| |
| |
| <!-- |
| Javascript to render AIRFLOW-XXX and PR references in text |
| as HTML links. |
| |
| Overrides extrahead block from sphinx_rtd_theme |
| https://www.sphinx-doc.org/en/master/templating.html |
| --> |
| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>airflow.contrib.operators.gcs_to_bq — Airflow Documentation</title> |
| |
| |
| |
| |
| <link rel="shortcut icon" href="../../../../_static/pin_32.png"/> |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../_static/language_data.js"></script> |
| <script type="text/javascript" src="../../../../_static/jira-links.js"></script> |
| |
| <script type="text/javascript" src="../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/graphviz.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../_static/exampleinclude.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| </script> |
| <style> |
| |
| </style> |
| |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.8 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../executor/index.html">Executor</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../dag-serialization.html">DAG Serialization</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../best-practices.html">Best Practices</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">References</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../configurations-ref.html">Configurations</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li><a href="../operators.html">airflow.contrib.operators</a> »</li> |
| |
| <li>airflow.contrib.operators.gcs_to_bq</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.gcs_to_bq</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.gcs_hook</span> <span class="kn">import</span> <span class="n">GoogleCloudStorageHook</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> |
| |
| |
| <div class="viewcode-block" id="GoogleCloudStorageToBigQueryOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/gcs_to_bq/index.html#airflow.contrib.operators.gcs_to_bq.GoogleCloudStorageToBigQueryOperator">[docs]</a><span class="k">class</span> <span class="nc">GoogleCloudStorageToBigQueryOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Loads files from Google cloud storage into BigQuery.</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"> .. seealso::</span> |
| <span class="sd"> For more information on how to use this operator, take a look at the guide:</span> |
| <span class="sd"> :ref:`howto/operator:GoogleCloudStorageToBigQueryOperator`</span> |
| |
| <span class="sd"> :param bucket: The bucket to load from. (templated)</span> |
| <span class="sd"> :type bucket: str</span> |
| <span class="sd"> :param source_objects: List of Google cloud storage URIs to load from. (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[str]</span> |
| <span class="sd"> :param destination_project_dataset_table: The dotted</span> |
| <span class="sd"> ``(<project>.|<project>:)<dataset>.<table>`` BigQuery table to load data into.</span> |
| <span class="sd"> If ``<project>`` is not included, project will be the project defined in</span> |
| <span class="sd"> the connection json. (templated)</span> |
| <span class="sd"> :type destination_project_dataset_table: str</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/v2/jobs#configuration.load</span> |
| <span class="sd"> Should not be set when source_format is 'DATASTORE_BACKUP'.</span> |
| <span class="sd"> Parameter must be defined if 'schema_object' is null and autodetect is False.</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"> Parameter must be defined if 'schema_fields' is null and autodetect is False.</span> |
| <span class="sd"> :type schema_object: str</span> |
| <span class="sd"> :param source_format: File format to export.</span> |
| <span class="sd"> :type source_format: str</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: str</span> |
| <span class="sd"> :param create_disposition: The create disposition if the table doesn't exist.</span> |
| <span class="sd"> :type create_disposition: str</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 write_disposition: The write disposition if the table already exists.</span> |
| <span class="sd"> :type write_disposition: str</span> |
| <span class="sd"> :param field_delimiter: The delimiter to use when loading from a CSV.</span> |
| <span class="sd"> :type field_delimiter: str</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: str</span> |
| <span class="sd"> :param ignore_unknown_values: [Optional] Indicates if BigQuery should allow</span> |
| <span class="sd"> extra values that are not represented in the table schema.</span> |
| <span class="sd"> If true, the extra values are ignored. If false, records with extra columns</span> |
| <span class="sd"> 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.</span> |
| <span class="sd"> :type ignore_unknown_values: bool</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: bool</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 encoding: The character encoding of the data. See:</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs#configuration.query.tableDefinitions.(key).csvOptions.encoding</span> |
| <span class="sd"> https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#externalDataConfiguration.csvOptions.encoding</span> |
| <span class="sd"> :type encoding: str</span> |
| <span class="sd"> :param max_id_key: If set, the name of a column in the BigQuery table</span> |
| <span class="sd"> that's to be loaded. This will be used to select the MAX value from</span> |
| <span class="sd"> BigQuery after the load occurs. The results will be returned by the</span> |
| <span class="sd"> execute() command, which in turn gets stored in XCom for future</span> |
| <span class="sd"> operators to use. This can be helpful with incremental loads--during</span> |
| <span class="sd"> future executions, you can pick up from the max ID.</span> |
| <span class="sd"> :type max_id_key: str</span> |
| <span class="sd"> :param bigquery_conn_id: Reference to a specific BigQuery hook.</span> |
| <span class="sd"> :type bigquery_conn_id: str</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: str</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: str</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: list</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 external_table: Flag to specify if the destination table should be</span> |
| <span class="sd"> a BigQuery external table. Default Value is False.</span> |
| <span class="sd"> :type external_table: bool</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"> Note that 'field' is not available in concurrency with</span> |
| <span class="sd"> dataset.table$partition.</span> |
| <span class="sd"> :type time_partitioning: dict</span> |
| <span class="sd"> :param cluster_fields: Request that the result of this load 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"> Not applicable for external tables.</span> |
| <span class="sd"> :type cluster_fields: list[str]</span> |
| <span class="sd"> :param autodetect: [Optional] Indicates if we should automatically infer the</span> |
| <span class="sd"> options and schema for CSV and JSON sources. (Default: ``True``).</span> |
| <span class="sd"> Parameter must be setted to True if 'schema_fields' and 'schema_object' are undefined.</span> |
| <span class="sd"> It is suggested to set to True if table are create outside of Airflow.</span> |
| <span class="sd"> :type autodetect: bool</span> |
| <span class="sd"> :param encryption_configuration: [Optional] Custom encryption configuration (e.g., Cloud KMS keys).</span> |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> encryption_configuration = {</span> |
| <span class="sd"> "kmsKeyName": "projects/testp/locations/us/keyRings/test-kr/cryptoKeys/test-key"</span> |
| <span class="sd"> }</span> |
| <span class="sd"> :type encryption_configuration: dict</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="GoogleCloudStorageToBigQueryOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/gcs_to_bq/index.html#airflow.contrib.operators.gcs_to_bq.GoogleCloudStorageToBigQueryOperator.template_fields">[docs]</a> <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></div> |
| <div class="viewcode-block" id="GoogleCloudStorageToBigQueryOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/gcs_to_bq/index.html#airflow.contrib.operators.gcs_to_bq.GoogleCloudStorageToBigQueryOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span></div> |
| <div class="viewcode-block" id="GoogleCloudStorageToBigQueryOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/gcs_to_bq/index.html#airflow.contrib.operators.gcs_to_bq.GoogleCloudStorageToBigQueryOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#f0eee4'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">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">create_disposition</span><span class="o">=</span><span class="s1">'CREATE_IF_NEEDED'</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">write_disposition</span><span class="o">=</span><span class="s1">'WRITE_EMPTY'</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">ignore_unknown_values</span><span class="o">=</span><span class="kc">False</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">encoding</span><span class="o">=</span><span class="s2">"UTF-8"</span><span class="p">,</span> |
| <span class="n">max_id_key</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">schema_update_options</span><span class="o">=</span><span class="p">(),</span> |
| <span class="n">src_fmt_configs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">external_table</span><span class="o">=</span><span class="kc">False</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">cluster_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">autodetect</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">encryption_configuration</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">GoogleCloudStorageToBigQueryOperator</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="k">if</span> <span class="n">src_fmt_configs</span> <span class="ow">is</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="k">if</span> <span class="n">time_partitioning</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">time_partitioning</span> <span class="o">=</span> <span class="p">{}</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">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">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">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">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">ignore_unknown_values</span> <span class="o">=</span> <span class="n">ignore_unknown_values</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">external_table</span> <span class="o">=</span> <span class="n">external_table</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">encoding</span> <span class="o">=</span> <span class="n">encoding</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_id_key</span> <span class="o">=</span> <span class="n">max_id_key</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">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">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">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">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">autodetect</span> <span class="o">=</span> <span class="n">autodetect</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">encryption_configuration</span> <span class="o">=</span> <span class="n">encryption_configuration</span> |
| |
| <div class="viewcode-block" id="GoogleCloudStorageToBigQueryOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/gcs_to_bq/index.html#airflow.contrib.operators.gcs_to_bq.GoogleCloudStorageToBigQueryOperator.execute">[docs]</a> <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="p">:</span> |
| <span class="k">if</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">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_object</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">autodetect</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'At least one of `schema_fields`, `schema_object`, '</span> |
| <span class="s1">'or `autodetect` must be passed.'</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="kc">None</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">external_table</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">ignore_unknown_values</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_values</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">encoding</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">encoding</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">encryption_configuration</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">encryption_configuration</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">cursor</span><span class="o">.</span><span class="n">run_load</span><span class="p">(</span> |
| <span class="n">destination_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">autodetect</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">autodetect</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">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">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">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">ignore_unknown_values</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">ignore_unknown_values</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">encoding</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">encoding</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">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">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">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="n">encryption_configuration</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">encryption_configuration</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_id_key</span><span class="p">:</span> |
| <span class="n">cursor</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="s1">'SELECT MAX(</span><span class="si">{}</span><span class="s1">) FROM </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">max_id_key</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">row</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">fetchone</span><span class="p">()</span> |
| <span class="n">max_id</span> <span class="o">=</span> <span class="n">row</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="n">row</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">else</span> <span class="mi">0</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">'Loaded BQ data with max </span><span class="si">%s</span><span class="s1">.</span><span class="si">%s</span><span class="s1">=</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">destination_project_dataset_table</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_id_key</span><span class="p">,</span> <span class="n">max_id</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">max_id</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="../../../../privacy_notice.html">Privacy Policy</a> |
| for more details. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |