| |
| |
| |
| |
| <!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.cassandra_to_gcs — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <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/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="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </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"> |
| 1.10.3 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">Experimental Rest API</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">API Reference</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li><a href="../operators.html">airflow.contrib.operators</a> »</li> |
| |
| <li>airflow.contrib.operators.cassandra_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.cassandra_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">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">unicode_literals</span> |
| |
| <span class="kn">import</span> <span class="nn">json</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">str</span> |
| <span class="kn">from</span> <span class="nn">base64</span> <span class="k">import</span> <span class="n">b64encode</span> |
| <span class="kn">from</span> <span class="nn">cassandra.util</span> <span class="k">import</span> <span class="n">Date</span><span class="p">,</span> <span class="n">Time</span><span class="p">,</span> <span class="n">SortedSet</span><span class="p">,</span> <span class="n">OrderedMapSerializedKey</span> |
| <span class="kn">from</span> <span class="nn">datetime</span> <span class="k">import</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">six</span> <span class="k">import</span> <span class="n">text_type</span><span class="p">,</span> <span class="n">binary_type</span><span class="p">,</span> <span class="n">PY3</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">uuid</span> <span class="k">import</span> <span class="n">UUID</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.contrib.hooks.cassandra_hook</span> <span class="k">import</span> <span class="n">CassandraHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> |
| |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">CassandraToGoogleCloudStorageOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Copy data from Cassandra to Google cloud storage in JSON format</span> |
| |
| <span class="sd"> Note: Arrays of arrays are not supported.</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'cql'</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></div> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.template_ext"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.template_ext">[docs]</a> <span class="n">template_ext</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'.cql'</span><span class="p">,)</span></div> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#a0e08c'</span></div> |
| |
| <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">cql</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">cassandra_conn_id</span><span class="o">=</span><span class="s1">'cassandra_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="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 cql: The CQL to execute on the Cassandra table.</span> |
| <span class="sd"> :type cql: str</span> |
| <span class="sd"> :param bucket: The bucket to upload to.</span> |
| <span class="sd"> :type bucket: str</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: str</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: str</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 cassandra_conn_id: Reference to a specific Cassandra hook.</span> |
| <span class="sd"> :type cassandra_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"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">CassandraToGoogleCloudStorageOperator</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">cql</span> <span class="o">=</span> <span class="n">cql</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">cassandra_conn_id</span> <span class="o">=</span> <span class="n">cassandra_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">hook</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="c1"># Default Cassandra to BigQuery type mapping</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.CQL_TYPE_MAP"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.CQL_TYPE_MAP">[docs]</a> <span class="n">CQL_TYPE_MAP</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'BytesType'</span><span class="p">:</span> <span class="s1">'BYTES'</span><span class="p">,</span> |
| <span class="s1">'DecimalType'</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> |
| <span class="s1">'UUIDType'</span><span class="p">:</span> <span class="s1">'BYTES'</span><span class="p">,</span> |
| <span class="s1">'BooleanType'</span><span class="p">:</span> <span class="s1">'BOOL'</span><span class="p">,</span> |
| <span class="s1">'ByteType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'AsciiType'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> |
| <span class="s1">'FloatType'</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> |
| <span class="s1">'DoubleType'</span><span class="p">:</span> <span class="s1">'FLOAT'</span><span class="p">,</span> |
| <span class="s1">'LongType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'Int32Type'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'IntegerType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'InetAddressType'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> |
| <span class="s1">'CounterColumnType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'DateType'</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> |
| <span class="s1">'SimpleDateType'</span><span class="p">:</span> <span class="s1">'DATE'</span><span class="p">,</span> |
| <span class="s1">'TimestampType'</span><span class="p">:</span> <span class="s1">'TIMESTAMP'</span><span class="p">,</span> |
| <span class="s1">'TimeUUIDType'</span><span class="p">:</span> <span class="s1">'BYTES'</span><span class="p">,</span> |
| <span class="s1">'ShortType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'TimeType'</span><span class="p">:</span> <span class="s1">'TIME'</span><span class="p">,</span> |
| <span class="s1">'DurationType'</span><span class="p">:</span> <span class="s1">'INTEGER'</span><span class="p">,</span> |
| <span class="s1">'UTF8Type'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span> |
| <span class="s1">'VarcharType'</span><span class="p">:</span> <span class="s1">'STRING'</span><span class="p">,</span></div> |
| <span class="p">}</span> |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.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">cursor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_query_cassandra</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="c1"># Close all sessions and connection associated with this Cassandra cluster</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">shutdown_cluster</span><span class="p">()</span></div> |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator._query_cassandra"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator._query_cassandra">[docs]</a> <span class="k">def</span> <span class="nf">_query_cassandra</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Queries cassandra and returns a cursor to the results.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hook</span> <span class="o">=</span> <span class="n">CassandraHook</span><span class="p">(</span><span class="n">cassandra_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">cassandra_conn_id</span><span class="p">)</span> |
| <span class="n">session</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="n">cursor</span> <span class="o">=</span> <span class="n">session</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">cql</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">cursor</span></div> |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator._write_local_data_files"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator._write_local_data_files">[docs]</a> <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">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="n">row_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">generate_data_dict</span><span class="p">(</span><span class="n">row</span><span class="o">.</span><span class="n">_fields</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="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="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></div> |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator._write_local_schema_file"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator._write_local_schema_file">[docs]</a> <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="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">for</span> <span class="n">name</span><span class="p">,</span> <span class="nb">type</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">cursor</span><span class="o">.</span><span class="n">column_names</span><span class="p">,</span> <span class="n">cursor</span><span class="o">.</span><span class="n">column_types</span><span class="p">):</span> |
| <span class="n">schema</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">generate_schema_dict</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">))</span> |
| <span class="n">json_serialized_schema</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">json_serialized_schema</span> <span class="o">=</span> <span class="n">json_serialized_schema</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">json_serialized_schema</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></div> |
| |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator._upload_to_gcs"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator._upload_to_gcs">[docs]</a> <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="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> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.generate_data_dict"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.generate_data_dict">[docs]</a> <span class="k">def</span> <span class="nf">generate_data_dict</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">names</span><span class="p">,</span> <span class="n">values</span><span class="p">):</span> |
| <span class="n">row_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">names</span><span class="p">,</span> <span class="n">values</span><span class="p">):</span> |
| <span class="n">row_dict</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="n">name</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)})</span> |
| <span class="k">return</span> <span class="n">row_dict</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.convert_value"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.convert_value">[docs]</a> <span class="k">def</span> <span class="nf">convert_value</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">value</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">value</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="p">(</span><span class="n">text_type</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">,</span> <span class="nb">bool</span><span class="p">,</span> <span class="nb">dict</span><span class="p">)):</span> |
| <span class="k">return</span> <span class="n">value</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">binary_type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">b64encode</span><span class="p">(</span><span class="n">value</span><span class="p">)</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">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">UUID</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">b64encode</span><span class="p">(</span><span class="n">value</span><span class="o">.</span><span class="n">bytes</span><span class="p">)</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">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</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="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)</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">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">Time</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">)</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</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="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="n">SortedSet</span><span class="p">)):</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_array_types</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="s1">'_fields'</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_user_type</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</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="nb">tuple</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_tuple_type</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</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">OrderedMapSerializedKey</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_map_type</span><span class="p">(</span><span class="n">name</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">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'unexpected value: '</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">value</span><span class="p">))</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.convert_array_types"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.convert_array_types">[docs]</a> <span class="k">def</span> <span class="nf">convert_array_types</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">nested_value</span><span class="p">)</span> <span class="k">for</span> <span class="n">nested_value</span> <span class="ow">in</span> <span class="n">value</span><span class="p">]</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.convert_user_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.convert_user_type">[docs]</a> <span class="k">def</span> <span class="nf">convert_user_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Converts a user type to RECORD that contains n fields, where n is the</span> |
| <span class="sd"> number of attributes. Each element in the user type class will be converted to its</span> |
| <span class="sd"> corresponding data type in BQ.</span> |
| <span class="sd"> """</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">_fields</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">name</span><span class="p">))</span> <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">names</span><span class="p">]</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">generate_data_dict</span><span class="p">(</span><span class="n">names</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.convert_tuple_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.convert_tuple_type">[docs]</a> <span class="k">def</span> <span class="nf">convert_tuple_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Converts a tuple to RECORD that contains n fields, each will be converted</span> |
| <span class="sd"> to its corresponding data type in bq and will be named 'field_<index>', where</span> |
| <span class="sd"> index is determined by the order of the tuple elements defined in cassandra.</span> |
| <span class="sd"> """</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'field_'</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">value</span><span class="p">))]</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> <span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">names</span><span class="p">,</span> <span class="n">value</span><span class="p">)]</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">generate_data_dict</span><span class="p">(</span><span class="n">names</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.convert_map_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.convert_map_type">[docs]</a> <span class="k">def</span> <span class="nf">convert_map_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Converts a map to a repeated RECORD that contains two fields: 'key' and 'value',</span> |
| <span class="sd"> each will be converted to its corresponding data type in BQ.</span> |
| <span class="sd"> """</span> |
| <span class="n">converted_map</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">value</span><span class="o">.</span><span class="n">keys</span><span class="p">(),</span> <span class="n">value</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span> |
| <span class="n">converted_map</span><span class="o">.</span><span class="n">append</span><span class="p">({</span> |
| <span class="s1">'key'</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="s1">'key'</span><span class="p">,</span> <span class="n">k</span><span class="p">),</span> |
| <span class="s1">'value'</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="n">convert_value</span><span class="p">(</span><span class="s1">'value'</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> |
| <span class="p">})</span> |
| <span class="k">return</span> <span class="n">converted_map</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.generate_schema_dict"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.generate_schema_dict">[docs]</a> <span class="k">def</span> <span class="nf">generate_schema_dict</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="n">field_schema</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="s1">'name'</span><span class="p">:</span> <span class="n">name</span><span class="p">})</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="s1">'type'</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="n">get_bq_type</span><span class="p">(</span><span class="nb">type</span><span class="p">)})</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="s1">'mode'</span><span class="p">:</span> <span class="bp">cls</span><span class="o">.</span><span class="n">get_bq_mode</span><span class="p">(</span><span class="nb">type</span><span class="p">)})</span> |
| <span class="n">fields</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">get_bq_fields</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">fields</span><span class="p">:</span> |
| <span class="n">field_schema</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="s1">'fields'</span><span class="p">:</span> <span class="n">fields</span><span class="p">})</span> |
| <span class="k">return</span> <span class="n">field_schema</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.get_bq_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.get_bq_fields">[docs]</a> <span class="k">def</span> <span class="nf">get_bq_fields</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="n">fields</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_simple_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="n">names</span><span class="p">,</span> <span class="n">types</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span> |
| |
| <span class="k">if</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_array_type</span><span class="p">(</span><span class="nb">type</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_record_type</span><span class="p">(</span><span class="nb">type</span><span class="o">.</span><span class="n">subtypes</span><span class="p">[</span><span class="mi">0</span><span class="p">]):</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="nb">type</span><span class="o">.</span><span class="n">subtypes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">fieldnames</span> |
| <span class="n">types</span> <span class="o">=</span> <span class="nb">type</span><span class="o">.</span><span class="n">subtypes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">subtypes</span> |
| <span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_record_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="nb">type</span><span class="o">.</span><span class="n">fieldnames</span> |
| <span class="n">types</span> <span class="o">=</span> <span class="nb">type</span><span class="o">.</span><span class="n">subtypes</span> |
| |
| <span class="k">if</span> <span class="n">types</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">names</span> <span class="ow">and</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="o">==</span> <span class="s1">'TupleType'</span><span class="p">:</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'field_'</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">types</span><span class="p">))]</span> |
| <span class="k">elif</span> <span class="n">types</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">names</span> <span class="ow">and</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="o">==</span> <span class="s1">'MapType'</span><span class="p">:</span> |
| <span class="n">names</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'key'</span><span class="p">,</span> <span class="s1">'value'</span><span class="p">]</span> |
| |
| <span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="nb">type</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">names</span><span class="p">,</span> <span class="n">types</span><span class="p">):</span> |
| <span class="n">field</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">generate_schema_dict</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">)</span> |
| <span class="n">fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">field</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">fields</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.is_simple_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.is_simple_type">[docs]</a> <span class="k">def</span> <span class="nf">is_simple_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="ow">in</span> <span class="n">CassandraToGoogleCloudStorageOperator</span><span class="o">.</span><span class="n">CQL_TYPE_MAP</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.is_array_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.is_array_type">[docs]</a> <span class="k">def</span> <span class="nf">is_array_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'ListType'</span><span class="p">,</span> <span class="s1">'SetType'</span><span class="p">]</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.is_record_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.is_record_type">[docs]</a> <span class="k">def</span> <span class="nf">is_record_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'UserType'</span><span class="p">,</span> <span class="s1">'TupleType'</span><span class="p">,</span> <span class="s1">'MapType'</span><span class="p">]</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.get_bq_type"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.get_bq_type">[docs]</a> <span class="k">def</span> <span class="nf">get_bq_type</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_simple_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">CassandraToGoogleCloudStorageOperator</span><span class="o">.</span><span class="n">CQL_TYPE_MAP</span><span class="p">[</span><span class="nb">type</span><span class="o">.</span><span class="n">cassname</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_record_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'RECORD'</span> |
| <span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_array_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">cls</span><span class="o">.</span><span class="n">get_bq_type</span><span class="p">(</span><span class="nb">type</span><span class="o">.</span><span class="n">subtypes</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Not a supported type: '</span> <span class="o">+</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span><span class="p">)</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <div class="viewcode-block" id="CassandraToGoogleCloudStorageOperator.get_bq_mode"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/cassandra_to_gcs/index.html#airflow.contrib.operators.cassandra_to_gcs.CassandraToGoogleCloudStorageOperator.get_bq_mode">[docs]</a> <span class="k">def</span> <span class="nf">get_bq_mode</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="nb">type</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_array_type</span><span class="p">(</span><span class="nb">type</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span> <span class="o">==</span> <span class="s1">'MapType'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'REPEATED'</span> |
| <span class="k">elif</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_record_type</span><span class="p">(</span><span class="nb">type</span><span class="p">)</span> <span class="ow">or</span> <span class="bp">cls</span><span class="o">.</span><span class="n">is_simple_type</span><span class="p">(</span><span class="nb">type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'NULLABLE'</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Not a supported type: '</span> <span class="o">+</span> <span class="nb">type</span><span class="o">.</span><span class="n">cassname</span><span class="p">)</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |