You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ma...@apache.org on 2016/06/05 05:24:10 UTC
[20/34] incubator-airflow-site git commit: Initial commit
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/9e19165c/_modules/sensors.html
----------------------------------------------------------------------
diff --git a/_modules/sensors.html b/_modules/sensors.html
new file mode 100644
index 0000000..7f4b8ec
--- /dev/null
+++ b/_modules/sensors.html
@@ -0,0 +1,721 @@
+
+
+<!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>sensors — Airflow Documentation</title>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+
+
+
+
+
+ <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="../configuration.html">Configuration</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="../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>sensors</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 sensors</h1><div class="highlight"><pre>
+<span></span><span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
+<span class="kn">from</span> <span class="nn">future</span> <span class="kn">import</span> <span class="n">standard_library</span>
+<span class="n">standard_library</span><span class="o">.</span><span class="n">install_aliases</span><span class="p">()</span>
+<span class="kn">from</span> <span class="nn">builtins</span> <span class="kn">import</span> <span class="nb">str</span>
+<span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span>
+<span class="kn">import</span> <span class="nn">logging</span>
+<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">urlparse</span>
+<span class="kn">from</span> <span class="nn">time</span> <span class="kn">import</span> <span class="n">sleep</span>
+
+<span class="kn">from</span> <span class="nn">airflow</span> <span class="kn">import</span> <span class="n">hooks</span><span class="p">,</span> <span class="n">settings</span>
+<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="kn">import</span> <span class="n">AirflowException</span><span class="p">,</span> <span class="n">AirflowSensorTimeout</span><span class="p">,</span> <span class="n">AirflowSkipException</span>
+<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span><span class="p">,</span> <span class="n">TaskInstance</span><span class="p">,</span> <span class="n">Connection</span> <span class="k">as</span> <span class="n">DB</span>
+<span class="kn">from</span> <span class="nn">airflow.hooks</span> <span class="kn">import</span> <span class="n">BaseHook</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.state</span> <span class="kn">import</span> <span class="n">State</span>
+<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span>
+
+
+<span class="k">class</span> <span class="nc">BaseSensorOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
+ <span class="sd">'''</span>
+<span class="sd"> Sensor operators are derived from this class an inherit these attributes.</span>
+
+<span class="sd"> Sensor operators keep executing at a time interval and succeed when</span>
+<span class="sd"> a criteria is met and fail if and when they time out.</span>
+
+<span class="sd"> :param soft_fail: Set to true to mark the task as SKIPPED on failure</span>
+<span class="sd"> :type soft_fail: bool</span>
+<span class="sd"> :param poke_interval: Time in seconds that the job should wait in</span>
+<span class="sd"> between each tries</span>
+<span class="sd"> :type poke_interval: int</span>
+<span class="sd"> :param timeout: Time, in seconds before the task times out and fails.</span>
+<span class="sd"> :type timeout: int</span>
+<span class="sd"> '''</span>
+ <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#e6f1f2'</span>
+
+ <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">poke_interval</span><span class="o">=</span><span class="mi">60</span><span class="p">,</span>
+ <span class="n">timeout</span><span class="o">=</span><span class="mi">60</span><span class="o">*</span><span class="mi">60</span><span class="o">*</span><span class="mi">24</span><span class="o">*</span><span class="mi">7</span><span class="p">,</span>
+ <span class="n">soft_fail</span><span class="o">=</span><span class="bp">False</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">BaseSensorOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">poke_interval</span> <span class="o">=</span> <span class="n">poke_interval</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">soft_fail</span> <span class="o">=</span> <span class="n">soft_fail</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">timeout</span> <span class="o">=</span> <span class="n">timeout</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="sd">'''</span>
+<span class="sd"> Function that the sensors defined while deriving this class should</span>
+<span class="sd"> override.</span>
+<span class="sd"> '''</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Override me.'</span><span class="p">)</span>
+
+ <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="p">):</span>
+ <span class="n">started_at</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span>
+ <span class="k">while</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">poke</span><span class="p">(</span><span class="n">context</span><span class="p">):</span>
+ <span class="n">sleep</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">poke_interval</span><span class="p">)</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span> <span class="o">-</span> <span class="n">started_at</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">timeout</span><span class="p">:</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">soft_fail</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowSkipException</span><span class="p">(</span><span class="s1">'Snap. Time is OUT.'</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowSensorTimeout</span><span class="p">(</span><span class="s1">'Snap. Time is OUT.'</span><span class="p">)</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"Success criteria met. Exiting."</span><span class="p">)</span>
+
+
+<div class="viewcode-block" id="SqlSensor"><a class="viewcode-back" href="../code.html#airflow.operators.SqlSensor">[docs]</a><span class="k">class</span> <span class="nc">SqlSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Runs a sql statement until a criteria is met. It will keep trying until</span>
+<span class="sd"> sql returns no row, or if the first cell in (0, '0', '').</span>
+
+<span class="sd"> :param conn_id: The connection to run the sensor against</span>
+<span class="sd"> :type conn_id: string</span>
+<span class="sd"> :param sql: The sql to run. To pass, it needs to return at least one cell</span>
+<span class="sd"> that contains a non-zero / empty string value.</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,)</span>
+ <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.hql'</span><span class="p">,</span> <span class="s1">'.sql'</span><span class="p">,)</span>
+
+ <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">conn_id</span><span class="p">,</span> <span class="n">sql</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">sql</span> <span class="o">=</span> <span class="n">sql</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">conn_id</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">SqlSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">hook</span> <span class="o">=</span> <span class="n">BaseHook</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">get_hook</span><span class="p">()</span>
+
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Poking: '</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">)</span>
+ <span class="n">records</span> <span class="o">=</span> <span class="n">hook</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">sql</span><span class="p">)</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">records</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">False</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">if</span> <span class="nb">str</span><span class="p">(</span><span class="n">records</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="ow">in</span> <span class="p">(</span><span class="s1">'0'</span><span class="p">,</span> <span class="s1">''</span><span class="p">,):</span>
+ <span class="k">return</span> <span class="bp">False</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">True</span>
+ <span class="k">print</span><span class="p">(</span><span class="n">records</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span></div>
+
+
+<div class="viewcode-block" id="MetastorePartitionSensor"><a class="viewcode-back" href="../code.html#airflow.operators.MetastorePartitionSensor">[docs]</a><span class="k">class</span> <span class="nc">MetastorePartitionSensor</span><span class="p">(</span><span class="n">SqlSensor</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> An alternative to the HivePartitionSensor that talk directly to the</span>
+<span class="sd"> MySQL db. This was created as a result of observing sub optimal</span>
+<span class="sd"> queries generated by the Metastore thrift service when hitting</span>
+<span class="sd"> subpartitioned tables. The Thrift service's queries were written in a</span>
+<span class="sd"> way that wouldn't leverage the indexes.</span>
+
+<span class="sd"> :param schema: the schema</span>
+<span class="sd"> :type schema: str</span>
+<span class="sd"> :param table: the table</span>
+<span class="sd"> :type table: str</span>
+<span class="sd"> :param partition_name: the partition name, as defined in the PARTITIONS</span>
+<span class="sd"> table of the Metastore. Order of the fields does matter.</span>
+<span class="sd"> Examples: ``ds=2016-01-01`` or</span>
+<span class="sd"> ``ds=2016-01-01/sub=foo`` for a sub partitioned table</span>
+<span class="sd"> :type partition_name: str</span>
+<span class="sd"> :param mysql_conn_id: a reference to the MySQL conn_id for the metastore</span>
+<span class="sd"> :type mysql_conn_id: str</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'partition_name'</span><span class="p">,</span> <span class="s1">'table'</span><span class="p">,</span> <span class="s1">'schema'</span><span class="p">)</span>
+
+ <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_name</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="s2">"default"</span><span class="p">,</span>
+ <span class="n">mysql_conn_id</span><span class="o">=</span><span class="s2">"metastore_mysql"</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">partition_name</span> <span class="o">=</span> <span class="n">partition_name</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">schema</span> <span class="o">=</span> <span class="n">schema</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">first_poke</span> <span class="o">=</span> <span class="bp">True</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">mysql_conn_id</span>
+ <span class="nb">super</span><span class="p">(</span><span class="n">SqlSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">first_poke</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">first_poke</span> <span class="o">=</span> <span class="bp">False</span>
+ <span class="k">if</span> <span class="s1">'.'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">schema</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="bp">self</span><span class="o">.</span><span class="n">table</span><span class="o">.</span><span class="n">split</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">sql</span> <span class="o">=</span> <span class="s2">"""</span>
+<span class="s2"> SELECT 'X'</span>
+<span class="s2"> FROM PARTITIONS A0</span>
+<span class="s2"> LEFT OUTER JOIN TBLS B0 ON A0.TBL_ID = B0.TBL_ID</span>
+<span class="s2"> LEFT OUTER JOIN DBS C0 ON B0.DB_ID = C0.DB_ID</span>
+<span class="s2"> WHERE</span>
+<span class="s2"> B0.TBL_NAME = '{self.table}' AND</span>
+<span class="s2"> C0.NAME = '{self.schema}' AND</span>
+<span class="s2"> A0.PART_NAME = '{self.partition_name}';</span>
+<span class="s2"> """</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">=</span><span class="bp">self</span><span class="p">)</span>
+ <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">MetastorePartitionSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">poke</span><span class="p">(</span><span class="n">context</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="ExternalTaskSensor"><a class="viewcode-back" href="../code.html#airflow.operators.ExternalTaskSensor">[docs]</a><span class="k">class</span> <span class="nc">ExternalTaskSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a task to complete in a different DAG</span>
+
+<span class="sd"> :param external_dag_id: The dag_id that contains the task you want to</span>
+<span class="sd"> wait for</span>
+<span class="sd"> :type external_dag_id: string</span>
+<span class="sd"> :param external_task_id: The task_id that contains the task you want to</span>
+<span class="sd"> wait for</span>
+<span class="sd"> :type external_task_id: string</span>
+<span class="sd"> :param allowed_states: list of allowed states, default is ``['success']``</span>
+<span class="sd"> :type allowed_states: list</span>
+<span class="sd"> :param execution_delta: time difference with the previous execution to</span>
+<span class="sd"> look at, the default is the same execution_date as the current task.</span>
+<span class="sd"> For yesterday, use [positive!] datetime.timedelta(days=1)</span>
+<span class="sd"> :type execution_delta: datetime.timedelta</span>
+<span class="sd"> """</span>
+
+ <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">external_dag_id</span><span class="p">,</span>
+ <span class="n">external_task_id</span><span class="p">,</span>
+ <span class="n">allowed_states</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">execution_delta</span><span class="o">=</span><span class="bp">None</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">ExternalTaskSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">allowed_states</span> <span class="o">=</span> <span class="n">allowed_states</span> <span class="ow">or</span> <span class="p">[</span><span class="n">State</span><span class="o">.</span><span class="n">SUCCESS</span><span class="p">]</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">execution_delta</span> <span class="o">=</span> <span class="n">execution_delta</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">external_dag_id</span> <span class="o">=</span> <span class="n">external_dag_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">external_task_id</span> <span class="o">=</span> <span class="n">external_task_id</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">execution_delta</span><span class="p">:</span>
+ <span class="n">dttm</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">'execution_date'</span><span class="p">]</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">execution_delta</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">dttm</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">'execution_date'</span><span class="p">]</span>
+
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Poking for '</span>
+ <span class="s1">'{self.external_dag_id}.'</span>
+ <span class="s1">'{self.external_task_id} on '</span>
+ <span class="s1">'{dttm} ... '</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">TI</span> <span class="o">=</span> <span class="n">TaskInstance</span>
+
+ <span class="n">session</span> <span class="o">=</span> <span class="n">settings</span><span class="o">.</span><span class="n">Session</span><span class="p">()</span>
+ <span class="n">count</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">TI</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span>
+ <span class="n">TI</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">external_dag_id</span><span class="p">,</span>
+ <span class="n">TI</span><span class="o">.</span><span class="n">task_id</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">external_task_id</span><span class="p">,</span>
+ <span class="n">TI</span><span class="o">.</span><span class="n">state</span><span class="o">.</span><span class="n">in_</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">allowed_states</span><span class="p">),</span>
+ <span class="n">TI</span><span class="o">.</span><span class="n">execution_date</span> <span class="o">==</span> <span class="n">dttm</span><span class="p">,</span>
+ <span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">()</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
+ <span class="k">return</span> <span class="n">count</span></div>
+
+
+<div class="viewcode-block" id="HivePartitionSensor"><a class="viewcode-back" href="../code.html#airflow.operators.HivePartitionSensor">[docs]</a><span class="k">class</span> <span class="nc">HivePartitionSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a partition to show up in Hive</span>
+
+<span class="sd"> :param table: The name of the table to wait for, supports the dot</span>
+<span class="sd"> notation (my_database.my_table)</span>
+<span class="sd"> :type table: string</span>
+<span class="sd"> :param partition: The partition clause to wait for. This is passed as</span>
+<span class="sd"> is to the Metastore Thrift client "get_partitions_by_filter" method,</span>
+<span class="sd"> and apparently supports SQL like notation as in `ds='2015-01-01'</span>
+<span class="sd"> AND type='value'` and > < sings as in "ds>=2015-01-01"</span>
+<span class="sd"> :type partition: string</span>
+<span class="sd"> :param metastore_conn_id: reference to the metastore thrift service</span>
+<span class="sd"> connection id</span>
+<span class="sd"> :type metastore_conn_id: str</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'schema'</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="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="o">=</span><span class="s2">"ds='{{ ds }}'"</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">schema</span><span class="o">=</span><span class="s1">'default'</span><span class="p">,</span>
+ <span class="n">poke_interval</span><span class="o">=</span><span class="mi">60</span><span class="o">*</span><span class="mi">3</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">HivePartitionSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span>
+ <span class="n">poke_interval</span><span class="o">=</span><span class="n">poke_interval</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="k">if</span> <span class="ow">not</span> <span class="n">partition</span><span class="p">:</span>
+ <span class="n">partition</span> <span class="o">=</span> <span class="s2">"ds='{{ ds }}'"</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">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">schema</span> <span class="o">=</span> <span class="n">schema</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="k">if</span> <span class="s1">'.'</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">table</span><span class="p">:</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">schema</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="bp">self</span><span class="o">.</span><span class="n">table</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Poking for table {self.schema}.{self.table}, '</span>
+ <span class="s1">'partition {self.partition}'</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="k">if</span> <span class="ow">not</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">'hook'</span><span class="p">):</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">hooks</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="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">check_for_partition</span><span class="p">(</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">schema</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="bp">self</span><span class="o">.</span><span class="n">partition</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="HdfsSensor"><a class="viewcode-back" href="../code.html#airflow.operators.HdfsSensor">[docs]</a><span class="k">class</span> <span class="nc">HdfsSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a file or folder to land in HDFS</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'filepath'</span><span class="p">,)</span>
+
+ <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">filepath</span><span class="p">,</span>
+ <span class="n">hdfs_conn_id</span><span class="o">=</span><span class="s1">'hdfs_default'</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">HdfsSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">filepath</span> <span class="o">=</span> <span class="n">filepath</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">hdfs_conn_id</span> <span class="o">=</span> <span class="n">hdfs_conn_id</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">sb</span> <span class="o">=</span> <span class="n">hooks</span><span class="o">.</span><span class="n">HDFSHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hdfs_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="s2">"snakebite"</span><span class="p">)</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">WARNING</span><span class="p">)</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Poking for file {self.filepath} '</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="k">try</span><span class="p">:</span>
+ <span class="n">files</span> <span class="o">=</span> <span class="p">[</span><span class="n">f</span> <span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">sb</span><span class="o">.</span><span class="n">ls</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">filepath</span><span class="p">])]</span>
+ <span class="k">except</span><span class="p">:</span>
+ <span class="k">return</span> <span class="bp">False</span>
+ <span class="k">return</span> <span class="bp">True</span></div>
+
+
+<div class="viewcode-block" id="WebHdfsSensor"><a class="viewcode-back" href="../code.html#airflow.operators.WebHdfsSensor">[docs]</a><span class="k">class</span> <span class="nc">WebHdfsSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a file or folder to land in HDFS</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'filepath'</span><span class="p">,)</span>
+
+ <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">filepath</span><span class="p">,</span>
+ <span class="n">webhdfs_conn_id</span><span class="o">=</span><span class="s1">'webhdfs_default'</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">WebHdfsSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">filepath</span> <span class="o">=</span> <span class="n">filepath</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">webhdfs_conn_id</span> <span class="o">=</span> <span class="n">webhdfs_conn_id</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">c</span> <span class="o">=</span> <span class="n">hooks</span><span class="o">.</span><span class="n">WebHDFSHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">webhdfs_conn_id</span><span class="p">)</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Poking for file {self.filepath} '</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="k">return</span> <span class="n">c</span><span class="o">.</span><span class="n">check_for_path</span><span class="p">(</span><span class="n">hdfs_path</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">filepath</span><span class="p">)</span></div>
+
+
+<div class="viewcode-block" id="S3KeySensor"><a class="viewcode-back" href="../code.html#airflow.operators.S3KeySensor">[docs]</a><span class="k">class</span> <span class="nc">S3KeySensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a key (a file-like instance on S3) to be present in a S3 bucket.</span>
+<span class="sd"> S3 being a key/value it does not support folders. The path is just a key</span>
+<span class="sd"> a resource.</span>
+
+<span class="sd"> :param bucket_key: The key being waited on. Supports full s3:// style url</span>
+<span class="sd"> or relative path from root level.</span>
+<span class="sd"> :type bucket_key: str</span>
+<span class="sd"> :param bucket_name: Name of the S3 bucket</span>
+<span class="sd"> :type bucket_name: str</span>
+<span class="sd"> :param wildcard_match: whether the bucket_key should be interpreted as a</span>
+<span class="sd"> Unix wildcard pattern</span>
+<span class="sd"> :type wildcard_match: bool</span>
+<span class="sd"> :param s3_conn_id: a reference to the s3 connection</span>
+<span class="sd"> :type s3_conn_id: str</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'bucket_key'</span><span class="p">,</span> <span class="s1">'bucket_name'</span><span class="p">)</span>
+
+ <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">bucket_key</span><span class="p">,</span>
+ <span class="n">bucket_name</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">wildcard_match</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
+ <span class="n">s3_conn_id</span><span class="o">=</span><span class="s1">'s3_default'</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">S3KeySensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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="n">session</span> <span class="o">=</span> <span class="n">settings</span><span class="o">.</span><span class="n">Session</span><span class="p">()</span>
+ <span class="n">db</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">DB</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">DB</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">==</span> <span class="n">s3_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">db</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"conn_id doesn't exist in the repository"</span><span class="p">)</span>
+ <span class="c1"># Parse</span>
+ <span class="k">if</span> <span class="n">bucket_name</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
+ <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">bucket_key</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="o">==</span> <span class="s1">''</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Please provide a bucket_name'</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">bucket_name</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span>
+ <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s1">'/'</span><span class="p">:</span>
+ <span class="n">bucket_key</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="p">[</span><span class="mi">1</span><span class="p">:]</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="n">bucket_key</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span> <span class="o">=</span> <span class="n">bucket_name</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">bucket_key</span> <span class="o">=</span> <span class="n">bucket_key</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">wildcard_match</span> <span class="o">=</span> <span class="n">wildcard_match</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span> <span class="o">=</span> <span class="n">s3_conn_id</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">hook</span> <span class="o">=</span> <span class="n">hooks</span><span class="o">.</span><span class="n">S3Hook</span><span class="p">(</span><span class="n">s3_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span><span class="p">)</span>
+ <span class="n">full_url</span> <span class="o">=</span> <span class="s2">"s3://"</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span> <span class="o">+</span> <span class="s2">"/"</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">bucket_key</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Poking for key : {full_url}'</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">wildcard_match</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">check_for_wildcard_key</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket_key</span><span class="p">,</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span><span class="p">)</span>
+ <span class="k">else</span><span class="p">:</span>
+ <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">check_for_key</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket_key</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span><span class="p">)</span></div>
+
+
+<span class="k">class</span> <span class="nc">S3PrefixSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a prefix to exist. A prefix is the first part of a key,</span>
+<span class="sd"> thus enabling checking of constructs similar to glob airfl* or</span>
+<span class="sd"> SQL LIKE 'airfl%'. There is the possibility to precise a delimiter to</span>
+<span class="sd"> indicate the hierarchy or keys, meaning that the match will stop at that</span>
+<span class="sd"> delimiter. Current code accepts sane delimiters, i.e. characters that</span>
+<span class="sd"> are NOT special characters in the Python regex engine.</span>
+
+<span class="sd"> :param bucket_name: Name of the S3 bucket</span>
+<span class="sd"> :type bucket_name: str</span>
+<span class="sd"> :param prefix: The prefix being waited on. Relative path from bucket root level.</span>
+<span class="sd"> :type prefix: str</span>
+<span class="sd"> :param delimiter: The delimiter intended to show hierarchy.</span>
+<span class="sd"> Defaults to '/'.</span>
+<span class="sd"> :type delimiter: str</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'prefix'</span><span class="p">,</span> <span class="s1">'bucket_name'</span><span class="p">)</span>
+
+ <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">bucket_name</span><span class="p">,</span>
+ <span class="n">prefix</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">'/'</span><span class="p">,</span>
+ <span class="n">s3_conn_id</span><span class="o">=</span><span class="s1">'s3_default'</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">S3PrefixSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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="n">session</span> <span class="o">=</span> <span class="n">settings</span><span class="o">.</span><span class="n">Session</span><span class="p">()</span>
+ <span class="n">db</span> <span class="o">=</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">DB</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">DB</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">==</span> <span class="n">s3_conn_id</span><span class="p">)</span><span class="o">.</span><span class="n">first</span><span class="p">()</span>
+ <span class="k">if</span> <span class="ow">not</span> <span class="n">db</span><span class="p">:</span>
+ <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s2">"conn_id doesn't exist in the repository"</span><span class="p">)</span>
+ <span class="c1"># Parse</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span> <span class="o">=</span> <span class="n">bucket_name</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">prefix</span> <span class="o">=</span> <span class="n">prefix</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span> <span class="o">=</span> <span class="n">delimiter</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">full_url</span> <span class="o">=</span> <span class="s2">"s3://"</span> <span class="o">+</span> <span class="n">bucket_name</span> <span class="o">+</span> <span class="s1">'/'</span> <span class="o">+</span> <span class="n">prefix</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span> <span class="o">=</span> <span class="n">s3_conn_id</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span>
+ <span class="n">session</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Poking for prefix : {self.prefix}</span><span class="se">\n</span><span class="s1">'</span>
+ <span class="s1">'in bucket s3://{self.bucket_name}'</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">hook</span> <span class="o">=</span> <span class="n">hooks</span><span class="o">.</span><span class="n">S3Hook</span><span class="p">(</span><span class="n">s3_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">s3_conn_id</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">check_for_prefix</span><span class="p">(</span>
+ <span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span>
+ <span class="n">delimiter</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delimiter</span><span class="p">,</span>
+ <span class="n">bucket_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket_name</span><span class="p">)</span>
+
+
+<div class="viewcode-block" id="TimeSensor"><a class="viewcode-back" href="../code.html#airflow.operators.TimeSensor">[docs]</a><span class="k">class</span> <span class="nc">TimeSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits until the specified time of the day.</span>
+
+<span class="sd"> :param target_time: time after which the job succeeds</span>
+<span class="sd"> :type target_time: datetime.time</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">()</span>
+
+ <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">target_time</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">TimeSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">target_time</span> <span class="o">=</span> <span class="n">target_time</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
+ <span class="s1">'Checking if the time ({0}) has come'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">target_time</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">target_time</span></div>
+
+
+<span class="k">class</span> <span class="nc">TimeDeltaSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Waits for a timedelta after the task's execution_date + schedule_interval.</span>
+<span class="sd"> In Airflow, the daily task stamped with ``execution_date``</span>
+<span class="sd"> 2016-01-01 can only start running on 2016-01-02. The timedelta here</span>
+<span class="sd"> represents the time after the execution period has closed.</span>
+
+<span class="sd"> :param delta: time length to wait after execution_date before succeeding</span>
+<span class="sd"> :type delta: datetime.timedelta</span>
+<span class="sd"> """</span>
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">()</span>
+
+ <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">delta</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">TimeDeltaSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">delta</span> <span class="o">=</span> <span class="n">delta</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">dag</span> <span class="o">=</span> <span class="n">context</span><span class="p">[</span><span class="s1">'dag'</span><span class="p">]</span>
+ <span class="n">target_dttm</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">following_schedule</span><span class="p">(</span><span class="n">context</span><span class="p">[</span><span class="s1">'execution_date'</span><span class="p">])</span>
+ <span class="n">target_dttm</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">delta</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Checking if the time ({0}) has come'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">target_dttm</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span> <span class="o">></span> <span class="n">target_dttm</span>
+
+
+<div class="viewcode-block" id="HttpSensor"><a class="viewcode-back" href="../code.html#airflow.operators.HttpSensor">[docs]</a><span class="k">class</span> <span class="nc">HttpSensor</span><span class="p">(</span><span class="n">BaseSensorOperator</span><span class="p">):</span>
+ <span class="sd">"""</span>
+<span class="sd"> Executes a HTTP get statement and returns False on failure:</span>
+<span class="sd"> 404 not found or response_check function returned False</span>
+
+<span class="sd"> :param http_conn_id: The connection to run the sensor against</span>
+<span class="sd"> :type http_conn_id: string</span>
+<span class="sd"> :param endpoint: The relative part of the full url</span>
+<span class="sd"> :type endpoint: string</span>
+<span class="sd"> :param params: The parameters to be added to the GET url</span>
+<span class="sd"> :type params: a dictionary of string key/value pairs</span>
+<span class="sd"> :param headers: The HTTP headers to be added to the GET request</span>
+<span class="sd"> :type headers: a dictionary of string key/value pairs</span>
+<span class="sd"> :param response_check: A check against the 'requests' response object.</span>
+<span class="sd"> Returns True for 'pass' and False otherwise.</span>
+<span class="sd"> :type response_check: A lambda or defined function.</span>
+<span class="sd"> :param extra_options: Extra options for the 'requests' library, see the</span>
+<span class="sd"> 'requests' documentation (options to modify timeout, ssl, etc.)</span>
+<span class="sd"> :type extra_options: A dictionary of options, where key is string and value</span>
+<span class="sd"> depends on the option that's being modified.</span>
+<span class="sd"> """</span>
+
+ <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'endpoint'</span><span class="p">,)</span>
+
+ <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">endpoint</span><span class="p">,</span>
+ <span class="n">http_conn_id</span><span class="o">=</span><span class="s1">'http_default'</span><span class="p">,</span>
+ <span class="n">params</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">headers</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">response_check</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
+ <span class="n">extra_options</span><span class="o">=</span><span class="bp">None</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">HttpSensor</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__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">endpoint</span> <span class="o">=</span> <span class="n">endpoint</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">http_conn_id</span> <span class="o">=</span> <span class="n">http_conn_id</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">params</span> <span class="o">=</span> <span class="n">params</span> <span class="ow">or</span> <span class="p">{}</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">headers</span> <span class="o">=</span> <span class="n">headers</span> <span class="ow">or</span> <span class="p">{}</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">extra_options</span> <span class="o">=</span> <span class="n">extra_options</span> <span class="ow">or</span> <span class="p">{}</span>
+ <span class="bp">self</span><span class="o">.</span><span class="n">response_check</span> <span class="o">=</span> <span class="n">response_check</span>
+
+ <span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">hooks</span><span class="o">.</span><span class="n">HttpHook</span><span class="p">(</span><span class="n">method</span><span class="o">=</span><span class="s1">'GET'</span><span class="p">,</span> <span class="n">http_conn_id</span><span class="o">=</span><span class="n">http_conn_id</span><span class="p">)</span>
+
+ <span class="k">def</span> <span class="nf">poke</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span>
+ <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Poking: '</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">endpoint</span><span class="p">)</span>
+ <span class="k">try</span><span class="p">:</span>
+ <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</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">endpoint</span><span class="p">,</span>
+ <span class="n">data</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="p">,</span>
+ <span class="n">headers</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">headers</span><span class="p">,</span>
+ <span class="n">extra_options</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">extra_options</span><span class="p">)</span>
+ <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">response_check</span><span class="p">:</span>
+ <span class="c1"># run content check on response</span>
+ <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">response_check</span><span class="p">(</span><span class="n">response</span><span class="p">)</span>
+ <span class="k">except</span> <span class="n">AirflowException</span> <span class="k">as</span> <span class="n">ae</span><span class="p">:</span>
+ <span class="k">if</span> <span class="n">ae</span><span class="o">.</span><span class="n">message</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"404"</span><span class="p">):</span>
+ <span class="k">return</span> <span class="bp">False</span>
+
+ <span class="k">raise</span> <span class="n">ae</span>
+
+ <span class="k">return</span> <span class="bp">True</span></div>
+</pre></div>
+
+ </div>
+ </div>
+ <footer>
+
+
+ <hr/>
+
+ <div role="contentinfo">
+ <p>
+ © Copyright 2014, Maxime Beauchemin, Airbnb.
+
+ </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
+ };
+ </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