blob: fa76bd8919cc782f7fc2a9be329da97f0e228673 [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.sensors.hdfs_sensor &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">
1.10.4
</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="../sensors.html">airflow.sensors</a> &raquo;</li>
<li>airflow.sensors.hdfs_sensor</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.sensors.hdfs_sensor</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">re</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">str</span>
<span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">settings</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.hdfs_hook</span> <span class="k">import</span> <span class="n">HDFSHook</span>
<span class="kn">from</span> <span class="nn">airflow.sensors.base_sensor_operator</span> <span class="k">import</span> <span class="n">BaseSensorOperator</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.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span>
<div class="viewcode-block" id="HdfsSensor"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor">[docs]</a><span class="k">class</span> <span class="nc">HdfsSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Waits for a file or folder to land in HDFS</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="HdfsSensor.template_fields"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;filepath&#39;</span><span class="p">,)</span></div>
<div class="viewcode-block" id="HdfsSensor.ui_color"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="n">settings</span><span class="o">.</span><span class="n">WEB_COLORS</span><span class="p">[</span><span class="s1">&#39;LIGHTBLUE&#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">filepath</span><span class="p">,</span>
<span class="n">hdfs_conn_id</span><span class="o">=</span><span class="s1">&#39;hdfs_default&#39;</span><span class="p">,</span>
<span class="n">ignored_ext</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">ignore_copying</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">file_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">hook</span><span class="o">=</span><span class="n">HDFSHook</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">HdfsSensor</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="k">if</span> <span class="n">ignored_ext</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">ignored_ext</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;_COPYING_&#39;</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">filepath</span> <span class="o">=</span> <span class="n">filepath</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hdfs_conn_id</span> <span class="o">=</span> <span class="n">hdfs_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_size</span> <span class="o">=</span> <span class="n">file_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ignored_ext</span> <span class="o">=</span> <span class="n">ignored_ext</span>
<span class="bp">self</span><span class="o">.</span><span class="n">ignore_copying</span> <span class="o">=</span> <span class="n">ignore_copying</span>
<span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">hook</span>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="HdfsSensor.filter_for_filesize"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor.filter_for_filesize">[docs]</a> <span class="k">def</span> <span class="nf">filter_for_filesize</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Will test the filepath result and test if its size is at least self.filesize</span>
<span class="sd"> :param result: a list of dicts returned by Snakebite ls</span>
<span class="sd"> :param size: the file size in MB a file should be at least to trigger True</span>
<span class="sd"> :return: (bool) depending on the matching criteria</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">size</span><span class="p">:</span>
<span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span>
<span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span>
<span class="s1">&#39;Filtering for file size &gt;= </span><span class="si">%s</span><span class="s1"> in files: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">size</span><span class="p">,</span> <span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><span class="s1">&#39;path&#39;</span><span class="p">],</span> <span class="n">result</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">size</span> <span class="o">*=</span> <span class="n">settings</span><span class="o">.</span><span class="n">MEGABYTE</span>
<span class="n">result</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">result</span> <span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="s1">&#39;length&#39;</span><span class="p">]</span> <span class="o">&gt;=</span> <span class="n">size</span><span class="p">]</span>
<span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;HdfsSensor.poke: after size filter result is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">result</span><span class="p">)</span>
<span class="k">return</span> <span class="n">result</span></div>
<span class="nd">@staticmethod</span>
<div class="viewcode-block" id="HdfsSensor.filter_for_ignored_ext"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor.filter_for_ignored_ext">[docs]</a> <span class="k">def</span> <span class="nf">filter_for_ignored_ext</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">ignored_ext</span><span class="p">,</span> <span class="n">ignore_copying</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Will filter if instructed to do so the result to remove matching criteria</span>
<span class="sd"> :param result: list of dicts returned by Snakebite ls</span>
<span class="sd"> :type result: list[dict]</span>
<span class="sd"> :param ignored_ext: list of ignored extensions</span>
<span class="sd"> :type ignored_ext: list</span>
<span class="sd"> :param ignore_copying: shall we ignore ?</span>
<span class="sd"> :type ignore_copying: bool</span>
<span class="sd"> :return: list of dicts which were not removed</span>
<span class="sd"> :rtype: list[dict]</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">ignore_copying</span><span class="p">:</span>
<span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span>
<span class="n">regex_builder</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">&quot;^.*\.(</span><span class="si">%s</span><span class="s2">$)$&quot;</span> <span class="o">%</span> <span class="s1">&#39;$|&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">ignored_ext</span><span class="p">)</span>
<span class="n">ignored_extensions_regex</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">regex_builder</span><span class="p">)</span>
<span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span>
<span class="s1">&#39;Filtering result for ignored extensions: </span><span class="si">%s</span><span class="s1"> in files </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="n">ignored_extensions_regex</span><span class="o">.</span><span class="n">pattern</span><span class="p">,</span> <span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><span class="s1">&#39;path&#39;</span><span class="p">],</span> <span class="n">result</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">result</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">ignored_extensions_regex</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">x</span><span class="p">[</span><span class="s1">&#39;path&#39;</span><span class="p">])]</span>
<span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;HdfsSensor.poke: after ext filter result is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">result</span><span class="p">)</span>
<span class="k">return</span> <span class="n">result</span></div>
<div class="viewcode-block" id="HdfsSensor.poke"><a class="viewcode-back" href="../../../_api/airflow/sensors/hdfs_sensor/index.html#airflow.sensors.hdfs_sensor.HdfsSensor.poke">[docs]</a> <span class="k">def</span> <span class="nf">poke</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">sb</span> <span class="o">=</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">hdfs_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">get_conn</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">&#39;Poking for file </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">filepath</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># IMOO it&#39;s not right here, as there no raise of any kind.</span>
<span class="c1"># if the filepath is let&#39;s say &#39;/data/mydirectory&#39;,</span>
<span class="c1"># it&#39;s correct but if it is &#39;/data/mydirectory/*&#39;,</span>
<span class="c1"># it&#39;s not correct as the directory exists and sb does not raise any error</span>
<span class="c1"># here is a quick fix</span>
<span class="n">result</span> <span class="o">=</span> <span class="p">[</span><span class="n">f</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">sb</span><span class="o">.</span><span class="n">ls</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">filepath</span><span class="p">],</span> <span class="n">include_toplevel</span><span class="o">=</span><span class="kc">False</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">debug</span><span class="p">(</span><span class="s1">&#39;HdfsSensor.poke: result is </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">result</span><span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">filter_for_ignored_ext</span><span class="p">(</span>
<span class="n">result</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">ignored_ext</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">ignore_copying</span>
<span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">filter_for_filesize</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_size</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">bool</span><span class="p">(</span><span class="n">result</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span>
<span class="n">e</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">exc_info</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">debug</span><span class="p">(</span><span class="s2">&quot;Caught an exception !: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">))</span>
<span class="k">return</span> <span class="kc">False</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>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>