http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/hooks/wasb_hook.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/hooks/wasb_hook.html b/_modules/airflow/contrib/hooks/wasb_hook.html new file mode 100644 index 0000000..2ff6ba4 --- /dev/null +++ b/_modules/airflow/contrib/hooks/wasb_hook.html @@ -0,0 +1,345 @@ + + +<!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.contrib.hooks.wasb_hook — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../../index.html" class="icon icon-home"> Airflow + + + + </a> + + + + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../configuration.html">Configuration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + + + + + + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + + <ul class="wy-breadcrumbs"> + + <li><a href="../../../../index.html">Docs</a> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.hooks.wasb_hook</li> + + + <li class="wy-breadcrumbs-aside"> + + + + </li> + + </ul> + + + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> + <div itemprop="articleBody"> + + <h1>Source code for airflow.contrib.hooks.wasb_hook</h1><div class="highlight"><pre> +<span></span><span class="c1"># -*- coding: utf-8 -*-</span> +<span class="c1">#</span> +<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span> +<span class="c1"># you may not use this file except in compliance with the License.</span> +<span class="c1"># 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, software</span> +<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> +<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> +<span class="c1"># See the License for the specific language governing permissions and</span> +<span class="c1"># limitations under the License.</span> +<span class="c1">#</span> + +<span class="kn">from</span> <span class="nn">airflow.hooks.base_hook</span> <span class="k">import</span> <span class="n">BaseHook</span> + +<span class="kn">from</span> <span class="nn">azure.storage.blob</span> <span class="k">import</span> <span class="n">BlockBlobService</span> + + +<div class="viewcode-block" id="WasbHook"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.hooks.wasb_hook.WasbHook">[docs]</a><span class="k">class</span> <span class="nc">WasbHook</span><span class="p">(</span><span class="n">BaseHook</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Interacts with Azure Blob Storage through the wasb:// protocol.</span> +<span class="sd"> </span> +<span class="sd"> Additional options passed in the 'extra' field of the connection will be</span> +<span class="sd"> passed to the `BlockBlockService()` constructor. For example, authenticate</span> +<span class="sd"> using a SAS token by adding {"sas_token": "YOUR_TOKEN"}.</span> +<span class="sd"> </span> +<span class="sd"> :param wasb_conn_id: Reference to the wasb connection.</span> +<span class="sd"> :type wasb_conn_id: str</span> +<span class="sd"> """</span> + + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">wasb_conn_id</span><span class="o">=</span><span class="s1">'wasb_default'</span><span class="p">):</span> + <span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span> <span class="o">=</span> <span class="n">wasb_conn_id</span> + <span class="bp">self</span><span class="o">.</span><span class="n">connection</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + + <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="sd">"""Return the BlockBlobService object."""</span> + <span class="n">conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_connection</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conn_id</span><span class="p">)</span> + <span class="n">service_options</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">extra_dejson</span> + <span class="k">return</span> <span class="n">BlockBlobService</span><span class="p">(</span><span class="n">account_name</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">login</span><span class="p">,</span> + <span class="n">account_key</span><span class="o">=</span><span class="n">conn</span><span class="o">.</span><span class="n">password</span><span class="p">,</span> <span class="o">**</span><span class="n">service_options</span><span class="p">)</span> + + <span class="k">def</span> <span class="nf">check_for_blob</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Check if a blob exists on Azure Blob Storage.</span> +<span class="sd"> </span> +<span class="sd"> :param container_name: Name of the container.</span> +<span class="sd"> :type container_name: str</span> +<span class="sd"> :param blob_name: Name of the blob.</span> +<span class="sd"> :type blob_name: str</span> +<span class="sd"> :param kwargs: Optional keyword arguments that</span> +<span class="sd"> `BlockBlobService.exists()` takes.</span> +<span class="sd"> :type kwargs: object</span> +<span class="sd"> :return: True if the blob exists, False otherwise.</span> +<span class="sd"> :rtype bool</span> +<span class="sd"> """</span> + <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + + <span class="k">def</span> <span class="nf">check_for_prefix</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">container_name</span><span class="p">,</span> <span class="n">prefix</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Check if a prefix exists on Azure Blob storage.</span> +<span class="sd"> </span> +<span class="sd"> :param container_name: Name of the container.</span> +<span class="sd"> :type container_name: str</span> +<span class="sd"> :param prefix: Prefix of the blob.</span> +<span class="sd"> :type prefix: str</span> +<span class="sd"> :param kwargs: Optional keyword arguments that</span> +<span class="sd"> `BlockBlobService.list_blobs()` takes.</span> +<span class="sd"> :type kwargs: object</span> +<span class="sd"> :return: True if blobs matching the prefix exist, False otherwise.</span> +<span class="sd"> :rtype bool</span> +<span class="sd"> """</span> + <span class="n">matches</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">list_blobs</span><span class="p">(</span><span class="n">container_name</span><span class="p">,</span> <span class="n">prefix</span><span class="p">,</span> + <span class="n">num_results</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">matches</span><span class="p">))</span> <span class="o">></span> <span class="mi">0</span> + + <span class="k">def</span> <span class="nf">load_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_path</span><span class="p">,</span> <span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Upload a file to Azure Blob Storage.</span> +<span class="sd"> </span> +<span class="sd"> :param file_path: Path to the file to load.</span> +<span class="sd"> :type file_path: str</span> +<span class="sd"> :param container_name: Name of the container.</span> +<span class="sd"> :type container_name: str</span> +<span class="sd"> :param blob_name: Name of the blob.</span> +<span class="sd"> :type blob_name: str</span> +<span class="sd"> :param kwargs: Optional keyword arguments that</span> +<span class="sd"> `BlockBlobService.create_blob_from_path()` takes.</span> +<span class="sd"> :type kwargs: object</span> +<span class="sd"> """</span> + <span class="c1"># Reorder the argument order from airflow.hooks.S3_hook.load_file.</span> + <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">create_blob_from_path</span><span class="p">(</span><span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> + <span class="n">file_path</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + + <span class="k">def</span> <span class="nf">load_string</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">string_data</span><span class="p">,</span> <span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Upload a string to Azure Blob Storage.</span> +<span class="sd"> </span> +<span class="sd"> :param string_data: String to load.</span> +<span class="sd"> :type string_data: str</span> +<span class="sd"> :param container_name: Name of the container.</span> +<span class="sd"> :type container_name: str</span> +<span class="sd"> :param blob_name: Name of the blob.</span> +<span class="sd"> :type blob_name: str</span> +<span class="sd"> :param kwargs: Optional keyword arguments that</span> +<span class="sd"> `BlockBlobService.create_blob_from_text()` takes.</span> +<span class="sd"> :type kwargs: object</span> +<span class="sd"> """</span> + <span class="c1"># Reorder the argument order from airflow.hooks.S3_hook.load_string.</span> + <span class="bp">self</span><span class="o">.</span><span class="n">connection</span><span class="o">.</span><span class="n">create_blob_from_text</span><span class="p">(</span><span class="n">container_name</span><span class="p">,</span> <span class="n">blob_name</span><span class="p">,</span> + <span class="n">string_data</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> +</pre></div> + + </div> + <div class="articleComments"> + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + + </p> + </div> + Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </script> + <script type="text/javascript" src="../../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/operators/bigquery_check_operator.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/operators/bigquery_check_operator.html b/_modules/airflow/contrib/operators/bigquery_check_operator.html new file mode 100644 index 0000000..cbad19f --- /dev/null +++ b/_modules/airflow/contrib/operators/bigquery_check_operator.html @@ -0,0 +1,358 @@ + + +<!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.contrib.operators.bigquery_check_operator — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../../index.html" class="icon icon-home"> Airflow + + + + </a> + + + + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../configuration.html">Configuration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + + + + + + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + + <ul class="wy-breadcrumbs"> + + <li><a href="../../../../index.html">Docs</a> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.operators.bigquery_check_operator</li> + + + <li class="wy-breadcrumbs-aside"> + + + + </li> + + </ul> + + + <hr/> +</div> + <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> + <div itemprop="articleBody"> + + <h1>Source code for airflow.contrib.operators.bigquery_check_operator</h1><div class="highlight"><pre> +<span></span><span class="c1"># -*- coding: utf-8 -*-</span> +<span class="c1">#</span> +<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span> +<span class="c1"># you may not use this file except in compliance with the License.</span> +<span class="c1"># 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, software</span> +<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> +<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> +<span class="c1"># See the License for the specific language governing permissions and</span> +<span class="c1"># limitations under the License.</span> + +<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</span> +<span class="kn">from</span> <span class="nn">airflow.operators.check_operator</span> <span class="k">import</span> <span class="n">CheckOperator</span><span class="p">,</span> <span class="n">ValueCheckOperator</span><span class="p">,</span> <span class="n">IntervalCheckOperator</span> +<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> + + +<div class="viewcode-block" id="BigQueryCheckOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_check_operator.BigQueryCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryCheckOperator</span><span class="p">(</span><span class="n">CheckOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Performs checks against BigQuery. The ``BigQueryCheckOperator`` expects</span> +<span class="sd"> a sql query that will return a single row. Each value on that</span> +<span class="sd"> first row is evaluated using python ``bool`` casting. If any of the</span> +<span class="sd"> values return ``False`` the check is failed and errors out.</span> + +<span class="sd"> Note that Python bool casting evals the following as ``False``:</span> + +<span class="sd"> * ``False``</span> +<span class="sd"> * ``0``</span> +<span class="sd"> * Empty string (``""``)</span> +<span class="sd"> * Empty list (``[]``)</span> +<span class="sd"> * Empty dictionary or set (``{}``)</span> + +<span class="sd"> Given a query like ``SELECT COUNT(*) FROM foo``, it will fail only if</span> +<span class="sd"> the count ``== 0``. You can craft much more complex query that could,</span> +<span class="sd"> for instance, check that the table has the same number of rows as</span> +<span class="sd"> the source table upstream, or that the count of today's partition is</span> +<span class="sd"> greater than yesterday's partition, or that a set of metrics are less</span> +<span class="sd"> than 3 standard deviation for the 7 day average.</span> + +<span class="sd"> This operator can be used as a data quality check in your pipeline, and</span> +<span class="sd"> depending on where you put it in your DAG, you have the choice to</span> +<span class="sd"> stop the critical path, preventing from</span> +<span class="sd"> publishing dubious data, or on the side and receive email alterts</span> +<span class="sd"> without stopping the progress of the DAG.</span> + +<span class="sd"> :param sql: the sql to be executed</span> +<span class="sd"> :type sql: string</span> +<span class="sd"> :param bigquery_conn_id: reference to the BigQuery database</span> +<span class="sd"> :type bigquery_conn_id: string</span> +<span class="sd"> """</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> + <span class="bp">self</span><span class="p">,</span> + <span class="n">sql</span><span class="p">,</span> + <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> + <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">sql</span><span class="o">=</span><span class="n">sql</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> + <span class="bp">self</span><span class="o">.</span><span class="n">sql</span> <span class="o">=</span> <span class="n">sql</span> + + <span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">)</span></div> + + +<div class="viewcode-block" id="BigQueryValueCheckOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_check_operator.BigQueryValueCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryValueCheckOperator</span><span class="p">(</span><span class="n">ValueCheckOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Performs a simple value check using sql code.</span> + +<span class="sd"> :param sql: the sql to be executed</span> +<span class="sd"> :type sql: string</span> +<span class="sd"> """</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> + <span class="bp">self</span><span class="p">,</span> <span class="n">sql</span><span class="p">,</span> <span class="n">pass_value</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryValueCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> + <span class="n">sql</span><span class="o">=</span><span class="n">sql</span><span class="p">,</span> <span class="n">pass_value</span><span class="o">=</span><span class="n">pass_value</span><span class="p">,</span> <span class="n">tolerance</span><span class="o">=</span><span class="n">tolerance</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> + + <span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">)</span></div> + + +<div class="viewcode-block" id="BigQueryIntervalCheckOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_check_operator.BigQueryIntervalCheckOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryIntervalCheckOperator</span><span class="p">(</span><span class="n">IntervalCheckOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Checks that the values of metrics given as SQL expressions are within</span> +<span class="sd"> a certain tolerance of the ones from days_back before.</span> + +<span class="sd"> This method constructs a query like so:</span> + +<span class="sd"> SELECT {metrics_threshold_dict_key} FROM {table}</span> +<span class="sd"> WHERE {date_filter_column}=<date></span> + +<span class="sd"> :param table: the table name</span> +<span class="sd"> :type table: str</span> +<span class="sd"> :param days_back: number of days between ds and the ds we want to check</span> +<span class="sd"> against. Defaults to 7 days</span> +<span class="sd"> :type days_back: int</span> +<span class="sd"> :param metrics_threshold: a dictionary of ratios indexed by metrics, for</span> +<span class="sd"> example 'COUNT(*)': 1.5 would require a 50 percent or less difference</span> +<span class="sd"> between the current day, and the prior days_back.</span> +<span class="sd"> :type metrics_threshold: dict</span> +<span class="sd"> """</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span> + <span class="bp">self</span><span class="p">,</span> <span class="n">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="p">,</span> + <span class="n">date_filter_column</span><span class="o">=</span><span class="s1">'ds'</span><span class="p">,</span> <span class="n">days_back</span><span class="o">=-</span><span class="mi">7</span><span class="p">,</span> + <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryIntervalCheckOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> + <span class="n">table</span><span class="o">=</span><span class="n">table</span><span class="p">,</span> <span class="n">metrics_thresholds</span><span class="o">=</span><span class="n">metrics_thresholds</span><span class="p">,</span> + <span class="n">date_filter_column</span><span class="o">=</span><span class="n">date_filter_column</span><span class="p">,</span> <span class="n">days_back</span><span class="o">=</span><span class="n">days_back</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> + + <span class="k">def</span> <span class="nf">get_db_hook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="k">return</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">)</span></div> +</pre></div> + + </div> + <div class="articleComments"> + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + + </p> + </div> + Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </script> + <script type="text/javascript" src="../../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/operators/bigquery_operator.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/operators/bigquery_operator.html b/_modules/airflow/contrib/operators/bigquery_operator.html index c7fcfd9..5a74ba1 100644 --- a/_modules/airflow/contrib/operators/bigquery_operator.html +++ b/_modules/airflow/contrib/operators/bigquery_operator.html @@ -13,6 +13,8 @@ + + @@ -30,6 +32,9 @@ + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> <link rel="up" title="Module code" href="../../../index.html"/> @@ -40,6 +45,7 @@ <body class="wy-body-for-nav" role="document"> + <div class="wy-grid-for-nav"> @@ -76,7 +82,10 @@ - <ul> + + + + <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> @@ -90,6 +99,8 @@ <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> </ul> @@ -104,8 +115,10 @@ <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> - <i data-toggle="wy-nav-top" class="fa fa-bars"></i> - <a href="../../../../index.html">Airflow</a> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + </nav> @@ -118,19 +131,36 @@ + + + + + + + + + + <div role="navigation" aria-label="breadcrumbs navigation"> + <ul class="wy-breadcrumbs"> - <li><a href="../../../../index.html">Docs</a> »</li> - + + <li><a href="../../../../index.html">Docs</a> »</li> + <li><a href="../../../index.html">Module code</a> »</li> - - <li>airflow.contrib.operators.bigquery_operator</li> + + <li>airflow.contrib.operators.bigquery_operator</li> + + <li class="wy-breadcrumbs-aside"> - + </li> + </ul> + + <hr/> </div> <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> @@ -151,16 +181,47 @@ <span class="c1"># See the License for the specific language governing permissions and</span> <span class="c1"># limitations under the License.</span> -<span class="kn">import</span> <span class="nn">logging</span> - -<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="kn">import</span> <span class="n">BigQueryHook</span> -<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="kn">import</span> <span class="n">BaseOperator</span> -<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="kn">import</span> <span class="n">apply_defaults</span> +<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</span> +<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> +<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> -<div class="viewcode-block" id="BigQueryOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.bigquery_operator.BigQueryOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> +<div class="viewcode-block" id="BigQueryOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_operator.BigQueryOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> <span class="sd">"""</span> <span class="sd"> Executes BigQuery SQL queries in a specific BigQuery database</span> + +<span class="sd"> :param bql: the sql code to be executed</span> +<span class="sd"> :type bql: Can receive a str representing a sql statement,</span> +<span class="sd"> a list of str (sql statements), or reference to a template file.</span> +<span class="sd"> Template reference are recognized by str ending in '.sql'</span> +<span class="sd"> :param destination_dataset_table: A dotted</span> +<span class="sd"> (<project>.|<project>:)<dataset>.<table> that, if set, will store the results</span> +<span class="sd"> of the query.</span> +<span class="sd"> :type destination_dataset_table: string</span> +<span class="sd"> :param write_disposition: Specifies the action that occurs if the destination table</span> +<span class="sd"> already exists. (default: 'WRITE_EMPTY')</span> +<span class="sd"> :type write_disposition: string</span> +<span class="sd"> :param create_disposition: Specifies whether the job is allowed to create new tables.</span> +<span class="sd"> (default: 'CREATE_IF_NEEDED')</span> +<span class="sd"> :type create_disposition: string</span> +<span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span> +<span class="sd"> :type bigquery_conn_id: string</span> +<span class="sd"> :param delegate_to: The account to impersonate, if any.</span> +<span class="sd"> For this to work, the service account making the request must have domain-wide</span> +<span class="sd"> delegation enabled.</span> +<span class="sd"> :type delegate_to: string</span> +<span class="sd"> :param udf_config: The User Defined Function configuration for the query.</span> +<span class="sd"> See https://cloud.google.com/bigquery/user-defined-functions for details.</span> +<span class="sd"> :type udf_config: list</span> +<span class="sd"> :param use_legacy_sql: Whether to use legacy SQL (true) or standard SQL (false).</span> +<span class="sd"> :type use_legacy_sql: boolean</span> +<span class="sd"> :param maximum_billing_tier: Positive integer that serves as a multiplier of the basic price.</span> +<span class="sd"> Defaults to None, in which case it uses the value set in the project.</span> +<span class="sd"> :type maximum_billing_tier: integer</span> +<span class="sd"> :param query_params: a dictionary containing query parameter types and values, passed to</span> +<span class="sd"> BigQuery.</span> +<span class="sd"> :type query_params: dict</span> + <span class="sd"> """</span> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'bql'</span><span class="p">,</span> <span class="s1">'destination_dataset_table'</span><span class="p">)</span> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span> @@ -169,51 +230,47 @@ <span class="nd">@apply_defaults</span> <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bql</span><span class="p">,</span> - <span class="n">destination_dataset_table</span> <span class="o">=</span> <span class="bp">False</span><span class="p">,</span> - <span class="n">write_disposition</span> <span class="o">=</span> <span class="s1">'WRITE_EMPTY'</span><span class="p">,</span> - <span class="n">allow_large_results</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> + <span class="n">destination_dataset_table</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> + <span class="n">write_disposition</span><span class="o">=</span><span class="s1">'WRITE_EMPTY'</span><span class="p">,</span> + <span class="n">allow_large_results</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> - <span class="n">delegate_to</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> - <span class="n">udf_config</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> + <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">udf_config</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> + <span class="n">use_legacy_sql</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> + <span class="n">maximum_billing_tier</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">create_disposition</span><span class="o">=</span><span class="s1">'CREATE_IF_NEEDED'</span><span class="p">,</span> + <span class="n">query_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> - <span class="sd">"""</span> -<span class="sd"> Create a new BigQueryOperator.</span> - -<span class="sd"> :param bql: the sql code to be executed</span> -<span class="sd"> :type bql: Can receive a str representing a sql statement,</span> -<span class="sd"> a list of str (sql statements), or reference to a template file.</span> -<span class="sd"> Template reference are recognized by str ending in '.sql'</span> -<span class="sd"> :param destination_dataset_table: A dotted dataset.table that, if set,</span> -<span class="sd"> will store the results of the query.</span> -<span class="sd"> :type destination_dataset_table: string</span> -<span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span> -<span class="sd"> :type bigquery_conn_id: string</span> -<span class="sd"> :param delegate_to: The account to impersonate, if any.</span> -<span class="sd"> For this to work, the service account making the request must have domain-wide delegation enabled.</span> -<span class="sd"> :type delegate_to: string</span> -<span class="sd"> :param udf_config: The User Defined Function configuration for the query.</span> -<span class="sd"> See https://cloud.google.com/bigquery/user-defined-functions for details.</span> -<span class="sd"> :type udf_config: list</span> -<span class="sd"> """</span> - <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> <span class="bp">self</span><span class="o">.</span><span class="n">bql</span> <span class="o">=</span> <span class="n">bql</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_dataset_table</span> <span class="o">=</span> <span class="n">destination_dataset_table</span> <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">write_disposition</span> + <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">create_disposition</span> <span class="bp">self</span><span class="o">.</span><span class="n">allow_large_results</span> <span class="o">=</span> <span class="n">allow_large_results</span> <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> <span class="bp">self</span><span class="o">.</span><span class="n">udf_config</span> <span class="o">=</span> <span class="n">udf_config</span> + <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span> <span class="o">=</span> <span class="n">use_legacy_sql</span> + <span class="bp">self</span><span class="o">.</span><span class="n">maximum_billing_tier</span> <span class="o">=</span> <span class="n">maximum_billing_tier</span> + <span class="bp">self</span><span class="o">.</span><span class="n">query_params</span> <span class="o">=</span> <span class="n">query_params</span> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> - <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bql</span><span class="p">))</span> - <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Executing: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">bql</span><span class="p">)</span> + <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span> + <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> <span class="n">conn</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> <span class="n">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> - <span class="n">cursor</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bql</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_dataset_table</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">allow_large_results</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">udf_config</span><span class="p">)</span></div> + <span class="n">cursor</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bql</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_dataset_table</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">allow_large_results</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">udf_config</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">maximum_billing_tier</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">query_params</span><span class="p">)</span></div> </pre></div> </div> + <div class="articleComments"> + + </div> </div> <footer> @@ -246,7 +303,8 @@ VERSION:'', COLLAPSE_INDEX:false, FILE_SUFFIX:'.html', - HAS_SOURCE: true + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' }; </script> <script type="text/javascript" src="../../../../_static/jquery.js"></script> http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/28a3eb60/_modules/airflow/contrib/operators/bigquery_to_bigquery.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/operators/bigquery_to_bigquery.html b/_modules/airflow/contrib/operators/bigquery_to_bigquery.html new file mode 100644 index 0000000..ab12d51 --- /dev/null +++ b/_modules/airflow/contrib/operators/bigquery_to_bigquery.html @@ -0,0 +1,316 @@ + + +<!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.contrib.operators.bigquery_to_bigquery — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../../index.html" class="icon icon-home"> Airflow + + + + </a> + + + + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../configuration.html">Configuration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + + + + + + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + + <ul class="wy-breadcrumbs"> + + <li><a href="../../../../index.html">Docs</a> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.operators.bigquery_to_bigquery</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.contrib.operators.bigquery_to_bigquery</h1><div class="highlight"><pre> +<span></span><span class="c1"># -*- coding: utf-8 -*-</span> +<span class="c1">#</span> +<span class="c1"># Licensed under the Apache License, Version 2.0 (the "License");</span> +<span class="c1"># you may not use this file except in compliance with the License.</span> +<span class="c1"># 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, software</span> +<span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> +<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> +<span class="c1"># See the License for the specific language governing permissions and</span> +<span class="c1"># limitations under the License.</span> + +<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</span> +<span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> +<span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> + + +<div class="viewcode-block" id="BigQueryToBigQueryOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_to_bigquery.BigQueryToBigQueryOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryToBigQueryOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Copies data from one BigQuery table to another. See here:</span> + +<span class="sd"> https://cloud.google.com/bigquery/docs/reference/v2/jobs#configuration.copy</span> + +<span class="sd"> For more details about these parameters.</span> + +<span class="sd"> :param source_project_dataset_tables: One or more</span> +<span class="sd"> dotted (project:|project.)<dataset>.<table> BigQuery tables to use as the</span> +<span class="sd"> source data. If <project> is not included, project will be the project defined</span> +<span class="sd"> in the connection json. Use a list if there are multiple source tables.</span> +<span class="sd"> :type source_project_dataset_tables: list|string</span> +<span class="sd"> :param destination_project_dataset_table: The destination BigQuery</span> +<span class="sd"> table. Format is: (project:|project.)<dataset>.<table></span> +<span class="sd"> :type destination_project_dataset_table: string</span> +<span class="sd"> :param write_disposition: The write disposition if the table already exists.</span> +<span class="sd"> :type write_disposition: string</span> +<span class="sd"> :param create_disposition: The create disposition if the table doesn't exist.</span> +<span class="sd"> :type create_disposition: string</span> +<span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span> +<span class="sd"> :type bigquery_conn_id: string</span> +<span class="sd"> :param delegate_to: The account to impersonate, if any.</span> +<span class="sd"> For this to work, the service account making the request must have domain-wide</span> +<span class="sd"> delegation enabled.</span> +<span class="sd"> :type delegate_to: string</span> +<span class="sd"> """</span> + <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'source_project_dataset_tables'</span><span class="p">,</span> + <span class="s1">'destination_project_dataset_table'</span><span class="p">)</span> + <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span> + <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#e6f0e4'</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> + <span class="n">source_project_dataset_tables</span><span class="p">,</span> + <span class="n">destination_project_dataset_table</span><span class="p">,</span> + <span class="n">write_disposition</span><span class="o">=</span><span class="s1">'WRITE_EMPTY'</span><span class="p">,</span> + <span class="n">create_disposition</span><span class="o">=</span><span class="s1">'CREATE_IF_NEEDED'</span><span class="p">,</span> + <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> + <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> + <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryToBigQueryOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> + <span class="bp">self</span><span class="o">.</span><span class="n">source_project_dataset_tables</span> <span class="o">=</span> <span class="n">source_project_dataset_tables</span> + <span class="bp">self</span><span class="o">.</span><span class="n">destination_project_dataset_table</span> <span class="o">=</span> <span class="n">destination_project_dataset_table</span> + <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span> <span class="o">=</span> <span class="n">write_disposition</span> + <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span> <span class="o">=</span> <span class="n">create_disposition</span> + <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> + <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> + + <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> + <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> + <span class="s1">'Executing copy of </span><span class="si">%s</span><span class="s1"> into: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">source_project_dataset_tables</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">destination_project_dataset_table</span> + <span class="p">)</span> + <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span> + <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> + <span class="n">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> + <span class="n">cursor</span><span class="o">.</span><span class="n">run_copy</span><span class="p">(</span> + <span class="bp">self</span><span class="o">.</span><span class="n">source_project_dataset_tables</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">destination_project_dataset_table</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> + <span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">)</span></div> +</pre></div> + + </div> + <div class="articleComments"> + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + + </p> + </div> + Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </script> + <script type="text/javascript" src="../../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file
