blob: 04e7d28124f8046b4ae1c2a1689dff4b32f34158 [file] [log] [blame]
<!--
Javascript to render AIRFLOW-XXX and PR references in text
as HTML links.
Overrides extrahead block from sphinx_rtd_theme
https://www.sphinx-doc.org/en/master/templating.html
-->
<!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="shortcut icon" href="../../../../_static/pin_32.png"/>
<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="stylesheet" href="../../../../_static/graphviz.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<link rel="next" title="airflow.hooks.zendesk_hook" href="../zendesk_hook/index.html" />
<link rel="prev" title="airflow.hooks.sqlite_hook" href="../sqlite_hook/index.html" />
<script>
document.addEventListener('DOMContentLoaded', function() {
var el = document.getElementById('changelog');
if (el !== null ) {
// [AIRFLOW-...]
el.innerHTML = el.innerHTML.replace(
/\[(AIRFLOW-[\d]+)\]/g,
`<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>`
);
// (#...)
el.innerHTML = el.innerHTML.replace(
/\(#([\d]+)\)/g,
`<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>`
);
};
})
</script>
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-140539454-1']);
_gaq.push(['_trackPageview']);
</script>
<style>
.example-header {
position: relative;
background: #9AAA7A;
padding: 8px 16px;
margin-bottom: 0;
}
.example-header--with-button {
padding-right: 166px;
}
.example-header:after{
content: '';
display: table;
clear: both;
}
.example-title {
display:block;
padding: 4px;
margin-right: 16px;
color: white;
overflow-x: auto;
}
.example-header-button {
top: 8px;
right: 16px;
position: absolute;
}
.example-header + .highlight-python {
margin-top: 0 !important;
}
.viewcode-button {
display: inline-block;
padding: 8px 16px;
border: 0;
margin: 0;
outline: 0;
border-radius: 2px;
-webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3);
box-shadow: 0 3px 6px 0 rgba(0,0,0,.3);
color: #404040;
background-color: #e7e7e7;
cursor: pointer;
font-size: 16px;
font-weight: 500;
line-height: 1;
text-decoration: none;
text-overflow: ellipsis;
overflow: hidden;
text-transform: uppercase;
-webkit-transition: background-color .2s;
transition: background-color .2s;
vertical-align: middle;
white-space: nowrap;
}
.viewcode-button:visited {
color: #404040;
}
.viewcode-button:hover, .viewcode-button:focus {
color: #404040;
background-color: #d6d6d6;
}
</style>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.6
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../../index.html">Python API Reference</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#operators">Operators</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="../../../index.html#hooks">Hooks</a><ul class="current">
<li class="toctree-l3 current"><a class="reference internal" href="../../../index.html#hooks-packages">Hooks packages</a><ul class="current">
<li class="toctree-l4 current"><a class="reference internal" href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../contrib/hooks/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks</span></code></a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#executors">Executors</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#core-and-community-package">Core and community package</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul class="current">
<li class="toctree-l1 current"><a class="reference internal" href="../../../index.html">Python API</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#operators">Operators</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="../../../index.html#hooks">Hooks</a><ul class="current">
<li class="toctree-l3 current"><a class="reference internal" href="../../../index.html#hooks-packages">Hooks packages</a><ul class="current">
<li class="toctree-l4 current"><a class="reference internal" href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../contrib/hooks/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.hooks</span></code></a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#executors">Executors</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#models">Models</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../index.html#core-and-community-package">Core and community package</a></li>
</ul>
</li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Python API Reference</a> &raquo;</li>
<li><a href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks</span></code></a> &raquo;</li>
<li><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks.webhdfs_hook</span></code></li>
<li class="wy-breadcrumbs-aside">
<a href="../../../../_sources/_api/airflow/hooks/webhdfs_hook/index.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="module-airflow.hooks.webhdfs_hook">
<span id="airflow-hooks-webhdfs-hook"></span><h1><a class="reference internal" href="#module-airflow.hooks.webhdfs_hook" title="airflow.hooks.webhdfs_hook"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.hooks.webhdfs_hook</span></code></a><a class="headerlink" href="#module-airflow.hooks.webhdfs_hook" title="Permalink to this headline"></a></h1>
<div class="section" id="module-contents">
<h2>Module Contents<a class="headerlink" href="#module-contents" title="Permalink to this headline"></a></h2>
<dl class="data">
<dt id="airflow.hooks.webhdfs_hook._kerberos_security_mode">
<code class="sig-prename descclassname">airflow.hooks.webhdfs_hook.</code><code class="sig-name descname">_kerberos_security_mode</code><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#_kerberos_security_mode"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook._kerberos_security_mode" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="data">
<dt id="airflow.hooks.webhdfs_hook.log">
<code class="sig-prename descclassname">airflow.hooks.webhdfs_hook.</code><code class="sig-name descname">log</code><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#log"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.log" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="exception">
<dt id="airflow.hooks.webhdfs_hook.AirflowWebHDFSHookException">
<em class="property">exception </em><code class="sig-prename descclassname">airflow.hooks.webhdfs_hook.</code><code class="sig-name descname">AirflowWebHDFSHookException</code><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#AirflowWebHDFSHookException"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.AirflowWebHDFSHookException" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">airflow.exceptions.AirflowException</span></code></p>
</dd></dl>
<dl class="class">
<dt id="airflow.hooks.webhdfs_hook.WebHDFSHook">
<em class="property">class </em><code class="sig-prename descclassname">airflow.hooks.webhdfs_hook.</code><code class="sig-name descname">WebHDFSHook</code><span class="sig-paren">(</span><em class="sig-param">webhdfs_conn_id='webhdfs_default'</em>, <em class="sig-param">proxy_user=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#WebHDFSHook"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.WebHDFSHook" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="../base_hook/index.html#airflow.hooks.base_hook.BaseHook" title="airflow.hooks.base_hook.BaseHook"><code class="xref py py-class docutils literal notranslate"><span class="pre">airflow.hooks.base_hook.BaseHook</span></code></a></p>
<p>Interact with HDFS. This class is a wrapper around the hdfscli library.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>webhdfs_conn_id</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><em>str</em></a>) – The connection id for the webhdfs client to connect to.</p></li>
<li><p><strong>proxy_user</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><em>str</em></a>) – The user used to authenticate.</p></li>
</ul>
</dd>
</dl>
<dl class="method">
<dt id="airflow.hooks.webhdfs_hook.WebHDFSHook.get_conn">
<code class="sig-name descname">get_conn</code><span class="sig-paren">(</span><em class="sig-param">self</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#WebHDFSHook.get_conn"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.WebHDFSHook.get_conn" title="Permalink to this definition"></a></dt>
<dd><p>Establishes a connection depending on the security mode set via config or environment variable.</p>
<dl class="field-list simple">
<dt class="field-odd">Returns</dt>
<dd class="field-odd"><p>a hdfscli InsecureClient or KerberosClient object.</p>
</dd>
<dt class="field-even">Return type</dt>
<dd class="field-even"><p>hdfs.InsecureClient or <a class="reference external" href="https://hdfscli.readthedocs.io/en/latest/api.html#hdfs.ext.kerberos.KerberosClient" title="(in HdfsCLI v2.5)">hdfs.ext.kerberos.KerberosClient</a></p>
</dd>
</dl>
</dd></dl>
<dl class="method">
<dt id="airflow.hooks.webhdfs_hook.WebHDFSHook._get_client">
<code class="sig-name descname">_get_client</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">connection</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#WebHDFSHook._get_client"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.WebHDFSHook._get_client" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="airflow.hooks.webhdfs_hook.WebHDFSHook.check_for_path">
<code class="sig-name descname">check_for_path</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">hdfs_path</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#WebHDFSHook.check_for_path"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.WebHDFSHook.check_for_path" title="Permalink to this definition"></a></dt>
<dd><p>Check for the existence of a path in HDFS by querying FileStatus.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><p><strong>hdfs_path</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><em>str</em></a>) – The path to check.</p>
</dd>
<dt class="field-even">Returns</dt>
<dd class="field-even"><p>True if the path exists and False if not.</p>
</dd>
<dt class="field-odd">Return type</dt>
<dd class="field-odd"><p><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.8)">bool</a></p>
</dd>
</dl>
</dd></dl>
<dl class="method">
<dt id="airflow.hooks.webhdfs_hook.WebHDFSHook.load_file">
<code class="sig-name descname">load_file</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">source</em>, <em class="sig-param">destination</em>, <em class="sig-param">overwrite=True</em>, <em class="sig-param">parallelism=1</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../_modules/airflow/hooks/webhdfs_hook.html#WebHDFSHook.load_file"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.hooks.webhdfs_hook.WebHDFSHook.load_file" title="Permalink to this definition"></a></dt>
<dd><p>Uploads a file to HDFS.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
<dd class="field-odd"><ul class="simple">
<li><p><strong>source</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><em>str</em></a>) – Local path to file or folder.
If it’s a folder, all the files inside of it will be uploaded.
.. note:: This implies that folders empty of files will not be created remotely.</p></li>
<li><p><strong>destination</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.8)"><em>str</em></a>) – PTarget HDFS path.
If it already exists and is a directory, files will be uploaded inside.</p></li>
<li><p><strong>overwrite</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.8)"><em>bool</em></a>) – Overwrite any existing file or directory.</p></li>
<li><p><strong>parallelism</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.8)"><em>int</em></a>) – Number of threads to use for parallelization.
A value of <cite>0</cite> (or negative) uses as many threads as there are files.</p></li>
<li><p><strong>**kwargs</strong> – Keyword arguments forwarded to <a class="reference external" href="https://hdfscli.readthedocs.io/en/latest/api.html#hdfs.client.Client.upload" title="(in HdfsCLI v2.5)"><code class="xref py py-meth docutils literal notranslate"><span class="pre">hdfs.client.Client.upload()</span></code></a>.</p></li>
</ul>
</dd>
</dl>
</dd></dl>
</dd></dl>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../zendesk_hook/index.html" class="btn btn-neutral float-right" title="airflow.hooks.zendesk_hook" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="../sqlite_hook/index.html" class="btn btn-neutral float-left" title="airflow.hooks.sqlite_hook" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../../privacy_notice.html">Privacy Policy</a>
for more details.
<script type="text/javascript">
(function() {
var ga = document.createElement('script');
ga.src = ('https:' == document.location.protocol ?
'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
ga.setAttribute('async', 'true');
var nodes = document.documentElement.childNodes;
var i = -1;
var node;
do {
i++;
node = nodes[i]
} while(node.nodeType !== Node.ELEMENT_NODE);
node.appendChild(ga);
})();
</script>
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>