span>
+<span class="sd"> :param recreate: whether to drop and recreate the table at every</span>
+<span class="sd"> execution</span>
+<span class="sd"> :type recreate: bool</span>
+<span class="sd"> :param partition: target partition as a dict of partition columns</span>
+<span class="sd"> and values</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 mysql_conn_id: source mysql connection</span>
+<span class="sd"> :type mysql_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"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,</span> <span class="s1">'partition'</span><span class="p">,</span> <span class="s1">'hive_table'</span><span class="p">)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#a0e08c'</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="bp">True</span><span class="p">,</span>
+ <span class="n">recreate</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
+ <span class="n">partition</span><span class="o">=</span><span class="bp">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">mysql_conn_id</span><span class="o">=</span><span class="s1">'mysql_default'</span><span class="p">,</span>
+ <span class="n">hive_cli_conn_id</span><span class="o">=</span><span class="s1">'hive_cli_default'</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">MySqlToHiveTransfer</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+ <span class="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="nb">str</span><span class="p">(</span><span class="n">delimiter</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span> <span class="o">=</span> <span class="n">mysql_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="nd">@classmethod</span>
+ <span class="k">def</span> <span class="nf">type_map</span><span class="p">(</span><span class="n">cls</span><span class="p">,</span> <span class="n">mysql_type</span><span class="p">):</span>
+ <span class="n">t</span> <span class="o">=</span> <span class="n">MySQLdb</span><span class="o">.</span><span class="n">constants</span><span class="o">.</span><span class="n">FIELD_TYPE</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">BIT</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">DECIMAL</span><span class="p">:</span> <span class="s1">'DOUBLE'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">DOUBLE</span><span class="p">:</span> <span class="s1">'DOUBLE'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">FLOAT</span><span class="p">:</span> <span class="s1">'DOUBLE'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">INT24</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">LONG</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">LONGLONG</span><span class="p">:</span> <span class="s1">'BIGINT'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">SHORT</span><span class="p">:</span> <span class="s1">'INT'</span><span class="p">,</span>
+ <span class="n">t</span><span class="o">.</span><span class="n">YEAR</span><span class="p">:</span> <span class="s1">'INT'</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">mysql_type</span><span class="p">]</span> <span class="k">if</span> <span class="n">mysql_type</span> <span class="ow">in</span> <span class="n">d</span> <span class="k">else</span> <span class="s1">'STRING'</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">mysql</span> <span class="o">=</span> <span class="n">MySqlHook</span><span class="p">(</span><span class="n">mysql_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span><span class="p">)</span>
+
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Dumping MySQL query results to local file"</span><span class="p">)</span>
+ <span class="n">conn</span> <span class="o">=</span> <span class="n">mysql</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">"wb"</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="s2">"utf-8"</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="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">field_dict</span><span class="p">[</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="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Loading file into Hive"</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></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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/9e19165c/_modules/postgres_hook.html
----------------------------------------------------------------------
diff --git a/_modules/postgres_hook.html b/_modules/postgres_hook.html
new file mode 100644
index 0000000..e0aa9eb
--- /dev/null
+++ b/_modules/postgres_hook.html
@@ -0,0 +1,236 @@
+
+
+<!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>postgres_hook — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="top" title="Airflow Documentation" href="../index.html"/>
+ <link rel="up" title="Module code" href="index.html"/>
+
+
+ <script src="../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../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>postgres_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 postgres_hook</h1><div class="highlight"><pre>
+<span></span><span class="kn">import</span> <span class="nn">psycopg2</span>
+<span class="kn">import</span> <span class="nn">psycopg2.extensions</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks.dbapi_hook</span> <span class="kn">import</span> <span class="n">DbApiHook</span>
+
+
+<div class="viewcode-block" id="PostgresHook"><a class="viewcode-back" href="../code.html#airflow.hooks.PostgresHook">[docs]</a><span class="k">class</span> <span class="nc">PostgresHook</span><span class="p">(</span><span class="n">DbApiHook</span><span class="p">):</span>
+ <span class="sd">'''</span>
+<span class="sd"> Interact with Postgres.</span>
+<span class="sd"> You can specify ssl parameters in the extra field of your connection</span>
+<span class="sd"> as ``{"sslmode": "require", "sslcert": "/path/to/cert.pem", etc}``.</span>
+<span class="sd"> '''</span>
+ <span class="n">conn_name_attr</span> <span class="o">=</span> <span class="s1">'postgres_conn_id'</span>
+ <span class="n">default_conn_name</span> <span class="o">=</span> <span class="s1">'postgres_default'</span>
+ <span class="n">supports_autocommit</span> <span class="o">=</span> <span class="bp">False</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="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">postgres_conn_id</span><span class="p">)</span>
+ <span class="n">conn_args</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span>
+ <span class="n">host</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">user</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">password</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">dbname</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="n">port</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="c1"># check for ssl parameters in conn.extra</span>
+ <span class="k">for</span> <span class="n">arg_name</span><span class="p">,</span> <span class="n">arg_val</span> <span class="ow">in</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
+ <span class="k">if</span> <span class="n">arg_name</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'sslmode'</span><span class="p">,</span> <span class="s1">'sslcert'</span><span class="p">,</span> <span class="s1">'sslkey'</span><span class="p">,</span> <span class="s1">'sslrootcert'</span><span class="p">,</span> <span class="s1">'sslcrl'</span><span class="p">]:</span>
+ <span class="n">conn_args</span><span class="p">[</span><span class="n">arg_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg_val</span>
+ <span class="n">psycopg2_conn</span> <span class="o">=</span> <span class="n">psycopg2</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="o">**</span><span class="n">conn_args</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">psycopg2_conn</span><span class="o">.</span><span class="n">server_version</span> <span class="o"><</span> <span class="mi">70400</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">supports_autocommit</span> <span class="o">=</span> <span class="bp">True</span>
+ <span class="k">return</span> <span class="n">psycopg2_conn</span>
+
+ <span class="nd">@staticmethod</span>
+ <span class="k">def</span> <span class="nf">_serialize_cell</span><span class="p">(</span><span class="n">cell</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">psycopg2</span><span class="o">.</span><span class="n">extensions</span><span class="o">.</span><span class="n">adapt</span><span class="p">(</span><span class="n">cell</span><span class="p">)</span><span class="o">.</span><span class="n">getquoted</span><span class="p">()</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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/9e19165c/_modules/postgres_operator.html
----------------------------------------------------------------------
diff --git a/_modules/postgres_operator.html b/_modules/postgres_operator.html
new file mode 100644
index 0000000..a9ec233
--- /dev/null
+++ b/_modules/postgres_operator.html
@@ -0,0 +1,239 @@
+
+
+<!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>postgres_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="top" title="Airflow Documentation" href="../index.html"/>
+ <link rel="up" title="Module code" href="index.html"/>
+
+
+ <script src="../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../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>postgres_operator</li>
+ <li class="wy-breadcrumbs-aside">
+
+
+
+ </li>
+ </ul>
+ <hr/>
+</div>
+ <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
+ <div itemprop="articleBody">
+
+ <h1>Source code for postgres_operator</h1><div class="highlight"><pre>
+<span></span><span class="kn">import</span> <span class="nn">logging</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">PostgresHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="PostgresOperator"><a class="viewcode-back" href="../code.html#airflow.operators.PostgresOperator">[docs]</a><span class="k">class</span> <span class="nc">PostgresOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Executes sql code in a specific Postgres database</span>
+
+<span class="sd"> :param postgres_conn_id: reference to a specific postgres database</span>
+<span class="sd"> :type postgres_conn_id: string</span>
+<span class="sd"> :param sql: the sql code to be executed</span>
+<span class="sd"> :type sql: Can receive a str representing a sql statement,</span>
+<span class="sd"> a list of str (sql statements), or reference to a template file.</span>
+<span class="sd"> Template reference are recognized by str ending in '.sql'</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#ededed'</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">postgres_conn_id</span><span class="o">=</span><span class="s1">'postgres_default'</span><span class="p">,</span> <span class="n">autocommit</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
+ <span class="n">parameters</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PostgresOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+ <span class="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">postgres_conn_id</span> <span class="o">=</span> <span class="n">postgres_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">autocommit</span> <span class="o">=</span> <span class="n">autocommit</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">parameters</span>
+
+ <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing: '</span> <span class="o">+</span> <span class="nb">str</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="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">PostgresHook</span><span class="p">(</span><span class="n">postgres_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">postgres_conn_id</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">run</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="bp">self</span><span class="o">.</span><span class="n">autocommit</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">parameters</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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/9e19165c/_modules/presto_check_operator.html
----------------------------------------------------------------------
diff --git a/_modules/presto_check_operator.html b/_modules/presto_check_operator.html
new file mode 100644
index 0000000..c99d551
--- /dev/null
+++ b/_modules/presto_check_operator.html
@@ -0,0 +1,303 @@
+
+
+<!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>presto_check_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <link rel="top" title="Airflow Documentation" href="../index.html"/>
+ <link rel="up" title="Module code" href="index.html"/>
+
+
+ <script src="../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../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>presto_check_operator</li>
+ <li class="wy-breadcrumbs-aside">
+
+
+
+ </li>
+ </ul>
+ <hr/>
+</div>
+ <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
+ <div itemprop="articleBody">
+
+ <h1>Source code for presto_check_operator</h1><div class="highlight"><pre>
+<span></span><span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">PrestoHook</span>
+<span class="kn">from</span> <span class="nn">airflow.operators</span> <span class="kn">import</span> <span class="n">CheckOperator</span><span class="p">,</span> <span class="n">ValueCheckOperator</span><span class="p">,</span> <span class="n">IntervalCheckOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="PrestoCheckOperator"><a class="viewcode-back" href="../code.html#airflow.operators.PrestoCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">PrestoCheckOperator</span><span class="p">(</span><span class="n">CheckOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Performs checks against Presto. The ``PrestoCheckOperator`` expects</span>
+<span class="sd"> a sql query that will return a single row. Each value on that</span>
+<span class="sd"> first row is evaluated using python ``bool`` casting. If any of the</span>
+<span class="sd"> values return ``False`` the check is failed and errors out.</span>
+
+<span class="sd"> Note that Python bool casting evals the following as ``False``:</span>
+<span class="sd"> * False</span>
+<span class="sd"> * 0</span>
+<span class="sd"> * Empty string (``""``)</span>
+<span class="sd"> * Empty list (``[]``)</span>
+<span class="sd"> * Empty dictionary or set (``{}``)</span>
+
+<span class="sd"> Given a query like ``SELECT COUNT(*) FROM foo``, it will fail only if</span>
+<span class="sd"> the count ``== 0``. You can craft much more complex query that could,</span>
+<span class="sd"> for instance, check that the table has the same number of rows as</span>
+<span class="sd"> the source table upstream, or that the count of today's partition is</span>
+<span class="sd"> greater than yesterday's partition, or that a set of metrics are less</span>
+<span class="sd"> than 3 standard deviation for the 7 day average.</span>
+
+<span class="sd"> This operator can be used as a data quality check in your pipeline, and</span>
+<span class="sd"> depending on where you put it in your DAG, you have the choice to</span>
+<span class="sd"> stop the critical path, preventing from</span>
+<span class="sd"> publishing dubious data, or on the side and receive email alterts</span>
+<span class="sd"> without stopping the progress of the DAG.</span>
+
+<span class="sd"> :param sql: the sql to be executed</span>
+<span class="sd"> :type sql: string</span>
+<span class="sd"> :param presto_conn_id: reference to the Presto database</span>
+<span class="sd"> :type presto_conn_id: string</span>
+<span class="sd"> """</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">presto_conn_id</span><span class="o">=</span><span class="s1">'presto_default'</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PrestoCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">sql</span><span class="o">=</span><span class="n">sql</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">presto_conn_id</span> <span class="o">=</span> <span class="n">presto_conn_id</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="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">PrestoHook</span><span class="p">(</span><span class="n">presto_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">presto_conn_id</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PrestoValueCheckOperator"><a class="viewcode-back" href="../code.html#airflow.operators.PrestoValueCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">PrestoValueCheckOperator</span><span class="p">(</span><span class="n">ValueCheckOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Performs a simple value check using sql code.</span>
+
+<span class="sd"> :param sql: the sql to be executed</span>
+<span class="sd"> :type sql: string</span>
+<span class="sd"> :param presto_conn_id: reference to the Presto database</span>
+<span class="sd"> :type presto_conn_id: string</span>
+<span class="sd"> """</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">pass_value</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">presto_conn_id</span><span class="o">=</span><span class="s1">'presto_default'</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PrestoValueCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="n">sql</span><span class="p">,</span> <span class="n">pass_value</span><span class="p">,</span> <span class="n">tolerance</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">presto_conn_id</span> <span class="o">=</span> <span class="n">presto_conn_id</span>
+
+ <span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">PrestoHook</span><span class="p">(</span><span class="n">presto_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">presto_conn_id</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="PrestoIntervalCheckOperator"><a class="viewcode-back" href="../code.html#airflow.operators.PrestoIntervalCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">PrestoIntervalCheckOperator</span><span class="p">(</span><span class="n">IntervalCheckOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Checks that the values of metrics given as SQL expressions are within</span>
+<span class="sd"> a certain tolerance of the ones from days_back before.</span>
+
+<span class="sd"> :param table: the table name</span>
+<span class="sd"> :type table: str</span>
+<span class="sd"> :param days_back: number of days between ds and the ds we want to check</span>
+<span class="sd"> against. Defaults to 7 days</span>
+<span class="sd"> :type days_back: int</span>
+<span class="sd"> :param metrics_threshold: a dictionary of ratios indexed by metrics</span>
+<span class="sd"> :type metrics_threshold: dict</span>
+<span class="sd"> :param presto_conn_id: reference to the Presto database</span>
+<span class="sd"> :type presto_conn_id: string</span>
+<span class="sd"> """</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">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="p">,</span>
+ <span class="n">date_filter_column</span><span class="o">=</span><span class="s1">'ds'</span><span class="p">,</span> <span class="n">days_back</span><span class="o">=-</span><span class="mi">7</span><span class="p">,</span>
+ <span class="n">presto_conn_id</span><span class="o">=</span><span class="s1">'presto_default'</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">PrestoIntervalCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span>
+ <span class="n">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="p">,</span> <span class="n">date_filter_column</span><span class="p">,</span> <span class="n">days_back</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">presto_conn_id</span> <span class="o">=</span> <span class="n">presto_conn_id</span>
+
+ <span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">PrestoHook</span><span class="p">(</span><span class="n">presto_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">presto_conn_id</span><span class="p">)</span></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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