http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/hooks/oracle_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/hooks/oracle_hook.html b/_modules/airflow/hooks/oracle_hook.html new file mode 100644 index 0000000..3683348 --- /dev/null +++ b/_modules/airflow/hooks/oracle_hook.html @@ -0,0 +1,382 @@ + + +<!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.oracle_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../genindex.html"/> + <link rel="search" title="Search" href="../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../index.html"/> + <link rel="up" title="Module code" href="../../index.html"/> + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <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 & 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" role="navigation" 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> »</li> + + <li><a href="../../index.html">Module code</a> »</li> + + <li>airflow.hooks.oracle_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.oracle_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"># "License"); 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"># "AS IS" 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">cx_Oracle</span> + +<span class="kn">from</span> <span class="nn">airflow.hooks.dbapi_hook</span> <span class="k">import</span> <span class="n">DbApiHook</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">past.builtins</span> <span class="k">import</span> <span class="n">basestring</span> +<span class="kn">from</span> <span class="nn">datetime</span> <span class="k">import</span> <span class="n">datetime</span> +<span class="kn">import</span> <span class="nn">numpy</span> + + +<div class="viewcode-block" id="OracleHook"><a class="viewcode-back" href="../../../code.html#airflow.hooks.oracle_hook.OracleHook">[docs]</a><span class="k">class</span> <span class="nc">OracleHook</span><span class="p">(</span><span class="n">DbApiHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Interact with Oracle SQL.</span> +<span class="sd"> """</span> + <span class="n">conn_name_attr</span> <span class="o">=</span> <span class="s1">'oracle_conn_id'</span> + <span class="n">default_conn_name</span> <span class="o">=</span> <span class="s1">'oracle_default'</span> + <span class="n">supports_autocommit</span> <span class="o">=</span> <span class="kc">False</span> + +<div class="viewcode-block" id="OracleHook.get_conn"><a class="viewcode-back" href="../../../code.html#airflow.hooks.oracle_hook.OracleHook.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">"""</span> +<span class="sd"> Returns a oracle connection object</span> +<span class="sd"> Optional parameters for using a custom DSN connection (instead of using a server alias from tnsnames.ora)</span> +<span class="sd"> The dsn (data source name) is the TNS entry (from the Oracle names server or tnsnames.ora file)</span> +<span class="sd"> or is a string like the one returned from makedsn().</span> + +<span class="sd"> :param dsn: the host address for the Oracle server</span> +<span class="sd"> :param service_name: the db_unique_name of the database that you are connecting to (CONNECT_DATA part of TNS)</span> +<span class="sd"> You can set these parameters in the extra fields of your connection</span> +<span class="sd"> as in ``{ "dsn":"some.host.address" , "service_name":"some.service.name" }``</span> +<span class="sd"> """</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">oracle_conn_id</span><span class="p">)</span> + <span class="n">dsn</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'dsn'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + <span class="n">sid</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'sid'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + <span class="n">mod</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'module'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + + <span class="n">service_name</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'service_name'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + <span class="k">if</span> <span class="n">dsn</span> <span class="ow">and</span> <span class="n">sid</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">service_name</span><span class="p">:</span> + <span class="n">dsn</span> <span class="o">=</span> <span class="n">cx_Oracle</span><span class="o">.</span><span class="n">makedsn</span><span class="p">(</span><span class="n">dsn</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">,</span> <span class="n">sid</span><span class="p">)</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">cx_Oracle</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">,</span> <span class="n">dsn</span><span class="o">=</span><span class="n">dsn</span><span class="p">)</span> + <span class="k">elif</span> <span class="n">dsn</span> <span class="ow">and</span> <span class="n">service_name</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">sid</span><span class="p">:</span> + <span class="n">dsn</span> <span class="o">=</span> <span class="n">cx_Oracle</span><span class="o">.</span><span class="n">makedsn</span><span class="p">(</span><span class="n">dsn</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">,</span> <span class="n">service_name</span><span class="o">=</span><span class="n">service_name</span><span class="p">)</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">cx_Oracle</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">,</span> <span class="n">dsn</span><span class="o">=</span><span class="n">dsn</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">cx_Oracle</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">,</span> <span class="n">conn</span><span class="o">.</span><span class="n">host</span><span class="p">)</span> + + <span class="k">if</span> <span class="n">mod</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> + <span class="n">conn</span><span class="o">.</span><span class="n">module</span> <span class="o">=</span> <span class="n">mod</span> + + <span class="k">return</span> <span class="n">conn</span></div> + +<div class="viewcode-block" id="OracleHook.insert_rows"><a class="viewcode-back" href="../../../code.html#airflow.hooks.oracle_hook.OracleHook.insert_rows">[docs]</a> <span class="k">def</span> <span class="nf">insert_rows</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">rows</span><span class="p">,</span> <span class="n">target_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">commit_every</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> A generic way to insert a set of tuples into a table,</span> +<span class="sd"> the whole set of inserts is treated as one transaction</span> +<span class="sd"> Changes from standard DbApiHook implementation:</span> +<span class="sd"> - Oracle SQL queries in cx_Oracle can not be terminated with a semicolon (';')</span> +<span class="sd"> - Replace NaN values with NULL using numpy.nan_to_num (not using is_nan() because of input types error for strings)</span> +<span class="sd"> - Coerce datetime cells to Oracle DATETIME format during insert</span> +<span class="sd"> """</span> + <span class="k">if</span> <span class="n">target_fields</span><span class="p">:</span> + <span class="n">target_fields</span> <span class="o">=</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">target_fields</span><span class="p">)</span> + <span class="n">target_fields</span> <span class="o">=</span> <span class="s1">'(</span><span class="si">{}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">target_fields</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">target_fields</span> <span class="o">=</span> <span class="s1">''</span> + <span class="n">conn</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">cur</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">supports_autocommit</span><span class="p">:</span> + <span class="n">cur</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="s1">'SET autocommit = 0'</span><span class="p">)</span> + <span class="n">conn</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span> + <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span> + <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">:</span> + <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> + <span class="n">l</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">for</span> <span class="n">cell</span> <span class="ow">in</span> <span class="n">row</span><span class="p">:</span> + <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cell</span><span class="p">,</span> <span class="n">basestring</span><span class="p">):</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"'"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">cell</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"'"</span><span class="p">,</span> <span class="s2">"''"</span><span class="p">)</span> <span class="o">+</span> <span class="s2">"'"</span><span class="p">)</span> + <span class="k">elif</span> <span class="n">cell</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">'NULL'</span><span class="p">)</span> + <span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="n">cell</span><span class="p">)</span> <span class="o">==</span> <span class="nb">float</span> <span class="ow">and</span> <span class="n">numpy</span><span class="o">.</span><span class="n">isnan</span><span class="p">(</span><span class="n">cell</span><span class="p">):</span> <span class="c1"># coerce numpy NaN to NULL</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">'NULL'</span><span class="p">)</span> + <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cell</span><span class="p">,</span> <span class="n">numpy</span><span class="o">.</span><span class="n">datetime64</span><span class="p">):</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"'"</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">cell</span><span class="p">)</span> <span class="o">+</span> <span class="s2">"'"</span><span class="p">)</span> + <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">cell</span><span class="p">,</span> <span class="n">datetime</span><span class="p">):</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"to_date('"</span> <span class="o">+</span> <span class="n">cell</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">'%Y-%m-</span><span class="si">%d</span><span class="s1"> %H:%M:%S'</span><span class="p">)</span> <span class="o">+</span> <span class="s2">"','YYYY-MM-DD HH24:MI:SS')"</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">l</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">cell</span><span class="p">))</span> + <span class="n">values</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">l</span><span class="p">)</span> + <span class="n">sql</span> <span class="o">=</span> <span class="s1">'INSERT /*+ APPEND */ INTO </span><span class="si">{0}</span><span class="s1"> </span><span class="si">{1}</span><span class="s1"> VALUES (</span><span class="si">{2}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">table</span><span class="p">,</span> <span class="n">target_fields</span><span class="p">,</span> <span class="s1">','</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">values</span><span class="p">))</span> + <span class="n">cur</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">sql</span><span class="p">)</span> + <span class="k">if</span> <span class="n">i</span> <span class="o">%</span> <span class="n">commit_every</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> + <span class="n">conn</span><span class="o">.</span><span class="n">commit</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">'Loaded </span><span class="si">{i}</span><span class="s1"> into </span><span class="si">{table}</span><span class="s1"> rows so far'</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="n">conn</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span> + <span class="n">cur</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> + <span class="n">conn</span><span class="o">.</span><span class="n">close</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">'Done loading. Loaded a total of </span><span class="si">{i}</span><span class="s1"> rows'</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></div> + +<div class="viewcode-block" id="OracleHook.bulk_insert_rows"><a class="viewcode-back" href="../../../code.html#airflow.hooks.oracle_hook.OracleHook.bulk_insert_rows">[docs]</a> <span class="k">def</span> <span class="nf">bulk_insert_rows</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">rows</span><span class="p">,</span> <span class="n">target_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">commit_every</span><span class="o">=</span><span class="mi">5000</span><span class="p">):</span> + <span class="sd">"""A performant bulk insert for cx_Oracle that uses prepared statements via `executemany()`.</span> +<span class="sd"> For best performance, pass in `rows` as an iterator.</span> +<span class="sd"> """</span> + <span class="n">conn</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">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> + <span class="n">values</span> <span class="o">=</span> <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">':</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">target_fields</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">))</span> + <span class="n">prepared_stm</span> <span class="o">=</span> <span class="s1">'insert into </span><span class="si">{tablename}</span><span class="s1"> (</span><span class="si">{columns}</span><span class="s1">) values (</span><span class="si">{values}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">tablename</span><span class="o">=</span><span class="n">table</span><span class="p">,</span> + <span class="n">columns</span><span class="o">=</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">target_fields</span><span class="p">),</span> + <span class="n">values</span><span class="o">=</span><span class="n">values</span><span class="p">,</span> + <span class="p">)</span> + <span class="n">row_count</span> <span class="o">=</span> <span class="mi">0</span> + <span class="c1"># Chunk the rows</span> + <span class="n">row_chunk</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">:</span> + <span class="n">row_chunk</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">row</span><span class="p">)</span> + <span class="n">row_count</span> <span class="o">+=</span> <span class="mi">1</span> + <span class="k">if</span> <span class="n">row_count</span> <span class="o">%</span> <span class="n">commit_every</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">prepare</span><span class="p">(</span><span class="n">prepared_stm</span><span class="p">)</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">executemany</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="n">row_chunk</span><span class="p">)</span> + <span class="n">conn</span><span class="o">.</span><span class="n">commit</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">'[</span><span class="si">%s</span><span class="s1">] inserted </span><span class="si">%s</span><span class="s1"> rows'</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">row_count</span><span class="p">)</span> + <span class="c1"># Empty chunk</span> + <span class="n">row_chunk</span> <span class="o">=</span> <span class="p">[]</span> + <span class="c1"># Commit the leftover chunk</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">prepare</span><span class="p">(</span><span class="n">prepared_stm</span><span class="p">)</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">executemany</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="n">row_chunk</span><span class="p">)</span> + <span class="n">conn</span><span class="o">.</span><span class="n">commit</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">'[</span><span class="si">%s</span><span class="s1">] inserted </span><span class="si">%s</span><span class="s1"> rows'</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">row_count</span><span class="p">)</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> + <span class="n">conn</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div></div> +</pre></div> + + </div> + <div class="articleComments"> + + </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/snide/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"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </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.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/hooks/pig_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/hooks/pig_hook.html b/_modules/airflow/hooks/pig_hook.html new file mode 100644 index 0000000..05fac3c --- /dev/null +++ b/_modules/airflow/hooks/pig_hook.html @@ -0,0 +1,329 @@ + + +<!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.pig_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../genindex.html"/> + <link rel="search" title="Search" href="../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../index.html"/> + <link rel="up" title="Module code" href="../../index.html"/> + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <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 & 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" role="navigation" 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> »</li> + + <li><a href="../../index.html">Module code</a> »</li> + + <li>airflow.hooks.pig_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.pig_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"># "License"); 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"># "AS IS" 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">__future__</span> <span class="k">import</span> <span class="n">print_function</span> +<span class="kn">import</span> <span class="nn">subprocess</span> +<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</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.file</span> <span class="k">import</span> <span class="n">TemporaryDirectory</span> + + +<div class="viewcode-block" id="PigCliHook"><a class="viewcode-back" href="../../../code.html#airflow.hooks.pig_hook.PigCliHook">[docs]</a><span class="k">class</span> <span class="nc">PigCliHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Simple wrapper around the pig CLI.</span> + +<span class="sd"> Note that you can also set default pig CLI properties using the</span> +<span class="sd"> ``pig_properties`` to be used in your connection as in</span> +<span class="sd"> ``{"pig_properties": "-Dpig.tmpfilecompression=true"}``</span> + +<span class="sd"> """</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">pig_cli_conn_id</span><span class="o">=</span><span class="s2">"pig_cli_default"</span><span class="p">):</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="n">pig_cli_conn_id</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">pig_properties</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'pig_properties'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> <span class="o">=</span> <span class="n">conn</span> + +<div class="viewcode-block" id="PigCliHook.run_cli"><a class="viewcode-back" href="../../../code.html#airflow.hooks.pig_hook.PigCliHook.run_cli">[docs]</a> <span class="k">def</span> <span class="nf">run_cli</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pig</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Run an pig script using the pig cli</span> + +<span class="sd"> >>> ph = PigCliHook()</span> +<span class="sd"> >>> result = ph.run_cli("ls /;")</span> +<span class="sd"> >>> ("hdfs://" in result)</span> +<span class="sd"> True</span> +<span class="sd"> """</span> + + <span class="k">with</span> <span class="n">TemporaryDirectory</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'airflow_pigop_'</span><span class="p">)</span> <span class="k">as</span> <span class="n">tmp_dir</span><span class="p">:</span> + <span class="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="nb">dir</span><span class="o">=</span><span class="n">tmp_dir</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> + <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">pig</span><span class="p">)</span> + <span class="n">f</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> + <span class="n">fname</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">name</span> + <span class="n">pig_bin</span> <span class="o">=</span> <span class="s1">'pig'</span> + <span class="n">cmd_extra</span> <span class="o">=</span> <span class="p">[]</span> + + <span class="n">pig_cmd</span> <span class="o">=</span> <span class="p">[</span><span class="n">pig_bin</span><span class="p">,</span> <span class="s1">'-f'</span><span class="p">,</span> <span class="n">fname</span><span class="p">]</span> <span class="o">+</span> <span class="n">cmd_extra</span> + + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">pig_properties</span><span class="p">:</span> + <span class="n">pig_properties_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pig_properties</span><span class="o">.</span><span class="n">split</span><span class="p">()</span> + <span class="n">pig_cmd</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">pig_properties_list</span><span class="p">)</span> + <span class="k">if</span> <span class="n">verbose</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">" "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">pig_cmd</span><span class="p">))</span> + <span class="n">sp</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">Popen</span><span class="p">(</span> + <span class="n">pig_cmd</span><span class="p">,</span> + <span class="n">stdout</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">PIPE</span><span class="p">,</span> + <span class="n">stderr</span><span class="o">=</span><span class="n">subprocess</span><span class="o">.</span><span class="n">STDOUT</span><span class="p">,</span> + <span class="n">cwd</span><span class="o">=</span><span class="n">tmp_dir</span><span class="p">,</span> + <span class="n">close_fds</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">sp</span> <span class="o">=</span> <span class="n">sp</span> + <span class="n">stdout</span> <span class="o">=</span> <span class="s1">''</span> + <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">iter</span><span class="p">(</span><span class="n">sp</span><span class="o">.</span><span class="n">stdout</span><span class="o">.</span><span class="n">readline</span><span class="p">,</span> <span class="s1">''</span><span class="p">):</span> + <span class="n">stdout</span> <span class="o">+=</span> <span class="n">line</span> + <span class="k">if</span> <span class="n">verbose</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="n">line</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span> + <span class="n">sp</span><span class="o">.</span><span class="n">wait</span><span class="p">()</span> + + <span class="k">if</span> <span class="n">sp</span><span class="o">.</span><span class="n">returncode</span><span class="p">:</span> + <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="n">stdout</span><span class="p">)</span> + + <span class="k">return</span> <span class="n">stdout</span></div> + + <span class="k">def</span> <span class="nf">kill</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'sp'</span><span class="p">):</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">sp</span><span class="o">.</span><span class="n">poll</span><span class="p">()</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> + <span class="nb">print</span><span class="p">(</span><span class="s2">"Killing the Pig job"</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">sp</span><span class="o">.</span><span class="n">kill</span><span class="p">()</span></div> +</pre></div> + + </div> + <div class="articleComments"> + + </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/snide/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"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </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.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/hooks/postgres_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/hooks/postgres_hook.html b/_modules/airflow/hooks/postgres_hook.html new file mode 100644 index 0000000..d912cc2 --- /dev/null +++ b/_modules/airflow/hooks/postgres_hook.html @@ -0,0 +1,323 @@ + + +<!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.postgres_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../genindex.html"/> + <link rel="search" title="Search" href="../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../index.html"/> + <link rel="up" title="Module code" href="../../index.html"/> + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <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 & 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" role="navigation" 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> »</li> + + <li><a href="../../index.html">Module code</a> »</li> + + <li>airflow.hooks.postgres_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.postgres_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"># "License"); 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"># "AS IS" 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">psycopg2</span> +<span class="kn">import</span> <span class="nn">psycopg2.extensions</span> +<span class="kn">from</span> <span class="nn">contextlib</span> <span class="k">import</span> <span class="n">closing</span> + +<span class="kn">from</span> <span class="nn">airflow.hooks.dbapi_hook</span> <span class="k">import</span> <span class="n">DbApiHook</span> + + +<div class="viewcode-block" id="PostgresHook"><a class="viewcode-back" href="../../../code.html#airflow.hooks.postgres_hook.PostgresHook">[docs]</a><span class="k">class</span> <span class="nc">PostgresHook</span><span class="p">(</span><span class="n">DbApiHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Interact with Postgres.</span> +<span class="sd"> You can specify ssl parameters in the extra field of your connection</span> +<span class="sd"> as ``{"sslmode": "require", "sslcert": "/path/to/cert.pem", etc}``.</span> + +<span class="sd"> Note: For Redshift, use keepalives_idle in the extra connection parameters</span> +<span class="sd"> and set it to less than 300 seconds.</span> +<span class="sd"> """</span> + <span class="n">conn_name_attr</span> <span class="o">=</span> <span class="s1">'postgres_conn_id'</span> + <span class="n">default_conn_name</span> <span class="o">=</span> <span class="s1">'postgres_default'</span> + <span class="n">supports_autocommit</span> <span class="o">=</span> <span class="kc">True</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="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">PostgresHook</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">schema</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s2">"schema"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> + + <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="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">postgres_conn_id</span><span class="p">)</span> + <span class="n">conn_args</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span> + <span class="n">host</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> + <span class="n">user</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">password</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">dbname</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="ow">or</span> <span class="n">conn</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> + <span class="n">port</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">port</span><span class="p">)</span> + <span class="c1"># check for ssl parameters in conn.extra</span> + <span class="k">for</span> <span class="n">arg_name</span><span class="p">,</span> <span class="n">arg_val</span> <span class="ow">in</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> + <span class="k">if</span> <span class="n">arg_name</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'sslmode'</span><span class="p">,</span> <span class="s1">'sslcert'</span><span class="p">,</span> <span class="s1">'sslkey'</span><span class="p">,</span> + <span class="s1">'sslrootcert'</span><span class="p">,</span> <span class="s1">'sslcrl'</span><span class="p">,</span> <span class="s1">'application_name'</span><span class="p">,</span> + <span class="s1">'keepalives_idle'</span><span class="p">]:</span> + <span class="n">conn_args</span><span class="p">[</span><span class="n">arg_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg_val</span> + + <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> <span class="o">=</span> <span class="n">psycopg2</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span><span class="o">**</span><span class="n">conn_args</span><span class="p">)</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">conn</span> + +<div class="viewcode-block" id="PostgresHook.copy_expert"><a class="viewcode-back" href="../../../code.html#airflow.hooks.postgres_hook.PostgresHook.copy_expert">[docs]</a> <span class="k">def</span> <span class="nf">copy_expert</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">filename</span><span class="p">,</span> <span class="nb">open</span><span class="o">=</span><span class="nb">open</span><span class="p">):</span> + <span class="sd">'''</span> +<span class="sd"> Executes SQL using psycopg2 copy_expert method</span> +<span class="sd"> Necessary to execute COPY command without access to a superuser</span> +<span class="sd"> '''</span> + <span class="n">f</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="s1">'w'</span><span class="p">)</span> + <span class="k">with</span> <span class="n">closing</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">())</span> <span class="k">as</span> <span class="n">conn</span><span class="p">:</span> + <span class="k">with</span> <span class="n">closing</span><span class="p">(</span><span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">())</span> <span class="k">as</span> <span class="n">cur</span><span class="p">:</span> + <span class="n">cur</span><span class="o">.</span><span class="n">copy_expert</span><span class="p">(</span><span class="n">sql</span><span class="p">,</span> <span class="n">f</span><span class="p">)</span></div> + + <span class="nd">@staticmethod</span> + <span class="k">def</span> <span class="nf">_serialize_cell</span><span class="p">(</span><span class="n">cell</span><span class="p">,</span> <span class="n">conn</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Postgresql will adapt all arguments to the execute() method internally,</span> +<span class="sd"> hence we return cell without any conversion.</span> + +<span class="sd"> See http://initd.org/psycopg/docs/advanced.html#adapting-new-types for</span> +<span class="sd"> more information.</span> + +<span class="sd"> :param cell: The cell to insert into the table</span> +<span class="sd"> :type cell: object</span> +<span class="sd"> :param conn: The database connection</span> +<span class="sd"> :type conn: connection object</span> +<span class="sd"> :return: The cell</span> +<span class="sd"> :rtype: object</span> +<span class="sd"> """</span> + <span class="k">return</span> <span class="n">cell</span></div> +</pre></div> + + </div> + <div class="articleComments"> + + </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/snide/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"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </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.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/hooks/presto_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/hooks/presto_hook.html b/_modules/airflow/hooks/presto_hook.html new file mode 100644 index 0000000..ab441fd --- /dev/null +++ b/_modules/airflow/hooks/presto_hook.html @@ -0,0 +1,366 @@ + + +<!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.presto_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../genindex.html"/> + <link rel="search" title="Search" href="../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../index.html"/> + <link rel="up" title="Module code" href="../../index.html"/> + + + <script src="../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <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 & 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" role="navigation" 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> »</li> + + <li><a href="../../index.html">Module code</a> »</li> + + <li>airflow.hooks.presto_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.presto_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"># "License"); 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"># "AS IS" 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">builtins</span> <span class="k">import</span> <span class="nb">str</span> + +<span class="kn">from</span> <span class="nn">pyhive</span> <span class="k">import</span> <span class="n">presto</span> +<span class="kn">from</span> <span class="nn">pyhive.exc</span> <span class="k">import</span> <span class="n">DatabaseError</span> + +<span class="kn">from</span> <span class="nn">airflow.hooks.dbapi_hook</span> <span class="k">import</span> <span class="n">DbApiHook</span> + +<span class="k">class</span> <span class="nc">PrestoException</span><span class="p">(</span><span class="ne">Exception</span><span class="p">):</span> + <span class="k">pass</span> + + +<div class="viewcode-block" id="PrestoHook"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook">[docs]</a><span class="k">class</span> <span class="nc">PrestoHook</span><span class="p">(</span><span class="n">DbApiHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Interact with Presto through PyHive!</span> + +<span class="sd"> >>> ph = PrestoHook()</span> +<span class="sd"> >>> sql = "SELECT count(1) AS num FROM airflow.static_babynames"</span> +<span class="sd"> >>> ph.get_records(sql)</span> +<span class="sd"> [[340698]]</span> +<span class="sd"> """</span> + + <span class="n">conn_name_attr</span> <span class="o">=</span> <span class="s1">'presto_conn_id'</span> + <span class="n">default_conn_name</span> <span class="o">=</span> <span class="s1">'presto_default'</span> + +<div class="viewcode-block" id="PrestoHook.get_conn"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.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">"""Returns a connection object"""</span> + <span class="n">db</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">presto_conn_id</span><span class="p">)</span> + <span class="k">return</span> <span class="n">presto</span><span class="o">.</span><span class="n">connect</span><span class="p">(</span> + <span class="n">host</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">host</span><span class="p">,</span> + <span class="n">port</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">port</span><span class="p">,</span> + <span class="n">username</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> + <span class="n">catalog</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">extra_dejson</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'catalog'</span><span class="p">,</span> <span class="s1">'hive'</span><span class="p">),</span> + <span class="n">schema</span><span class="o">=</span><span class="n">db</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span></div> + + <span class="nd">@staticmethod</span> + <span class="k">def</span> <span class="nf">_strip_sql</span><span class="p">(</span><span class="n">sql</span><span class="p">):</span> + <span class="k">return</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">rstrip</span><span class="p">(</span><span class="s1">';'</span><span class="p">)</span> + + <span class="k">def</span> <span class="nf">_get_pretty_exception_message</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">e</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Parses some DatabaseError to provide a better error message</span> +<span class="sd"> """</span> + <span class="k">if</span> <span class="p">(</span><span class="nb">hasattr</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="s1">'message'</span><span class="p">)</span> + <span class="ow">and</span> <span class="s1">'errorName'</span> <span class="ow">in</span> <span class="n">e</span><span class="o">.</span><span class="n">message</span> + <span class="ow">and</span> <span class="s1">'message'</span> <span class="ow">in</span> <span class="n">e</span><span class="o">.</span><span class="n">message</span><span class="p">):</span> + <span class="k">return</span> <span class="p">(</span><span class="s1">'</span><span class="si">{name}</span><span class="s1">: </span><span class="si">{message}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> + <span class="n">name</span><span class="o">=</span><span class="n">e</span><span class="o">.</span><span class="n">message</span><span class="p">[</span><span class="s1">'errorName'</span><span class="p">],</span> + <span class="n">message</span><span class="o">=</span><span class="n">e</span><span class="o">.</span><span class="n">message</span><span class="p">[</span><span class="s1">'message'</span><span class="p">]))</span> + <span class="k">else</span><span class="p">:</span> + <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> + +<div class="viewcode-block" id="PrestoHook.get_records"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.get_records">[docs]</a> <span class="k">def</span> <span class="nf">get_records</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Get a set of records from Presto</span> +<span class="sd"> """</span> + <span class="k">try</span><span class="p">:</span> + <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">PrestoHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">get_records</span><span class="p">(</span> + <span class="bp">self</span><span class="o">.</span><span class="n">_strip_sql</span><span class="p">(</span><span class="n">hql</span><span class="p">),</span> <span class="n">parameters</span><span class="p">)</span> + <span class="k">except</span> <span class="n">DatabaseError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">raise</span> <span class="n">PrestoException</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_pretty_exception_message</span><span class="p">(</span><span class="n">e</span><span class="p">))</span></div> + +<div class="viewcode-block" id="PrestoHook.get_first"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.get_first">[docs]</a> <span class="k">def</span> <span class="nf">get_first</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Returns only the first row, regardless of how many rows the query</span> +<span class="sd"> returns.</span> +<span class="sd"> """</span> + <span class="k">try</span><span class="p">:</span> + <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">PrestoHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span> + <span class="bp">self</span><span class="o">.</span><span class="n">_strip_sql</span><span class="p">(</span><span class="n">hql</span><span class="p">),</span> <span class="n">parameters</span><span class="p">)</span> + <span class="k">except</span> <span class="n">DatabaseError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">raise</span> <span class="n">PrestoException</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_pretty_exception_message</span><span class="p">(</span><span class="n">e</span><span class="p">))</span></div> + +<div class="viewcode-block" id="PrestoHook.get_pandas_df"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.get_pandas_df">[docs]</a> <span class="k">def</span> <span class="nf">get_pandas_df</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Get a pandas dataframe from a sql query.</span> +<span class="sd"> """</span> + <span class="kn">import</span> <span class="nn">pandas</span> + <span class="n">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_cursor</span><span class="p">()</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_strip_sql</span><span class="p">(</span><span class="n">hql</span><span class="p">),</span> <span class="n">parameters</span><span class="p">)</span> + <span class="n">data</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">fetchall</span><span class="p">()</span> + <span class="k">except</span> <span class="n">DatabaseError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> + <span class="k">raise</span> <span class="n">PrestoException</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_pretty_exception_message</span><span class="p">(</span><span class="n">e</span><span class="p">))</span> + <span class="n">column_descriptions</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span> + <span class="k">if</span> <span class="n">data</span><span class="p">:</span> + <span class="n">df</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> + <span class="n">df</span><span class="o">.</span><span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">column_descriptions</span><span class="p">]</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">df</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">()</span> + <span class="k">return</span> <span class="n">df</span></div> + +<div class="viewcode-block" id="PrestoHook.run"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.run">[docs]</a> <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hql</span><span class="p">,</span> <span class="n">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Execute the statement against Presto. Can be used to create views.</span> +<span class="sd"> """</span> + <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">PrestoHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_strip_sql</span><span class="p">(</span><span class="n">hql</span><span class="p">),</span> <span class="n">parameters</span><span class="p">)</span></div> + + <span class="c1"># TODO Enable commit_every once PyHive supports transaction.</span> + <span class="c1"># Unfortunately, PyHive 0.5.1 doesn't support transaction for now,</span> + <span class="c1"># whereas Presto 0.132+ does.</span> +<div class="viewcode-block" id="PrestoHook.insert_rows"><a class="viewcode-back" href="../../../code.html#airflow.hooks.presto_hook.PrestoHook.insert_rows">[docs]</a> <span class="k">def</span> <span class="nf">insert_rows</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">rows</span><span class="p">,</span> <span class="n">target_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> A generic way to insert a set of tuples into a table.</span> + +<span class="sd"> :param table: Name of the target table</span> +<span class="sd"> :type table: str</span> +<span class="sd"> :param rows: The rows to insert into the table</span> +<span class="sd"> :type rows: iterable of tuples</span> +<span class="sd"> :param target_fields: The names of the columns to fill in the table</span> +<span class="sd"> :type target_fields: iterable of strings</span> +<span class="sd"> """</span> + <span class="nb">super</span><span class="p">(</span><span class="n">PrestoHook</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">insert_rows</span><span class="p">(</span><span class="n">table</span><span class="p">,</span> <span class="n">rows</span><span class="p">,</span> <span class="n">target_fields</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span></div></div> +</pre></div> + + </div> + <div class="articleComments"> + + </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/snide/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"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </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.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file