| |
| |
| <!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_operator — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| |
| <script src="../../../../_static/js/modernizr.min.js"></script> |
| |
| </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"> |
| 1.10.2 |
| </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</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">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="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../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" 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_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_operator</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="kn">import</span> <span class="nn">json</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.contrib.hooks.gcs_hook</span> <span class="k">import</span> <span class="n">GoogleCloudStorageHook</span><span class="p">,</span> <span class="n">_parse_gcs_url</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="../../../../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: (Deprecated. Use `sql` parameter instead) the sql code to be</span> |
| <span class="sd"> executed (templated)</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 sql: the sql code to be executed (templated)</span> |
| <span class="sd"> :type sql: 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. (templated)</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 allow_large_results: Whether to allow large results.</span> |
| <span class="sd"> :type allow_large_results: boolean</span> |
| <span class="sd"> :param flatten_results: If true and query uses legacy SQL dialect, flattens</span> |
| <span class="sd"> all nested and repeated fields in the query results. ``allow_large_results``</span> |
| <span class="sd"> must be ``true`` if this is set to ``false``. For standard SQL queries, this</span> |
| <span class="sd"> flag is ignored and results are never flattened.</span> |
| <span class="sd"> :type flatten_results: boolean</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</span> |
| <span class="sd"> 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 maximum_bytes_billed: Limits the bytes billed for this job.</span> |
| <span class="sd"> Queries that will have bytes billed beyond this limit will fail</span> |
| <span class="sd"> (without incurring a charge). If unspecified, this will be</span> |
| <span class="sd"> set to your project default.</span> |
| <span class="sd"> :type maximum_bytes_billed: float</span> |
| <span class="sd"> :param api_resource_configs: a dictionary that contain params</span> |
| <span class="sd"> 'configuration' applied for Google BigQuery Jobs API:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs</span> |
| <span class="sd"> for example, {'query': {'useQueryCache': False}}. You could use it</span> |
| <span class="sd"> if you need to provide some params that are not supported by BigQueryOperator</span> |
| <span class="sd"> like args.</span> |
| <span class="sd"> :type api_resource_configs: dict</span> |
| <span class="sd"> :param schema_update_options: Allows the schema of the destination</span> |
| <span class="sd"> table to be updated as a side effect of the load job.</span> |
| <span class="sd"> :type schema_update_options: tuple</span> |
| <span class="sd"> :param query_params: a dictionary containing query parameter types and</span> |
| <span class="sd"> values, passed to BigQuery.</span> |
| <span class="sd"> :type query_params: dict</span> |
| <span class="sd"> :param labels: a dictionary containing labels for the job/query,</span> |
| <span class="sd"> passed to BigQuery</span> |
| <span class="sd"> :type labels: dict</span> |
| <span class="sd"> :param priority: Specifies a priority for the query.</span> |
| <span class="sd"> Possible values include INTERACTIVE and BATCH.</span> |
| <span class="sd"> The default value is INTERACTIVE.</span> |
| <span class="sd"> :type priority: string</span> |
| <span class="sd"> :param time_partitioning: configure optional time partitioning fields i.e.</span> |
| <span class="sd"> partition by field, type and expiration as per API specifications.</span> |
| <span class="sd"> :type time_partitioning: dict</span> |
| <span class="sd"> :param cluster_fields: Request that the result of this query be stored sorted</span> |
| <span class="sd"> by one or more columns. This is only available in conjunction with</span> |
| <span class="sd"> time_partitioning. The order of columns given determines the sort order.</span> |
| <span class="sd"> :type cluster_fields: list of str</span> |
| <span class="sd"> :param location: The geographic location of the job. Required except for</span> |
| <span class="sd"> US and EU. See details at</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/locations#specifying_your_location</span> |
| <span class="sd"> :type location: str</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">'sql'</span><span class="p">,</span> <span class="s1">'destination_dataset_table'</span><span class="p">,</span> <span class="s1">'labels'</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="p">)</span> |
| <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#e4f0e8'</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">bql</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">sql</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">destination_dataset_table</span><span class="o">=</span><span class="kc">None</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">flatten_results</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="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">None</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">maximum_bytes_billed</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">schema_update_options</span><span class="o">=</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="n">labels</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">priority</span><span class="o">=</span><span class="s1">'INTERACTIVE'</span><span class="p">,</span> |
| <span class="n">time_partitioning</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">api_resource_configs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">cluster_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">location</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">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">sql</span> <span class="o">=</span> <span class="n">sql</span> <span class="k">if</span> <span class="n">sql</span> <span class="k">else</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">flatten_results</span> <span class="o">=</span> <span class="n">flatten_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">maximum_bytes_billed</span> <span class="o">=</span> <span class="n">maximum_bytes_billed</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_update_options</span> <span class="o">=</span> <span class="n">schema_update_options</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="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bq_cursor</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">priority</span> <span class="o">=</span> <span class="n">priority</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">time_partitioning</span> <span class="o">=</span> <span class="n">time_partitioning</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">api_resource_configs</span> <span class="o">=</span> <span class="n">api_resource_configs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">cluster_fields</span> <span class="o">=</span> <span class="n">cluster_fields</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">location</span> <span class="o">=</span> <span class="n">location</span> |
| |
| <span class="c1"># TODO remove `bql` in Airflow 2.0</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bql</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">warnings</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'Deprecated parameter `bql` used in Task id: </span><span class="si">{}</span><span class="s1">. '</span> |
| <span class="s1">'Use `sql` parameter instead to pass the sql to be '</span> |
| <span class="s1">'executed. `bql` parameter is deprecated and '</span> |
| <span class="s1">'will be removed in a future version of '</span> |
| <span class="s1">'Airflow.'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">),</span> |
| <span class="n">category</span><span class="o">=</span><span class="ne">DeprecationWarning</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">sql</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'</span><span class="si">{}</span><span class="s1"> missing 1 required positional '</span> |
| <span class="s1">'argument: `sql`'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">task_id</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bq_cursor</span> <span class="ow">is</span> <span class="kc">None</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">sql</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">use_legacy_sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">use_legacy_sql</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">location</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">location</span><span class="p">,</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="bp">self</span><span class="o">.</span><span class="n">bq_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="bp">self</span><span class="o">.</span><span class="n">bq_cursor</span><span class="o">.</span><span class="n">run_query</span><span class="p">(</span> |
| <span class="n">sql</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">sql</span><span class="p">,</span> |
| <span class="n">destination_dataset_table</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">destination_dataset_table</span><span class="p">,</span> |
| <span class="n">write_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">write_disposition</span><span class="p">,</span> |
| <span class="n">allow_large_results</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">allow_large_results</span><span class="p">,</span> |
| <span class="n">flatten_results</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">flatten_results</span><span class="p">,</span> |
| <span class="n">udf_config</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">udf_config</span><span class="p">,</span> |
| <span class="n">maximum_billing_tier</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">maximum_billing_tier</span><span class="p">,</span> |
| <span class="n">maximum_bytes_billed</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">maximum_bytes_billed</span><span class="p">,</span> |
| <span class="n">create_disposition</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">create_disposition</span><span class="p">,</span> |
| <span class="n">query_params</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">query_params</span><span class="p">,</span> |
| <span class="n">labels</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">labels</span><span class="p">,</span> |
| <span class="n">schema_update_options</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_update_options</span><span class="p">,</span> |
| <span class="n">priority</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">priority</span><span class="p">,</span> |
| <span class="n">time_partitioning</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">time_partitioning</span><span class="p">,</span> |
| <span class="n">api_resource_configs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">api_resource_configs</span><span class="p">,</span> |
| <span class="n">cluster_fields</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">cluster_fields</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">on_kill</span><span class="p">(</span><span class="bp">self</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="n">on_kill</span><span class="p">()</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">bq_cursor</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</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">'Cancelling running query'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bq_cursor</span><span class="o">.</span><span class="n">cancel_query</span><span class="p">()</span></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryCreateEmptyTableOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_operator.BigQueryCreateEmptyTableOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryCreateEmptyTableOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Creates a new, empty table in the specified BigQuery dataset,</span> |
| <span class="sd"> optionally with schema.</span> |
| |
| <span class="sd"> The schema to be used for the BigQuery table may be specified in one of</span> |
| <span class="sd"> two ways. You may either directly pass the schema fields in, or you may</span> |
| <span class="sd"> point the operator to a Google cloud storage object name. The object in</span> |
| <span class="sd"> Google cloud storage must be a JSON file with the schema fields in it.</span> |
| <span class="sd"> You can also create a table without schema.</span> |
| |
| <span class="sd"> :param project_id: The project to create the table into. (templated)</span> |
| <span class="sd"> :type project_id: string</span> |
| <span class="sd"> :param dataset_id: The dataset to create the table into. (templated)</span> |
| <span class="sd"> :type dataset_id: string</span> |
| <span class="sd"> :param table_id: The Name of the table to be created. (templated)</span> |
| <span class="sd"> :type table_id: string</span> |
| <span class="sd"> :param schema_fields: If set, the schema field list as defined here:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.load.schema</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> schema_fields=[{"name": "emp_name", "type": "STRING", "mode": "REQUIRED"},</span> |
| <span class="sd"> {"name": "salary", "type": "INTEGER", "mode": "NULLABLE"}]</span> |
| |
| <span class="sd"> :type schema_fields: list</span> |
| <span class="sd"> :param gcs_schema_object: Full path to the JSON file containing</span> |
| <span class="sd"> schema (templated). For</span> |
| <span class="sd"> example: ``gs://test-bucket/dir1/dir2/employee_schema.json``</span> |
| <span class="sd"> :type gcs_schema_object: string</span> |
| <span class="sd"> :param time_partitioning: configure optional time partitioning fields i.e.</span> |
| <span class="sd"> partition by field, type and expiration as per API specifications.</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#timePartitioning</span> |
| <span class="sd"> :type time_partitioning: dict</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 google_cloud_storage_conn_id: Reference to a specific Google</span> |
| <span class="sd"> cloud storage hook.</span> |
| <span class="sd"> :type google_cloud_storage_conn_id: string</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any. For this to</span> |
| <span class="sd"> 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 labels: a dictionary containing labels for the table, passed to BigQuery</span> |
| |
| <span class="sd"> **Example (with schema JSON in GCS)**: ::</span> |
| |
| <span class="sd"> CreateTable = BigQueryCreateEmptyTableOperator(</span> |
| <span class="sd"> task_id='BigQueryCreateEmptyTableOperator_task',</span> |
| <span class="sd"> dataset_id='ODS',</span> |
| <span class="sd"> table_id='Employees',</span> |
| <span class="sd"> project_id='internal-gcp-project',</span> |
| <span class="sd"> gcs_schema_object='gs://schema-bucket/employee_schema.json',</span> |
| <span class="sd"> bigquery_conn_id='airflow-service-account',</span> |
| <span class="sd"> google_cloud_storage_conn_id='airflow-service-account'</span> |
| <span class="sd"> )</span> |
| |
| <span class="sd"> **Corresponding Schema file** (``employee_schema.json``): ::</span> |
| |
| <span class="sd"> [</span> |
| <span class="sd"> {</span> |
| <span class="sd"> "mode": "NULLABLE",</span> |
| <span class="sd"> "name": "emp_name",</span> |
| <span class="sd"> "type": "STRING"</span> |
| <span class="sd"> },</span> |
| <span class="sd"> {</span> |
| <span class="sd"> "mode": "REQUIRED",</span> |
| <span class="sd"> "name": "salary",</span> |
| <span class="sd"> "type": "INTEGER"</span> |
| <span class="sd"> }</span> |
| <span class="sd"> ]</span> |
| |
| <span class="sd"> **Example (with schema in the DAG)**: ::</span> |
| |
| <span class="sd"> CreateTable = BigQueryCreateEmptyTableOperator(</span> |
| <span class="sd"> task_id='BigQueryCreateEmptyTableOperator_task',</span> |
| <span class="sd"> dataset_id='ODS',</span> |
| <span class="sd"> table_id='Employees',</span> |
| <span class="sd"> project_id='internal-gcp-project',</span> |
| <span class="sd"> schema_fields=[{"name": "emp_name", "type": "STRING", "mode": "REQUIRED"},</span> |
| <span class="sd"> {"name": "salary", "type": "INTEGER", "mode": "NULLABLE"}],</span> |
| <span class="sd"> bigquery_conn_id='airflow-service-account',</span> |
| <span class="sd"> google_cloud_storage_conn_id='airflow-service-account'</span> |
| <span class="sd"> )</span> |
| <span class="sd"> :type labels: dict</span> |
| |
| <span class="sd"> """</span> |
| <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'dataset_id'</span><span class="p">,</span> <span class="s1">'table_id'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">,</span> |
| <span class="s1">'gcs_schema_object'</span><span class="p">,</span> <span class="s1">'labels'</span><span class="p">)</span> |
| <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#f0eee4'</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">dataset_id</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">schema_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">gcs_schema_object</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">time_partitioning</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="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_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="n">labels</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">BigQueryCreateEmptyTableOperator</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">project_id</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span> <span class="o">=</span> <span class="n">dataset_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_id</span> <span class="o">=</span> <span class="n">table_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_fields</span> <span class="o">=</span> <span class="n">schema_fields</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">gcs_schema_object</span> <span class="o">=</span> <span class="n">gcs_schema_object</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">google_cloud_storage_conn_id</span> <span class="o">=</span> <span class="n">google_cloud_storage_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">time_partitioning</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">time_partitioning</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">time_partitioning</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</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">bq_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="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_fields</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">gcs_schema_object</span><span class="p">:</span> |
| |
| <span class="n">gcs_bucket</span><span class="p">,</span> <span class="n">gcs_object</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">gcs_schema_object</span><span class="p">)</span> |
| |
| <span class="n">gcs_hook</span> <span class="o">=</span> <span class="n">GoogleCloudStorageHook</span><span class="p">(</span> |
| <span class="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">google_cloud_storage_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">schema_fields</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">gcs_hook</span><span class="o">.</span><span class="n">download</span><span class="p">(</span> |
| <span class="n">gcs_bucket</span><span class="p">,</span> |
| <span class="n">gcs_object</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">schema_fields</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_fields</span> |
| |
| <span class="n">conn</span> <span class="o">=</span> <span class="n">bq_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">create_empty_table</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="n">dataset_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table_id</span><span class="p">,</span> |
| <span class="n">schema_fields</span><span class="o">=</span><span class="n">schema_fields</span><span class="p">,</span> |
| <span class="n">time_partitioning</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">time_partitioning</span><span class="p">,</span> |
| <span class="n">labels</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">labels</span> |
| <span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryCreateExternalTableOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_operator.BigQueryCreateExternalTableOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryCreateExternalTableOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Creates a new external table in the dataset with the data in Google Cloud</span> |
| <span class="sd"> Storage.</span> |
| |
| <span class="sd"> The schema to be used for the BigQuery table may be specified in one of</span> |
| <span class="sd"> two ways. You may either directly pass the schema fields in, or you may</span> |
| <span class="sd"> point the operator to a Google cloud storage object name. The object in</span> |
| <span class="sd"> Google cloud storage must be a JSON file with the schema fields in it.</span> |
| |
| <span class="sd"> :param bucket: The bucket to point the external table to. (templated)</span> |
| <span class="sd"> :type bucket: string</span> |
| <span class="sd"> :param source_objects: List of Google cloud storage URIs to point</span> |
| <span class="sd"> table to. (templated)</span> |
| <span class="sd"> If source_format is 'DATASTORE_BACKUP', the list must only contain a single URI.</span> |
| <span class="sd"> :type source_objects: list</span> |
| <span class="sd"> :param destination_project_dataset_table: The dotted (<project>.)<dataset>.<table></span> |
| <span class="sd"> BigQuery table to load data into (templated). If <project> is not included,</span> |
| <span class="sd"> project will be the project defined in the connection json.</span> |
| <span class="sd"> :type destination_project_dataset_table: string</span> |
| <span class="sd"> :param schema_fields: If set, the schema field list as defined here:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.load.schema</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> schema_fields=[{"name": "emp_name", "type": "STRING", "mode": "REQUIRED"},</span> |
| <span class="sd"> {"name": "salary", "type": "INTEGER", "mode": "NULLABLE"}]</span> |
| |
| <span class="sd"> Should not be set when source_format is 'DATASTORE_BACKUP'.</span> |
| <span class="sd"> :type schema_fields: list</span> |
| <span class="sd"> :param schema_object: If set, a GCS object path pointing to a .json file that</span> |
| <span class="sd"> contains the schema for the table. (templated)</span> |
| <span class="sd"> :type schema_object: string</span> |
| <span class="sd"> :param source_format: File format of the data.</span> |
| <span class="sd"> :type source_format: string</span> |
| <span class="sd"> :param compression: [Optional] The compression type of the data source.</span> |
| <span class="sd"> Possible values include GZIP and NONE.</span> |
| <span class="sd"> The default value is NONE.</span> |
| <span class="sd"> This setting is ignored for Google Cloud Bigtable,</span> |
| <span class="sd"> Google Cloud Datastore backups and Avro formats.</span> |
| <span class="sd"> :type compression: string</span> |
| <span class="sd"> :param skip_leading_rows: Number of rows to skip when loading from a CSV.</span> |
| <span class="sd"> :type skip_leading_rows: int</span> |
| <span class="sd"> :param field_delimiter: The delimiter to use for the CSV.</span> |
| <span class="sd"> :type field_delimiter: string</span> |
| <span class="sd"> :param max_bad_records: The maximum number of bad records that BigQuery can</span> |
| <span class="sd"> ignore when running the job.</span> |
| <span class="sd"> :type max_bad_records: int</span> |
| <span class="sd"> :param quote_character: The value that is used to quote data sections in a CSV file.</span> |
| <span class="sd"> :type quote_character: string</span> |
| <span class="sd"> :param allow_quoted_newlines: Whether to allow quoted newlines (true) or not (false).</span> |
| <span class="sd"> :type allow_quoted_newlines: boolean</span> |
| <span class="sd"> :param allow_jagged_rows: Accept rows that are missing trailing optional columns.</span> |
| <span class="sd"> The missing values are treated as nulls. If false, records with missing trailing</span> |
| <span class="sd"> columns are treated as bad records, and if there are too many bad records, an</span> |
| <span class="sd"> invalid error is returned in the job result. Only applicable to CSV, ignored</span> |
| <span class="sd"> for other formats.</span> |
| <span class="sd"> :type allow_jagged_rows: bool</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 google_cloud_storage_conn_id: Reference to a specific Google</span> |
| <span class="sd"> cloud storage hook.</span> |
| <span class="sd"> :type google_cloud_storage_conn_id: string</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any. For this to</span> |
| <span class="sd"> 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 src_fmt_configs: configure optional fields specific to the source format</span> |
| <span class="sd"> :type src_fmt_configs: dict</span> |
| <span class="sd"> :param labels a dictionary containing labels for the table, passed to BigQuery</span> |
| <span class="sd"> :type labels: dict</span> |
| <span class="sd"> """</span> |
| <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'bucket'</span><span class="p">,</span> <span class="s1">'source_objects'</span><span class="p">,</span> |
| <span class="s1">'schema_object'</span><span class="p">,</span> <span class="s1">'destination_project_dataset_table'</span><span class="p">,</span> <span class="s1">'labels'</span><span class="p">)</span> |
| <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#f0eee4'</span> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">bucket</span><span class="p">,</span> |
| <span class="n">source_objects</span><span class="p">,</span> |
| <span class="n">destination_project_dataset_table</span><span class="p">,</span> |
| <span class="n">schema_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">schema_object</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">source_format</span><span class="o">=</span><span class="s1">'CSV'</span><span class="p">,</span> |
| <span class="n">compression</span><span class="o">=</span><span class="s1">'NONE'</span><span class="p">,</span> |
| <span class="n">skip_leading_rows</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">field_delimiter</span><span class="o">=</span><span class="s1">','</span><span class="p">,</span> |
| <span class="n">max_bad_records</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">quote_character</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">allow_quoted_newlines</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">allow_jagged_rows</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">google_cloud_storage_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_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="n">src_fmt_configs</span><span class="o">=</span><span class="p">{},</span> |
| <span class="n">labels</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">BigQueryCreateExternalTableOperator</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="c1"># GCS config</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bucket</span> <span class="o">=</span> <span class="n">bucket</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">source_objects</span> <span class="o">=</span> <span class="n">source_objects</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_object</span> <span class="o">=</span> <span class="n">schema_object</span> |
| |
| <span class="c1"># BQ config</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">schema_fields</span> <span class="o">=</span> <span class="n">schema_fields</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">source_format</span> <span class="o">=</span> <span class="n">source_format</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">compression</span> <span class="o">=</span> <span class="n">compression</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">skip_leading_rows</span> <span class="o">=</span> <span class="n">skip_leading_rows</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">field_delimiter</span> <span class="o">=</span> <span class="n">field_delimiter</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_bad_records</span> <span class="o">=</span> <span class="n">max_bad_records</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">quote_character</span> <span class="o">=</span> <span class="n">quote_character</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">allow_quoted_newlines</span> <span class="o">=</span> <span class="n">allow_quoted_newlines</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">allow_jagged_rows</span> <span class="o">=</span> <span class="n">allow_jagged_rows</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">google_cloud_storage_conn_id</span> <span class="o">=</span> <span class="n">google_cloud_storage_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">src_fmt_configs</span> <span class="o">=</span> <span class="n">src_fmt_configs</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">labels</span> <span class="o">=</span> <span class="n">labels</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">bq_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="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_fields</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_object</span> \ |
| <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_format</span> <span class="o">!=</span> <span class="s1">'DATASTORE_BACKUP'</span><span class="p">:</span> |
| <span class="n">gcs_hook</span> <span class="o">=</span> <span class="n">GoogleCloudStorageHook</span><span class="p">(</span> |
| <span class="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">google_cloud_storage_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">schema_fields</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">gcs_hook</span><span class="o">.</span><span class="n">download</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bucket</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">schema_object</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">schema_fields</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_fields</span> |
| |
| <span class="n">source_uris</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'gs://</span><span class="si">{}</span><span class="s1">/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bucket</span><span class="p">,</span> <span class="n">source_object</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">source_object</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">source_objects</span><span class="p">]</span> |
| <span class="n">conn</span> <span class="o">=</span> <span class="n">bq_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">create_external_table</span><span class="p">(</span> |
| <span class="n">external_project_dataset_table</span><span class="o">=</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">schema_fields</span><span class="o">=</span><span class="n">schema_fields</span><span class="p">,</span> |
| <span class="n">source_uris</span><span class="o">=</span><span class="n">source_uris</span><span class="p">,</span> |
| <span class="n">source_format</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">source_format</span><span class="p">,</span> |
| <span class="n">compression</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">compression</span><span class="p">,</span> |
| <span class="n">skip_leading_rows</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">skip_leading_rows</span><span class="p">,</span> |
| <span class="n">field_delimiter</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">field_delimiter</span><span class="p">,</span> |
| <span class="n">max_bad_records</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">max_bad_records</span><span class="p">,</span> |
| <span class="n">quote_character</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">quote_character</span><span class="p">,</span> |
| <span class="n">allow_quoted_newlines</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">allow_quoted_newlines</span><span class="p">,</span> |
| <span class="n">allow_jagged_rows</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">allow_jagged_rows</span><span class="p">,</span> |
| <span class="n">src_fmt_configs</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">src_fmt_configs</span><span class="p">,</span> |
| <span class="n">labels</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">labels</span> |
| <span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryDeleteDatasetOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_operator.BigQueryDeleteDatasetOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryDeleteDatasetOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">""""</span> |
| <span class="sd"> This operator deletes an existing dataset from your Project in Big query.</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets/delete</span> |
| <span class="sd"> :param project_id: The project id of the dataset.</span> |
| <span class="sd"> :type project_id: string</span> |
| <span class="sd"> :param dataset_id: The dataset to be deleted.</span> |
| <span class="sd"> :type dataset_id: string</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> delete_temp_data = BigQueryDeleteDatasetOperator(dataset_id = 'temp-dataset',</span> |
| <span class="sd"> project_id = 'temp-project',</span> |
| <span class="sd"> bigquery_conn_id='_my_gcp_conn_',</span> |
| <span class="sd"> task_id='Deletetemp',</span> |
| <span class="sd"> dag=dag)</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'dataset_id'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">)</span> |
| <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#f00004'</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">dataset_id</span><span class="p">,</span> |
| <span class="n">project_id</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="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="bp">self</span><span class="o">.</span><span class="n">dataset_id</span> <span class="o">=</span> <span class="n">dataset_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project_id</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Dataset id: </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">dataset_id</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Project id: </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">project_id</span><span class="p">)</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryDeleteDatasetOperator</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="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">bq_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">bq_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">delete_dataset</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="n">dataset_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span> |
| <span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="BigQueryCreateEmptyDatasetOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.bigquery_operator.BigQueryCreateEmptyDatasetOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryCreateEmptyDatasetOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">""""</span> |
| <span class="sd"> This operator is used to create new dataset for your Project in Big query.</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets#resource</span> |
| |
| <span class="sd"> :param project_id: The name of the project where we want to create the dataset.</span> |
| <span class="sd"> Don't need to provide, if projectId in dataset_reference.</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param dataset_id: The id of dataset. Don't need to provide,</span> |
| <span class="sd"> if datasetId in dataset_reference.</span> |
| <span class="sd"> :type dataset_id: str</span> |
| <span class="sd"> :param dataset_reference: Dataset reference that could be provided with request body.</span> |
| <span class="sd"> More info:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/datasets#resource</span> |
| <span class="sd"> :type dataset_reference: dict</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> create_new_dataset = BigQueryCreateEmptyDatasetOperator(</span> |
| <span class="sd"> dataset_id = 'new-dataset',</span> |
| <span class="sd"> project_id = 'my-project',</span> |
| <span class="sd"> dataset_reference = {"friendlyName": "New Dataset"}</span> |
| <span class="sd"> bigquery_conn_id='_my_gcp_conn_',</span> |
| <span class="sd"> task_id='newDatasetCreator',</span> |
| <span class="sd"> dag=dag)</span> |
| |
| <span class="sd"> """</span> |
| |
| <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'dataset_id'</span><span class="p">,</span> <span class="s1">'project_id'</span><span class="p">)</span> |
| <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#f0eee4'</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">dataset_id</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dataset_reference</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="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="bp">self</span><span class="o">.</span><span class="n">dataset_id</span> <span class="o">=</span> <span class="n">dataset_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">project_id</span> <span class="o">=</span> <span class="n">project_id</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">dataset_reference</span> <span class="o">=</span> <span class="n">dataset_reference</span> <span class="k">if</span> <span class="n">dataset_reference</span> <span class="k">else</span> <span class="p">{}</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">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Dataset id: </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">dataset_id</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Project id: </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">project_id</span><span class="p">)</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryCreateEmptyDatasetOperator</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="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">bq_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">bq_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">create_empty_dataset</span><span class="p">(</span> |
| <span class="n">project_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">project_id</span><span class="p">,</span> |
| <span class="n">dataset_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span><span class="p">,</span> |
| <span class="n">dataset_reference</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset_reference</span><span class="p">)</span></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>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |