Google Git
Sign in
apache / airflow-site / f81e48aadee354653679693fa54b04ac42d24bfd / . / docs-archive / 1.10.5 / _modules / airflow / operators / hive_to_druid.html
blob: 45e0cc5d2723c78c18392eb2bb33c9d6271ef722 [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.operators.hive_to_druid &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>
<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>
<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"><a class="reference internal" href="../../../_api/index.html">Python API Reference</a></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">Module code</a> &raquo;</li>
<li><a href="../operators.html">airflow.operators</a> &raquo;</li>
<li>airflow.operators.hive_to_druid</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for airflow.operators.hive_to_druid</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">from</span> <span class="nn">airflow.hooks.hive_hooks</span> <span class="k">import</span> <span class="n">HiveCliHook</span><span class="p">,</span> <span class="n">HiveMetastoreHook</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.druid_hook</span> <span class="k">import</span> <span class="n">DruidHook</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="LOAD_CHECK_INTERVAL"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.LOAD_CHECK_INTERVAL">[docs]</a><span class="n">LOAD_CHECK_INTERVAL</span> <span class="o">=</span> <span class="mi">5</span></div>
<div class="viewcode-block" id="DEFAULT_TARGET_PARTITION_SIZE"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.DEFAULT_TARGET_PARTITION_SIZE">[docs]</a><span class="n">DEFAULT_TARGET_PARTITION_SIZE</span> <span class="o">=</span> <span class="mi">5000000</span></div>
<div class="viewcode-block" id="HiveToDruidTransfer"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.HiveToDruidTransfer">[docs]</a><span class="k">class</span> <span class="nc">HiveToDruidTransfer</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Moves data from Hive to Druid, [del]note that for now the data is loaded</span>
<span class="sd"> into memory before being pushed to Druid, so this operator should</span>
<span class="sd"> be used for smallish amount of data.[/del]</span>
<span class="sd"> :param sql: SQL query to execute against the Druid database. (templated)</span>
<span class="sd"> :type sql: str</span>
<span class="sd"> :param druid_datasource: the datasource you want to ingest into in druid</span>
<span class="sd"> :type druid_datasource: str</span>
<span class="sd"> :param ts_dim: the timestamp dimension</span>
<span class="sd"> :type ts_dim: str</span>
<span class="sd"> :param metric_spec: the metrics you want to define for your data</span>
<span class="sd"> :type metric_spec: list</span>
<span class="sd"> :param hive_cli_conn_id: the hive connection id</span>
<span class="sd"> :type hive_cli_conn_id: str</span>
<span class="sd"> :param druid_ingest_conn_id: the druid ingest connection id</span>
<span class="sd"> :type druid_ingest_conn_id: str</span>
<span class="sd"> :param metastore_conn_id: the metastore connection id</span>
<span class="sd"> :type metastore_conn_id: str</span>
<span class="sd"> :param hadoop_dependency_coordinates: list of coordinates to squeeze</span>
<span class="sd"> int the ingest json</span>
<span class="sd"> :type hadoop_dependency_coordinates: list[str]</span>
<span class="sd"> :param intervals: list of time intervals that defines segments,</span>
<span class="sd"> this is passed as is to the json object. (templated)</span>
<span class="sd"> :type intervals: list</span>
<span class="sd"> :param hive_tblproperties: additional properties for tblproperties in</span>
<span class="sd"> hive for the staging table</span>
<span class="sd"> :type hive_tblproperties: dict</span>
<span class="sd"> :param job_properties: additional properties for job</span>
<span class="sd"> :type job_properties: dict</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="HiveToDruidTransfer.template_fields"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.HiveToDruidTransfer.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;sql&#39;</span><span class="p">,</span> <span class="s1">&#39;intervals&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="HiveToDruidTransfer.template_ext"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.HiveToDruidTransfer.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;.sql&#39;</span><span class="p">,)</span></div>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">sql</span><span class="p">,</span>
<span class="n">druid_datasource</span><span class="p">,</span>
<span class="n">ts_dim</span><span class="p">,</span>
<span class="n">metric_spec</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">hive_cli_conn_id</span><span class="o">=</span><span class="s1">&#39;hive_cli_default&#39;</span><span class="p">,</span>
<span class="n">druid_ingest_conn_id</span><span class="o">=</span><span class="s1">&#39;druid_ingest_default&#39;</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="n">hadoop_dependency_coordinates</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">intervals</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">num_shards</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span>
<span class="n">target_partition_size</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span>
<span class="n">query_granularity</span><span class="o">=</span><span class="s2">&quot;NONE&quot;</span><span class="p">,</span>
<span class="n">segment_granularity</span><span class="o">=</span><span class="s2">&quot;DAY&quot;</span><span class="p">,</span>
<span class="n">hive_tblproperties</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">job_properties</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">HiveToDruidTransfer</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">sql</span> <span class="o">=</span> <span class="n">sql</span>
<span class="bp">self</span><span class="o">.</span><span class="n">druid_datasource</span> <span class="o">=</span> <span class="n">druid_datasource</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ts_dim</span> <span class="o">=</span> <span class="n">ts_dim</span>
<span class="bp">self</span><span class="o">.</span><span class="n">intervals</span> <span class="o">=</span> <span class="n">intervals</span> <span class="ow">or</span> <span class="p">[</span><span class="s1">&#39;{{ ds }}/{{ tomorrow_ds }}&#39;</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">num_shards</span> <span class="o">=</span> <span class="n">num_shards</span>
<span class="bp">self</span><span class="o">.</span><span class="n">target_partition_size</span> <span class="o">=</span> <span class="n">target_partition_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">query_granularity</span> <span class="o">=</span> <span class="n">query_granularity</span>
<span class="bp">self</span><span class="o">.</span><span class="n">segment_granularity</span> <span class="o">=</span> <span class="n">segment_granularity</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metric_spec</span> <span class="o">=</span> <span class="n">metric_spec</span> <span class="ow">or</span> <span class="p">[{</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="s2">&quot;count&quot;</span><span class="p">,</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;count&quot;</span><span class="p">}]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_cli_conn_id</span> <span class="o">=</span> <span class="n">hive_cli_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hadoop_dependency_coordinates</span> <span class="o">=</span> <span class="n">hadoop_dependency_coordinates</span>
<span class="bp">self</span><span class="o">.</span><span class="n">druid_ingest_conn_id</span> <span class="o">=</span> <span class="n">druid_ingest_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span> <span class="o">=</span> <span class="n">metastore_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hive_tblproperties</span> <span class="o">=</span> <span class="n">hive_tblproperties</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">job_properties</span> <span class="o">=</span> <span class="n">job_properties</span>
<div class="viewcode-block" id="HiveToDruidTransfer.execute"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.HiveToDruidTransfer.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
<span class="n">hive</span> <span class="o">=</span> <span class="n">HiveCliHook</span><span class="p">(</span><span class="n">hive_cli_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">hive_cli_conn_id</span><span class="p">)</span>
<span class="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">&quot;Extracting data from Hive&quot;</span><span class="p">)</span>
<span class="n">hive_table</span> <span class="o">=</span> <span class="s1">&#39;druid.&#39;</span> <span class="o">+</span> <span class="n">context</span><span class="p">[</span><span class="s1">&#39;task_instance_key_str&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">,</span> <span class="s1">&#39;_&#39;</span><span class="p">)</span>
<span class="n">sql</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s1">&#39;;&#39;</span><span class="p">)</span>
<span class="n">tblproperties</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s2">&quot;, &#39;</span><span class="si">{}</span><span class="s2">&#39; = &#39;</span><span class="si">{}</span><span class="s2">&#39;&quot;</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">hive_tblproperties</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
<span class="n">hql</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span><span class="se">\</span>
<span class="s2"> SET mapred.output.compress=false;</span>
<span class="s2"> SET hive.exec.compress.output=false;</span>
<span class="s2"> DROP TABLE IF EXISTS </span><span class="si">{hive_table}</span><span class="s2">;</span>
<span class="s2"> CREATE TABLE </span><span class="si">{hive_table}</span><span class="s2"></span>
<span class="s2"> ROW FORMAT DELIMITED FIELDS TERMINATED BY &#39;</span><span class="se">\t</span><span class="s2">&#39;</span>
<span class="s2"> STORED AS TEXTFILE</span>
<span class="s2"> TBLPROPERTIES (&#39;serialization.null.format&#39; = &#39;&#39;</span><span class="si">{tblproperties}</span><span class="s2">)</span>
<span class="s2"> AS</span>
<span class="s2"> </span><span class="si">{sql}</span><span class="s2"></span>
<span class="s2"> &quot;&quot;&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hive_table</span><span class="o">=</span><span class="n">hive_table</span><span class="p">,</span> <span class="n">tblproperties</span><span class="o">=</span><span class="n">tblproperties</span><span class="p">,</span> <span class="n">sql</span><span class="o">=</span><span class="n">sql</span><span class="p">)</span>
<span class="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">&quot;Running command:</span><span class="se">\n</span><span class="s2"> </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">hql</span><span class="p">)</span>
<span class="n">hive</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">HiveMetastoreHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span><span class="p">)</span>
<span class="c1"># Get the Hive table and extract the columns</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span>
<span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">col</span><span class="o">.</span><span class="n">name</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">t</span><span class="o">.</span><span class="n">sd</span><span class="o">.</span><span class="n">cols</span><span class="p">]</span>
<span class="c1"># Get the path on hdfs</span>
<span class="n">hdfs_uri</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span><span class="o">.</span><span class="n">sd</span><span class="o">.</span><span class="n">location</span>
<span class="n">pos</span> <span class="o">=</span> <span class="n">hdfs_uri</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">&#39;/user&#39;</span><span class="p">)</span>
<span class="n">static_path</span> <span class="o">=</span> <span class="n">hdfs_uri</span><span class="p">[</span><span class="n">pos</span><span class="p">:]</span>
<span class="n">schema</span><span class="p">,</span> <span class="n">table</span> <span class="o">=</span> <span class="n">hive_table</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">)</span>
<span class="n">druid</span> <span class="o">=</span> <span class="n">DruidHook</span><span class="p">(</span><span class="n">druid_ingest_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">druid_ingest_conn_id</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">index_spec</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">construct_ingest_query</span><span class="p">(</span>
<span class="n">static_path</span><span class="o">=</span><span class="n">static_path</span><span class="p">,</span>
<span class="n">columns</span><span class="o">=</span><span class="n">columns</span><span class="p">,</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">&quot;Inserting rows into Druid, hdfs path: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">static_path</span><span class="p">)</span>
<span class="n">druid</span><span class="o">.</span><span class="n">submit_indexing_job</span><span class="p">(</span><span class="n">index_spec</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">&quot;Load seems to have succeeded!&quot;</span><span class="p">)</span>
<span class="k">finally</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">&quot;Cleaning up by dropping the temp Hive table </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
<span class="n">hive_table</span>
<span class="p">)</span>
<span class="n">hql</span> <span class="o">=</span> <span class="s2">&quot;DROP TABLE IF EXISTS </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">hive_table</span><span class="p">)</span>
<span class="n">hive</span><span class="o">.</span><span class="n">run_cli</span><span class="p">(</span><span class="n">hql</span><span class="p">)</span></div>
<div class="viewcode-block" id="HiveToDruidTransfer.construct_ingest_query"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_to_druid/index.html#airflow.operators.hive_to_druid.HiveToDruidTransfer.construct_ingest_query">[docs]</a> <span class="k">def</span> <span class="nf">construct_ingest_query</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">static_path</span><span class="p">,</span> <span class="n">columns</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Builds an ingest query for an HDFS TSV load.</span>
<span class="sd"> :param static_path: The path on hdfs where the data is</span>
<span class="sd"> :type static_path: str</span>
<span class="sd"> :param columns: List of all the columns that are available</span>
<span class="sd"> :type columns: list</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># backward compatibility for num_shards,</span>
<span class="c1"># but target_partition_size is the default setting</span>
<span class="c1"># and overwrites the num_shards</span>
<span class="n">num_shards</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_shards</span>
<span class="n">target_partition_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_partition_size</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">target_partition_size</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_shards</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span>
<span class="n">target_partition_size</span> <span class="o">=</span> <span class="n">DEFAULT_TARGET_PARTITION_SIZE</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">num_shards</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
<span class="n">metric_names</span> <span class="o">=</span> <span class="p">[</span><span class="n">m</span><span class="p">[</span><span class="s1">&#39;fieldName&#39;</span><span class="p">]</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">metric_spec</span> <span class="k">if</span> <span class="n">m</span><span class="p">[</span><span class="s1">&#39;type&#39;</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">&#39;count&#39;</span><span class="p">]</span>
<span class="c1"># Take all the columns, which are not the time dimension</span>
<span class="c1"># or a metric, as the dimension columns</span>
<span class="n">dimensions</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">columns</span> <span class="k">if</span> <span class="n">c</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">metric_names</span> <span class="ow">and</span> <span class="n">c</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ts_dim</span><span class="p">]</span>
<span class="n">ingest_query_dict</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;index_hadoop&quot;</span><span class="p">,</span>
<span class="s2">&quot;spec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;dataSchema&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;metricsSpec&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">metric_spec</span><span class="p">,</span>
<span class="s2">&quot;granularitySpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;queryGranularity&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_granularity</span><span class="p">,</span>
<span class="s2">&quot;intervals&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">intervals</span><span class="p">,</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;uniform&quot;</span><span class="p">,</span>
<span class="s2">&quot;segmentGranularity&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">segment_granularity</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;parser&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;parseSpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;columns&quot;</span><span class="p">:</span> <span class="n">columns</span><span class="p">,</span>
<span class="s2">&quot;dimensionsSpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;dimensionExclusions&quot;</span><span class="p">:</span> <span class="p">[],</span>
<span class="s2">&quot;dimensions&quot;</span><span class="p">:</span> <span class="n">dimensions</span><span class="p">,</span> <span class="c1"># list of names</span>
<span class="s2">&quot;spatialDimensions&quot;</span><span class="p">:</span> <span class="p">[]</span>
<span class="p">},</span>
<span class="s2">&quot;timestampSpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;column&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">ts_dim</span><span class="p">,</span>
<span class="s2">&quot;format&quot;</span><span class="p">:</span> <span class="s2">&quot;auto&quot;</span>
<span class="p">},</span>
<span class="s2">&quot;format&quot;</span><span class="p">:</span> <span class="s2">&quot;tsv&quot;</span>
<span class="p">}</span>
<span class="p">},</span>
<span class="s2">&quot;dataSource&quot;</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">druid_datasource</span>
<span class="p">},</span>
<span class="s2">&quot;tuningConfig&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;hadoop&quot;</span><span class="p">,</span>
<span class="s2">&quot;jobProperties&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;mapreduce.job.user.classpath.first&quot;</span><span class="p">:</span> <span class="s2">&quot;false&quot;</span><span class="p">,</span>
<span class="s2">&quot;mapreduce.map.output.compress&quot;</span><span class="p">:</span> <span class="s2">&quot;false&quot;</span><span class="p">,</span>
<span class="s2">&quot;mapreduce.output.fileoutputformat.compress&quot;</span><span class="p">:</span> <span class="s2">&quot;false&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;partitionsSpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;hashed&quot;</span><span class="p">,</span>
<span class="s2">&quot;targetPartitionSize&quot;</span><span class="p">:</span> <span class="n">target_partition_size</span><span class="p">,</span>
<span class="s2">&quot;numShards&quot;</span><span class="p">:</span> <span class="n">num_shards</span><span class="p">,</span>
<span class="p">},</span>
<span class="p">},</span>
<span class="s2">&quot;ioConfig&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;inputSpec&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;paths&quot;</span><span class="p">:</span> <span class="n">static_path</span><span class="p">,</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;static&quot;</span>
<span class="p">},</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;hadoop&quot;</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">job_properties</span><span class="p">:</span>
<span class="n">ingest_query_dict</span><span class="p">[</span><span class="s1">&#39;spec&#39;</span><span class="p">][</span><span class="s1">&#39;tuningConfig&#39;</span><span class="p">][</span><span class="s1">&#39;jobProperties&#39;</span><span class="p">]</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">job_properties</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">hadoop_dependency_coordinates</span><span class="p">:</span>
<span class="n">ingest_query_dict</span><span class="p">[</span><span class="s1">&#39;hadoopDependencyCoordinates&#39;</span><span class="p">]</span> \
<span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hadoop_dependency_coordinates</span>
<span class="k">return</span> <span class="n">ingest_query_dict</span></div></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>.
<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>