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 05:24:14 UTC
[24/34] incubator-airflow-site git commit: Initial commit
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/9e19165c/_modules/hive_operator.html
----------------------------------------------------------------------
diff --git a/_modules/hive_operator.html b/_modules/hive_operator.html
new file mode 100644
index 0000000..6b6f4bb
--- /dev/null
+++ b/_modules/hive_operator.html
@@ -0,0 +1,272 @@
+
+
+<!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>hive_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>hive_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 hive_operator</h1><div class="highlight"><pre>
+<span></span><span class="kn">import</span> <span class="nn">logging</span>
+<span class="kn">import</span> <span class="nn">re</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">HiveCliHook</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="HiveOperator"><a class="viewcode-back" href="../code.html#airflow.operators.HiveOperator">[docs]</a><span class="k">class</span> <span class="nc">HiveOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Executes hql code in a specific Hive database.</span>
+
+<span class="sd"> :param hql: the hql to be executed</span>
+<span class="sd"> :type hql: string</span>
+<span class="sd"> :param hive_cli_conn_id: reference to the Hive database</span>
+<span class="sd"> :type hive_cli_conn_id: string</span>
+<span class="sd"> :param hiveconf_jinja_translate: when True, hiveconf-type templating</span>
+<span class="sd"> ${var} gets translated into jinja-type templating {{ var }}. Note that</span>
+<span class="sd"> you may want to use this along with the</span>
+<span class="sd"> ``DAG(user_defined_macros=myargs)`` parameter. View the DAG</span>
+<span class="sd"> object documentation for more details.</span>
+<span class="sd"> :type hiveconf_jinja_translate: boolean</span>
+<span class="sd"> :param script_begin_tag: If defined, the operator will get rid of the</span>
+<span class="sd"> part of the script before the first occurrence of `script_begin_tag`</span>
+<span class="sd"> :type script_begin_tag: str</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'hql'</span><span class="p">,</span> <span class="s1">'schema'</span><span class="p">)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.hql'</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">'#f0e4ec'</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">hql</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="n">schema</span><span class="o">=</span><span class="s1">'default'</span><span class="p">,</span>
+ <span class="n">hiveconf_jinja_translate</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
+ <span class="n">script_begin_tag</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">run_as_owner</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">HiveOperator</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">hiveconf_jinja_translate</span> <span class="o">=</span> <span class="n">hiveconf_jinja_translate</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hql</span> <span class="o">=</span> <span class="n">hql</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="o">=</span> <span class="n">schema</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">script_begin_tag</span> <span class="o">=</span> <span class="n">script_begin_tag</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">run_as</span> <span class="o">=</span> <span class="bp">None</span>
+ <span class="k">if</span> <span class="n">run_as_owner</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">run_as</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag</span><span class="o">.</span><span class="n">owner</span>
+
+ <span class="k">def</span> <span class="nf">get_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">return</span> <span class="n">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">run_as</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">run_as</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">prepare_template</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hiveconf_jinja_translate</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hql</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span>
+ <span class="s2">"(\$\{([ a-zA-Z0-9_]*)\})"</span><span class="p">,</span> <span class="s2">"{{ \g<2> }}"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hql</span><span class="p">)</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">script_begin_tag</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">script_begin_tag</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">hql</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hql</span> <span class="o">=</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</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">hql</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">script_begin_tag</span><span class="p">)[</span><span class="mi">1</span><span class="p">:])</span>
+
+ <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">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="bp">self</span><span class="o">.</span><span class="n">hql</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="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hql</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">dry_run</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">test_hql</span><span class="p">(</span><span class="n">hql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hql</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">on_kill</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">kill</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/hive_to_druid.html
----------------------------------------------------------------------
diff --git a/_modules/hive_to_druid.html b/_modules/hive_to_druid.html
new file mode 100644
index 0000000..8dfe4e4
--- /dev/null
+++ b/_modules/hive_to_druid.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>hive_to_druid — 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>hive_to_druid</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 hive_to_druid</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">HiveCliHook</span><span class="p">,</span> <span class="n">DruidHook</span><span class="p">,</span> <span class="n">HiveMetastoreHook</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="HiveToDruidTransfer"><a class="viewcode-back" href="../code.html#airflow.operators.HiveToDruidTransfer">[docs]</a><span class="k">class</span> <span class="nc">HiveToDruidTransfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Moves data from Hive to Druid, [del]note that for now the data is loaded</span>
+<span class="sd"> into memory before being pushed to Druid, so this operator should</span>
+<span class="sd"> be used for smallish amount of data.[/del]</span>
+
+<span class="sd"> :param sql: SQL query to execute against the Druid database</span>
+<span class="sd"> :type sql: str</span>
+<span class="sd"> :param druid_datasource: the datasource you want to ingest into in druid</span>
+<span class="sd"> :type druid_datasource: str</span>
+<span class="sd"> :param ts_dim: the timestamp dimension</span>
+<span class="sd"> :type ts_dim: str</span>
+<span class="sd"> :param metric_spec: the metrics you want to define for your data</span>
+<span class="sd"> :type metric_spec: list</span>
+<span class="sd"> :param hive_cli_conn_id: the hive connection id</span>
+<span class="sd"> :type hive_cli_conn_id: str</span>
+<span class="sd"> :param druid_ingest_conn_id: the druid ingest connection id</span>
+<span class="sd"> :type druid_ingest_conn_id: str</span>
+<span class="sd"> :param metastore_conn_id: the metastore connection id</span>
+<span class="sd"> :type metastore_conn_id: str</span>
+<span class="sd"> :param hadoop_dependency_coordinates: list of coordinates to squeeze</span>
+<span class="sd"> int the ingest json</span>
+<span class="sd"> :type hadoop_dependency_coordinates: list of str</span>
+<span class="sd"> :param intervals: list of time intervals that defines segments, this</span>
+<span class="sd"> is passed as is to the json object</span>
+<span class="sd"> :type intervals: list</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">'intervals'</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="c1">#ui_color = '#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">druid_datasource</span><span class="p">,</span>
+ <span class="n">ts_dim</span><span class="p">,</span>
+ <span class="n">metric_spec</span><span class="o">=</span><span class="bp">None</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="n">druid_ingest_conn_id</span><span class="o">=</span><span class="s1">'druid_ingest_default'</span><span class="p">,</span>
+ <span class="n">metastore_conn_id</span><span class="o">=</span><span class="s1">'metastore_default'</span><span class="p">,</span>
+ <span class="n">hadoop_dependency_coordinates</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">intervals</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">num_shards</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span>
+ <span class="n">target_partition_size</span><span class="o">=-</span><span class="mi">1</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">HiveToDruidTransfer</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">druid_datasource</span> <span class="o">=</span> <span class="n">druid_datasource</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">ts_dim</span> <span class="o">=</span> <span class="n">ts_dim</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">intervals</span> <span class="o">=</span> <span class="n">intervals</span> <span class="ow">or</span> <span class="p">[</span><span class="s1">'{{ ds }}/{{ tomorrow_ds }}'</span><span class="p">]</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">num_shards</span> <span class="o">=</span> <span class="n">num_shards</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">target_partition_size</span> <span class="o">=</span> <span class="n">target_partition_size</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">metric_spec</span> <span class="o">=</span> <span class="n">metric_spec</span> <span class="ow">or</span> <span class="p">[{</span>
+ <span class="s2">"name"</span><span class="p">:</span> <span class="s2">"count"</span><span class="p">,</span>
+ <span class="s2">"type"</span><span class="p">:</span> <span class="s2">"count"</span><span class="p">}]</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">hadoop_dependency_coordinates</span> <span class="o">=</span> <span class="n">hadoop_dependency_coordinates</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">druid_ingest_conn_id</span> <span class="o">=</span> <span class="n">druid_ingest_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span> <span class="o">=</span> <span class="n">metastore_conn_id</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">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Extracting data from Hive"</span><span class="p">)</span>
+ <span class="n">hive_table</span> <span class="o">=</span> <span class="s1">'druid.'</span> <span class="o">+</span> <span class="n">context</span><span class="p">[</span><span class="s1">'task_instance_key_str'</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'.'</span><span class="p">,</span> <span class="s1">'_'</span><span class="p">)</span>
+ <span class="n">sql</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s1">';'</span><span class="p">)</span>
+ <span class="n">hql</span> <span class="o">=</span> <span class="s2">"""</span><span class="se">\</span>
+<span class="s2"> set mapred.output.compress=false;</span>
+<span class="s2"> set hive.exec.compress.output=false;</span>
+<span class="s2"> DROP TABLE IF EXISTS {hive_table};</span>
+<span class="s2"> CREATE TABLE {hive_table}</span>
+<span class="s2"> ROW FORMAT DELIMITED FIELDS TERMINATED BY '</span><span class="se">\t</span><span class="s2">'</span>
+<span class="s2"> STORED AS TEXTFILE</span>
+<span class="s2"> TBLPROPERTIES ('serialization.null.format' = '')</span>
+<span class="s2"> AS</span>
+<span class="s2"> {sql}</span>
+<span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</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">"Running command:</span><span class="se">\n</span><span class="s2"> {}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hql</span><span class="p">))</span>
+ <span class="n">hive</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span>
+
+ <span class="n">m</span> <span class="o">=</span> <span class="n">HiveMetastoreHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span><span class="p">)</span>
+ <span class="n">t</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span>
+
+ <span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">col</span><span class="o">.</span><span class="n">name</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">t</span><span class="o">.</span><span class="n">sd</span><span class="o">.</span><span class="n">cols</span><span class="p">]</span>
+
+ <span class="n">hdfs_uri</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span><span class="o">.</span><span class="n">sd</span><span class="o">.</span><span class="n">location</span>
+ <span class="n">pos</span> <span class="o">=</span> <span class="n">hdfs_uri</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'/user'</span><span class="p">)</span>
+ <span class="n">static_path</span> <span class="o">=</span> <span class="n">hdfs_uri</span><span class="p">[</span><span class="n">pos</span><span class="p">:]</span>
+
+ <span class="n">schema</span><span class="p">,</span> <span class="n">table</span> <span class="o">=</span> <span class="n">hive_table</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)</span>
+
+ <span class="n">druid</span> <span class="o">=</span> <span class="n">DruidHook</span><span class="p">(</span><span class="n">druid_ingest_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">druid_ingest_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">"Inserting rows into Druid"</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">"HDFS path: "</span> <span class="o">+</span> <span class="n">static_path</span><span class="p">)</span>
+
+ <span class="n">druid</span><span class="o">.</span><span class="n">load_from_hdfs</span><span class="p">(</span>
+ <span class="n">datasource</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">druid_datasource</span><span class="p">,</span>
+ <span class="n">intervals</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">intervals</span><span class="p">,</span>
+ <span class="n">static_path</span><span class="o">=</span><span class="n">static_path</span><span class="p">,</span> <span class="n">ts_dim</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ts_dim</span><span class="p">,</span>
+ <span class="n">columns</span><span class="o">=</span><span class="n">columns</span><span class="p">,</span> <span class="n">num_shards</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_shards</span><span class="p">,</span> <span class="n">target_partition_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">target_partition_size</span><span class="p">,</span>
+ <span class="n">metric_spec</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">metric_spec</span><span class="p">,</span> <span class="n">hadoop_dependency_coordinates</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hadoop_dependency_coordinates</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">"Load seems to have succeeded!"</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">"Cleaning up by dropping the temp "</span>
+ <span class="s2">"Hive table {}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hive_table</span><span class="p">))</span>
+ <span class="n">hql</span> <span class="o">=</span> <span class="s2">"DROP TABLE IF EXISTS {}"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span>
+ <span class="n">hive</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</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/hive_to_mysql.html
----------------------------------------------------------------------
diff --git a/_modules/hive_to_mysql.html b/_modules/hive_to_mysql.html
new file mode 100644
index 0000000..13b223d
--- /dev/null
+++ b/_modules/hive_to_mysql.html
@@ -0,0 +1,294 @@
+
+
+<!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>hive_to_mysql — 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>hive_to_mysql</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 hive_to_mysql</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">HiveServer2Hook</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>
+
+<span class="kn">from</span> <span class="nn">tempfile</span> <span class="kn">import</span> <span class="n">NamedTemporaryFile</span>
+
+<div class="viewcode-block" id="HiveToMySqlTransfer"><a class="viewcode-back" href="../code.html#airflow.operators.HiveToMySqlTransfer">[docs]</a><span class="k">class</span> <span class="nc">HiveToMySqlTransfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Moves data from Hive to MySQL, note that for now the data is loaded</span>
+<span class="sd"> into memory before being pushed to MySQL, so this operator should</span>
+<span class="sd"> be used for smallish amount of data.</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 mysql_table: target MySQL table, use dot notation to target a</span>
+<span class="sd"> specific database</span>
+<span class="sd"> :type mysql_table: 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 hiveserver2_conn_id: destination hive connection</span>
+<span class="sd"> :type hiveserver2_conn_id: str</span>
+<span class="sd"> :param mysql_preoperator: sql statement to run against mysql prior to</span>
+<span class="sd"> import, typically use to truncate of delete in place of the data</span>
+<span class="sd"> coming in, allowing the task to be idempotent (running the task</span>
+<span class="sd"> twice won't double load data)</span>
+<span class="sd"> :type mysql_preoperator: str</span>
+<span class="sd"> :param mysql_postoperator: sql statement to run against mysql after the</span>
+<span class="sd"> import, typically used to move data from staging to production</span>
+<span class="sd"> and issue cleanup commands.</span>
+<span class="sd"> :type mysql_postoperator: str</span>
+<span class="sd"> :param bulk_load: flag to use bulk_load option. This loads mysql directly</span>
+<span class="sd"> from a tab-delimited text file using the LOAD DATA LOCAL INFILE command.</span>
+<span class="sd"> This option requires an extra connection parameter for the</span>
+<span class="sd"> destination MySQL connection: {'local_infile': true}.</span>
+<span class="sd"> :type bulk_load: bool</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">'mysql_table'</span><span class="p">,</span> <span class="s1">'mysql_preoperator'</span><span class="p">,</span>
+ <span class="s1">'mysql_postoperator'</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">mysql_table</span><span class="p">,</span>
+ <span class="n">hiveserver2_conn_id</span><span class="o">=</span><span class="s1">'hiveserver2_default'</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">mysql_preoperator</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">mysql_postoperator</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">bulk_load</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">HiveToMySqlTransfer</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">mysql_table</span> <span class="o">=</span> <span class="n">mysql_table</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">mysql_preoperator</span> <span class="o">=</span> <span class="n">mysql_preoperator</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">mysql_postoperator</span> <span class="o">=</span> <span class="n">mysql_postoperator</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_conn_id</span> <span class="o">=</span> <span class="n">hiveserver2_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">bulk_load</span> <span class="o">=</span> <span class="n">bulk_load</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">HiveServer2Hook</span><span class="p">(</span><span class="n">hiveserver2_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_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">"Extracting data from Hive"</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="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bulk_load</span><span class="p">:</span>
+ <span class="n">tmpfile</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">()</span>
+ <span class="n">hive</span><span class="o">.</span><span class="n">to_csv</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">tmpfile</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">'</span><span class="se">\t</span><span class="s1">'</span><span class="p">,</span>
+ <span class="n">lineterminator</span><span class="o">=</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">,</span> <span class="n">output_header</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">results</span> <span class="o">=</span> <span class="n">hive</span><span class="o">.</span><span class="n">get_records</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">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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mysql_preoperator</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">"Running MySQL preoperator"</span><span class="p">)</span>
+ <span class="n">mysql</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">mysql_preoperator</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">"Inserting rows into MySQL"</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bulk_load</span><span class="p">:</span>
+ <span class="n">mysql</span><span class="o">.</span><span class="n">bulk_load</span><span class="p">(</span><span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_table</span><span class="p">,</span> <span class="n">tmp_file</span><span class="o">=</span><span class="n">tmpfile</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
+ <span class="n">tmpfile</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">mysql</span><span class="o">.</span><span class="n">insert_rows</span><span class="p">(</span><span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_table</span><span class="p">,</span> <span class="n">rows</span><span class="o">=</span><span class="n">results</span><span class="p">)</span>
+
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mysql_postoperator</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">"Running MySQL postoperator"</span><span class="p">)</span>
+ <span class="n">mysql</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">mysql_postoperator</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">"Done."</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/hive_to_samba_operator.html
----------------------------------------------------------------------
diff --git a/_modules/hive_to_samba_operator.html b/_modules/hive_to_samba_operator.html
new file mode 100644
index 0000000..9eb09b5
--- /dev/null
+++ b/_modules/hive_to_samba_operator.html
@@ -0,0 +1,246 @@
+
+
+<!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>hive_to_samba_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>hive_to_samba_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 hive_to_samba_operator</h1><div class="highlight"><pre>
+<span></span><span class="kn">import</span> <span class="nn">logging</span>
+<span class="kn">import</span> <span class="nn">tempfile</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">HiveServer2Hook</span><span class="p">,</span> <span class="n">SambaHook</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="Hive2SambaOperator"><a class="viewcode-back" href="../code.html#airflow.operators.Hive2SambaOperator">[docs]</a><span class="k">class</span> <span class="nc">Hive2SambaOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Executes hql code in a specific Hive database and loads the</span>
+<span class="sd"> results of the query as a csv to a Samba location.</span>
+
+<span class="sd"> :param hql: the hql to be exported</span>
+<span class="sd"> :type hql: string</span>
+<span class="sd"> :param hiveserver2_conn_id: reference to the hiveserver2 service</span>
+<span class="sd"> :type hiveserver2_conn_id: string</span>
+<span class="sd"> :param samba_conn_id: reference to the samba destination</span>
+<span class="sd"> :type samba_conn_id: string</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'hql'</span><span class="p">,</span> <span class="s1">'destination_filepath'</span><span class="p">)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.hql'</span><span class="p">,</span> <span class="s1">'.sql'</span><span class="p">,)</span>
+
+ <span class="nd">@apply_defaults</span>
+ <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
+ <span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span>
+ <span class="n">destination_filepath</span><span class="p">,</span>
+ <span class="n">samba_conn_id</span><span class="o">=</span><span class="s1">'samba_default'</span><span class="p">,</span>
+ <span class="n">hiveserver2_conn_id</span><span class="o">=</span><span class="s1">'hiveserver2_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">Hive2SambaOperator</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">hiveserver2_conn_id</span> <span class="o">=</span> <span class="n">hiveserver2_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">samba_conn_id</span> <span class="o">=</span> <span class="n">samba_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">destination_filepath</span> <span class="o">=</span> <span class="n">destination_filepath</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hql</span> <span class="o">=</span> <span class="n">hql</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">rstrip</span><span class="p">(</span><span class="s1">';'</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">samba</span> <span class="o">=</span> <span class="n">SambaHook</span><span class="p">(</span><span class="n">samba_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">samba_conn_id</span><span class="p">)</span>
+ <span class="n">hive</span> <span class="o">=</span> <span class="n">HiveServer2Hook</span><span class="p">(</span><span class="n">hiveserver2_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hiveserver2_conn_id</span><span class="p">)</span>
+ <span class="n">tmpfile</span> <span class="o">=</span> <span class="n">tempfile</span><span class="o">.</span><span class="n">NamedTemporaryFile</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">"Fetching file from Hive"</span><span class="p">)</span>
+ <span class="n">hive</span><span class="o">.</span><span class="n">to_csv</span><span class="p">(</span><span class="n">hql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hql</span><span class="p">,</span> <span class="n">csv_filepath</span><span class="o">=</span><span class="n">tmpfile</span><span class="o">.</span><span class="n">name</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">"Pushing to samba"</span><span class="p">)</span>
+ <span class="n">samba</span><span class="o">.</span><span class="n">push_from_local</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">destination_filepath</span><span class="p">,</span> <span class="n">tmpfile</span><span class="o">.</span><span class="n">name</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/http_hook.html
----------------------------------------------------------------------
diff --git a/_modules/http_hook.html b/_modules/http_hook.html
new file mode 100644
index 0000000..6f79193
--- /dev/null
+++ b/_modules/http_hook.html
@@ -0,0 +1,310 @@
+
+
+<!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>http_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>http_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 http_hook</h1><div class="highlight"><pre>
+<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span>
+<span class="c1"># you may not use this file except in compliance with the License.</span>
+<span class="c1"># You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
+<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span>
+<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
+<span class="c1"># See the License for the specific language governing permissions and</span>
+<span class="c1"># limitations under the License.</span>
+<span class="c1">#</span>
+<span class="kn">from</span> <span class="nn">builtins</span> <span class="kn">import</span> <span class="nb">str</span>
+<span class="kn">import</span> <span class="nn">logging</span>
+
+<span class="kn">import</span> <span class="nn">requests</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="kn">import</span> <span class="n">BaseHook</span>
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="kn">import</span> <span class="n">AirflowException</span>
+
+
+<div class="viewcode-block" id="HttpHook"><a class="viewcode-back" href="../code.html#airflow.hooks.HttpHook">[docs]</a><span class="k">class</span> <span class="nc">HttpHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Interact with HTTP servers.</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">method</span><span class="o">=</span><span class="s1">'POST'</span><span class="p">,</span> <span class="n">http_conn_id</span><span class="o">=</span><span class="s1">'http_default'</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">http_conn_id</span> <span class="o">=</span> <span class="n">http_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">=</span> <span class="n">method</span>
+
+ <span class="c1"># headers is required to make it required</span>
+<div class="viewcode-block" id="HttpHook.get_conn"><a class="viewcode-back" href="../code.html#airflow.hooks.HttpHook.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="n">headers</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Returns http session for use with requests</span>
+<span class="sd"> """</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">http_conn_id</span><span class="p">)</span>
+ <span class="n">session</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">Session</span><span class="p">()</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">host</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'http'</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span> <span class="o">=</span> <span class="s1">'http://'</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span>
+
+ <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span> <span class="o">+</span> <span class="s2">":"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">)</span> <span class="o">+</span> <span class="s2">"/"</span>
+ <span class="k">if</span> <span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">:</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">auth</span> <span class="o">=</span> <span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</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="n">headers</span><span class="p">:</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">headers</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">headers</span><span class="p">)</span>
+
+ <span class="k">return</span> <span class="n">session</span></div>
+
+<div class="viewcode-block" id="HttpHook.run"><a class="viewcode-back" href="../code.html#airflow.hooks.HttpHook.run">[docs]</a> <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">endpoint</span><span class="p">,</span> <span class="n">data</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">extra_options</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Performs the request</span>
+<span class="sd"> """</span>
+ <span class="n">extra_options</span> <span class="o">=</span> <span class="n">extra_options</span> <span class="ow">or</span> <span class="p">{}</span>
+
+ <span class="n">session</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">(</span><span class="n">headers</span><span class="p">)</span>
+
+ <span class="n">url</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">base_url</span> <span class="o">+</span> <span class="n">endpoint</span>
+ <span class="n">req</span> <span class="o">=</span> <span class="bp">None</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">==</span> <span class="s1">'GET'</span><span class="p">:</span>
+ <span class="c1"># GET uses params</span>
+ <span class="n">req</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">Request</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span>
+ <span class="n">url</span><span class="p">,</span>
+ <span class="n">params</span><span class="o">=</span><span class="n">data</span><span class="p">,</span>
+ <span class="n">headers</span><span class="o">=</span><span class="n">headers</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="c1"># Others use data</span>
+ <span class="n">req</span> <span class="o">=</span> <span class="n">requests</span><span class="o">.</span><span class="n">Request</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">method</span><span class="p">,</span>
+ <span class="n">url</span><span class="p">,</span>
+ <span class="n">data</span><span class="o">=</span><span class="n">data</span><span class="p">,</span>
+ <span class="n">headers</span><span class="o">=</span><span class="n">headers</span><span class="p">)</span>
+
+ <span class="n">prepped_request</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">prepare_request</span><span class="p">(</span><span class="n">req</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">"Sending '"</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">+</span> <span class="s2">"' to url: "</span> <span class="o">+</span> <span class="n">url</span><span class="p">)</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">run_and_check</span><span class="p">(</span><span class="n">session</span><span class="p">,</span> <span class="n">prepped_request</span><span class="p">,</span> <span class="n">extra_options</span><span class="p">)</span></div>
+
+<div class="viewcode-block" id="HttpHook.run_and_check"><a class="viewcode-back" href="../code.html#airflow.hooks.HttpHook.run_and_check">[docs]</a> <span class="k">def</span> <span class="nf">run_and_check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">,</span> <span class="n">prepped_request</span><span class="p">,</span> <span class="n">extra_options</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Grabs extra options like timeout and actually runs the request,</span>
+<span class="sd"> checking for the result</span>
+<span class="sd"> """</span>
+ <span class="n">extra_options</span> <span class="o">=</span> <span class="n">extra_options</span> <span class="ow">or</span> <span class="p">{}</span>
+
+ <span class="n">response</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">send</span><span class="p">(</span>
+ <span class="n">prepped_request</span><span class="p">,</span>
+ <span class="n">stream</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"stream"</span><span class="p">,</span> <span class="bp">False</span><span class="p">),</span>
+ <span class="n">verify</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"verify"</span><span class="p">,</span> <span class="bp">False</span><span class="p">),</span>
+ <span class="n">proxies</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"proxies"</span><span class="p">,</span> <span class="p">{}),</span>
+ <span class="n">cert</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"cert"</span><span class="p">),</span>
+ <span class="n">timeout</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"timeout"</span><span class="p">),</span>
+ <span class="n">allow_redirects</span><span class="o">=</span><span class="n">extra_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"allow_redirects"</span><span class="p">,</span> <span class="bp">True</span><span class="p">))</span>
+
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
+ <span class="k">except</span> <span class="n">requests</span><span class="o">.</span><span class="n">exceptions</span><span class="o">.</span><span class="n">HTTPError</span><span class="p">:</span>
+ <span class="c1"># Tried rewrapping, but not supported. This way, it's possible</span>
+ <span class="c1"># to get reason and code for failure by checking first 3 chars</span>
+ <span class="c1"># for the code, or do a split on ':'</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"HTTP error: "</span> <span class="o">+</span> <span class="n">response</span><span class="o">.</span><span class="n">reason</span><span class="p">)</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">method</span> <span class="o">!=</span> <span class="s1">'GET'</span><span class="p">:</span>
+ <span class="c1"># The sensor uses GET, so this prevents filling up the log</span>
+ <span class="c1"># with the body every time the GET 'misses'.</span>
+ <span class="c1"># That's ok to do, because GETs should be repeatable and</span>
+ <span class="c1"># all data should be visible in the log (no post data)</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">status_code</span><span class="p">)</span><span class="o">+</span><span class="s2">":"</span><span class="o">+</span><span class="n">response</span><span class="o">.</span><span class="n">reason</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">response</span></div></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