blob: 098f7a35d4f0fc9047a9e9b379aea3377ea9c459 [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.contrib.hooks.azure_data_lake_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/jira-links.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="stylesheet" href="../../../../_static/exampleinclude.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script>
</script>
<style>
</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">
1.10.8
</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="../../../../executor/index.html">Executor</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="../../../../dag-serialization.html">DAG Serialization</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="../../../../best-practices.html">Best Practices</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="../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../configurations-ref.html">Configurations</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="../hooks.html">airflow.contrib.hooks</a> &raquo;</li>
<li>airflow.contrib.hooks.azure_data_lake_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.contrib.hooks.azure_data_lake_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="c1">#</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="kn">import</span> <span class="n">BaseHook</span>
<span class="kn">from</span> <span class="nn">azure.datalake.store</span> <span class="kn">import</span> <span class="n">core</span><span class="p">,</span> <span class="n">lib</span><span class="p">,</span> <span class="n">multithread</span>
<div class="viewcode-block" id="AzureDataLakeHook"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook">[docs]</a><span class="k">class</span> <span class="nc">AzureDataLakeHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Interacts with Azure Data Lake.</span>
<span class="sd"> Client ID and client secret should be in user and password parameters.</span>
<span class="sd"> Tenant and account name should be extra field as</span>
<span class="sd"> {&quot;tenant&quot;: &quot;&lt;TENANT&gt;&quot;, &quot;account_name&quot;: &quot;ACCOUNT_NAME&quot;}.</span>
<span class="sd"> :param azure_data_lake_conn_id: Reference to the Azure Data Lake connection.</span>
<span class="sd"> :type azure_data_lake_conn_id: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">azure_data_lake_conn_id</span><span class="o">=</span><span class="s1">&#39;azure_data_lake_default&#39;</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">azure_data_lake_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">connection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<div class="viewcode-block" id="AzureDataLakeHook.get_conn"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook.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;Return a AzureDLFileSystem object.&quot;&quot;&quot;</span>
<span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span>
<span class="n">service_options</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span>
<span class="bp">self</span><span class="o">.</span><span class="n">account_name</span> <span class="o">=</span> <span class="n">service_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;account_name&#39;</span><span class="p">)</span>
<span class="n">adlCreds</span> <span class="o">=</span> <span class="n">lib</span><span class="o">.</span><span class="n">auth</span><span class="p">(</span><span class="n">tenant_id</span><span class="o">=</span><span class="n">service_options</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;tenant&#39;</span><span class="p">),</span>
<span class="n">client_secret</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">,</span>
<span class="n">client_id</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">)</span>
<span class="n">adlsFileSystemClient</span> <span class="o">=</span> <span class="n">core</span><span class="o">.</span><span class="n">AzureDLFileSystem</span><span class="p">(</span><span class="n">adlCreds</span><span class="p">,</span>
<span class="n">store_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">account_name</span><span class="p">)</span>
<span class="n">adlsFileSystemClient</span><span class="o">.</span><span class="n">connect</span><span class="p">()</span>
<span class="k">return</span> <span class="n">adlsFileSystemClient</span></div>
<div class="viewcode-block" id="AzureDataLakeHook.check_for_file"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook.check_for_file">[docs]</a> <span class="k">def</span> <span class="nf">check_for_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Check if a file exists on Azure Data Lake.</span>
<span class="sd"> :param file_path: Path and name of the file.</span>
<span class="sd"> :type file_path: str</span>
<span class="sd"> :return: True if the file exists, False otherwise.</span>
<span class="sd"> :rtype: bool</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">files</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="n">file_path</span><span class="p">,</span> <span class="n">details</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">invalidate_cache</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">files</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span>
<span class="k">except</span> <span class="ne">FileNotFoundError</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="AzureDataLakeHook.upload_file"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook.upload_file">[docs]</a> <span class="k">def</span> <span class="nf">upload_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">local_path</span><span class="p">,</span> <span class="n">remote_path</span><span class="p">,</span> <span class="n">nthreads</span><span class="o">=</span><span class="mi">64</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">buffersize</span><span class="o">=</span><span class="mi">4194304</span><span class="p">,</span> <span class="n">blocksize</span><span class="o">=</span><span class="mi">4194304</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Upload a file to Azure Data Lake.</span>
<span class="sd"> :param local_path: local path. Can be single file, directory (in which case,</span>
<span class="sd"> upload recursively) or glob pattern. Recursive glob patterns using `**`</span>
<span class="sd"> are not supported.</span>
<span class="sd"> :type local_path: str</span>
<span class="sd"> :param remote_path: Remote path to upload to; if multiple files, this is the</span>
<span class="sd"> directory root to write within.</span>
<span class="sd"> :type remote_path: str</span>
<span class="sd"> :param nthreads: Number of threads to use. If None, uses the number of cores.</span>
<span class="sd"> :type nthreads: int</span>
<span class="sd"> :param overwrite: Whether to forcibly overwrite existing files/directories.</span>
<span class="sd"> If False and remote path is a directory, will quit regardless if any files</span>
<span class="sd"> would be overwritten or not. If True, only matching filenames are actually</span>
<span class="sd"> overwritten.</span>
<span class="sd"> :type overwrite: bool</span>
<span class="sd"> :param buffersize: int [2**22]</span>
<span class="sd"> Number of bytes for internal buffer. This block cannot be bigger than</span>
<span class="sd"> a chunk and cannot be smaller than a block.</span>
<span class="sd"> :type buffersize: int</span>
<span class="sd"> :param blocksize: int [2**22]</span>
<span class="sd"> Number of bytes for a block. Within each chunk, we write a smaller</span>
<span class="sd"> block for each API call. This block cannot be bigger than a chunk.</span>
<span class="sd"> :type blocksize: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">multithread</span><span class="o">.</span><span class="n">ADLUploader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="p">,</span>
<span class="n">lpath</span><span class="o">=</span><span class="n">local_path</span><span class="p">,</span>
<span class="n">rpath</span><span class="o">=</span><span class="n">remote_path</span><span class="p">,</span>
<span class="n">nthreads</span><span class="o">=</span><span class="n">nthreads</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">buffersize</span><span class="o">=</span><span class="n">buffersize</span><span class="p">,</span>
<span class="n">blocksize</span><span class="o">=</span><span class="n">blocksize</span><span class="p">)</span></div>
<div class="viewcode-block" id="AzureDataLakeHook.download_file"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook.download_file">[docs]</a> <span class="k">def</span> <span class="nf">download_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">local_path</span><span class="p">,</span> <span class="n">remote_path</span><span class="p">,</span> <span class="n">nthreads</span><span class="o">=</span><span class="mi">64</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">buffersize</span><span class="o">=</span><span class="mi">4194304</span><span class="p">,</span> <span class="n">blocksize</span><span class="o">=</span><span class="mi">4194304</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Download a file from Azure Blob Storage.</span>
<span class="sd"> :param local_path: local path. If downloading a single file, will write to this</span>
<span class="sd"> specific file, unless it is an existing directory, in which case a file is</span>
<span class="sd"> created within it. If downloading multiple files, this is the root</span>
<span class="sd"> directory to write within. Will create directories as required.</span>
<span class="sd"> :type local_path: str</span>
<span class="sd"> :param remote_path: remote path/globstring to use to find remote files.</span>
<span class="sd"> Recursive glob patterns using `**` are not supported.</span>
<span class="sd"> :type remote_path: str</span>
<span class="sd"> :param nthreads: Number of threads to use. If None, uses the number of cores.</span>
<span class="sd"> :type nthreads: int</span>
<span class="sd"> :param overwrite: Whether to forcibly overwrite existing files/directories.</span>
<span class="sd"> If False and remote path is a directory, will quit regardless if any files</span>
<span class="sd"> would be overwritten or not. If True, only matching filenames are actually</span>
<span class="sd"> overwritten.</span>
<span class="sd"> :type overwrite: bool</span>
<span class="sd"> :param buffersize: int [2**22]</span>
<span class="sd"> Number of bytes for internal buffer. This block cannot be bigger than</span>
<span class="sd"> a chunk and cannot be smaller than a block.</span>
<span class="sd"> :type buffersize: int</span>
<span class="sd"> :param blocksize: int [2**22]</span>
<span class="sd"> Number of bytes for a block. Within each chunk, we write a smaller</span>
<span class="sd"> block for each API call. This block cannot be bigger than a chunk.</span>
<span class="sd"> :type blocksize: int</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">multithread</span><span class="o">.</span><span class="n">ADLDownloader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="p">,</span>
<span class="n">lpath</span><span class="o">=</span><span class="n">local_path</span><span class="p">,</span>
<span class="n">rpath</span><span class="o">=</span><span class="n">remote_path</span><span class="p">,</span>
<span class="n">nthreads</span><span class="o">=</span><span class="n">nthreads</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">buffersize</span><span class="o">=</span><span class="n">buffersize</span><span class="p">,</span>
<span class="n">blocksize</span><span class="o">=</span><span class="n">blocksize</span><span class="p">)</span></div>
<div class="viewcode-block" id="AzureDataLakeHook.list"><a class="viewcode-back" href="../../../../_api/airflow/contrib/hooks/azure_data_lake_hook/index.html#airflow.contrib.hooks.azure_data_lake_hook.AzureDataLakeHook.list">[docs]</a> <span class="k">def</span> <span class="nf">list</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> List files in Azure Data Lake Storage</span>
<span class="sd"> :param path: full path/globstring to use to list files in ADLS</span>
<span class="sd"> :type path: str</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="s2">&quot;*&quot;</span> <span class="ow">in</span> <span class="n">path</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">path</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>.
<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.
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
<!-- Theme Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-140539454-1', 'auto');
ga('send', 'pageview');
</script>
</body>
</html>