blob: 2c0c2a40d379e9e02c6563471c371ebf13dd4a44 [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.contrib.hooks.aws_glue_catalog_hook &mdash; Airflow Documentation</title>
<script type="text/javascript" src="../../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../../" src="../../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../../_static/language_data.js"></script>
<script type="text/javascript" src="../../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../../search.html" />
<link rel="next" title="airflow.contrib.hooks.aws_hook" href="../aws_hook/index.html" />
<link rel="prev" title="airflow.contrib.hooks.aws_firehose_hook" href="../aws_firehose_hook/index.html" />
<script>
document.addEventListener('DOMContentLoaded', function() {
var el = document.getElementById('changelog');
if (el !== null ) {
// [AIRFLOW-...]
el.innerHTML = el.innerHTML.replace(
/\[(AIRFLOW-[\d]+)\]/g,
`<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>`
);
// (#...)
el.innerHTML = el.innerHTML.replace(
/\(#([\d]+)\)/g,
`<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>`
);
};
})
</script>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-140539454-1']);
_gaq.push(['_trackPageview']);
</script>
<style>
.example-header {
position: relative;
background: #9AAA7A;
padding: 8px 16px;
margin-bottom: 0;
}
.example-header--with-button {
padding-right: 166px;
}
.example-header:after{
content: '';
display: table;
clear: both;
}
.example-title {
display:block;
padding: 4px;
margin-right: 16px;
color: white;
overflow-x: auto;
}
.example-header-button {
top: 8px;
right: 16px;
position: absolute;
}
.example-header + .highlight-python {
margin-top: 0 !important;
}
.viewcode-button {
display: inline-block;
padding: 8px 16px;
border: 0;
margin: 0;
outline: 0;
border-radius: 2px;
-webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3);
box-shadow: 0 3px 6px 0 rgba(0,0,0,.3);
color: #404040;
background-color: #e7e7e7;
cursor: pointer;
font-size: 16px;
font-weight: 500;
line-height: 1;
text-decoration: none;
text-overflow: ellipsis;
overflow: hidden;
text-transform: uppercase;
-webkit-transition: background-color .2s;
transition: background-color .2s;
vertical-align: middle;
white-space: nowrap;
}
.viewcode-button:visited {
color: #404040;
}
.viewcode-button:hover, .viewcode-button:focus {
color: #404040;
background-color: #d6d6d6;
}
</style>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.5
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul class="current">
<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 Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../api.html">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../../../index.html">Python API Reference</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../../../index.html#operators">Operators</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="../../../../index.html#hooks">Hooks</a><ul class="current">
<li class="toctree-l3 current"><a class="reference internal" href="../../../../index.html#hooks-packages">Hooks packages</a><ul class="current">
<li class="toctree-l4"><a class="reference internal" href="../../../hooks/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks</span></code></a></li>
<li class="toctree-l4 current"><a class="reference internal" href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks</span></code></a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../index.html#executors">Executors</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../index.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../index.html#core-and-community-package">Core and community package</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../../index.html">Python API Reference</a> &raquo;</li>
<li><a href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks</span></code></a> &raquo;</li>
<li><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks.aws_glue_catalog_hook</span></code></li>
<li class="wy-breadcrumbs-aside">
<a href="../../../../../_sources/_api/airflow/contrib/hooks/aws_glue_catalog_hook/index.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="module-airflow.contrib.hooks.aws_glue_catalog_hook">
<span id="airflow-contrib-hooks-aws-glue-catalog-hook"></span><h1><a class="reference internal" href="#module-airflow.contrib.hooks.aws_glue_catalog_hook" title="airflow.contrib.hooks.aws_glue_catalog_hook"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks.aws_glue_catalog_hook</span></code></a><a class="headerlink" href="#module-airflow.contrib.hooks.aws_glue_catalog_hook" title="Permalink to this headline"></a></h1>
<div class="section" id="module-contents">
<h2>Module Contents<a class="headerlink" href="#module-contents" title="Permalink to this headline"></a></h2>
<dl class="class">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook">
<em class="property">class </em><code class="sig-prename descclassname">airflow.contrib.hooks.aws_glue_catalog_hook.</code><code class="sig-name descname">AwsGlueCatalogHook</code><span class="sig-paren">(</span><em class="sig-param">aws_conn_id='aws_default'</em>, <em class="sig-param">region_name=None</em>, <em class="sig-param">*args</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="../aws_hook/index.html#airflow.contrib.hooks.aws_hook.AwsHook" title="airflow.contrib.hooks.aws_hook.AwsHook"><code class="xref py py-class docutils literal notranslate"><span class="pre">airflow.contrib.hooks.aws_hook.AwsHook</span></code></a></p>
<p>Interact with AWS Glue Catalog</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>aws_conn_id</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – ID of the Airflow connection where
credentials and extra configuration are stored</p></li>
<li><p><strong>region_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – aws region name (example: us-east-1)</p></li>
</ul>
</dd>
</dl>
<dl class="method">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_conn">
<code class="sig-name descname">get_conn</code><span class="sig-paren">(</span><em class="sig-param">self</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook.get_conn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_conn" title="Permalink to this definition"></a></dt>
<dd><p>Returns glue connection object.</p>
</dd></dl>
<dl class="method">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_partitions">
<code class="sig-name descname">get_partitions</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">database_name</em>, <em class="sig-param">table_name</em>, <em class="sig-param">expression=''</em>, <em class="sig-param">page_size=None</em>, <em class="sig-param">max_items=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook.get_partitions"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_partitions" title="Permalink to this definition"></a></dt>
<dd><p>Retrieves the partition values for a table.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>database_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – The name of the catalog database where the partitions reside.</p></li>
<li><p><strong>table_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – The name of the partitions’ table.</p></li>
<li><p><strong>expression</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – An expression filtering the partitions to be returned.
Please see official AWS documentation for further information.
<a class="reference external" href="https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-catalog-partitions.html#aws-glue-api-catalog-partitions-GetPartitions">https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-catalog-partitions.html#aws-glue-api-catalog-partitions-GetPartitions</a></p></li>
<li><p><strong>page_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.7)"><em>int</em></a>) – pagination size</p></li>
<li><p><strong>max_items</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.7)"><em>int</em></a>) – maximum items to return</p></li>
</ul>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><p>set of partition values where each value is a tuple since
a partition may be composed of multiple columns. For example:
<code class="docutils literal notranslate"><span class="pre">{('2018-01-01','1'),</span> <span class="pre">('2018-01-01','2')}</span></code></p>
</dd>
</dl>
</dd></dl>
<dl class="method">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.check_for_partition">
<code class="sig-name descname">check_for_partition</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">database_name</em>, <em class="sig-param">table_name</em>, <em class="sig-param">expression</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook.check_for_partition"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.check_for_partition" title="Permalink to this definition"></a></dt>
<dd><p>Checks whether a partition exists</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>database_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive database (schema) &#64;table belongs to</p></li>
<li><p><strong>table_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive table &#64;partition belongs to</p></li>
</ul>
</dd>
<dt class="field-even">Expression</dt>
<dd class="field-even"><p>Expression that matches the partitions to check for
(eg <cite>a = ‘b’ AND c = ‘d’</cite>)</p>
</dd>
<dt class="field-odd">Return type</dt>
<dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.7)">bool</a></p>
</dd>
</dl>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">hook</span> <span class="o">=</span> <span class="n">AwsGlueCatalogHook</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">t</span> <span class="o">=</span> <span class="s1">&#39;static_babynames_partitioned&#39;</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">hook</span><span class="o">.</span><span class="n">check_for_partition</span><span class="p">(</span><span class="s1">&#39;airflow&#39;</span><span class="p">,</span> <span class="n">t</span><span class="p">,</span> <span class="s2">&quot;ds=&#39;2015-01-01&#39;&quot;</span><span class="p">)</span>
<span class="go">True</span>
</pre></div>
</div>
</dd></dl>
<dl class="method">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_table">
<code class="sig-name descname">get_table</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">database_name</em>, <em class="sig-param">table_name</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook.get_table"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_table" title="Permalink to this definition"></a></dt>
<dd><p>Get the information of the table</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>database_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive database (schema) &#64;table belongs to</p></li>
<li><p><strong>table_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive table</p></li>
</ul>
</dd>
<dt class="field-even">Return type</dt>
<dd class="field-even"><p><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.7)">dict</a></p>
</dd>
</dl>
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">hook</span> <span class="o">=</span> <span class="n">AwsGlueCatalogHook</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">r</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="s1">&#39;db&#39;</span><span class="p">,</span> <span class="s1">&#39;table_foo&#39;</span><span class="p">)</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">r</span><span class="p">[</span><span class="s1">&#39;Name&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;table_foo&#39;</span>
</pre></div>
</div>
</dd></dl>
<dl class="method">
<dt id="airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_table_location">
<code class="sig-name descname">get_table_location</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">database_name</em>, <em class="sig-param">table_name</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/hooks/aws_glue_catalog_hook.html#AwsGlueCatalogHook.get_table_location"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.hooks.aws_glue_catalog_hook.AwsGlueCatalogHook.get_table_location" title="Permalink to this definition"></a></dt>
<dd><p>Get the physical location of the table</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>database_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive database (schema) &#64;table belongs to</p></li>
<li><p><strong>table_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.7)"><em>str</em></a>) – Name of hive table</p></li>
</ul>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><p>str</p>
</dd>
</dl>
</dd></dl>
</dd></dl>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../aws_hook/index.html" class="btn btn-neutral float-right" title="airflow.contrib.hooks.aws_hook" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="../aws_firehose_hook/index.html" class="btn btn-neutral float-left" title="airflow.contrib.hooks.aws_firehose_hook" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<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>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../../../privacy_notice.html">Privacy Policy</a>
for more details.
<script type="text/javascript">
(function() {
var ga = document.createElement('script');
ga.src = ('https:' == document.location.protocol ?
'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
ga.setAttribute('async', 'true');
var nodes = document.documentElement.childNodes;
var i = -1;
var node;
do {
i++;
node = nodes[i]
} while(node.nodeType !== Node.ELEMENT_NODE);
node.appendChild(ga);
})();
</script>
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>