blob: f85985712f957ec9c1ca00135fcd4ed470ed6749 [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.macros.hive &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" />
<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>
<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">
1.10.3
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../api.html">Experimental Rest API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../_api/index.html">API Reference</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li><a href="../macros.html">airflow.macros</a> &raquo;</li>
<li>airflow.macros.hive</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for airflow.macros.hive</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># &quot;License&quot;); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="kn">import</span> <span class="nn">datetime</span>
<div class="viewcode-block" id="max_partition"><a class="viewcode-back" href="../../../macros.html#airflow.macros.hive.max_partition">[docs]</a><span class="k">def</span> <span class="nf">max_partition</span><span class="p">(</span>
<span class="n">table</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="s2">&quot;default&quot;</span><span class="p">,</span> <span class="n">field</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">filter_map</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">&#39;metastore_default&#39;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the max partition for a table.</span>
<span class="sd"> :param schema: The hive schema the table lives in</span>
<span class="sd"> :type schema: str</span>
<span class="sd"> :param table: The hive table you are interested in, supports the dot</span>
<span class="sd"> notation as in &quot;my_database.my_table&quot;, if a dot is found,</span>
<span class="sd"> the schema param is disregarded</span>
<span class="sd"> :type table: str</span>
<span class="sd"> :param metastore_conn_id: The hive connection you are interested in.</span>
<span class="sd"> If your default is set you don&#39;t need to use this parameter.</span>
<span class="sd"> :type metastore_conn_id: str</span>
<span class="sd"> :param filter_map: partition_key:partition_value map used for partition filtering,</span>
<span class="sd"> e.g. {&#39;key1&#39;: &#39;value1&#39;, &#39;key2&#39;: &#39;value2&#39;}.</span>
<span class="sd"> Only partitions matching all partition_key:partition_value</span>
<span class="sd"> pairs will be considered as candidates of max partition.</span>
<span class="sd"> :type filter_map: map</span>
<span class="sd"> :param field: the field to get the max value from. If there&#39;s only</span>
<span class="sd"> one partition field, this will be inferred</span>
<span class="sd"> :type field: str</span>
<span class="sd"> &gt;&gt;&gt; max_partition(&#39;airflow.static_babynames_partitioned&#39;)</span>
<span class="sd"> &#39;2015-01-01&#39;</span>
<span class="sd"> &quot;&quot;&quot;</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="k">if</span> <span class="s1">&#39;.&#39;</span> <span class="ow">in</span> <span class="n">table</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">table</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">)</span>
<span class="n">hh</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="n">metastore_conn_id</span><span class="p">)</span>
<span class="k">return</span> <span class="n">hh</span><span class="o">.</span><span class="n">max_partition</span><span class="p">(</span>
<span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="o">=</span><span class="n">table</span><span class="p">,</span> <span class="n">field</span><span class="o">=</span><span class="n">field</span><span class="p">,</span> <span class="n">filter_map</span><span class="o">=</span><span class="n">filter_map</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_closest_date</span><span class="p">(</span><span class="n">target_dt</span><span class="p">,</span> <span class="n">date_list</span><span class="p">,</span> <span class="n">before_target</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> This function finds the date in a list closest to the target date.</span>
<span class="sd"> An optional parameter can be given to get the closest before or after.</span>
<span class="sd"> :param target_dt: The target date</span>
<span class="sd"> :type target_dt: datetime.date</span>
<span class="sd"> :param date_list: The list of dates to search</span>
<span class="sd"> :type date_list: list[datetime.date]</span>
<span class="sd"> :param before_target: closest before or after the target</span>
<span class="sd"> :type before_target: bool or None</span>
<span class="sd"> :returns: The closest date</span>
<span class="sd"> :rtype: datetime.date or None</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">fb</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">d</span><span class="p">:</span> <span class="n">target_dt</span> <span class="o">-</span> <span class="n">d</span> <span class="k">if</span> <span class="n">d</span> <span class="o">&lt;=</span> <span class="n">target_dt</span> <span class="k">else</span> <span class="n">datetime</span><span class="o">.</span><span class="n">timedelta</span><span class="o">.</span><span class="n">max</span>
<span class="n">fa</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">d</span><span class="p">:</span> <span class="n">d</span> <span class="o">-</span> <span class="n">target_dt</span> <span class="k">if</span> <span class="n">d</span> <span class="o">&gt;=</span> <span class="n">target_dt</span> <span class="k">else</span> <span class="n">datetime</span><span class="o">.</span><span class="n">timedelta</span><span class="o">.</span><span class="n">max</span>
<span class="n">fnone</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">d</span><span class="p">:</span> <span class="n">target_dt</span> <span class="o">-</span> <span class="n">d</span> <span class="k">if</span> <span class="n">d</span> <span class="o">&lt;</span> <span class="n">target_dt</span> <span class="k">else</span> <span class="n">d</span> <span class="o">-</span> <span class="n">target_dt</span>
<span class="k">if</span> <span class="n">before_target</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">min</span><span class="p">(</span><span class="n">date_list</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="n">fnone</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">()</span>
<span class="k">if</span> <span class="n">before_target</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">min</span><span class="p">(</span><span class="n">date_list</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="n">fb</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">min</span><span class="p">(</span><span class="n">date_list</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="n">fa</span><span class="p">)</span><span class="o">.</span><span class="n">date</span><span class="p">()</span>
<div class="viewcode-block" id="closest_ds_partition"><a class="viewcode-back" href="../../../macros.html#airflow.macros.hive.closest_ds_partition">[docs]</a><span class="k">def</span> <span class="nf">closest_ds_partition</span><span class="p">(</span>
<span class="n">table</span><span class="p">,</span> <span class="n">ds</span><span class="p">,</span> <span class="n">before</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="s2">&quot;default&quot;</span><span class="p">,</span>
<span class="n">metastore_conn_id</span><span class="o">=</span><span class="s1">&#39;metastore_default&#39;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> This function finds the date in a list closest to the target date.</span>
<span class="sd"> An optional parameter can be given to get the closest before or after.</span>
<span class="sd"> :param table: A hive table name</span>
<span class="sd"> :type table: str</span>
<span class="sd"> :param ds: A datestamp ``%Y-%m-%d`` e.g. ``yyyy-mm-dd``</span>
<span class="sd"> :type ds: list[datetime.date]</span>
<span class="sd"> :param before: closest before (True), after (False) or either side of ds</span>
<span class="sd"> :type before: bool or None</span>
<span class="sd"> :returns: The closest date</span>
<span class="sd"> :rtype: str or None</span>
<span class="sd"> &gt;&gt;&gt; tbl = &#39;airflow.static_babynames_partitioned&#39;</span>
<span class="sd"> &gt;&gt;&gt; closest_ds_partition(tbl, &#39;2015-01-02&#39;)</span>
<span class="sd"> &#39;2015-01-01&#39;</span>
<span class="sd"> &quot;&quot;&quot;</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="k">if</span> <span class="s1">&#39;.&#39;</span> <span class="ow">in</span> <span class="n">table</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">table</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">)</span>
<span class="n">hh</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="n">metastore_conn_id</span><span class="p">)</span>
<span class="n">partitions</span> <span class="o">=</span> <span class="n">hh</span><span class="o">.</span><span class="n">get_partitions</span><span class="p">(</span><span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> <span class="n">table_name</span><span class="o">=</span><span class="n">table</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">partitions</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="n">part_vals</span> <span class="o">=</span> <span class="p">[</span><span class="nb">list</span><span class="p">(</span><span class="n">p</span><span class="o">.</span><span class="n">values</span><span class="p">())[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">partitions</span><span class="p">]</span>
<span class="k">if</span> <span class="n">ds</span> <span class="ow">in</span> <span class="n">part_vals</span><span class="p">:</span>
<span class="k">return</span> <span class="n">ds</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">parts</span> <span class="o">=</span> <span class="p">[</span><span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">pv</span><span class="p">,</span> <span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">pv</span> <span class="ow">in</span> <span class="n">part_vals</span><span class="p">]</span>
<span class="n">target_dt</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">ds</span><span class="p">,</span> <span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="n">closest_ds</span> <span class="o">=</span> <span class="n">_closest_date</span><span class="p">(</span><span class="n">target_dt</span><span class="p">,</span> <span class="n">parts</span><span class="p">,</span> <span class="n">before_target</span><span class="o">=</span><span class="n">before</span><span class="p">)</span>
<span class="k">return</span> <span class="n">closest_ds</span><span class="o">.</span><span class="n">isoformat</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">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>