blob: 141409149c7adfd403625f05e64e1d2189aed57a [file] [log] [blame]
<!--
Javascript to render AIRFLOW-XXX and PR references in text
as HTML links.
Overrides extrahead block from sphinx_rtd_theme
https://www.sphinx-doc.org/en/master/templating.html
-->
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.models.dagbag &mdash; Airflow Documentation</title>
<link rel="shortcut icon" href="../../../_static/pin_32.png"/>
<script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/language_data.js"></script>
<script type="text/javascript" src="../../../_static/jira-links.js"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/graphviz.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/exampleinclude.css" type="text/css" />
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<script>
</script>
<style>
</style>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.8
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../cli.html">Command Line Interface Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../executor/index.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../api.html">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../errors.html">Error Tracking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dag-serialization.html">DAG Serialization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../best-practices.html">Best Practices</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../_api/index.html">Python API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configurations-ref.html">Configurations</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li><a href="../models.html">airflow.models</a> &raquo;</li>
<li>airflow.models.dagbag</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.models.dagbag</h1><div class="highlight"><pre>
<span></span><span class="c1"># -*- coding: utf-8 -*-</span>
<span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># &quot;License&quot;); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">division</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">unicode_literals</span>
<span class="kn">import</span> <span class="nn">hashlib</span>
<span class="kn">import</span> <span class="nn">imp</span>
<span class="kn">import</span> <span class="nn">importlib</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">textwrap</span>
<span class="kn">import</span> <span class="nn">zipfile</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">namedtuple</span>
<span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span>
<span class="kn">from</span> <span class="nn">croniter</span> <span class="kn">import</span> <span class="n">CroniterBadCronError</span><span class="p">,</span> <span class="n">CroniterBadDateError</span><span class="p">,</span> <span class="n">CroniterNotAlphaError</span><span class="p">,</span> <span class="n">croniter</span>
<span class="kn">import</span> <span class="nn">six</span>
<span class="kn">from</span> <span class="nn">airflow</span> <span class="kn">import</span> <span class="n">settings</span>
<span class="kn">from</span> <span class="nn">airflow.configuration</span> <span class="kn">import</span> <span class="n">conf</span>
<span class="kn">from</span> <span class="nn">airflow.dag.base_dag</span> <span class="kn">import</span> <span class="n">BaseDagBag</span>
<span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="kn">import</span> <span class="n">AirflowDagCycleException</span>
<span class="kn">from</span> <span class="nn">airflow.executors</span> <span class="kn">import</span> <span class="n">get_default_executor</span>
<span class="kn">from</span> <span class="nn">airflow.settings</span> <span class="kn">import</span> <span class="n">Stats</span>
<span class="kn">from</span> <span class="nn">airflow.utils</span> <span class="kn">import</span> <span class="n">timezone</span>
<span class="kn">from</span> <span class="nn">airflow.utils.dag_processing</span> <span class="kn">import</span> <span class="n">list_py_file_paths</span><span class="p">,</span> <span class="n">correct_maybe_zipped</span>
<span class="kn">from</span> <span class="nn">airflow.utils.db</span> <span class="kn">import</span> <span class="n">provide_session</span>
<span class="kn">from</span> <span class="nn">airflow.utils.helpers</span> <span class="kn">import</span> <span class="n">pprinttable</span>
<span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="kn">import</span> <span class="n">LoggingMixin</span>
<span class="kn">from</span> <span class="nn">airflow.utils.timeout</span> <span class="kn">import</span> <span class="n">timeout</span>
<div class="viewcode-block" id="DagBag"><a class="viewcode-back" href="../../../_api/airflow/models/index.html#airflow.models.dagbag.DagBag">[docs]</a><span class="k">class</span> <span class="nc">DagBag</span><span class="p">(</span><span class="n">BaseDagBag</span><span class="p">,</span> <span class="n">LoggingMixin</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> A dagbag is a collection of dags, parsed out of a folder tree and has high</span>
<span class="sd"> level configuration settings, like what database to use as a backend and</span>
<span class="sd"> what executor to use to fire off tasks. This makes it easier to run</span>
<span class="sd"> distinct environments for say production and development, tests, or for</span>
<span class="sd"> different teams or security profiles. What would have been system level</span>
<span class="sd"> settings are now dagbag level so that one system can run multiple,</span>
<span class="sd"> independent settings sets.</span>
<span class="sd"> :param dag_folder: the folder to scan to find DAGs</span>
<span class="sd"> :type dag_folder: unicode</span>
<span class="sd"> :param executor: the executor to use when executing task instances</span>
<span class="sd"> in this DagBag</span>
<span class="sd"> :param include_examples: whether to include the examples that ship</span>
<span class="sd"> with airflow or not</span>
<span class="sd"> :type include_examples: bool</span>
<span class="sd"> :param has_logged: an instance boolean that gets flipped from False to True after a</span>
<span class="sd"> file has been skipped. This is to prevent overloading the user with logging</span>
<span class="sd"> messages about skipped files. Therefore only once per DagBag is a file logged</span>
<span class="sd"> being skipped.</span>
<span class="sd"> :param store_serialized_dags: Read DAGs from DB if store_serialized_dags is ``True``.</span>
<span class="sd"> If ``False`` DAGs are read from python files.</span>
<span class="sd"> :type store_serialized_dags: bool</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># static class variables to detetct dag cycle</span>
<div class="viewcode-block" id="DagBag.CYCLE_NEW"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.CYCLE_NEW">[docs]</a> <span class="n">CYCLE_NEW</span> <span class="o">=</span> <span class="mi">0</span></div>
<div class="viewcode-block" id="DagBag.CYCLE_IN_PROGRESS"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.CYCLE_IN_PROGRESS">[docs]</a> <span class="n">CYCLE_IN_PROGRESS</span> <span class="o">=</span> <span class="mi">1</span></div>
<div class="viewcode-block" id="DagBag.CYCLE_DONE"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.CYCLE_DONE">[docs]</a> <span class="n">CYCLE_DONE</span> <span class="o">=</span> <span class="mi">2</span></div>
<div class="viewcode-block" id="DagBag.DAGBAG_IMPORT_TIMEOUT"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.DAGBAG_IMPORT_TIMEOUT">[docs]</a> <span class="n">DAGBAG_IMPORT_TIMEOUT</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;DAGBAG_IMPORT_TIMEOUT&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="DagBag.UNIT_TEST_MODE"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.UNIT_TEST_MODE">[docs]</a> <span class="n">UNIT_TEST_MODE</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;UNIT_TEST_MODE&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="DagBag.SCHEDULER_ZOMBIE_TASK_THRESHOLD"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.SCHEDULER_ZOMBIE_TASK_THRESHOLD">[docs]</a> <span class="n">SCHEDULER_ZOMBIE_TASK_THRESHOLD</span> <span class="o">=</span> <span class="n">conf</span><span class="o">.</span><span class="n">getint</span><span class="p">(</span><span class="s1">&#39;scheduler&#39;</span><span class="p">,</span> <span class="s1">&#39;scheduler_zombie_task_threshold&#39;</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">dag_folder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">executor</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">include_examples</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;LOAD_EXAMPLES&#39;</span><span class="p">),</span>
<span class="n">safe_mode</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;DAG_DISCOVERY_SAFE_MODE&#39;</span><span class="p">),</span>
<span class="n">store_serialized_dags</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="p">):</span>
<span class="c1"># do not use default arg in signature, to fix import cycle on plugin load</span>
<span class="k">if</span> <span class="n">executor</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">executor</span> <span class="o">=</span> <span class="n">get_default_executor</span><span class="p">()</span>
<span class="n">dag_folder</span> <span class="o">=</span> <span class="n">dag_folder</span> <span class="ow">or</span> <span class="n">settings</span><span class="o">.</span><span class="n">DAGS_FOLDER</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dag_folder</span> <span class="o">=</span> <span class="n">dag_folder</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span> <span class="o">=</span> <span class="p">{}</span>
<span class="c1"># the file&#39;s last modified timestamp when we last read it</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">executor</span> <span class="o">=</span> <span class="n">executor</span>
<span class="bp">self</span><span class="o">.</span><span class="n">import_errors</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_logged</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">store_serialized_dags</span> <span class="o">=</span> <span class="n">store_serialized_dags</span>
<span class="bp">self</span><span class="o">.</span><span class="n">collect_dags</span><span class="p">(</span>
<span class="n">dag_folder</span><span class="o">=</span><span class="n">dag_folder</span><span class="p">,</span>
<span class="n">include_examples</span><span class="o">=</span><span class="n">include_examples</span><span class="p">,</span>
<span class="n">safe_mode</span><span class="o">=</span><span class="n">safe_mode</span><span class="p">)</span>
<div class="viewcode-block" id="DagBag.size"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.size">[docs]</a> <span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> :return: the amount of dags contained in this dagbag</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">)</span></div>
<span class="nd">@property</span>
<div class="viewcode-block" id="DagBag.dag_ids"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.dag_ids">[docs]</a> <span class="k">def</span> <span class="nf">dag_ids</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span></div>
<div class="viewcode-block" id="DagBag.get_dag"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.get_dag">[docs]</a> <span class="k">def</span> <span class="nf">get_dag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dag_id</span><span class="p">,</span> <span class="n">from_file_only</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Gets the DAG out of the dictionary, and refreshes it if expired</span>
<span class="sd"> :param dag_id: DAG Id</span>
<span class="sd"> :type dag_id: str</span>
<span class="sd"> :param from_file_only: returns a DAG loaded from file.</span>
<span class="sd"> :type from_file_only: bool</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">airflow.models.dag</span> <span class="kn">import</span> <span class="n">DagModel</span> <span class="c1"># Avoid circular import</span>
<span class="c1"># Only read DAGs from DB if this dagbag is store_serialized_dags.</span>
<span class="c1"># from_file_only is an exception, currently it is for renderring templates</span>
<span class="c1"># in UI only. Because functions are gone in serialized DAGs, DAGs must be</span>
<span class="c1"># imported from files.</span>
<span class="c1"># FIXME: this exception should be removed in future, then webserver can be</span>
<span class="c1"># decoupled from DAG files.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">store_serialized_dags</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">from_file_only</span><span class="p">:</span>
<span class="c1"># Import here so that serialized dag is only imported when serialization is enabled</span>
<span class="kn">from</span> <span class="nn">airflow.models.serialized_dag</span> <span class="kn">import</span> <span class="n">SerializedDagModel</span>
<span class="k">if</span> <span class="n">dag_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">:</span>
<span class="c1"># Load from DB if not (yet) in the bag</span>
<span class="n">row</span> <span class="o">=</span> <span class="n">SerializedDagModel</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">dag_id</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">return</span> <span class="kc">None</span>
<span class="n">dag</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">dag</span>
<span class="k">for</span> <span class="n">subdag</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">subdags</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">subdag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">subdag</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">dag</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">dag_id</span><span class="p">)</span>
<span class="c1"># If asking for a known subdag, we want to refresh the parent</span>
<span class="n">dag</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">root_dag_id</span> <span class="o">=</span> <span class="n">dag_id</span>
<span class="k">if</span> <span class="n">dag_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">:</span>
<span class="n">dag</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">dag_id</span><span class="p">]</span>
<span class="k">if</span> <span class="n">dag</span><span class="o">.</span><span class="n">is_subdag</span><span class="p">:</span>
<span class="n">root_dag_id</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">parent_dag</span><span class="o">.</span><span class="n">dag_id</span>
<span class="c1"># Needs to load from file for a store_serialized_dags dagbag.</span>
<span class="n">enforce_from_file</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">store_serialized_dags</span> <span class="ow">and</span> <span class="n">dag</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">airflow.serialization.serialized_objects</span> <span class="kn">import</span> <span class="n">SerializedDAG</span>
<span class="n">enforce_from_file</span> <span class="o">=</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dag</span><span class="p">,</span> <span class="n">SerializedDAG</span><span class="p">)</span>
<span class="c1"># If the dag corresponding to root_dag_id is absent or expired</span>
<span class="n">orm_dag</span> <span class="o">=</span> <span class="n">DagModel</span><span class="o">.</span><span class="n">get_current</span><span class="p">(</span><span class="n">root_dag_id</span><span class="p">)</span>
<span class="k">if</span> <span class="p">(</span><span class="n">orm_dag</span> <span class="ow">and</span> <span class="p">(</span>
<span class="n">root_dag_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span> <span class="ow">or</span>
<span class="p">(</span>
<span class="n">orm_dag</span><span class="o">.</span><span class="n">last_expired</span> <span class="ow">and</span>
<span class="n">dag</span><span class="o">.</span><span class="n">last_loaded</span> <span class="o">&lt;</span> <span class="n">orm_dag</span><span class="o">.</span><span class="n">last_expired</span>
<span class="p">)</span>
<span class="p">))</span> <span class="ow">or</span> <span class="n">enforce_from_file</span><span class="p">:</span>
<span class="c1"># Reprocess source file</span>
<span class="n">found_dags</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">process_file</span><span class="p">(</span>
<span class="n">filepath</span><span class="o">=</span><span class="n">correct_maybe_zipped</span><span class="p">(</span><span class="n">orm_dag</span><span class="o">.</span><span class="n">fileloc</span><span class="p">),</span> <span class="n">only_if_updated</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="c1"># If the source file no longer exports `dag_id`, delete it from self.dags</span>
<span class="k">if</span> <span class="n">found_dags</span> <span class="ow">and</span> <span class="n">dag_id</span> <span class="ow">in</span> <span class="p">[</span><span class="n">found_dag</span><span class="o">.</span><span class="n">dag_id</span> <span class="k">for</span> <span class="n">found_dag</span> <span class="ow">in</span> <span class="n">found_dags</span><span class="p">]:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">dag_id</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">dag_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">:</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">dag_id</span><span class="p">]</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">dag_id</span><span class="p">)</span></div>
<div class="viewcode-block" id="DagBag.process_file"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.process_file">[docs]</a> <span class="k">def</span> <span class="nf">process_file</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">only_if_updated</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">safe_mode</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Given a path to a python module or zip file, this method imports</span>
<span class="sd"> the module and look for dag objects within it.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">airflow.models.dag</span> <span class="kn">import</span> <span class="n">DAG</span> <span class="c1"># Avoid circular import</span>
<span class="n">found_dags</span> <span class="o">=</span> <span class="p">[]</span>
<span class="c1"># if the source file no longer exists in the DB or in the filesystem,</span>
<span class="c1"># return an empty list</span>
<span class="c1"># todo: raise exception?</span>
<span class="k">if</span> <span class="n">filepath</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">filepath</span><span class="p">):</span>
<span class="k">return</span> <span class="n">found_dags</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># This failed before in what may have been a git sync</span>
<span class="c1"># race condition</span>
<span class="n">file_last_changed_on_disk</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">fromtimestamp</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">getmtime</span><span class="p">(</span><span class="n">filepath</span><span class="p">))</span>
<span class="k">if</span> <span class="n">only_if_updated</span> \
<span class="ow">and</span> <span class="n">filepath</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span> \
<span class="ow">and</span> <span class="n">file_last_changed_on_disk</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]:</span>
<span class="k">return</span> <span class="n">found_dags</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</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">exception</span><span class="p">(</span><span class="n">e</span><span class="p">)</span>
<span class="k">return</span> <span class="n">found_dags</span>
<span class="n">mods</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">is_zipfile</span> <span class="o">=</span> <span class="n">zipfile</span><span class="o">.</span><span class="n">is_zipfile</span><span class="p">(</span><span class="n">filepath</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">is_zipfile</span><span class="p">:</span>
<span class="k">if</span> <span class="n">safe_mode</span><span class="p">:</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filepath</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">content</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">([</span><span class="n">s</span> <span class="ow">in</span> <span class="n">content</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="p">(</span><span class="sa">b</span><span class="s1">&#39;DAG&#39;</span><span class="p">,</span> <span class="sa">b</span><span class="s1">&#39;airflow&#39;</span><span class="p">)]):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="n">file_last_changed_on_disk</span>
<span class="c1"># Don&#39;t want to spam user with skip messages</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_logged</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_logged</span> <span class="o">=</span> <span class="kc">True</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">&quot;File </span><span class="si">%s</span><span class="s2"> assumed to contain no DAGs. Skipping.&quot;</span><span class="p">,</span>
<span class="n">filepath</span><span class="p">)</span>
<span class="k">return</span> <span class="n">found_dags</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;Importing </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="n">org_mod_name</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">filepath</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
<span class="n">mod_name</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;unusual_prefix_&#39;</span> <span class="o">+</span>
<span class="n">hashlib</span><span class="o">.</span><span class="n">sha1</span><span class="p">(</span><span class="n">filepath</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">hexdigest</span><span class="p">()</span> <span class="o">+</span>
<span class="s1">&#39;_&#39;</span> <span class="o">+</span> <span class="n">org_mod_name</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mod_name</span> <span class="ow">in</span> <span class="n">sys</span><span class="o">.</span><span class="n">modules</span><span class="p">:</span>
<span class="k">del</span> <span class="n">sys</span><span class="o">.</span><span class="n">modules</span><span class="p">[</span><span class="n">mod_name</span><span class="p">]</span>
<span class="k">with</span> <span class="n">timeout</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">DAGBAG_IMPORT_TIMEOUT</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">imp</span><span class="o">.</span><span class="n">load_source</span><span class="p">(</span><span class="n">mod_name</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="n">mods</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">m</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</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">exception</span><span class="p">(</span><span class="s2">&quot;Failed to import: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">import_errors</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="n">file_last_changed_on_disk</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">zip_file</span> <span class="o">=</span> <span class="n">zipfile</span><span class="o">.</span><span class="n">ZipFile</span><span class="p">(</span><span class="n">filepath</span><span class="p">)</span>
<span class="k">for</span> <span class="n">mod</span> <span class="ow">in</span> <span class="n">zip_file</span><span class="o">.</span><span class="n">infolist</span><span class="p">():</span>
<span class="n">head</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">mod</span><span class="o">.</span><span class="n">filename</span><span class="p">)</span>
<span class="n">mod_name</span><span class="p">,</span> <span class="n">ext</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</span><span class="p">(</span><span class="n">mod</span><span class="o">.</span><span class="n">filename</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">head</span> <span class="ow">and</span> <span class="p">(</span><span class="n">ext</span> <span class="o">==</span> <span class="s1">&#39;.py&#39;</span> <span class="ow">or</span> <span class="n">ext</span> <span class="o">==</span> <span class="s1">&#39;.pyc&#39;</span><span class="p">):</span>
<span class="k">if</span> <span class="n">mod_name</span> <span class="o">==</span> <span class="s1">&#39;__init__&#39;</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">warning</span><span class="p">(</span><span class="s2">&quot;Found __init__.</span><span class="si">%s</span><span class="s2"> at root of </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">ext</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="k">if</span> <span class="n">safe_mode</span><span class="p">:</span>
<span class="k">with</span> <span class="n">zip_file</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">mod</span><span class="o">.</span><span class="n">filename</span><span class="p">)</span> <span class="k">as</span> <span class="n">zf</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">debug</span><span class="p">(</span><span class="s2">&quot;Reading </span><span class="si">%s</span><span class="s2"> from </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">mod</span><span class="o">.</span><span class="n">filename</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="n">content</span> <span class="o">=</span> <span class="n">zf</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">all</span><span class="p">([</span><span class="n">s</span> <span class="ow">in</span> <span class="n">content</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="p">(</span><span class="sa">b</span><span class="s1">&#39;DAG&#39;</span><span class="p">,</span> <span class="sa">b</span><span class="s1">&#39;airflow&#39;</span><span class="p">)]):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">file_last_changed_on_disk</span><span class="p">)</span>
<span class="c1"># todo: create ignore list</span>
<span class="c1"># Don&#39;t want to spam user with skip messages</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">has_logged</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">has_logged</span> <span class="o">=</span> <span class="kc">True</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">&quot;File </span><span class="si">%s</span><span class="s2"> assumed to contain no DAGs. Skipping.&quot;</span><span class="p">,</span>
<span class="n">filepath</span><span class="p">)</span>
<span class="k">if</span> <span class="n">mod_name</span> <span class="ow">in</span> <span class="n">sys</span><span class="o">.</span><span class="n">modules</span><span class="p">:</span>
<span class="k">del</span> <span class="n">sys</span><span class="o">.</span><span class="n">modules</span><span class="p">[</span><span class="n">mod_name</span><span class="p">]</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">importlib</span><span class="o">.</span><span class="n">import_module</span><span class="p">(</span><span class="n">mod_name</span><span class="p">)</span>
<span class="n">mods</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">m</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</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">exception</span><span class="p">(</span><span class="s2">&quot;Failed to import: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">filepath</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">import_errors</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="n">file_last_changed_on_disk</span>
<span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">mods</span><span class="p">:</span>
<span class="k">for</span> <span class="n">dag</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dag</span><span class="p">,</span> <span class="n">DAG</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">:</span>
<span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span> <span class="o">=</span> <span class="n">filepath</span>
<span class="k">if</span> <span class="n">dag</span><span class="o">.</span><span class="n">fileloc</span> <span class="o">!=</span> <span class="n">filepath</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">is_zipfile</span><span class="p">:</span>
<span class="n">dag</span><span class="o">.</span><span class="n">fileloc</span> <span class="o">=</span> <span class="n">filepath</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">dag</span><span class="o">.</span><span class="n">is_subdag</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bag_dag</span><span class="p">(</span><span class="n">dag</span><span class="p">,</span> <span class="n">parent_dag</span><span class="o">=</span><span class="n">dag</span><span class="p">,</span> <span class="n">root_dag</span><span class="o">=</span><span class="n">dag</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">dag</span><span class="o">.</span><span class="n">_schedule_interval</span><span class="p">,</span> <span class="n">six</span><span class="o">.</span><span class="n">string_types</span><span class="p">):</span>
<span class="n">croniter</span><span class="p">(</span><span class="n">dag</span><span class="o">.</span><span class="n">_schedule_interval</span><span class="p">)</span>
<span class="n">found_dags</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">dag</span><span class="p">)</span>
<span class="n">found_dags</span> <span class="o">+=</span> <span class="n">dag</span><span class="o">.</span><span class="n">subdags</span>
<span class="k">except</span> <span class="p">(</span><span class="n">CroniterBadCronError</span><span class="p">,</span>
<span class="n">CroniterBadDateError</span><span class="p">,</span>
<span class="n">CroniterNotAlphaError</span><span class="p">)</span> <span class="k">as</span> <span class="n">cron_e</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">exception</span><span class="p">(</span><span class="s2">&quot;Failed to bag_dag: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">import_errors</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">]</span> <span class="o">=</span> \
<span class="s2">&quot;Invalid Cron expression: &quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">cron_e</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">]</span> <span class="o">=</span> \
<span class="n">file_last_changed_on_disk</span>
<span class="k">except</span> <span class="n">AirflowDagCycleException</span> <span class="k">as</span> <span class="n">cycle_exception</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">exception</span><span class="p">(</span><span class="s2">&quot;Failed to bag_dag: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">import_errors</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">cycle_exception</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span><span class="p">]</span> <span class="o">=</span> \
<span class="n">file_last_changed_on_disk</span>
<span class="bp">self</span><span class="o">.</span><span class="n">file_last_changed</span><span class="p">[</span><span class="n">filepath</span><span class="p">]</span> <span class="o">=</span> <span class="n">file_last_changed_on_disk</span>
<span class="k">return</span> <span class="n">found_dags</span></div>
<span class="nd">@provide_session</span>
<div class="viewcode-block" id="DagBag.kill_zombies"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.kill_zombies">[docs]</a> <span class="k">def</span> <span class="nf">kill_zombies</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">zombies</span><span class="p">,</span> <span class="n">session</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Fail given zombie tasks, which are tasks that haven&#39;t</span>
<span class="sd"> had a heartbeat for too long, in the current DagBag.</span>
<span class="sd"> :param zombies: zombie task instances to kill.</span>
<span class="sd"> :type zombies: airflow.utils.dag_processing.SimpleTaskInstance</span>
<span class="sd"> :param session: DB session.</span>
<span class="sd"> :type session: sqlalchemy.orm.session.Session</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">airflow.models.taskinstance</span> <span class="kn">import</span> <span class="n">TaskInstance</span> <span class="c1"># Avoid circular import</span>
<span class="k">for</span> <span class="n">zombie</span> <span class="ow">in</span> <span class="n">zombies</span><span class="p">:</span>
<span class="k">if</span> <span class="n">zombie</span><span class="o">.</span><span class="n">dag_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">:</span>
<span class="n">dag</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">zombie</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span>
<span class="k">if</span> <span class="n">zombie</span><span class="o">.</span><span class="n">task_id</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">task_ids</span><span class="p">:</span>
<span class="n">task</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">get_task</span><span class="p">(</span><span class="n">zombie</span><span class="o">.</span><span class="n">task_id</span><span class="p">)</span>
<span class="n">ti</span> <span class="o">=</span> <span class="n">TaskInstance</span><span class="p">(</span><span class="n">task</span><span class="p">,</span> <span class="n">zombie</span><span class="o">.</span><span class="n">execution_date</span><span class="p">)</span>
<span class="c1"># Get properties needed for failure handling from SimpleTaskInstance.</span>
<span class="n">ti</span><span class="o">.</span><span class="n">start_date</span> <span class="o">=</span> <span class="n">zombie</span><span class="o">.</span><span class="n">start_date</span>
<span class="n">ti</span><span class="o">.</span><span class="n">end_date</span> <span class="o">=</span> <span class="n">zombie</span><span class="o">.</span><span class="n">end_date</span>
<span class="n">ti</span><span class="o">.</span><span class="n">try_number</span> <span class="o">=</span> <span class="n">zombie</span><span class="o">.</span><span class="n">try_number</span>
<span class="n">ti</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="n">zombie</span><span class="o">.</span><span class="n">state</span>
<span class="n">ti</span><span class="o">.</span><span class="n">test_mode</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">UNIT_TEST_MODE</span>
<span class="n">ti</span><span class="o">.</span><span class="n">handle_failure</span><span class="p">(</span><span class="s2">&quot;</span><span class="si">{}</span><span class="s2"> detected as zombie&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">ti</span><span class="p">),</span>
<span class="n">ti</span><span class="o">.</span><span class="n">test_mode</span><span class="p">,</span> <span class="n">ti</span><span class="o">.</span><span class="n">get_template_context</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">&#39;Marked zombie job </span><span class="si">%s</span><span class="s1"> as </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">ti</span><span class="p">,</span> <span class="n">ti</span><span class="o">.</span><span class="n">state</span><span class="p">)</span>
<span class="n">session</span><span class="o">.</span><span class="n">commit</span><span class="p">()</span></div>
<div class="viewcode-block" id="DagBag.bag_dag"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.bag_dag">[docs]</a> <span class="k">def</span> <span class="nf">bag_dag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dag</span><span class="p">,</span> <span class="n">parent_dag</span><span class="p">,</span> <span class="n">root_dag</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Adds the DAG into the bag, recurses into sub dags.</span>
<span class="sd"> Throws AirflowDagCycleException if a cycle is detected in this dag or its subdags</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">dag</span><span class="o">.</span><span class="n">test_cycle</span><span class="p">()</span> <span class="c1"># throws if a task cycle is found</span>
<span class="n">dag</span><span class="o">.</span><span class="n">resolve_template_files</span><span class="p">()</span>
<span class="n">dag</span><span class="o">.</span><span class="n">last_loaded</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span>
<span class="k">for</span> <span class="n">task</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">tasks</span><span class="p">:</span>
<span class="n">settings</span><span class="o">.</span><span class="n">policy</span><span class="p">(</span><span class="n">task</span><span class="p">)</span>
<span class="n">subdags</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">subdags</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">for</span> <span class="n">subdag</span> <span class="ow">in</span> <span class="n">subdags</span><span class="p">:</span>
<span class="n">subdag</span><span class="o">.</span><span class="n">full_filepath</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span>
<span class="n">subdag</span><span class="o">.</span><span class="n">parent_dag</span> <span class="o">=</span> <span class="n">dag</span>
<span class="n">subdag</span><span class="o">.</span><span class="n">is_subdag</span> <span class="o">=</span> <span class="kc">True</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bag_dag</span><span class="p">(</span><span class="n">subdag</span><span class="p">,</span> <span class="n">parent_dag</span><span class="o">=</span><span class="n">dag</span><span class="p">,</span> <span class="n">root_dag</span><span class="o">=</span><span class="n">root_dag</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">dag</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;Loaded DAG </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">dag</span><span class="p">)</span>
<span class="k">except</span> <span class="n">AirflowDagCycleException</span> <span class="k">as</span> <span class="n">cycle_exception</span><span class="p">:</span>
<span class="c1"># There was an error in bagging the dag. Remove it from the list of dags</span>
<span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">exception</span><span class="p">(</span><span class="s1">&#39;Exception bagging dag: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">)</span>
<span class="c1"># Only necessary at the root level since DAG.subdags automatically</span>
<span class="c1"># performs DFS to search through all subdags</span>
<span class="k">if</span> <span class="n">dag</span> <span class="o">==</span> <span class="n">root_dag</span><span class="p">:</span>
<span class="k">for</span> <span class="n">subdag</span> <span class="ow">in</span> <span class="n">subdags</span><span class="p">:</span>
<span class="k">if</span> <span class="n">subdag</span><span class="o">.</span><span class="n">dag_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">:</span>
<span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="p">[</span><span class="n">subdag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span>
<span class="k">raise</span> <span class="n">cycle_exception</span></div>
<div class="viewcode-block" id="DagBag.collect_dags"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.collect_dags">[docs]</a> <span class="k">def</span> <span class="nf">collect_dags</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">dag_folder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">only_if_updated</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">include_examples</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;LOAD_EXAMPLES&#39;</span><span class="p">),</span>
<span class="n">safe_mode</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">getboolean</span><span class="p">(</span><span class="s1">&#39;core&#39;</span><span class="p">,</span> <span class="s1">&#39;DAG_DISCOVERY_SAFE_MODE&#39;</span><span class="p">)):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Given a file path or a folder, this method looks for python modules,</span>
<span class="sd"> imports them and adds them to the dagbag collection.</span>
<span class="sd"> Note that if a ``.airflowignore`` file is found while processing</span>
<span class="sd"> the directory, it will behave much like a ``.gitignore``,</span>
<span class="sd"> ignoring files that match any of the regex patterns specified</span>
<span class="sd"> in the file.</span>
<span class="sd"> **Note**: The patterns in .airflowignore are treated as</span>
<span class="sd"> un-anchored regexes, not shell-like glob patterns.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">store_serialized_dags</span><span class="p">:</span>
<span class="k">return</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">&quot;Filling up the DagBag from </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dag_folder</span><span class="p">)</span>
<span class="n">dag_folder</span> <span class="o">=</span> <span class="n">dag_folder</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_folder</span>
<span class="c1"># Used to store stats around DagBag processing</span>
<span class="n">stats</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">FileLoadStat</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span>
<span class="s1">&#39;FileLoadStat&#39;</span><span class="p">,</span> <span class="s2">&quot;file duration dag_num task_num dags&quot;</span><span class="p">)</span>
<span class="n">dag_folder</span> <span class="o">=</span> <span class="n">correct_maybe_zipped</span><span class="p">(</span><span class="n">dag_folder</span><span class="p">)</span>
<span class="n">dags_by_name</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">filepath</span> <span class="ow">in</span> <span class="n">list_py_file_paths</span><span class="p">(</span><span class="n">dag_folder</span><span class="p">,</span> <span class="n">safe_mode</span><span class="o">=</span><span class="n">safe_mode</span><span class="p">,</span>
<span class="n">include_examples</span><span class="o">=</span><span class="n">include_examples</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">ts</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span>
<span class="n">found_dags</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">process_file</span><span class="p">(</span>
<span class="n">filepath</span><span class="p">,</span> <span class="n">only_if_updated</span><span class="o">=</span><span class="n">only_if_updated</span><span class="p">,</span>
<span class="n">safe_mode</span><span class="o">=</span><span class="n">safe_mode</span><span class="p">)</span>
<span class="n">dag_ids</span> <span class="o">=</span> <span class="p">[</span><span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span> <span class="k">for</span> <span class="n">dag</span> <span class="ow">in</span> <span class="n">found_dags</span><span class="p">]</span>
<span class="n">dag_id_names</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">dag_ids</span><span class="p">)</span>
<span class="n">td</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="n">ts</span>
<span class="n">td</span> <span class="o">=</span> <span class="n">td</span><span class="o">.</span><span class="n">total_seconds</span><span class="p">()</span> <span class="o">+</span> <span class="p">(</span>
<span class="nb">float</span><span class="p">(</span><span class="n">td</span><span class="o">.</span><span class="n">microseconds</span><span class="p">)</span> <span class="o">/</span> <span class="mi">1000000</span><span class="p">)</span>
<span class="n">dags_by_name</span><span class="p">[</span><span class="n">dag_id_names</span><span class="p">]</span> <span class="o">=</span> <span class="n">dag_ids</span>
<span class="n">stats</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">FileLoadStat</span><span class="p">(</span>
<span class="n">filepath</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">settings</span><span class="o">.</span><span class="n">DAGS_FOLDER</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">),</span>
<span class="n">td</span><span class="p">,</span>
<span class="nb">len</span><span class="p">(</span><span class="n">found_dags</span><span class="p">),</span>
<span class="nb">sum</span><span class="p">([</span><span class="nb">len</span><span class="p">(</span><span class="n">dag</span><span class="o">.</span><span class="n">tasks</span><span class="p">)</span> <span class="k">for</span> <span class="n">dag</span> <span class="ow">in</span> <span class="n">found_dags</span><span class="p">]),</span>
<span class="n">dag_id_names</span><span class="p">,</span>
<span class="p">))</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</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">exception</span><span class="p">(</span><span class="n">e</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dagbag_stats</span> <span class="o">=</span> <span class="nb">sorted</span><span class="p">(</span>
<span class="n">stats</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">duration</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">for</span> <span class="n">file_stat</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dagbag_stats</span><span class="p">:</span>
<span class="n">dag_ids</span> <span class="o">=</span> <span class="n">dags_by_name</span><span class="p">[</span><span class="n">file_stat</span><span class="o">.</span><span class="n">dags</span><span class="p">]</span>
<span class="k">if</span> <span class="n">file_stat</span><span class="o">.</span><span class="n">dag_num</span> <span class="o">&gt;=</span> <span class="mi">1</span><span class="p">:</span>
<span class="c1"># if we found multiple dags per file, the stat is &#39;dag_id1 _ dag_id2&#39;</span>
<span class="n">dag_names</span> <span class="o">=</span> <span class="s1">&#39;_&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">dag_ids</span><span class="p">)</span>
<span class="n">Stats</span><span class="o">.</span><span class="n">timing</span><span class="p">(</span><span class="s1">&#39;dag.loading-duration.</span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span>
<span class="nb">format</span><span class="p">(</span><span class="n">dag_names</span><span class="p">),</span>
<span class="n">file_stat</span><span class="o">.</span><span class="n">duration</span><span class="p">)</span></div>
<div class="viewcode-block" id="DagBag.collect_dags_from_db"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.collect_dags_from_db">[docs]</a> <span class="k">def</span> <span class="nf">collect_dags_from_db</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Collects DAGs from database.&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">airflow.models.serialized_dag</span> <span class="kn">import</span> <span class="n">SerializedDagModel</span>
<span class="n">start_dttm</span> <span class="o">=</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</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">&quot;Filling up the DagBag from database&quot;</span><span class="p">)</span>
<span class="c1"># The dagbag contains all rows in serialized_dag table. Deleted DAGs are deleted</span>
<span class="c1"># from the table by the scheduler job.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span> <span class="o">=</span> <span class="n">SerializedDagModel</span><span class="o">.</span><span class="n">read_all_dags</span><span class="p">()</span>
<span class="c1"># Adds subdags.</span>
<span class="c1"># DAG post-processing steps such as self.bag_dag and croniter are not needed as</span>
<span class="c1"># they are done by scheduler before serialization.</span>
<span class="n">subdags</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">dag</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="k">for</span> <span class="n">subdag</span> <span class="ow">in</span> <span class="n">dag</span><span class="o">.</span><span class="n">subdags</span><span class="p">:</span>
<span class="n">subdags</span><span class="p">[</span><span class="n">subdag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">subdag</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dags</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">subdags</span><span class="p">)</span>
<span class="n">Stats</span><span class="o">.</span><span class="n">timing</span><span class="p">(</span><span class="s1">&#39;collect_db_dags&#39;</span><span class="p">,</span> <span class="n">timezone</span><span class="o">.</span><span class="n">utcnow</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_dttm</span><span class="p">)</span></div>
<div class="viewcode-block" id="DagBag.dagbag_report"><a class="viewcode-back" href="../../../_api/airflow/models/dagbag/index.html#airflow.models.dagbag.DagBag.dagbag_report">[docs]</a> <span class="k">def</span> <span class="nf">dagbag_report</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Prints a report around DagBag loading stats&quot;&quot;&quot;</span>
<span class="n">report</span> <span class="o">=</span> <span class="n">textwrap</span><span class="o">.</span><span class="n">dedent</span><span class="p">(</span><span class="s2">&quot;&quot;&quot;</span><span class="se">\n</span><span class="s2"></span>
<span class="s2"> -------------------------------------------------------------------</span>
<span class="s2"> DagBag loading stats for </span><span class="si">{dag_folder}</span><span class="s2"></span>
<span class="s2"> -------------------------------------------------------------------</span>
<span class="s2"> Number of DAGs: </span><span class="si">{dag_num}</span><span class="s2"></span>
<span class="s2"> Total task number: </span><span class="si">{task_num}</span><span class="s2"></span>
<span class="s2"> DagBag parsing time: </span><span class="si">{duration}</span><span class="s2"></span>
<span class="s2"> </span><span class="si">{table}</span><span class="s2"></span>
<span class="s2"> &quot;&quot;&quot;</span><span class="p">)</span>
<span class="n">stats</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dagbag_stats</span>
<span class="k">return</span> <span class="n">report</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">dag_folder</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dag_folder</span><span class="p">,</span>
<span class="n">duration</span><span class="o">=</span><span class="nb">sum</span><span class="p">([</span><span class="n">o</span><span class="o">.</span><span class="n">duration</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">stats</span><span class="p">]),</span>
<span class="n">dag_num</span><span class="o">=</span><span class="nb">sum</span><span class="p">([</span><span class="n">o</span><span class="o">.</span><span class="n">dag_num</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">stats</span><span class="p">]),</span>
<span class="n">task_num</span><span class="o">=</span><span class="nb">sum</span><span class="p">([</span><span class="n">o</span><span class="o">.</span><span class="n">task_num</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">stats</span><span class="p">]),</span>
<span class="n">table</span><span class="o">=</span><span class="n">pprinttable</span><span class="p">(</span><span class="n">stats</span><span class="p">),</span></div></div>
<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.
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
<!-- Theme Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-140539454-1', 'auto');
ga('send', 'pageview');
</script>
</body>
</html>