| |
| |
| <!-- |
| 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.serialized_dag — 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 & 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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li><a href="../models.html">airflow.models</a> »</li> |
| |
| <li>airflow.models.serialized_dag</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.serialized_dag</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="sd">"""Serialzed DAG table in database."""</span> |
| |
| <span class="kn">import</span> <span class="nn">hashlib</span> |
| <span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">timedelta</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Optional</span> |
| |
| <span class="kn">import</span> <span class="nn">sqlalchemy_jsonfield</span> |
| <span class="kn">from</span> <span class="nn">sqlalchemy</span> <span class="kn">import</span> <span class="n">Column</span><span class="p">,</span> <span class="n">Index</span><span class="p">,</span> <span class="n">Integer</span><span class="p">,</span> <span class="n">String</span><span class="p">,</span> <span class="n">and_</span> |
| <span class="kn">from</span> <span class="nn">sqlalchemy.sql</span> <span class="kn">import</span> <span class="n">exists</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow</span> <span class="kn">import</span> <span class="n">DAG</span> |
| <span class="kn">from</span> <span class="nn">airflow.models.base</span> <span class="kn">import</span> <span class="n">ID_LEN</span><span class="p">,</span> <span class="n">Base</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="kn">from</span> <span class="nn">airflow.settings</span> <span class="kn">import</span> <span class="n">json</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils</span> <span class="kn">import</span> <span class="n">db</span><span class="p">,</span> <span class="n">timezone</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.sqlalchemy</span> <span class="kn">import</span> <span class="n">UtcDateTime</span> |
| |
| |
| <div class="viewcode-block" id="log"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.log">[docs]</a><span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span></div> |
| |
| |
| <div class="viewcode-block" id="SerializedDagModel"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel">[docs]</a><span class="k">class</span> <span class="nc">SerializedDagModel</span><span class="p">(</span><span class="n">Base</span><span class="p">):</span> |
| <span class="sd">"""A table for serialized DAGs.</span> |
| |
| <span class="sd"> serialized_dag table is a snapshot of DAG files synchronized by scheduler.</span> |
| <span class="sd"> This feature is controlled by:</span> |
| |
| <span class="sd"> * ``[core] store_serialized_dags = True``: enable this feature</span> |
| <span class="sd"> * ``[core] min_serialized_dag_update_interval = 30`` (s):</span> |
| <span class="sd"> serialized DAGs are updated in DB when a file gets processed by scheduler,</span> |
| <span class="sd"> to reduce DB write rate, there is a minimal interval of updating serialized DAGs.</span> |
| <span class="sd"> * ``[scheduler] dag_dir_list_interval = 300`` (s):</span> |
| <span class="sd"> interval of deleting serialized DAGs in DB when the files are deleted, suggest</span> |
| <span class="sd"> to use a smaller interval such as 60</span> |
| |
| <span class="sd"> It is used by webserver to load dagbags when ``store_serialized_dags=True``.</span> |
| <span class="sd"> Because reading from database is lightweight compared to importing from files,</span> |
| <span class="sd"> it solves the webserver scalability issue.</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="SerializedDagModel.__tablename__"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.__tablename__">[docs]</a> <span class="n">__tablename__</span> <span class="o">=</span> <span class="s1">'serialized_dag'</span></div> |
| |
| <div class="viewcode-block" id="SerializedDagModel.dag_id"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.dag_id">[docs]</a> <span class="n">dag_id</span> <span class="o">=</span> <span class="n">Column</span><span class="p">(</span><span class="n">String</span><span class="p">(</span><span class="n">ID_LEN</span><span class="p">),</span> <span class="n">primary_key</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></div> |
| <div class="viewcode-block" id="SerializedDagModel.fileloc"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.fileloc">[docs]</a> <span class="n">fileloc</span> <span class="o">=</span> <span class="n">Column</span><span class="p">(</span><span class="n">String</span><span class="p">(</span><span class="mi">2000</span><span class="p">),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div> |
| <span class="c1"># The max length of fileloc exceeds the limit of indexing.</span> |
| <div class="viewcode-block" id="SerializedDagModel.fileloc_hash"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.fileloc_hash">[docs]</a> <span class="n">fileloc_hash</span> <span class="o">=</span> <span class="n">Column</span><span class="p">(</span><span class="n">Integer</span><span class="p">,</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div> |
| <div class="viewcode-block" id="SerializedDagModel.data"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.data">[docs]</a> <span class="n">data</span> <span class="o">=</span> <span class="n">Column</span><span class="p">(</span><span class="n">sqlalchemy_jsonfield</span><span class="o">.</span><span class="n">JSONField</span><span class="p">(</span><span class="n">json</span><span class="o">=</span><span class="n">json</span><span class="p">),</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div> |
| <div class="viewcode-block" id="SerializedDagModel.last_updated"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.last_updated">[docs]</a> <span class="n">last_updated</span> <span class="o">=</span> <span class="n">Column</span><span class="p">(</span><span class="n">UtcDateTime</span><span class="p">,</span> <span class="n">nullable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SerializedDagModel.__table_args__"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.__table_args__">[docs]</a> <span class="n">__table_args__</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">Index</span><span class="p">(</span><span class="s1">'idx_fileloc_hash'</span><span class="p">,</span> <span class="n">fileloc_hash</span><span class="p">,</span> <span class="n">unique</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span></div> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dag</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fileloc</span> <span class="o">=</span> <span class="n">dag</span><span class="o">.</span><span class="n">full_filepath</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fileloc_hash</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">dag_fileloc_hash</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fileloc</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">SerializedDAG</span><span class="o">.</span><span class="n">to_dict</span><span class="p">(</span><span class="n">dag</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">last_updated</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="nd">@staticmethod</span> |
| <div class="viewcode-block" id="SerializedDagModel.dag_fileloc_hash"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.dag_fileloc_hash">[docs]</a> <span class="k">def</span> <span class="nf">dag_fileloc_hash</span><span class="p">(</span><span class="n">full_filepath</span><span class="p">):</span> |
| <span class="c1"># type: (str) -> int</span> |
| <span class="sd">""""Hashing file location for indexing.</span> |
| |
| <span class="sd"> :param full_filepath: full filepath of DAG file</span> |
| <span class="sd"> :return: hashed full_filepath</span> |
| <span class="sd"> """</span> |
| <span class="c1"># hashing is needed because the length of fileloc is 2000 as an Airflow convention,</span> |
| <span class="c1"># which is over the limit of indexing. If we can reduce the length of fileloc, then</span> |
| <span class="c1"># hashing is not needed.</span> |
| <span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="mh">0xFFFF</span> <span class="o">&</span> <span class="nb">int</span><span class="p">(</span> |
| <span class="n">hashlib</span><span class="o">.</span><span class="n">sha1</span><span class="p">(</span><span class="n">full_filepath</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">))</span><span class="o">.</span><span class="n">hexdigest</span><span class="p">(),</span> <span class="mi">16</span><span class="p">))</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.write_dag"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.write_dag">[docs]</a> <span class="k">def</span> <span class="nf">write_dag</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> |
| <span class="n">dag</span><span class="p">,</span> <span class="c1"># type: DAG</span> |
| <span class="n">min_update_interval</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[int]</span> |
| <span class="n">session</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Serializes a DAG and writes it into database.</span> |
| |
| <span class="sd"> :param dag: a DAG to be written into database</span> |
| <span class="sd"> :param min_update_interval: minimal interval in seconds to update serialized DAG</span> |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> """</span> |
| <span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Writing DAG: </span><span class="si">%s</span><span class="s2"> to the DB"</span><span class="p">,</span> <span class="n">dag</span><span class="p">)</span> |
| <span class="c1"># Checks if (Current Time - Time when the DAG was written to DB) < min_update_interval</span> |
| <span class="c1"># If Yes, does nothing</span> |
| <span class="c1"># If No or the DAG does not exists, updates / writes Serialized DAG to DB</span> |
| <span class="k">if</span> <span class="n">min_update_interval</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">exists</span><span class="p">()</span><span class="o">.</span><span class="n">where</span><span class="p">(</span> |
| <span class="n">and_</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">,</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">timedelta</span><span class="p">(</span><span class="n">seconds</span><span class="o">=</span><span class="n">min_update_interval</span><span class="p">))</span> <span class="o"><</span> <span class="bp">cls</span><span class="o">.</span><span class="n">last_updated</span><span class="p">))</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">scalar</span><span class="p">():</span> |
| <span class="k">return</span> |
| |
| <span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Writing DAG: </span><span class="si">%s</span><span class="s2"> to the DB"</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="n">session</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="bp">cls</span><span class="p">(</span><span class="n">dag</span><span class="p">))</span> |
| <span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"DAG: </span><span class="si">%s</span><span class="s2"> written to the DB"</span><span class="p">,</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span><span class="p">)</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.read_all_dags"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.read_all_dags">[docs]</a> <span class="k">def</span> <span class="nf">read_all_dags</span><span class="p">(</span><span class="bp">cls</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">"""Reads all DAGs in serialized_dag table.</span> |
| |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> :returns: a dict of DAGs read from database</span> |
| <span class="sd"> """</span> |
| <span class="n">serialized_dags</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="bp">cls</span><span class="p">)</span> |
| |
| <span class="n">dags</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">serialized_dags</span><span class="p">:</span> |
| <span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Deserializing DAG: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">row</span><span class="o">.</span><span class="n">dag_id</span><span class="p">)</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="c1"># Sanity check.</span> |
| <span class="k">if</span> <span class="n">dag</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">row</span><span class="o">.</span><span class="n">dag_id</span><span class="p">:</span> |
| <span class="n">dags</span><span class="p">[</span><span class="n">row</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">else</span><span class="p">:</span> |
| <span class="n">log</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span> |
| <span class="s2">"dag_id Mismatch in DB: Row with dag_id '</span><span class="si">%s</span><span class="s2">' has Serialised DAG "</span> |
| <span class="s2">"with '</span><span class="si">%s</span><span class="s2">' dag_id"</span><span class="p">,</span> <span class="n">row</span><span class="o">.</span><span class="n">dag_id</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="k">return</span> <span class="n">dags</span></div> |
| |
| <span class="nd">@property</span> |
| <div class="viewcode-block" id="SerializedDagModel.dag"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.dag">[docs]</a> <span class="k">def</span> <span class="nf">dag</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""The DAG deserialized from the ``data`` column"""</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="n">dag</span> <span class="o">=</span> <span class="n">SerializedDAG</span><span class="o">.</span><span class="n">from_dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">)</span> <span class="c1"># type: Any</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># noinspection PyTypeChecker</span> |
| <span class="n">dag</span> <span class="o">=</span> <span class="n">SerializedDAG</span><span class="o">.</span><span class="n">from_json</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">dag</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.remove_dag"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.remove_dag">[docs]</a> <span class="k">def</span> <span class="nf">remove_dag</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">dag_id</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">"""Deletes a DAG with given dag_id.</span> |
| |
| <span class="sd"> :param dag_id: dag_id to be deleted</span> |
| <span class="sd"> :type dag_id: str</span> |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> """</span> |
| <span class="n">session</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">__table__</span><span class="o">.</span><span class="n">delete</span><span class="p">()</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">dag_id</span><span class="p">))</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.remove_deleted_dags"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.remove_deleted_dags">[docs]</a> <span class="k">def</span> <span class="nf">remove_deleted_dags</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">alive_dag_filelocs</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">"""Deletes DAGs not included in alive_dag_filelocs.</span> |
| |
| <span class="sd"> :param alive_dag_filelocs: file paths of alive DAGs</span> |
| <span class="sd"> :type alive_dag_filelocs: list</span> |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> """</span> |
| <span class="n">alive_fileloc_hashes</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">dag_fileloc_hash</span><span class="p">(</span><span class="n">fileloc</span><span class="p">)</span> <span class="k">for</span> <span class="n">fileloc</span> <span class="ow">in</span> <span class="n">alive_dag_filelocs</span><span class="p">]</span> |
| |
| <span class="n">log</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"Deleting Serialized DAGs (for which DAG files are deleted) "</span> |
| <span class="s2">"from </span><span class="si">%s</span><span class="s2"> table "</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="n">__tablename__</span><span class="p">)</span> |
| |
| <span class="n">session</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">__table__</span><span class="o">.</span><span class="n">delete</span><span class="p">()</span><span class="o">.</span><span class="n">where</span><span class="p">(</span> |
| <span class="n">and_</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">fileloc_hash</span><span class="o">.</span><span class="n">notin_</span><span class="p">(</span><span class="n">alive_fileloc_hashes</span><span class="p">),</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">fileloc</span><span class="o">.</span><span class="n">notin_</span><span class="p">(</span><span class="n">alive_dag_filelocs</span><span class="p">))))</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.has_dag"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.has_dag">[docs]</a> <span class="k">def</span> <span class="nf">has_dag</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">dag_id</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">"""Checks a DAG exist in serialized_dag table.</span> |
| |
| <span class="sd"> :param dag_id: the DAG to check</span> |
| <span class="sd"> :type dag_id: str</span> |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> :rtype: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="n">exists</span><span class="p">()</span><span class="o">.</span><span class="n">where</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">dag_id</span><span class="p">))</span><span class="o">.</span><span class="n">scalar</span><span class="p">()</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="nd">@db</span><span class="o">.</span><span class="n">provide_session</span> |
| <div class="viewcode-block" id="SerializedDagModel.get"><a class="viewcode-back" href="../../../_api/airflow/models/serialized_dag/index.html#airflow.models.serialized_dag.SerializedDagModel.get">[docs]</a> <span class="k">def</span> <span class="nf">get</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">dag_id</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">"""</span> |
| <span class="sd"> Get the SerializedDAG for the given dag ID.</span> |
| <span class="sd"> It will cope with being passed the ID of a subdag by looking up the</span> |
| <span class="sd"> root dag_id from the DAG table.</span> |
| |
| <span class="sd"> :param dag_id: the DAG to fetch</span> |
| <span class="sd"> :param session: ORM Session</span> |
| <span class="sd"> """</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="n">row</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="bp">cls</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">dag_id</span><span class="p">)</span><span class="o">.</span><span class="n">one_or_none</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">row</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">row</span> |
| |
| <span class="c1"># If we didn't find a matching DAG id then ask the DAG table to find</span> |
| <span class="c1"># out the root dag</span> |
| <span class="n">root_dag_id</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">DagModel</span><span class="o">.</span><span class="n">root_dag_id</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">DagModel</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">dag_id</span><span class="p">)</span><span class="o">.</span><span class="n">scalar</span><span class="p">()</span> |
| |
| <span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">query</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">dag_id</span> <span class="o">==</span> <span class="n">root_dag_id</span><span class="p">)</span><span class="o">.</span><span class="n">one_or_none</span><span class="p">()</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="../../../privacy_notice.html">Privacy Policy</a> |
| for more details. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |