You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/29 20:24:53 UTC
[25/48] incubator-airflow-site git commit: 1.10.0 with Updated Api
Reference
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/7d4d7628/_modules/airflow/operators/dummy_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/dummy_operator.html b/_modules/airflow/operators/dummy_operator.html
index e730cbe..5502644 100644
--- a/_modules/airflow/operators/dummy_operator.html
+++ b/_modules/airflow/operators/dummy_operator.html
@@ -24,26 +24,17 @@
-
-
- <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
-
-
-
-
-
- <link rel="index" title="Index"
- href="../../../genindex.html"/>
- <link rel="search" title="Search" href="../../../search.html"/>
- <link rel="top" title="Airflow Documentation" href="../../../index.html"/>
- <link rel="up" title="Module code" href="../../index.html"/>
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+ <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
+ <link rel="index" title="Index" href="../../../genindex.html" />
+ <link rel="search" title="Search" href="../../../search.html" />
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
-<body class="wy-body-for-nav" role="document">
+<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
@@ -116,7 +107,7 @@
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
- <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+ <nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
@@ -124,9 +115,10 @@
</nav>
-
<div class="wy-nav-content">
+
<div class="rst-content">
+
@@ -156,8 +148,6 @@
<li class="wy-breadcrumbs-aside">
-
-
</li>
</ul>
@@ -178,9 +168,9 @@
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># "License"); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
-<span class="c1"># </span>
+<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
-<span class="c1"># </span>
+<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
@@ -210,9 +200,7 @@
</pre></div>
</div>
- <div class="articleComments">
-
- </div>
+
</div>
<footer>
@@ -224,7 +212,7 @@
</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>.
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
@@ -243,6 +231,7 @@
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
+ LANGUAGE:'None',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
@@ -255,19 +244,13 @@
-
-
- <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
+ <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
-
<script type="text/javascript">
jQuery(function () {
- SphinxRtdTheme.StickyNav.enable();
+ SphinxRtdTheme.Navigation.enable(true);
});
- </script>
-
+ </script>
</body>
</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/7d4d7628/_modules/airflow/operators/email_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/email_operator.html b/_modules/airflow/operators/email_operator.html
index 6a5980a..d365677 100644
--- a/_modules/airflow/operators/email_operator.html
+++ b/_modules/airflow/operators/email_operator.html
@@ -24,26 +24,17 @@
-
-
- <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
-
-
-
-
-
- <link rel="index" title="Index"
- href="../../../genindex.html"/>
- <link rel="search" title="Search" href="../../../search.html"/>
- <link rel="top" title="Airflow Documentation" href="../../../index.html"/>
- <link rel="up" title="Module code" href="../../index.html"/>
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+ <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
+ <link rel="index" title="Index" href="../../../genindex.html" />
+ <link rel="search" title="Search" href="../../../search.html" />
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
-<body class="wy-body-for-nav" role="document">
+<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
@@ -116,7 +107,7 @@
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
- <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+ <nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
@@ -124,9 +115,10 @@
</nav>
-
<div class="wy-nav-content">
+
<div class="rst-content">
+
@@ -156,8 +148,6 @@
<li class="wy-breadcrumbs-aside">
-
-
</li>
</ul>
@@ -197,12 +187,12 @@
<span class="sd">"""</span>
<span class="sd"> Sends an email.</span>
-<span class="sd"> :param to: list of emails to send the email to</span>
+<span class="sd"> :param to: list of emails to send the email to. (templated)</span>
<span class="sd"> :type to: list or string (comma or semicolon delimited)</span>
-<span class="sd"> :param subject: subject line for the email (templated)</span>
+<span class="sd"> :param subject: subject line for the email. (templated)</span>
<span class="sd"> :type subject: string</span>
-<span class="sd"> :param html_content: content of the email (templated), html markup</span>
-<span class="sd"> is allowed</span>
+<span class="sd"> :param html_content: content of the email, html markup</span>
+<span class="sd"> is allowed. (templated)</span>
<span class="sd"> :type html_content: string</span>
<span class="sd"> :param files: file names to attach in email</span>
<span class="sd"> :type files: list</span>
@@ -246,13 +236,11 @@
<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">send_email</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">to</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">subject</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">html_content</span><span class="p">,</span>
<span class="n">files</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">files</span><span class="p">,</span> <span class="n">cc</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">cc</span><span class="p">,</span> <span class="n">bcc</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bcc</span><span class="p">,</span>
- <span class="n">mime_subtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mime_subtype</span><span class="p">,</span> <span class="n">mine_charset</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mime_charset</span><span class="p">)</span></div>
+ <span class="n">mime_subtype</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mime_subtype</span><span class="p">,</span> <span class="n">mime_charset</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mime_charset</span><span class="p">)</span></div>
</pre></div>
</div>
- <div class="articleComments">
-
- </div>
+
</div>
<footer>
@@ -264,7 +252,7 @@
</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>.
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
@@ -283,6 +271,7 @@
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
+ LANGUAGE:'None',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
@@ -295,19 +284,13 @@
-
-
- <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
+ <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
-
<script type="text/javascript">
jQuery(function () {
- SphinxRtdTheme.StickyNav.enable();
+ SphinxRtdTheme.Navigation.enable(true);
});
- </script>
-
+ </script>
</body>
</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/7d4d7628/_modules/airflow/operators/generic_transfer.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/generic_transfer.html b/_modules/airflow/operators/generic_transfer.html
index 4a03958..9cacd65 100644
--- a/_modules/airflow/operators/generic_transfer.html
+++ b/_modules/airflow/operators/generic_transfer.html
@@ -24,26 +24,17 @@
-
-
- <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
-
-
-
-
-
- <link rel="index" title="Index"
- href="../../../genindex.html"/>
- <link rel="search" title="Search" href="../../../search.html"/>
- <link rel="top" title="Airflow Documentation" href="../../../index.html"/>
- <link rel="up" title="Module code" href="../../index.html"/>
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+ <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
+ <link rel="index" title="Index" href="../../../genindex.html" />
+ <link rel="search" title="Search" href="../../../search.html" />
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
-<body class="wy-body-for-nav" role="document">
+<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
@@ -116,7 +107,7 @@
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
- <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+ <nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
@@ -124,9 +115,10 @@
</nav>
-
<div class="wy-nav-content">
+
<div class="rst-content">
+
@@ -156,8 +148,6 @@
<li class="wy-breadcrumbs-aside">
-
-
</li>
</ul>
@@ -178,15 +168,16 @@
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># "License"); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
-<span class="c1"># </span>
+<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
-<span class="c1"># </span>
+<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
+
<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span>
@@ -201,16 +192,16 @@
<span class="sd"> This is meant to be used on small-ish datasets that fit in memory.</span>
-<span class="sd"> :param sql: SQL query to execute against the source database</span>
+<span class="sd"> :param sql: SQL query to execute against the source database. (templated)</span>
<span class="sd"> :type sql: str</span>
-<span class="sd"> :param destination_table: target table</span>
+<span class="sd"> :param destination_table: target table. (templated)</span>
<span class="sd"> :type destination_table: str</span>
<span class="sd"> :param source_conn_id: source connection</span>
<span class="sd"> :type source_conn_id: str</span>
<span class="sd"> :param destination_conn_id: source connection</span>
<span class="sd"> :type destination_conn_id: str</span>
<span class="sd"> :param preoperator: sql statement or list of statements to be</span>
-<span class="sd"> executed prior to loading the data</span>
+<span class="sd"> executed prior to loading the data. (templated)</span>
<span class="sd"> :type preoperator: str or list of str</span>
<span class="sd"> """</span>
@@ -252,9 +243,7 @@
</pre></div>
</div>
- <div class="articleComments">
-
- </div>
+
</div>
<footer>
@@ -266,7 +255,7 @@
</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>.
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
@@ -285,6 +274,7 @@
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
+ LANGUAGE:'None',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
@@ -297,19 +287,13 @@
-
-
- <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
+ <script type="text/javascript" src="../../../_static/js/theme.js"></script>
-
-
<script type="text/javascript">
jQuery(function () {
- SphinxRtdTheme.StickyNav.enable();
+ SphinxRtdTheme.Navigation.enable(true);
});
- </script>
-
+ </script>
</body>
</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/7d4d7628/_modules/airflow/operators/hive_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/hive_operator.html b/_modules/airflow/operators/hive_operator.html
new file mode 100644
index 0000000..ba86f39
--- /dev/null
+++ b/_modules/airflow/operators/hive_operator.html
@@ -0,0 +1,360 @@
+
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
+<head>
+ <meta charset="utf-8">
+
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+ <title>airflow.operators.hive_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+ <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
+ <link rel="index" title="Index" href="../../../genindex.html" />
+ <link rel="search" title="Search" href="../../../search.html" />
+
+
+ <script src="../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../api.html">Experimental Rest API</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../index.html">Airflow</a>
+
+ </nav>
+
+
+ <div class="wy-nav-content">
+
+ <div class="rst-content">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<div role="navigation" aria-label="breadcrumbs navigation">
+
+ <ul class="wy-breadcrumbs">
+
+ <li><a href="../../../index.html">Docs</a> »</li>
+
+ <li><a href="../../index.html">Module code</a> »</li>
+
+ <li>airflow.operators.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 airflow.operators.hive_operator</h1><div class="highlight"><pre>
+<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
+<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
+<span class="c1"># distributed with this work for additional information</span>
+<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
+<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
+<span class="c1"># "License"); you may not use this file except in compliance</span>
+<span class="c1"># with the License. You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
+<span class="c1"># software distributed under the License is distributed on an</span>
+<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+
+<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">unicode_literals</span>
+
+<span class="kn">import</span> <span class="nn">re</span>
+
+<span class="kn">from</span> <span class="nn">airflow.hooks.hive_hooks</span> <span class="k">import</span> <span class="n">HiveCliHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.operator_helpers</span> <span class="k">import</span> <span class="n">context_to_airflow_vars</span>
+
+
+<div class="viewcode-block" id="HiveOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.hive_operator.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 or hive script in a specific Hive database.</span>
+
+<span class="sd"> :param hql: the hql to be executed. Note that you may also use</span>
+<span class="sd"> a relative path from the dag file of a (template) hive</span>
+<span class="sd"> script. (templated)</span>
+<span class="sd"> :type hql: string</span>
+<span class="sd"> :param hive_cli_conn_id: reference to the Hive database. (templated)</span>
+<span class="sd"> :type hive_cli_conn_id: string</span>
+<span class="sd"> :param hiveconfs: if defined, these key value pairs will be passed</span>
+<span class="sd"> to hive as ``-hiveconf "key"="value"``</span>
+<span class="sd"> :type hiveconfs: dict</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 }} and</span>
+<span class="sd"> ${hiveconf:var} gets translated into jinja-type templating {{ var }}.</span>
+<span class="sd"> Note that 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"> :param mapred_queue: queue used by the Hadoop CapacityScheduler. (templated)</span>
+<span class="sd"> :type mapred_queue: string</span>
+<span class="sd"> :param mapred_queue_priority: priority within CapacityScheduler queue.</span>
+<span class="sd"> Possible settings include: VERY_HIGH, HIGH, NORMAL, LOW, VERY_LOW</span>
+<span class="sd"> :type mapred_queue_priority: string</span>
+<span class="sd"> :param mapred_job_name: This name will appear in the jobtracker.</span>
+<span class="sd"> This can make monitoring easier.</span>
+<span class="sd"> :type mapred_job_name: 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">'schema'</span><span class="p">,</span> <span class="s1">'hive_cli_conn_id'</span><span class="p">,</span> <span class="s1">'mapred_queue'</span><span class="p">,</span>
+ <span class="s1">'hiveconfs'</span><span class="p">,</span> <span class="s1">'mapred_job_name'</span><span class="p">,</span> <span class="s1">'mapred_queue_priority'</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">hiveconfs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">hiveconf_jinja_translate</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">script_begin_tag</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">run_as_owner</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
+ <span class="n">mapred_queue</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">mapred_queue_priority</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">mapred_job_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
+
+ <span class="nb">super</span><span class="p">(</span><span class="n">HiveOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hql</span> <span class="o">=</span> <span class="n">hql</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">schema</span> <span class="o">=</span> <span class="n">schema</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hiveconfs</span> <span class="o">=</span> <span class="n">hiveconfs</span> <span class="ow">or</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">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="kc">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="bp">self</span><span class="o">.</span><span class="n">mapred_queue</span> <span class="o">=</span> <span class="n">mapred_queue</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue_priority</span> <span class="o">=</span> <span class="n">mapred_queue_priority</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">mapred_job_name</span> <span class="o">=</span> <span class="n">mapred_job_name</span>
+
+ <span class="c1"># assigned lazily - just for consistency we can create the attribute with a</span>
+ <span class="c1"># `None` initial value, later it will be populated by the execute method.</span>
+ <span class="c1"># This also makes `on_kill` implementation consistent since it assumes `self.hook`</span>
+ <span class="c1"># is defined.</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="kc">None</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="n">mapred_queue</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue</span><span class="p">,</span>
+ <span class="n">mapred_queue_priority</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mapred_queue_priority</span><span class="p">,</span>
+ <span class="n">mapred_job_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mapred_job_name</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">"(\$\{(hiveconf:)?([ a-zA-Z0-9_]*)\})"</span><span class="p">,</span> <span class="s2">"{{ \g<3> }}"</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="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing: </span><span class="si">%s</span><span class="s1">'</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="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="c1"># set the mapred_job_name if it's not set with dag, task, execution time info</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">mapred_job_name</span><span class="p">:</span>
+ <span class="n">ti</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">'ti'</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">mapred_job_name</span> <span class="o">=</span> <span class="s1">'Airflow HiveOperator task for </span><span class="si">{}</span><span class="s1">.</span><span class="si">{}</span><span class="s1">.</span><span class="si">{}</span><span class="s1">.</span><span class="si">{}</span><span class="s1">'</span>\
+ <span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">ti</span><span class="o">.</span><span class="n">hostname</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span> <span class="n">ti</span><span class="o">.</span><span class="n">dag_id</span><span class="p">,</span> <span class="n">ti</span><span class="o">.</span><span class="n">task_id</span><span class="p">,</span>
+ <span class="n">ti</span><span class="o">.</span><span class="n">execution_date</span><span class="o">.</span><span class="n">isoformat</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">hiveconfs</span> <span class="o">=</span> <span class="n">context_to_airflow_vars</span><span class="p">(</span><span class="n">context</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hiveconfs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">context_to_airflow_vars</span><span class="p">(</span><span class="n">context</span><span class="p">))</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Passing HiveConf: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hiveconfs</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="n">hive_conf</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hiveconfs</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">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">kill</span><span class="p">()</span></div>
+</pre></div>
+
+ </div>
+
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+
+ </p>
+ </div>
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../',
+ VERSION:'',
+ LANGUAGE:'None',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../_static/doctools.js"></script>
+
+
+
+ <script type="text/javascript" src="../../../_static/js/theme.js"></script>
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.Navigation.enable(true);
+ });
+ </script>
+
+</body>
+</html>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/7d4d7628/_modules/airflow/operators/hive_stats_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/operators/hive_stats_operator.html b/_modules/airflow/operators/hive_stats_operator.html
new file mode 100644
index 0000000..bee4e35
--- /dev/null
+++ b/_modules/airflow/operators/hive_stats_operator.html
@@ -0,0 +1,408 @@
+
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
+<head>
+ <meta charset="utf-8">
+
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+ <title>airflow.operators.hive_stats_operator — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
+ <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
+ <link rel="index" title="Index" href="../../../genindex.html" />
+ <link rel="search" title="Search" href="../../../search.html" />
+
+
+ <script src="../../../_static/js/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav">
+
+
+ <div class="wy-grid-for-nav">
+
+
+ <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+ <div class="wy-side-scroll">
+ <div class="wy-side-nav-search">
+
+
+
+ <a href="../../../index.html" class="icon icon-home"> Airflow
+
+
+
+ </a>
+
+
+
+
+
+
+
+<div role="search">
+ <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
+ <input type="text" name="q" placeholder="Search docs" />
+ <input type="hidden" name="check_keywords" value="yes" />
+ <input type="hidden" name="area" value="default" />
+ </form>
+</div>
+
+
+ </div>
+
+ <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+
+
+
+
+
+
+ <ul>
+<li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling & Triggers</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../api.html">Experimental Rest API</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../../../code.html">API Reference</a></li>
+</ul>
+
+
+
+ </div>
+ </div>
+ </nav>
+
+ <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+
+ <nav class="wy-nav-top" aria-label="top navigation">
+
+ <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+ <a href="../../../index.html">Airflow</a>
+
+ </nav>
+
+
+ <div class="wy-nav-content">
+
+ <div class="rst-content">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+<div role="navigation" aria-label="breadcrumbs navigation">
+
+ <ul class="wy-breadcrumbs">
+
+ <li><a href="../../../index.html">Docs</a> »</li>
+
+ <li><a href="../../index.html">Module code</a> »</li>
+
+ <li>airflow.operators.hive_stats_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 airflow.operators.hive_stats_operator</h1><div class="highlight"><pre>
+<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
+<span class="c1">#</span>
+<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
+<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
+<span class="c1"># distributed with this work for additional information</span>
+<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
+<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
+<span class="c1"># "License"); you may not use this file except in compliance</span>
+<span class="c1"># with the License. You may obtain a copy of the License at</span>
+<span class="c1">#</span>
+<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
+<span class="c1">#</span>
+<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
+<span class="c1"># software distributed under the License is distributed on an</span>
+<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
+<span class="c1"># KIND, either express or implied. See the License for the</span>
+<span class="c1"># specific language governing permissions and limitations</span>
+<span class="c1"># under the License.</span>
+
+<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">zip</span>
+<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span>
+<span class="kn">import</span> <span class="nn">json</span>
+
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span>
+<span class="kn">from</span> <span class="nn">airflow.hooks.mysql_hook</span> <span class="k">import</span> <span class="n">MySqlHook</span>
+<span class="kn">from</span> <span class="nn">airflow.hooks.presto_hook</span> <span class="k">import</span> <span class="n">PrestoHook</span>
+<span class="kn">from</span> <span class="nn">airflow.hooks.hive_hooks</span> <span class="k">import</span> <span class="n">HiveMetastoreHook</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span>
+
+
+<div class="viewcode-block" id="HiveStatsCollectionOperator"><a class="viewcode-back" href="../../../code.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator">[docs]</a><span class="k">class</span> <span class="nc">HiveStatsCollectionOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Gathers partition statistics using a dynamically generated Presto</span>
+<span class="sd"> query, inserts the stats into a MySql table with this format. Stats</span>
+<span class="sd"> overwrite themselves if you rerun the same date/partition. ::</span>
+
+<span class="sd"> CREATE TABLE hive_stats (</span>
+<span class="sd"> ds VARCHAR(16),</span>
+<span class="sd"> table_name VARCHAR(500),</span>
+<span class="sd"> metric VARCHAR(200),</span>
+<span class="sd"> value BIGINT</span>
+<span class="sd"> );</span>
+
+<span class="sd"> :param table: the source table, in the format ``database.table_name``. (templated)</span>
+<span class="sd"> :type table: str</span>
+<span class="sd"> :param partition: the source partition. (templated)</span>
+<span class="sd"> :type partition: dict of {col:value}</span>
+<span class="sd"> :param extra_exprs: dict of expression to run against the table where</span>
+<span class="sd"> keys are metric names and values are Presto compatible expressions</span>
+<span class="sd"> :type extra_exprs: dict</span>
+<span class="sd"> :param col_blacklist: list of columns to blacklist, consider</span>
+<span class="sd"> blacklisting blobs, large json columns, ...</span>
+<span class="sd"> :type col_blacklist: list</span>
+<span class="sd"> :param assignment_func: a function that receives a column name and</span>
+<span class="sd"> a type, and returns a dict of metric names and an Presto expressions.</span>
+<span class="sd"> If None is returned, the global defaults are applied. If an</span>
+<span class="sd"> empty dictionary is returned, no stats are computed for that</span>
+<span class="sd"> column.</span>
+<span class="sd"> :type assignment_func: function</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'table'</span><span class="p">,</span> <span class="s1">'partition'</span><span class="p">,</span> <span class="s1">'ds'</span><span class="p">,</span> <span class="s1">'dttm'</span><span class="p">)</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#aff7a6'</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">partition</span><span class="p">,</span>
+ <span class="n">extra_exprs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">col_blacklist</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
+ <span class="n">assignment_func</span><span class="o">=</span><span class="kc">None</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">presto_conn_id</span><span class="o">=</span><span class="s1">'presto_default'</span><span class="p">,</span>
+ <span class="n">mysql_conn_id</span><span class="o">=</span><span class="s1">'airflow_db'</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">HiveStatsCollectionOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">table</span> <span class="o">=</span> <span class="n">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">extra_exprs</span> <span class="o">=</span> <span class="n">extra_exprs</span> <span class="ow">or</span> <span class="p">{}</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">col_blacklist</span> <span class="o">=</span> <span class="n">col_blacklist</span> <span class="ow">or</span> <span class="p">{}</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="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">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">assignment_func</span> <span class="o">=</span> <span class="n">assignment_func</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">ds</span> <span class="o">=</span> <span class="s1">'{{ ds }}'</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">dttm</span> <span class="o">=</span> <span class="s1">'{{ execution_date.isoformat() }}'</span>
+
+ <span class="k">def</span> <span class="nf">get_default_exprs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">):</span>
+ <span class="k">if</span> <span class="n">col</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">col_blacklist</span><span class="p">:</span>
+ <span class="k">return</span> <span class="p">{}</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="p">{}</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'non_null'</span><span class="p">)]</span> <span class="o">=</span> <span class="s2">"COUNT(</span><span class="si">{col}</span><span class="s2">)"</span>
+ <span class="k">if</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'double'</span><span class="p">,</span> <span class="s1">'int'</span><span class="p">,</span> <span class="s1">'bigint'</span><span class="p">,</span> <span class="s1">'float'</span><span class="p">,</span> <span class="s1">'double'</span><span class="p">]:</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'sum'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(</span><span class="si">{col}</span><span class="s1">)'</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'min'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'MIN(</span><span class="si">{col}</span><span class="s1">)'</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'MAX(</span><span class="si">{col}</span><span class="s1">)'</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'AVG(</span><span class="si">{col}</span><span class="s1">)'</span>
+ <span class="k">elif</span> <span class="n">col_type</span> <span class="o">==</span> <span class="s1">'boolean'</span><span class="p">:</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'true'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CASE WHEN </span><span class="si">{col}</span><span class="s1"> THEN 1 ELSE 0 END)'</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'false'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CASE WHEN NOT </span><span class="si">{col}</span><span class="s1"> THEN 1 ELSE 0 END)'</span>
+ <span class="k">elif</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'string'</span><span class="p">]:</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'len'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CAST(LENGTH(</span><span class="si">{col}</span><span class="s1">) AS BIGINT))'</span>
+ <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'approx_distinct'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'APPROX_DISTINCT(</span><span class="si">{col}</span><span class="s1">)'</span>
+
+ <span class="k">return</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">col</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">items</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="o">=</span><span class="kc">None</span><span class="p">):</span>
+ <span class="n">metastore</span> <span class="o">=</span> <span class="n">HiveMetastoreHook</span><span class="p">(</span><span class="n">metastore_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span><span class="p">)</span>
+ <span class="n">table</span> <span class="o">=</span> <span class="n">metastore</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">table_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span>
+ <span class="n">field_types</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="p">:</span> <span class="n">col</span><span class="o">.</span><span class="n">type</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">table</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">exprs</span> <span class="o">=</span> <span class="p">{</span>
+ <span class="p">(</span><span class="s1">''</span><span class="p">,</span> <span class="s1">'count'</span><span class="p">):</span> <span class="s1">'COUNT(*)'</span>
+ <span class="p">}</span>
+ <span class="k">for</span> <span class="n">col</span><span class="p">,</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="n">field_types</span><span class="o">.</span><span class="n">items</span><span class="p">()):</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="p">{}</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">assignment_func</span><span class="p">:</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">assignment_func</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">d</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_default_exprs</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_default_exprs</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span>
+ <span class="n">exprs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">d</span><span class="p">)</span>
+ <span class="n">exprs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">extra_exprs</span><span class="p">)</span>
+ <span class="n">exprs</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">(</span><span class="n">exprs</span><span class="p">)</span>
+ <span class="n">exprs_str</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="n">v</span> <span class="o">+</span> <span class="s2">" AS "</span> <span class="o">+</span> <span class="n">k</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s1">'__'</span> <span class="o">+</span> <span class="n">k</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
+ <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">exprs</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
+
+ <span class="n">where_clause</span> <span class="o">=</span> <span class="p">[</span>
+ <span class="s2">"</span><span class="si">{0}</span><span class="s2"> = '</span><span class="si">{1}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span>
+ <span class="n">where_clause</span> <span class="o">=</span> <span class="s2">" AND</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="n">where_clause</span><span class="p">)</span>
+ <span class="n">sql</span> <span class="o">=</span> <span class="s2">"""</span>
+<span class="s2"> SELECT</span>
+<span class="s2"> </span><span class="si">{exprs_str}</span><span class="s2"></span>
+<span class="s2"> FROM </span><span class="si">{self.table}</span><span class="s2"></span>
+<span class="s2"> WHERE</span>
+<span class="s2"> </span><span class="si">{where_clause}</span><span class="s2">;</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">hook</span> <span class="o">=</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>
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing SQL check: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">sql</span><span class="p">)</span>
+ <span class="n">row</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="n">hql</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Record: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">row</span><span class="p">)</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">row</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"The query returned None"</span><span class="p">)</span>
+
+ <span class="n">part_json</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Deleting rows from previous runs if they exist"</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="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span><span class="p">)</span>
+ <span class="n">sql</span> <span class="o">=</span> <span class="s2">"""</span>
+<span class="s2"> SELECT 1 FROM hive_stats</span>
+<span class="s2"> WHERE</span>
+<span class="s2"> table_name='</span><span class="si">{self.table}</span><span class="s2">' AND</span>
+<span class="s2"> partition_repr='</span><span class="si">{part_json}</span><span class="s2">' AND</span>
+<span class="s2"> dttm='</span><span class="si">{self.dttm}</span><span class="s2">'</span>
+<span class="s2"> LIMIT 1;</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="k">if</span> <span class="n">mysql</span><span class="o">.</span><span class="n">get_records</span><span class="p">(</span><span class="n">sql</span><span class="p">):</span>
+ <span class="n">sql</span> <span class="o">=</span> <span class="s2">"""</span>
+<span class="s2"> DELETE FROM hive_stats</span>
+<span class="s2"> WHERE</span>
+<span class="s2"> table_name='</span><span class="si">{self.table}</span><span class="s2">' AND</span>
+<span class="s2"> partition_repr='</span><span class="si">{part_json}</span><span class="s2">' AND</span>
+<span class="s2"> dttm='</span><span class="si">{self.dttm}</span><span class="s2">';</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">mysql</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Pivoting and loading cells into the Airflow db"</span><span class="p">)</span>
+ <span class="n">rows</span> <span class="o">=</span> <span class="p">[</span>
+ <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ds</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dttm</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">part_json</span><span class="p">)</span> <span class="o">+</span>
+ <span class="p">(</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
+ <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">exprs</span><span class="p">,</span> <span class="n">row</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="s1">'hive_stats'</span><span class="p">,</span>
+ <span class="n">rows</span><span class="o">=</span><span class="n">rows</span><span class="p">,</span>
+ <span class="n">target_fields</span><span class="o">=</span><span class="p">[</span>
+ <span class="s1">'ds'</span><span class="p">,</span>
+ <span class="s1">'dttm'</span><span class="p">,</span>
+ <span class="s1">'table_name'</span><span class="p">,</span>
+ <span class="s1">'partition_repr'</span><span class="p">,</span>
+ <span class="s1">'col'</span><span class="p">,</span>
+ <span class="s1">'metric'</span><span class="p">,</span>
+ <span class="s1">'value'</span><span class="p">,</span>
+ <span class="p">]</span>
+ <span class="p">)</span></div>
+</pre></div>
+
+ </div>
+
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+
+ </p>
+ </div>
+ Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
+
+</footer>
+
+ </div>
+ </div>
+
+ </section>
+
+ </div>
+
+
+
+
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT:'../../../',
+ VERSION:'',
+ LANGUAGE:'None',
+ COLLAPSE_INDEX:false,
+ FILE_SUFFIX:'.html',
+ HAS_SOURCE: true,
+ SOURCELINK_SUFFIX: '.txt'
+ };
+ </script>
+ <script type="text/javascript" src="../../../_static/jquery.js"></script>
+ <script type="text/javascript" src="../../../_static/underscore.js"></script>
+ <script type="text/javascript" src="../../../_static/doctools.js"></script>
+
+
+
+ <script type="text/javascript" src="../../../_static/js/theme.js"></script>
+
+ <script type="text/javascript">
+ jQuery(function () {
+ SphinxRtdTheme.Navigation.enable(true);
+ });
+ </script>
+
+</body>
+</html>
\ No newline at end of file