http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/mysql_to_gcs.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/operators/mysql_to_gcs.html b/_modules/airflow/contrib/operators/mysql_to_gcs.html new file mode 100644 index 0000000..47346f5 --- /dev/null +++ b/_modules/airflow/contrib/operators/mysql_to_gcs.html @@ -0,0 +1,524 @@ + + +<!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.mysql_to_gcs — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../../index.html" class="icon icon-home"> Airflow + + + + </a> + + + + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../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="../../../../lineage.html">Lineage</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + + + + + + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + + <ul class="wy-breadcrumbs"> + + <li><a href="../../../../index.html">Docs</a> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.operators.mysql_to_gcs</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.mysql_to_gcs</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">sys</span> +<span class="kn">import</span> <span class="nn">json</span> +<span class="kn">import</span> <span class="nn">time</span> +<span class="kn">import</span> <span class="nn">base64</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="kn">from</span> <span class="nn">airflow.hooks.mysql_hook</span> <span class="k">import</span> <span class="n">MySqlHook</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> +<span class="kn">from</span> <span class="nn">datetime</span> <span class="k">import</span> <span class="n">date</span><span class="p">,</span> <span class="n">datetime</span> +<span class="kn">from</span> <span class="nn">decimal</span> <span class="k">import</span> <span class="n">Decimal</span> +<span class="kn">from</span> <span class="nn">MySQLdb.constants</span> <span class="k">import</span> <span class="n">FIELD_TYPE</span> +<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span> +<span class="kn">from</span> <span class="nn">six</span> <span class="k">import</span> <span class="n">string_types</span> + +<span class="n">PY3</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="mi">3</span> + + +<div class="viewcode-block" id="MySqlToGoogleCloudStorageOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.mysql_to_gcs.MySqlToGoogleCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">MySqlToGoogleCloudStorageOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Copy data from MySQL to Google cloud storage in JSON format.</span> +<span class="sd"> """</span> + <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,</span> <span class="s1">'bucket'</span><span class="p">,</span> <span class="s1">'filename'</span><span class="p">,</span> <span class="s1">'schema_filename'</span><span class="p">,</span> <span class="s1">'schema'</span><span class="p">)</span> + <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.sql'</span><span class="p">,)</span> + <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#a0e08c'</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> + <span class="n">sql</span><span class="p">,</span> + <span class="n">bucket</span><span class="p">,</span> + <span class="n">filename</span><span class="p">,</span> + <span class="n">schema_filename</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">approx_max_file_size_bytes</span><span class="o">=</span><span class="mi">1900000000</span><span class="p">,</span> + <span class="n">mysql_conn_id</span><span class="o">=</span><span class="s1">'mysql_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">schema</span><span class="o">=</span><span class="kc">None</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="sd">"""</span> +<span class="sd"> :param sql: The SQL to execute on the MySQL table.</span> +<span class="sd"> :type sql: string</span> +<span class="sd"> :param bucket: The bucket to upload to.</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param filename: The filename to use as the object name when uploading</span> +<span class="sd"> to Google cloud storage. A {} should be specified in the filename</span> +<span class="sd"> to allow the operator to inject file numbers in cases where the</span> +<span class="sd"> file is split due to size.</span> +<span class="sd"> :type filename: string</span> +<span class="sd"> :param schema_filename: If set, the filename to use as the object name</span> +<span class="sd"> when uploading a .json file containing the BigQuery schema fields</span> +<span class="sd"> for the table that was dumped from MySQL.</span> +<span class="sd"> :type schema_filename: string</span> +<span class="sd"> :param approx_max_file_size_bytes: This operator supports the ability</span> +<span class="sd"> to split large table dumps into multiple files (see notes in the</span> +<span class="sd"> filenamed param docs above). Google cloud storage allows for files</span> +<span class="sd"> to be a maximum of 4GB. This param allows developers to specify the</span> +<span class="sd"> file size of the splits.</span> +<span class="sd"> :type approx_max_file_size_bytes: long</span> +<span class="sd"> :param mysql_conn_id: Reference to a specific MySQL hook.</span> +<span class="sd"> :type mysql_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 schema: The schema to use, if any. Should be a list of dict or</span> +<span class="sd"> a str. Pass a string if using Jinja template, otherwise, pass a list of</span> +<span class="sd"> dict. Examples could be seen: https://cloud.google.com/bigquery/docs</span> +<span class="sd"> /schemas#specifying_a_json_schema_file</span> +<span class="sd"> :type schema: str or list</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"> """</span> + <span class="nb">super</span><span class="p">(</span><span class="n">MySqlToGoogleCloudStorageOperator</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">sql</span> <span class="o">=</span> <span class="n">sql</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">filename</span> <span class="o">=</span> <span class="n">filename</span> + <span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span> <span class="o">=</span> <span class="n">schema_filename</span> + <span class="bp">self</span><span class="o">.</span><span class="n">approx_max_file_size_bytes</span> <span class="o">=</span> <span class="n">approx_max_file_size_bytes</span> + <span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span> <span class="o">=</span> <span class="n">mysql_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">schema</span> <span class="o">=</span> <span class="n">schema</span> + <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> + + <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> + <span class="n">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query_mysql</span><span class="p">()</span> + <span class="n">files_to_upload</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_write_local_data_files</span><span class="p">(</span><span class="n">cursor</span><span class="p">)</span> + + <span class="c1"># If a schema is set, create a BQ schema JSON file.</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span><span class="p">:</span> + <span class="n">files_to_upload</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_write_local_schema_file</span><span class="p">(</span><span class="n">cursor</span><span class="p">))</span> + + <span class="c1"># Flush all files before uploading.</span> + <span class="k">for</span> <span class="n">file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> + <span class="n">file_handle</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> + + <span class="bp">self</span><span class="o">.</span><span class="n">_upload_to_gcs</span><span class="p">(</span><span class="n">files_to_upload</span><span class="p">)</span> + + <span class="c1"># Close all temp file handles.</span> + <span class="k">for</span> <span class="n">file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> + <span class="n">file_handle</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> + + <span class="k">def</span> <span class="nf">_query_mysql</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Queries mysql and returns a cursor to the results.</span> +<span class="sd"> """</span> + <span class="n">mysql</span> <span class="o">=</span> <span class="n">MySqlHook</span><span class="p">(</span><span class="n">mysql_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">mysql_conn_id</span><span class="p">)</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">mysql</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">execute</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="k">return</span> <span class="n">cursor</span> + + <span class="k">def</span> <span class="nf">_write_local_data_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cursor</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a cursor, and writes results to a local file.</span> + +<span class="sd"> :return: A dictionary where keys are filenames to be used as object</span> +<span class="sd"> names in GCS, and values are file handles to local files that</span> +<span class="sd"> contain the data for the GCS objects.</span> +<span class="sd"> """</span> + <span class="n">schema</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">schema_tuple</span><span class="p">:</span> <span class="n">schema_tuple</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span><span class="p">))</span> + <span class="n">col_type_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_col_type_dict</span><span class="p">()</span> + <span class="n">file_no</span> <span class="o">=</span> <span class="mi">0</span> + <span class="n">tmp_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="n">tmp_file_handles</span> <span class="o">=</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_no</span><span class="p">):</span> <span class="n">tmp_file_handle</span><span class="p">}</span> + + <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">cursor</span><span class="p">:</span> + <span class="c1"># Convert datetime objects to utc seconds, and decimals to floats.</span> + <span class="c1"># Convert binary type object to string encoded with base64.</span> + <span class="n">row</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_types</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">col_type_dict</span><span class="p">,</span> <span class="n">row</span><span class="p">)</span> + <span class="n">row_dict</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">row</span><span class="p">))</span> + + <span class="c1"># TODO validate that row isn't > 2MB. BQ enforces a hard row size of 2MB.</span> + <span class="n">s</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">row_dict</span><span class="p">)</span> + <span class="k">if</span> <span class="n">PY3</span><span class="p">:</span> + <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> + <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> + + <span class="c1"># Append newline to make dumps BigQuery compatible.</span> + <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span> + + <span class="c1"># Stop if the file exceeds the file size limit.</span> + <span class="k">if</span> <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">approx_max_file_size_bytes</span><span class="p">:</span> + <span class="n">file_no</span> <span class="o">+=</span> <span class="mi">1</span> + <span class="n">tmp_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="n">tmp_file_handles</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_no</span><span class="p">)]</span> <span class="o">=</span> <span class="n">tmp_file_handle</span> + + <span class="k">return</span> <span class="n">tmp_file_handles</span> + + <span class="k">def</span> <span class="nf">_write_local_schema_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cursor</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a cursor, and writes the BigQuery schema for the results to a</span> +<span class="sd"> local file system.</span> + +<span class="sd"> :return: A dictionary where key is a filename to be used as an object</span> +<span class="sd"> name in GCS, and values are file handles to local files that</span> +<span class="sd"> contains the BigQuery schema fields in .json format.</span> +<span class="sd"> """</span> + <span class="n">schema_str</span> <span class="o">=</span> <span class="kc">None</span> + <span class="n">tmp_schema_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="n">string_types</span><span class="p">):</span> + <span class="n">schema_str</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> + <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> + <span class="n">schema_str</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">schema</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span><span class="p">:</span> + <span class="c1"># See PEP 249 for details about the description tuple.</span> + <span class="n">field_name</span> <span class="o">=</span> <span class="n">field</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> + <span class="n">field_type</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_map</span><span class="p">(</span><span class="n">field</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> + <span class="c1"># Always allow TIMESTAMP to be nullable. MySQLdb returns None types</span> + <span class="c1"># for required fields because some MySQL timestamps can't be</span> + <span class="c1"># represented by Python's datetime (e.g. 0000-00-00 00:00:00).</span> + <span class="k">if</span> <span class="n">field</span><span class="p">[</span><span class="mi">6</span><span class="p">]</span> <span class="ow">or</span> <span class="n">field_type</span> <span class="o">==</span> <span class="s1">'TIMESTAMP'</span><span class="p">:</span> + <span class="n">field_mode</span> <span class="o">=</span> <span class="s1">'NULLABLE'</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">field_mode</span> <span class="o">=</span> <span class="s1">'REQUIRED'</span> + <span class="n">schema</span><span class="o">.</span><span class="n">append</span><span class="p">({</span> + <span class="s1">'name'</span><span class="p">:</span> <span class="n">field_name</span><span class="p">,</span> + <span class="s1">'type'</span><span class="p">:</span> <span class="n">field_type</span><span class="p">,</span> + <span class="s1">'mode'</span><span class="p">:</span> <span class="n">field_mode</span><span class="p">,</span> + <span class="p">})</span> + <span class="n">schema_str</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> + <span class="k">if</span> <span class="n">PY3</span><span class="p">:</span> + <span class="n">schema_str</span> <span class="o">=</span> <span class="n">schema_str</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> + <span class="n">tmp_schema_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">schema_str</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">'Using schema for </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">schema_filename</span><span class="p">,</span> <span class="n">schema_str</span><span class="p">)</span> + <span class="k">return</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span><span class="p">:</span> <span class="n">tmp_schema_file_handle</span><span class="p">}</span> + + <span class="k">def</span> <span class="nf">_upload_to_gcs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">files_to_upload</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Upload all of the file splits (and optionally the schema .json file) to</span> +<span class="sd"> Google cloud storage.</span> +<span class="sd"> """</span> + <span class="n">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="k">for</span> <span class="nb">object</span><span class="p">,</span> <span class="n">tmp_file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> + <span class="n">hook</span><span class="o">.</span><span class="n">upload</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="nb">object</span><span class="p">,</span> <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="s1">'application/json'</span><span class="p">)</span> + + <span class="k">def</span> <span class="nf">_convert_types</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">col_type_dict</span><span class="p">,</span> <span class="n">row</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a value from MySQLdb, and converts it to a value that's safe for</span> +<span class="sd"> JSON/Google cloud storage/BigQuery. Dates are converted to UTC seconds.</span> +<span class="sd"> Decimals are converted to floats. Binary type fields are encoded with base64,</span> +<span class="sd"> as imported BYTES data must be base64-encoded according to Bigquery SQL</span> +<span class="sd"> date type documentation: https://cloud.google.com/bigquery/data-types</span> +<span class="sd"> """</span> + <span class="n">converted_row</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">for</span> <span class="n">col_name</span><span class="p">,</span> <span class="n">col_val</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">row</span><span class="p">):</span> + <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">col_val</span><span class="p">)</span> <span class="ow">in</span> <span class="p">(</span><span class="n">datetime</span><span class="p">,</span> <span class="n">date</span><span class="p">):</span> + <span class="n">col_val</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">mktime</span><span class="p">(</span><span class="n">col_val</span><span class="o">.</span><span class="n">timetuple</span><span class="p">())</span> + <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">col_val</span><span class="p">,</span> <span class="n">Decimal</span><span class="p">):</span> + <span class="n">col_val</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">col_val</span><span class="p">)</span> + <span class="k">elif</span> <span class="n">col_type_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">col_name</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"BYTES"</span><span class="p">:</span> + <span class="n">col_val</span> <span class="o">=</span> <span class="n">base64</span><span class="o">.</span><span class="n">urlsafe_b64encode</span><span class="p">(</span><span class="n">col_val</span><span class="p">)</span> + <span class="k">if</span> <span class="n">PY3</span><span class="p">:</span> + <span class="n">col_val</span> <span class="o">=</span> <span class="n">col_val</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'ascii'</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="n">col_val</span> <span class="o">=</span> <span class="n">col_val</span> + <span class="n">converted_row</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">col_val</span><span class="p">)</span> + <span class="k">return</span> <span class="n">converted_row</span> + + <span class="k">def</span> <span class="nf">_get_col_type_dict</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Return a dict of column name and column type based on self.schema if not None.</span> +<span class="sd"> """</span> + <span class="n">schema</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="n">string_types</span><span class="p">):</span> + <span class="n">schema</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="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span> + <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">schema</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> + <span class="n">schema</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</span> + <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema</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">warn</span><span class="p">(</span><span class="s1">'Using default schema due to unexpected type.'</span> + <span class="s1">'Should be a string or list.'</span><span class="p">)</span> + + <span class="n">col_type_dict</span> <span class="o">=</span> <span class="p">{}</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">col_type_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">col</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]:</span> <span class="n">col</span><span class="p">[</span><span class="s1">'type'</span><span class="p">]</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">schema</span><span class="p">}</span> + <span class="k">except</span> <span class="ne">KeyError</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">warn</span><span class="p">(</span><span class="s1">'Using default schema due to missing name or type. Please '</span> + <span class="s1">'refer to: https://cloud.google.com/bigquery/docs/schemas'</span> + <span class="s1">'#specifying_a_json_schema_file'</span><span class="p">)</span> + <span class="k">return</span> <span class="n">col_type_dict</span> + +<div class="viewcode-block" id="MySqlToGoogleCloudStorageOperator.type_map"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.mysql_to_gcs.MySqlToGoogleCloudStorageOperator.type_map">[docs]</a> <span class="nd">@classmethod</span> + <span class="k">def</span> <span class="nf">type_map</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">mysql_type</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Helper function that maps from MySQL fields to BigQuery fields. Used</span> +<span class="sd"> when a schema_filename is set.</span> +<span class="sd"> """</span> + <span class="n">d</span> <span class="o">=</span> <span class="p">{</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">INT24</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">TINY</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">BIT</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">DATETIME</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">DATE</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">DECIMAL</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">NEWDECIMAL</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">DOUBLE</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">FLOAT</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">INT24</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">LONG</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">LONGLONG</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">SHORT</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">TIMESTAMP</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="n">FIELD_TYPE</span><span class="o">.</span><span class="n">YEAR</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="p">}</span> + <span class="k">return</span> <span class="n">d</span><span class="p">[</span><span class="n">mysql_type</span><span class="p">]</span> <span class="k">if</span> <span class="n">mysql_type</span> <span class="ow">in</span> <span class="n">d</span> <span class="k">else</span> <span class="s1">'STRING'</span></div></div> +</pre></div> + + </div> + <div class="articleComments"> + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + + </p> + </div> + Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </script> + <script type="text/javascript" src="../../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/postgres_to_gcs_operator.html ---------------------------------------------------------------------- diff --git a/_modules/airflow/contrib/operators/postgres_to_gcs_operator.html b/_modules/airflow/contrib/operators/postgres_to_gcs_operator.html new file mode 100644 index 0000000..10c7d8f --- /dev/null +++ b/_modules/airflow/contrib/operators/postgres_to_gcs_operator.html @@ -0,0 +1,481 @@ + + +<!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.postgres_to_gcs_operator — Airflow Documentation</title> + + + + + + + + + + + + + + + + + + <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" /> + + + + + + <link rel="index" title="Index" + href="../../../../genindex.html"/> + <link rel="search" title="Search" href="../../../../search.html"/> + <link rel="top" title="Airflow Documentation" href="../../../../index.html"/> + <link rel="up" title="Module code" href="../../../index.html"/> + + + <script src="../../../../_static/js/modernizr.min.js"></script> + +</head> + +<body class="wy-body-for-nav" role="document"> + + + <div class="wy-grid-for-nav"> + + + <nav data-toggle="wy-nav-shift" class="wy-nav-side"> + <div class="wy-side-scroll"> + <div class="wy-side-nav-search"> + + + + <a href="../../../../index.html" class="icon icon-home"> Airflow + + + + </a> + + + + + + + +<div role="search"> + <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> + <input type="text" name="q" placeholder="Search docs" /> + <input type="hidden" name="check_keywords" value="yes" /> + <input type="hidden" name="area" value="default" /> + </form> +</div> + + + </div> + + <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> + + + + + + + <ul> +<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../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="../../../../lineage.html">Lineage</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> +<li class="toctree-l1"><a class="reference internal" href="../../../../code.html">API Reference</a></li> +</ul> + + + + </div> + </div> + </nav> + + <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> + + + <nav class="wy-nav-top" role="navigation" aria-label="top navigation"> + + <i data-toggle="wy-nav-top" class="fa fa-bars"></i> + <a href="../../../../index.html">Airflow</a> + + </nav> + + + + <div class="wy-nav-content"> + <div class="rst-content"> + + + + + + + + + + + + + + + + +<div role="navigation" aria-label="breadcrumbs navigation"> + + <ul class="wy-breadcrumbs"> + + <li><a href="../../../../index.html">Docs</a> »</li> + + <li><a href="../../../index.html">Module code</a> »</li> + + <li>airflow.contrib.operators.postgres_to_gcs_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.postgres_to_gcs_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">sys</span> +<span class="kn">import</span> <span class="nn">json</span> +<span class="kn">import</span> <span class="nn">time</span> +<span class="kn">import</span> <span class="nn">datetime</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="kn">from</span> <span class="nn">airflow.hooks.postgres_hook</span> <span class="k">import</span> <span class="n">PostgresHook</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> +<span class="kn">from</span> <span class="nn">decimal</span> <span class="k">import</span> <span class="n">Decimal</span> +<span class="kn">from</span> <span class="nn">tempfile</span> <span class="k">import</span> <span class="n">NamedTemporaryFile</span> + +<span class="n">PY3</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="mi">3</span> + + +<div class="viewcode-block" id="PostgresToGoogleCloudStorageOperator"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.postgres_to_gcs_operator.PostgresToGoogleCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">PostgresToGoogleCloudStorageOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Copy data from Postgres to Google Cloud Storage in JSON format.</span> +<span class="sd"> """</span> + <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'sql'</span><span class="p">,</span> <span class="s1">'bucket'</span><span class="p">,</span> <span class="s1">'filename'</span><span class="p">,</span> <span class="s1">'schema_filename'</span><span class="p">,</span> + <span class="s1">'parameters'</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">'#a0e08c'</span> + + <span class="nd">@apply_defaults</span> + <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> + <span class="n">sql</span><span class="p">,</span> + <span class="n">bucket</span><span class="p">,</span> + <span class="n">filename</span><span class="p">,</span> + <span class="n">schema_filename</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="n">approx_max_file_size_bytes</span><span class="o">=</span><span class="mi">1900000000</span><span class="p">,</span> + <span class="n">postgres_conn_id</span><span class="o">=</span><span class="s1">'postgres_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">parameters</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> + <span class="o">*</span><span class="n">args</span><span class="p">,</span> + <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> :param sql: The SQL to execute on the Postgres table.</span> +<span class="sd"> :type sql: string</span> +<span class="sd"> :param bucket: The bucket to upload to.</span> +<span class="sd"> :type bucket: string</span> +<span class="sd"> :param filename: The filename to use as the object name when uploading</span> +<span class="sd"> to Google Cloud Storage. A {} should be specified in the filename</span> +<span class="sd"> to allow the operator to inject file numbers in cases where the</span> +<span class="sd"> file is split due to size.</span> +<span class="sd"> :type filename: string</span> +<span class="sd"> :param schema_filename: If set, the filename to use as the object name</span> +<span class="sd"> when uploading a .json file containing the BigQuery schema fields</span> +<span class="sd"> for the table that was dumped from Postgres.</span> +<span class="sd"> :type schema_filename: string</span> +<span class="sd"> :param approx_max_file_size_bytes: This operator supports the ability</span> +<span class="sd"> to split large table dumps into multiple files (see notes in the</span> +<span class="sd"> filenamed param docs above). Google Cloud Storage allows for files</span> +<span class="sd"> to be a maximum of 4GB. This param allows developers to specify the</span> +<span class="sd"> file size of the splits.</span> +<span class="sd"> :type approx_max_file_size_bytes: long</span> +<span class="sd"> :param postgres_conn_id: Reference to a specific Postgres hook.</span> +<span class="sd"> :type postgres_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"> :param parameters: a parameters dict that is substituted at query runtime.</span> +<span class="sd"> :type parameters: dict</span> +<span class="sd"> """</span> + <span class="nb">super</span><span class="p">(</span><span class="n">PostgresToGoogleCloudStorageOperator</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">sql</span> <span class="o">=</span> <span class="n">sql</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">filename</span> <span class="o">=</span> <span class="n">filename</span> + <span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span> <span class="o">=</span> <span class="n">schema_filename</span> + <span class="bp">self</span><span class="o">.</span><span class="n">approx_max_file_size_bytes</span> <span class="o">=</span> <span class="n">approx_max_file_size_bytes</span> + <span class="bp">self</span><span class="o">.</span><span class="n">postgres_conn_id</span> <span class="o">=</span> <span class="n">postgres_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">parameters</span> <span class="o">=</span> <span class="n">parameters</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">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query_postgres</span><span class="p">()</span> + <span class="n">files_to_upload</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_write_local_data_files</span><span class="p">(</span><span class="n">cursor</span><span class="p">)</span> + + <span class="c1"># If a schema is set, create a BQ schema JSON file.</span> + <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span><span class="p">:</span> + <span class="n">files_to_upload</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_write_local_schema_file</span><span class="p">(</span><span class="n">cursor</span><span class="p">))</span> + + <span class="c1"># Flush all files before uploading</span> + <span class="k">for</span> <span class="n">file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> + <span class="n">file_handle</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> + + <span class="bp">self</span><span class="o">.</span><span class="n">_upload_to_gcs</span><span class="p">(</span><span class="n">files_to_upload</span><span class="p">)</span> + + <span class="c1"># Close all temp file handles.</span> + <span class="k">for</span> <span class="n">file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> + <span class="n">file_handle</span><span class="o">.</span><span class="n">close</span><span class="p">()</span> + + <span class="k">def</span> <span class="nf">_query_postgres</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Queries Postgres and returns a cursor to the results.</span> +<span class="sd"> """</span> + <span class="n">postgres</span> <span class="o">=</span> <span class="n">PostgresHook</span><span class="p">(</span><span class="n">postgres_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">postgres_conn_id</span><span class="p">)</span> + <span class="n">conn</span> <span class="o">=</span> <span class="n">postgres</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">execute</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="bp">self</span><span class="o">.</span><span class="n">parameters</span><span class="p">)</span> + <span class="k">return</span> <span class="n">cursor</span> + + <span class="k">def</span> <span class="nf">_write_local_data_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cursor</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a cursor, and writes results to a local file.</span> + +<span class="sd"> :return: A dictionary where keys are filenames to be used as object</span> +<span class="sd"> names in GCS, and values are file handles to local files that</span> +<span class="sd"> contain the data for the GCS objects.</span> +<span class="sd"> """</span> + <span class="n">schema</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">schema_tuple</span><span class="p">:</span> <span class="n">schema_tuple</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span><span class="p">))</span> + <span class="n">file_no</span> <span class="o">=</span> <span class="mi">0</span> + <span class="n">tmp_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="n">tmp_file_handles</span> <span class="o">=</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_no</span><span class="p">):</span> <span class="n">tmp_file_handle</span><span class="p">}</span> + + <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">cursor</span><span class="p">:</span> + <span class="c1"># Convert datetime objects to utc seconds, and decimals to floats</span> + <span class="n">row</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">convert_types</span><span class="p">,</span> <span class="n">row</span><span class="p">)</span> + <span class="n">row_dict</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">row</span><span class="p">))</span> + + <span class="n">s</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">row_dict</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="k">if</span> <span class="n">PY3</span><span class="p">:</span> + <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> + <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> + + <span class="c1"># Append newline to make dumps BigQuery compatible.</span> + <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span> + + <span class="c1"># Stop if the file exceeds the file size limit.</span> + <span class="k">if</span> <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">approx_max_file_size_bytes</span><span class="p">:</span> + <span class="n">file_no</span> <span class="o">+=</span> <span class="mi">1</span> + <span class="n">tmp_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="n">tmp_file_handles</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">filename</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">file_no</span><span class="p">)]</span> <span class="o">=</span> <span class="n">tmp_file_handle</span> + + <span class="k">return</span> <span class="n">tmp_file_handles</span> + + <span class="k">def</span> <span class="nf">_write_local_schema_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cursor</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a cursor, and writes the BigQuery schema for the results to a</span> +<span class="sd"> local file system.</span> + +<span class="sd"> :return: A dictionary where key is a filename to be used as an object</span> +<span class="sd"> name in GCS, and values are file handles to local files that</span> +<span class="sd"> contains the BigQuery schema fields in .json format.</span> +<span class="sd"> """</span> + <span class="n">schema</span> <span class="o">=</span> <span class="p">[]</span> + <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">cursor</span><span class="o">.</span><span class="n">description</span><span class="p">:</span> + <span class="c1"># See PEP 249 for details about the description tuple.</span> + <span class="n">field_name</span> <span class="o">=</span> <span class="n">field</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> + <span class="n">field_type</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">type_map</span><span class="p">(</span><span class="n">field</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> + <span class="n">field_mode</span> <span class="o">=</span> <span class="s1">'REPEATED'</span> <span class="k">if</span> <span class="n">field</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">in</span> <span class="p">(</span><span class="mi">1009</span><span class="p">,</span> <span class="mi">1005</span><span class="p">,</span> <span class="mi">1007</span><span class="p">,</span> + <span class="mi">1016</span><span class="p">)</span> <span class="k">else</span> <span class="s1">'NULLABLE'</span> + <span class="n">schema</span><span class="o">.</span><span class="n">append</span><span class="p">({</span> + <span class="s1">'name'</span><span class="p">:</span> <span class="n">field_name</span><span class="p">,</span> + <span class="s1">'type'</span><span class="p">:</span> <span class="n">field_type</span><span class="p">,</span> + <span class="s1">'mode'</span><span class="p">:</span> <span class="n">field_mode</span><span class="p">,</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">'Using schema for </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">schema_filename</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span> + <span class="n">tmp_schema_file_handle</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">delete</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="n">s</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> + <span class="k">if</span> <span class="n">PY3</span><span class="p">:</span> + <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> + <span class="n">tmp_schema_file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> + <span class="k">return</span> <span class="p">{</span><span class="bp">self</span><span class="o">.</span><span class="n">schema_filename</span><span class="p">:</span> <span class="n">tmp_schema_file_handle</span><span class="p">}</span> + + <span class="k">def</span> <span class="nf">_upload_to_gcs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">files_to_upload</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Upload all of the file splits (and optionally the schema .json file) to</span> +<span class="sd"> Google Cloud Storage.</span> +<span class="sd"> """</span> + <span class="n">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="k">for</span> <span class="nb">object</span><span class="p">,</span> <span class="n">tmp_file_handle</span> <span class="ow">in</span> <span class="n">files_to_upload</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> + <span class="n">hook</span><span class="o">.</span><span class="n">upload</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="nb">object</span><span class="p">,</span> <span class="n">tmp_file_handle</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> + <span class="s1">'application/json'</span><span class="p">)</span> + +<div class="viewcode-block" id="PostgresToGoogleCloudStorageOperator.convert_types"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.postgres_to_gcs_operator.PostgresToGoogleCloudStorageOperator.convert_types">[docs]</a> <span class="nd">@classmethod</span> + <span class="k">def</span> <span class="nf">convert_types</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Takes a value from Postgres, and converts it to a value that's safe for</span> +<span class="sd"> JSON/Google Cloud Storage/BigQuery. Dates are converted to UTC seconds.</span> +<span class="sd"> Decimals are converted to floats. Times are converted to seconds.</span> +<span class="sd"> """</span> + <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> <span class="ow">in</span> <span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="p">,</span> <span class="n">datetime</span><span class="o">.</span><span class="n">date</span><span class="p">):</span> + <span class="k">return</span> <span class="n">time</span><span class="o">.</span><span class="n">mktime</span><span class="p">(</span><span class="n">value</span><span class="o">.</span><span class="n">timetuple</span><span class="p">())</span> + <span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> <span class="o">==</span> <span class="n">datetime</span><span class="o">.</span><span class="n">time</span><span class="p">:</span> + <span class="n">formated_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">),</span> <span class="s2">"%H:%M:%S"</span><span class="p">)</span> + <span class="k">return</span> <span class="n">datetime</span><span class="o">.</span><span class="n">timedelta</span><span class="p">(</span> + <span class="n">hours</span><span class="o">=</span><span class="n">formated_time</span><span class="o">.</span><span class="n">tm_hour</span><span class="p">,</span> + <span class="n">minutes</span><span class="o">=</span><span class="n">formated_time</span><span class="o">.</span><span class="n">tm_min</span><span class="p">,</span> + <span class="n">seconds</span><span class="o">=</span><span class="n">formated_time</span><span class="o">.</span><span class="n">tm_sec</span><span class="p">)</span><span class="o">.</span><span class="n">seconds</span> + <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">Decimal</span><span class="p">):</span> + <span class="k">return</span> <span class="nb">float</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> + <span class="k">else</span><span class="p">:</span> + <span class="k">return</span> <span class="n">value</span></div> + +<div class="viewcode-block" id="PostgresToGoogleCloudStorageOperator.type_map"><a class="viewcode-back" href="../../../../code.html#airflow.contrib.operators.postgres_to_gcs_operator.PostgresToGoogleCloudStorageOperator.type_map">[docs]</a> <span class="nd">@classmethod</span> + <span class="k">def</span> <span class="nf">type_map</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">postgres_type</span><span class="p">):</span> + <span class="sd">"""</span> +<span class="sd"> Helper function that maps from Postgres fields to BigQuery fields. Used</span> +<span class="sd"> when a schema_filename is set.</span> +<span class="sd"> """</span> + <span class="n">d</span> <span class="o">=</span> <span class="p">{</span> + <span class="mi">1114</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="mi">1184</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="mi">1082</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="mi">1083</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> + <span class="mi">1005</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">1007</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">1016</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">20</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">21</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">23</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> + <span class="mi">16</span><span class="p">:</span> <span class="s1">'BOOLEAN'</span><span class="p">,</span> + <span class="mi">700</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="mi">701</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> + <span class="mi">1700</span><span class="p">:</span> <span class="s1">'FLOAT'</span> + <span class="p">}</span> + + <span class="k">return</span> <span class="n">d</span><span class="p">[</span><span class="n">postgres_type</span><span class="p">]</span> <span class="k">if</span> <span class="n">postgres_type</span> <span class="ow">in</span> <span class="n">d</span> <span class="k">else</span> <span class="s1">'STRING'</span></div></div> +</pre></div> + + </div> + <div class="articleComments"> + + </div> + </div> + <footer> + + + <hr/> + + <div role="contentinfo"> + <p> + + </p> + </div> + Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. + +</footer> + + </div> + </div> + + </section> + + </div> + + + + + + <script type="text/javascript"> + var DOCUMENTATION_OPTIONS = { + URL_ROOT:'../../../../', + VERSION:'', + COLLAPSE_INDEX:false, + FILE_SUFFIX:'.html', + HAS_SOURCE: true, + SOURCELINK_SUFFIX: '.txt' + }; + </script> + <script type="text/javascript" src="../../../../_static/jquery.js"></script> + <script type="text/javascript" src="../../../../_static/underscore.js"></script> + <script type="text/javascript" src="../../../../_static/doctools.js"></script> + + + + + + <script type="text/javascript" src="../../../../_static/js/theme.js"></script> + + + + + <script type="text/javascript"> + jQuery(function () { + SphinxRtdTheme.StickyNav.enable(); + }); + </script> + + +</body> +</html> \ No newline at end of file