blob: 021ad88423b20b795ca4b3ef7efcbb9edfa6a6d1 [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.hooks.webhdfs_hook &mdash; Airflow Documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Airflow
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling &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="../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../code.html">API Reference</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>airflow.hooks.webhdfs_hook</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.hooks.webhdfs_hook</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">hdfs</span> <span class="k">import</span> <span class="n">InsecureClient</span><span class="p">,</span> <span class="n">HdfsError</span>
<span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">configuration</span>
<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</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>
<span class="n">_kerberos_security_mode</span> <span class="o">=</span> <span class="n">configuration</span><span class="o">.</span><span class="n">conf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;core&quot;</span><span class="p">,</span> <span class="s2">&quot;security&quot;</span><span class="p">)</span> <span class="o">==</span> <span class="s2">&quot;kerberos&quot;</span>
<span class="k">if</span> <span class="n">_kerberos_security_mode</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">hdfs.ext.kerberos</span> <span class="k">import</span> <span class="n">KerberosClient</span>
<span class="k">except</span> <span class="ne">ImportError</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">error</span><span class="p">(</span><span class="s2">&quot;Could not load the Kerberos extension for the WebHDFSHook.&quot;</span><span class="p">)</span>
<span class="k">raise</span>
<span class="k">class</span> <span class="nc">AirflowWebHDFSHookException</span><span class="p">(</span><span class="n">AirflowException</span><span class="p">):</span>
<span class="k">pass</span>
<div class="viewcode-block" id="WebHDFSHook"><a class="viewcode-back" href="../../../code.html#airflow.hooks.webhdfs_hook.WebHDFSHook">[docs]</a><span class="k">class</span> <span class="nc">WebHDFSHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Interact with HDFS. This class is a wrapper around the hdfscli library.</span>
<span class="sd"> &quot;&quot;&quot;</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">webhdfs_conn_id</span><span class="o">=</span><span class="s1">&#39;webhdfs_default&#39;</span><span class="p">,</span> <span class="n">proxy_user</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">webhdfs_conn_id</span> <span class="o">=</span> <span class="n">webhdfs_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">proxy_user</span> <span class="o">=</span> <span class="n">proxy_user</span>
<div class="viewcode-block" id="WebHDFSHook.get_conn"><a class="viewcode-back" href="../../../code.html#airflow.hooks.webhdfs_hook.WebHDFSHook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Returns a hdfscli InsecureClient object.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">nn_connections</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connections</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">webhdfs_conn_id</span><span class="p">)</span>
<span class="k">for</span> <span class="n">nn</span> <span class="ow">in</span> <span class="n">nn_connections</span><span class="p">:</span>
<span class="k">try</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;Trying namenode </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">host</span><span class="p">)</span>
<span class="n">connection_str</span> <span class="o">=</span> <span class="s1">&#39;http://</span><span class="si">{nn.host}</span><span class="s1">:</span><span class="si">{nn.port}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">nn</span><span class="o">=</span><span class="n">nn</span><span class="p">)</span>
<span class="k">if</span> <span class="n">_kerberos_security_mode</span><span class="p">:</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">KerberosClient</span><span class="p">(</span><span class="n">connection_str</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">proxy_user</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">proxy_user</span> <span class="ow">or</span> <span class="n">nn</span><span class="o">.</span><span class="n">login</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">InsecureClient</span><span class="p">(</span><span class="n">connection_str</span><span class="p">,</span> <span class="n">user</span><span class="o">=</span><span class="n">proxy_user</span><span class="p">)</span>
<span class="n">client</span><span class="o">.</span><span class="n">status</span><span class="p">(</span><span class="s1">&#39;/&#39;</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;Using namenode </span><span class="si">%s</span><span class="s1"> for hook&#39;</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">host</span><span class="p">)</span>
<span class="k">return</span> <span class="n">client</span>
<span class="k">except</span> <span class="n">HdfsError</span> <span class="k">as</span> <span class="n">e</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;Read operation on namenode </span><span class="si">{nn.host}</span><span class="s2"> &quot;</span>
<span class="s2">&quot;failed with error: </span><span class="si">{e}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="nb">locals</span><span class="p">())</span>
<span class="p">)</span>
<span class="n">nn_hosts</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">host</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">nn_connections</span><span class="p">]</span>
<span class="n">no_nn_error</span> <span class="o">=</span> <span class="s2">&quot;Read operations failed &quot;</span> \
<span class="s2">&quot;on the namenodes below:</span><span class="se">\n</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="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">nn_hosts</span><span class="p">))</span>
<span class="k">raise</span> <span class="n">AirflowWebHDFSHookException</span><span class="p">(</span><span class="n">no_nn_error</span><span class="p">)</span></div>
<div class="viewcode-block" id="WebHDFSHook.check_for_path"><a class="viewcode-back" href="../../../code.html#airflow.hooks.webhdfs_hook.WebHDFSHook.check_for_path">[docs]</a> <span class="k">def</span> <span class="nf">check_for_path</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hdfs_path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Check for the existence of a path in HDFS by querying FileStatus.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">c</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="k">return</span> <span class="nb">bool</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">status</span><span class="p">(</span><span class="n">hdfs_path</span><span class="p">,</span> <span class="n">strict</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span></div>
<div class="viewcode-block" id="WebHDFSHook.load_file"><a class="viewcode-back" href="../../../code.html#airflow.hooks.webhdfs_hook.WebHDFSHook.load_file">[docs]</a> <span class="k">def</span> <span class="nf">load_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">,</span> <span class="n">overwrite</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">parallelism</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Uploads a file to HDFS</span>
<span class="sd"> :param source: Local path to file or folder. If a folder, all the files</span>
<span class="sd"> inside of it will be uploaded (note that this implies that folders empty</span>
<span class="sd"> of files will not be created remotely).</span>
<span class="sd"> :type source: str</span>
<span class="sd"> :param destination: PTarget HDFS path. If it already exists and is a</span>
<span class="sd"> directory, files will be uploaded inside.</span>
<span class="sd"> :type destination: str</span>
<span class="sd"> :param overwrite: Overwrite any existing file or directory.</span>
<span class="sd"> :type overwrite: bool</span>
<span class="sd"> :param parallelism: Number of threads to use for parallelization. A value of</span>
<span class="sd"> `0` (or negative) uses as many threads as there are files.</span>
<span class="sd"> :type parallelism: int</span>
<span class="sd"> :param \*\*kwargs: Keyword arguments forwarded to :meth:`upload`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">c</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="n">c</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span><span class="n">hdfs_path</span><span class="o">=</span><span class="n">destination</span><span class="p">,</span>
<span class="n">local_path</span><span class="o">=</span><span class="n">source</span><span class="p">,</span>
<span class="n">overwrite</span><span class="o">=</span><span class="n">overwrite</span><span class="p">,</span>
<span class="n">n_threads</span><span class="o">=</span><span class="n">parallelism</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">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;Uploaded file </span><span class="si">%s</span><span class="s2"> to </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">destination</span><span class="p">)</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" 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/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>