| |
| |
| |
| |
| |
| <!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.operators.hive_stats_operator — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <script type="text/javascript"> |
| var _gaq = _gaq || []; |
| _gaq.push(['_setAccount', 'UA-140539454-1']); |
| _gaq.push(['_trackPageview']); |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </style> |
| |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.5 |
| </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 & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../api.html">REST API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../_api/index.html">Python API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../privacy_notice.html">Privacy Notice</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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li><a href="../operators.html">airflow.operators</a> »</li> |
| |
| <li>airflow.operators.hive_stats_operator</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.operators.hive_stats_operator</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">zip</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span> |
| <span class="kn">import</span> <span class="nn">json</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.mysql_hook</span> <span class="k">import</span> <span class="n">MySqlHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.hooks.presto_hook</span> <span class="k">import</span> <span class="n">PrestoHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.hooks.hive_hooks</span> <span class="k">import</span> <span class="n">HiveMetastoreHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> |
| |
| |
| <div class="viewcode-block" id="HiveStatsCollectionOperator"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_stats_operator/index.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator">[docs]</a><span class="k">class</span> <span class="nc">HiveStatsCollectionOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Gathers partition statistics using a dynamically generated Presto</span> |
| <span class="sd"> query, inserts the stats into a MySql table with this format. Stats</span> |
| <span class="sd"> overwrite themselves if you rerun the same date/partition. ::</span> |
| |
| <span class="sd"> CREATE TABLE hive_stats (</span> |
| <span class="sd"> ds VARCHAR(16),</span> |
| <span class="sd"> table_name VARCHAR(500),</span> |
| <span class="sd"> metric VARCHAR(200),</span> |
| <span class="sd"> value BIGINT</span> |
| <span class="sd"> );</span> |
| |
| <span class="sd"> :param table: the source table, in the format ``database.table_name``. (templated)</span> |
| <span class="sd"> :type table: str</span> |
| <span class="sd"> :param partition: the source partition. (templated)</span> |
| <span class="sd"> :type partition: dict of {col:value}</span> |
| <span class="sd"> :param extra_exprs: dict of expression to run against the table where</span> |
| <span class="sd"> keys are metric names and values are Presto compatible expressions</span> |
| <span class="sd"> :type extra_exprs: dict</span> |
| <span class="sd"> :param col_blacklist: list of columns to blacklist, consider</span> |
| <span class="sd"> blacklisting blobs, large json columns, ...</span> |
| <span class="sd"> :type col_blacklist: list</span> |
| <span class="sd"> :param assignment_func: a function that receives a column name and</span> |
| <span class="sd"> a type, and returns a dict of metric names and an Presto expressions.</span> |
| <span class="sd"> If None is returned, the global defaults are applied. If an</span> |
| <span class="sd"> empty dictionary is returned, no stats are computed for that</span> |
| <span class="sd"> column.</span> |
| <span class="sd"> :type assignment_func: function</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="HiveStatsCollectionOperator.template_fields"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_stats_operator/index.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'table'</span><span class="p">,</span> <span class="s1">'partition'</span><span class="p">,</span> <span class="s1">'ds'</span><span class="p">,</span> <span class="s1">'dttm'</span><span class="p">)</span></div> |
| <div class="viewcode-block" id="HiveStatsCollectionOperator.ui_color"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_stats_operator/index.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#aff7a6'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">table</span><span class="p">,</span> |
| <span class="n">partition</span><span class="p">,</span> |
| <span class="n">extra_exprs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">col_blacklist</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">assignment_func</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">metastore_conn_id</span><span class="o">=</span><span class="s1">'metastore_default'</span><span class="p">,</span> |
| <span class="n">presto_conn_id</span><span class="o">=</span><span class="s1">'presto_default'</span><span class="p">,</span> |
| <span class="n">mysql_conn_id</span><span class="o">=</span><span class="s1">'airflow_db'</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">HiveStatsCollectionOperator</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">table</span> <span class="o">=</span> <span class="n">table</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">partition</span> <span class="o">=</span> <span class="n">partition</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">extra_exprs</span> <span class="o">=</span> <span class="n">extra_exprs</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">col_blacklist</span> <span class="o">=</span> <span class="n">col_blacklist</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span> <span class="o">=</span> <span class="n">metastore_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">presto_conn_id</span> <span class="o">=</span> <span class="n">presto_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span> <span class="o">=</span> <span class="n">mysql_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">assignment_func</span> <span class="o">=</span> <span class="n">assignment_func</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">ds</span> <span class="o">=</span> <span class="s1">'{{ ds }}'</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dttm</span> <span class="o">=</span> <span class="s1">'{{ execution_date.isoformat() }}'</span> |
| |
| <div class="viewcode-block" id="HiveStatsCollectionOperator.get_default_exprs"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_stats_operator/index.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator.get_default_exprs">[docs]</a> <span class="k">def</span> <span class="nf">get_default_exprs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">col</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">col_blacklist</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">{}</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="p">{(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'non_null'</span><span class="p">):</span> <span class="s2">"COUNT(</span><span class="si">{col}</span><span class="s2">)"</span><span class="p">}</span> |
| <span class="k">if</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'double'</span><span class="p">,</span> <span class="s1">'int'</span><span class="p">,</span> <span class="s1">'bigint'</span><span class="p">,</span> <span class="s1">'float'</span><span class="p">,</span> <span class="s1">'double'</span><span class="p">]:</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'sum'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(</span><span class="si">{col}</span><span class="s1">)'</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'min'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'MIN(</span><span class="si">{col}</span><span class="s1">)'</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'MAX(</span><span class="si">{col}</span><span class="s1">)'</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'avg'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'AVG(</span><span class="si">{col}</span><span class="s1">)'</span> |
| <span class="k">elif</span> <span class="n">col_type</span> <span class="o">==</span> <span class="s1">'boolean'</span><span class="p">:</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'true'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CASE WHEN </span><span class="si">{col}</span><span class="s1"> THEN 1 ELSE 0 END)'</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'false'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CASE WHEN NOT </span><span class="si">{col}</span><span class="s1"> THEN 1 ELSE 0 END)'</span> |
| <span class="k">elif</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'string'</span><span class="p">]:</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'len'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'SUM(CAST(LENGTH(</span><span class="si">{col}</span><span class="s1">) AS BIGINT))'</span> |
| <span class="n">d</span><span class="p">[(</span><span class="n">col</span><span class="p">,</span> <span class="s1">'approx_distinct'</span><span class="p">)]</span> <span class="o">=</span> <span class="s1">'APPROX_DISTINCT(</span><span class="si">{col}</span><span class="s1">)'</span> |
| |
| <span class="k">return</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">col</span><span class="o">=</span><span class="n">col</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">d</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span></div> |
| |
| <div class="viewcode-block" id="HiveStatsCollectionOperator.execute"><a class="viewcode-back" href="../../../_api/airflow/operators/hive_stats_operator/index.html#airflow.operators.hive_stats_operator.HiveStatsCollectionOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">metastore</span> <span class="o">=</span> <span class="n">HiveMetastoreHook</span><span class="p">(</span><span class="n">metastore_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">metastore_conn_id</span><span class="p">)</span> |
| <span class="n">table</span> <span class="o">=</span> <span class="n">metastore</span><span class="o">.</span><span class="n">get_table</span><span class="p">(</span><span class="n">table_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">)</span> |
| <span class="n">field_types</span> <span class="o">=</span> <span class="p">{</span><span class="n">col</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">col</span><span class="o">.</span><span class="n">type</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">table</span><span class="o">.</span><span class="n">sd</span><span class="o">.</span><span class="n">cols</span><span class="p">}</span> |
| |
| <span class="n">exprs</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="p">(</span><span class="s1">''</span><span class="p">,</span> <span class="s1">'count'</span><span class="p">):</span> <span class="s1">'COUNT(*)'</span> |
| <span class="p">}</span> |
| <span class="k">for</span> <span class="n">col</span><span class="p">,</span> <span class="n">col_type</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="n">field_types</span><span class="o">.</span><span class="n">items</span><span class="p">()):</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">assignment_func</span><span class="p">:</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">assignment_func</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">d</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_default_exprs</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_default_exprs</span><span class="p">(</span><span class="n">col</span><span class="p">,</span> <span class="n">col_type</span><span class="p">)</span> |
| <span class="n">exprs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">d</span><span class="p">)</span> |
| <span class="n">exprs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">extra_exprs</span><span class="p">)</span> |
| <span class="n">exprs</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">(</span><span class="n">exprs</span><span class="p">)</span> |
| <span class="n">exprs_str</span> <span class="o">=</span> <span class="s2">",</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">([</span> |
| <span class="n">v</span> <span class="o">+</span> <span class="s2">" AS "</span> <span class="o">+</span> <span class="n">k</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s1">'__'</span> <span class="o">+</span> <span class="n">k</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">exprs</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span> |
| |
| <span class="n">where_clause</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"</span><span class="si">{0}</span><span class="s2"> = '</span><span class="si">{1}</span><span class="s2">'"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="o">.</span><span class="n">items</span><span class="p">()]</span> |
| <span class="n">where_clause</span> <span class="o">=</span> <span class="s2">" AND</span><span class="se">\n</span><span class="s2"> "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">where_clause</span><span class="p">)</span> |
| <span class="n">sql</span> <span class="o">=</span> <span class="s2">"SELECT </span><span class="si">{exprs_str}</span><span class="s2"> FROM </span><span class="si">{table}</span><span class="s2"> WHERE </span><span class="si">{where_clause}</span><span class="s2">;"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">exprs_str</span><span class="o">=</span><span class="n">exprs_str</span><span class="p">,</span> <span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">where_clause</span><span class="o">=</span><span class="n">where_clause</span><span class="p">)</span> |
| |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">PrestoHook</span><span class="p">(</span><span class="n">presto_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">presto_conn_id</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">'Executing SQL check: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">sql</span><span class="p">)</span> |
| <span class="n">row</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_first</span><span class="p">(</span><span class="n">hql</span><span class="o">=</span><span class="n">sql</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">"Record: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">row</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">row</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"The query returned None"</span><span class="p">)</span> |
| |
| <span class="n">part_json</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="p">,</span> <span class="n">sort_keys</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Deleting rows from previous runs if they exist"</span><span class="p">)</span> |
| <span class="n">mysql</span> <span class="o">=</span> <span class="n">MySqlHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span><span class="p">)</span> |
| <span class="n">sql</span> <span class="o">=</span> <span class="s2">"""</span> |
| <span class="s2"> SELECT 1 FROM hive_stats</span> |
| <span class="s2"> WHERE</span> |
| <span class="s2"> table_name='</span><span class="si">{table}</span><span class="s2">' AND</span> |
| <span class="s2"> partition_repr='</span><span class="si">{part_json}</span><span class="s2">' AND</span> |
| <span class="s2"> dttm='</span><span class="si">{dttm}</span><span class="s2">'</span> |
| <span class="s2"> LIMIT 1;</span> |
| <span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">part_json</span><span class="o">=</span><span class="n">part_json</span><span class="p">,</span> <span class="n">dttm</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dttm</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">mysql</span><span class="o">.</span><span class="n">get_records</span><span class="p">(</span><span class="n">sql</span><span class="p">):</span> |
| <span class="n">sql</span> <span class="o">=</span> <span class="s2">"""</span> |
| <span class="s2"> DELETE FROM hive_stats</span> |
| <span class="s2"> WHERE</span> |
| <span class="s2"> table_name='</span><span class="si">{table}</span><span class="s2">' AND</span> |
| <span class="s2"> partition_repr='</span><span class="si">{part_json}</span><span class="s2">' AND</span> |
| <span class="s2"> dttm='</span><span class="si">{dttm}</span><span class="s2">';</span> |
| <span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">part_json</span><span class="o">=</span><span class="n">part_json</span><span class="p">,</span> <span class="n">dttm</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dttm</span><span class="p">)</span> |
| <span class="n">mysql</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">sql</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">"Pivoting and loading cells into the Airflow db"</span><span class="p">)</span> |
| <span class="n">rows</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ds</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">dttm</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">,</span> <span class="n">part_json</span><span class="p">)</span> <span class="o">+</span> |
| <span class="p">(</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span> <span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| <span class="k">for</span> <span class="n">r</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">exprs</span><span class="p">,</span> <span class="n">row</span><span class="p">)]</span> |
| <span class="n">mysql</span><span class="o">.</span><span class="n">insert_rows</span><span class="p">(</span> |
| <span class="n">table</span><span class="o">=</span><span class="s1">'hive_stats'</span><span class="p">,</span> |
| <span class="n">rows</span><span class="o">=</span><span class="n">rows</span><span class="p">,</span> |
| <span class="n">target_fields</span><span class="o">=</span><span class="p">[</span> |
| <span class="s1">'ds'</span><span class="p">,</span> |
| <span class="s1">'dttm'</span><span class="p">,</span> |
| <span class="s1">'table_name'</span><span class="p">,</span> |
| <span class="s1">'partition_repr'</span><span class="p">,</span> |
| <span class="s1">'col'</span><span class="p">,</span> |
| <span class="s1">'metric'</span><span class="p">,</span> |
| <span class="s1">'value'</span><span class="p">,</span></div></div> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| </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. |
| <script type="text/javascript"> |
| (function() { |
| var ga = document.createElement('script'); |
| ga.src = ('https:' == document.location.protocol ? |
| 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
| ga.setAttribute('async', 'true'); |
| var nodes = document.documentElement.childNodes; |
| var i = -1; |
| var node; |
| do { |
| i++; |
| node = nodes[i] |
| } while(node.nodeType !== Node.ELEMENT_NODE); |
| node.appendChild(ga); |
| })(); |
| </script> |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |