blob: dacd6c0d0636585adefc94c8653dc29f4ee32149 [file] [log] [blame]
<!--
Javascript to render AIRFLOW-XXX and PR references in text
as HTML links.
Overrides extrahead block from sphinx_rtd_theme
https://www.sphinx-doc.org/en/master/templating.html
-->
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>airflow.contrib.operators.dynamodb_to_s3 &mdash; Airflow Documentation</title>
<link rel="shortcut icon" href="../../../../_static/pin_32.png"/>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script type="text/javascript" src="../../../../_static/jira-links.js"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/graphviz.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/exampleinclude.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script>
</script>
<style>
</style>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Airflow
</a>
<div class="version">
1.10.8
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../project.html">Project</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling &amp; Triggers</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../executor/index.html">Executor</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../errors.html">Error Tracking</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../dag-serialization.html">DAG Serialization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../best-practices.html">Best Practices</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</a></li>
</ul>
<p class="caption"><span class="caption-text">References</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../configurations-ref.html">Configurations</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Airflow</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li><a href="../operators.html">airflow.contrib.operators</a> &raquo;</li>
<li>airflow.contrib.operators.dynamodb_to_s3</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.dynamodb_to_s3</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"># &quot;License&quot;); 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"># &quot;AS IS&quot; 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="c1">#</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd">This module contains operators to replicate records from</span>
<span class="sd">DynamoDB table to S3.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">copy</span> <span class="kn">import</span> <span class="n">copy</span>
<span class="kn">from</span> <span class="nn">os.path</span> <span class="kn">import</span> <span class="n">getsize</span>
<span class="kn">from</span> <span class="nn">tempfile</span> <span class="kn">import</span> <span class="n">NamedTemporaryFile</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Optional</span>
<span class="kn">from</span> <span class="nn">uuid</span> <span class="kn">import</span> <span class="n">uuid4</span>
<span class="kn">from</span> <span class="nn">boto.compat</span> <span class="kn">import</span> <span class="n">json</span> <span class="c1"># type: ignore</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.hooks.aws_dynamodb_hook</span> <span class="kn">import</span> <span class="n">AwsDynamoDBHook</span>
<span class="kn">from</span> <span class="nn">airflow.hooks.S3_hook</span> <span class="kn">import</span> <span class="n">S3Hook</span>
<span class="kn">from</span> <span class="nn">airflow.models.baseoperator</span> <span class="kn">import</span> <span class="n">BaseOperator</span>
<div class="viewcode-block" id="_convert_item_to_json_bytes"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dynamodb_to_s3/index.html#airflow.contrib.operators.dynamodb_to_s3._convert_item_to_json_bytes">[docs]</a><span class="k">def</span> <span class="nf">_convert_item_to_json_bytes</span><span class="p">(</span><span class="n">item</span><span class="p">):</span>
<span class="k">return</span> <span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">item</span><span class="p">)</span> <span class="o">+</span> <span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="_upload_file_to_s3"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dynamodb_to_s3/index.html#airflow.contrib.operators.dynamodb_to_s3._upload_file_to_s3">[docs]</a><span class="k">def</span> <span class="nf">_upload_file_to_s3</span><span class="p">(</span><span class="n">file_obj</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">s3_key_prefix</span><span class="p">):</span>
<span class="n">s3_client</span> <span class="o">=</span> <span class="n">S3Hook</span><span class="p">()</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span>
<span class="n">file_obj</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">s3_client</span><span class="o">.</span><span class="n">upload_file</span><span class="p">(</span>
<span class="n">Filename</span><span class="o">=</span><span class="n">file_obj</span><span class="o">.</span><span class="n">name</span><span class="p">,</span>
<span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span>
<span class="n">Key</span><span class="o">=</span><span class="n">s3_key_prefix</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">uuid4</span><span class="p">()),</span></div>
<span class="p">)</span>
<div class="viewcode-block" id="DynamoDBToS3Operator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dynamodb_to_s3/index.html#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator">[docs]</a><span class="k">class</span> <span class="nc">DynamoDBToS3Operator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Replicates records from a DynamoDB table to S3.</span>
<span class="sd"> It scans a DynamoDB table and write the received records to a file</span>
<span class="sd"> on the local filesystem. It flushes the file to S3 once the file size</span>
<span class="sd"> exceeds the file size limit specified by the user.</span>
<span class="sd"> Users can also specify a filtering criteria using dynamodb_scan_kwargs</span>
<span class="sd"> to only replicate records that satisfy the criteria.</span>
<span class="sd"> To parallelize the replication, users can create multiple tasks of DynamoDBToS3Operator.</span>
<span class="sd"> For instance to replicate with parallelism of 2, create two tasks like:</span>
<span class="sd"> .. code-block::</span>
<span class="sd"> op1 = DynamoDBToS3Operator(</span>
<span class="sd"> task_id=&#39;replicator-1&#39;,</span>
<span class="sd"> dynamodb_table_name=&#39;hello&#39;,</span>
<span class="sd"> dynamodb_scan_kwargs={</span>
<span class="sd"> &#39;TotalSegments&#39;: 2,</span>
<span class="sd"> &#39;Segment&#39;: 0,</span>
<span class="sd"> },</span>
<span class="sd"> ...</span>
<span class="sd"> )</span>
<span class="sd"> op2 = DynamoDBToS3Operator(</span>
<span class="sd"> task_id=&#39;replicator-2&#39;,</span>
<span class="sd"> dynamodb_table_name=&#39;hello&#39;,</span>
<span class="sd"> dynamodb_scan_kwargs={</span>
<span class="sd"> &#39;TotalSegments&#39;: 2,</span>
<span class="sd"> &#39;Segment&#39;: 1,</span>
<span class="sd"> },</span>
<span class="sd"> ...</span>
<span class="sd"> )</span>
<span class="sd"> :param dynamodb_table_name: Dynamodb table to replicate data from</span>
<span class="sd"> :param s3_bucket_name: S3 bucket to replicate data to</span>
<span class="sd"> :param file_size: Flush file to s3 if file size &gt;= file_size</span>
<span class="sd"> :param dynamodb_scan_kwargs: kwargs pass to &lt;https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb.html#DynamoDB.Table.scan&gt; # noqa: E501 pylint: disable=line-too-long</span>
<span class="sd"> :param s3_key_prefix: Prefix of s3 object key</span>
<span class="sd"> :param process_func: How we transforms a dynamodb item to bytes. By default we dump the json</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">dynamodb_table_name</span><span class="p">,</span> <span class="c1"># type: str</span>
<span class="n">s3_bucket_name</span><span class="p">,</span> <span class="c1"># type: str</span>
<span class="n">file_size</span><span class="p">,</span> <span class="c1"># ty: int</span>
<span class="n">dynamodb_scan_kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[Dict[str, Any]]</span>
<span class="n">s3_key_prefix</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="c1"># type: str</span>
<span class="n">process_func</span><span class="o">=</span><span class="n">_convert_item_to_json_bytes</span><span class="p">,</span> <span class="c1"># type: Callable[[Dict[str, Any]], bytes]</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">DynamoDBToS3Operator</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">file_size</span> <span class="o">=</span> <span class="n">file_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">process_func</span> <span class="o">=</span> <span class="n">process_func</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dynamodb_table_name</span> <span class="o">=</span> <span class="n">dynamodb_table_name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dynamodb_scan_kwargs</span> <span class="o">=</span> <span class="n">dynamodb_scan_kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket_name</span> <span class="o">=</span> <span class="n">s3_bucket_name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_key_prefix</span> <span class="o">=</span> <span class="n">s3_key_prefix</span>
<div class="viewcode-block" id="DynamoDBToS3Operator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dynamodb_to_s3/index.html#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator.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">table</span> <span class="o">=</span> <span class="n">AwsDynamoDBHook</span><span class="p">()</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">Table</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dynamodb_table_name</span><span class="p">)</span>
<span class="n">scan_kwargs</span> <span class="o">=</span> <span class="n">copy</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dynamodb_scan_kwargs</span><span class="p">)</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">dynamodb_scan_kwargs</span> <span class="k">else</span> <span class="p">{}</span>
<span class="n">err</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">f</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">()</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">f</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scan_dynamodb_and_upload_to_s3</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">scan_kwargs</span><span class="p">,</span> <span class="n">table</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">err</span> <span class="o">=</span> <span class="n">e</span>
<span class="k">raise</span> <span class="n">e</span>
<span class="k">finally</span><span class="p">:</span>
<span class="k">if</span> <span class="n">err</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">_upload_file_to_s3</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_key_prefix</span><span class="p">)</span>
<span class="n">f</span><span class="o">.</span><span class="n">close</span><span class="p">()</span></div>
<div class="viewcode-block" id="DynamoDBToS3Operator._scan_dynamodb_and_upload_to_s3"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/dynamodb_to_s3/index.html#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator._scan_dynamodb_and_upload_to_s3">[docs]</a> <span class="k">def</span> <span class="nf">_scan_dynamodb_and_upload_to_s3</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">temp_file</span><span class="p">,</span> <span class="n">scan_kwargs</span><span class="p">,</span> <span class="n">table</span><span class="p">):</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">table</span><span class="o">.</span><span class="n">scan</span><span class="p">(</span><span class="o">**</span><span class="n">scan_kwargs</span><span class="p">)</span>
<span class="n">items</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">&#39;Items&#39;</span><span class="p">]</span>
<span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">items</span><span class="p">:</span>
<span class="n">temp_file</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">process_func</span><span class="p">(</span><span class="n">item</span><span class="p">))</span>
<span class="k">if</span> <span class="s1">&#39;LastEvaluatedKey&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span>
<span class="c1"># no more items to scan</span>
<span class="k">break</span>
<span class="n">last_evaluated_key</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">&#39;LastEvaluatedKey&#39;</span><span class="p">]</span>
<span class="n">scan_kwargs</span><span class="p">[</span><span class="s1">&#39;ExclusiveStartKey&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">last_evaluated_key</span>
<span class="c1"># Upload the file to S3 if reach file size limit</span>
<span class="k">if</span> <span class="n">getsize</span><span class="p">(</span><span class="n">temp_file</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="bp">self</span><span class="o">.</span><span class="n">file_size</span><span class="p">:</span>
<span class="n">_upload_file_to_s3</span><span class="p">(</span><span class="n">temp_file</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">s3_bucket_name</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">s3_key_prefix</span><span class="p">)</span>
<span class="n">temp_file</span><span class="o">.</span><span class="n">close</span><span class="p">()</span>
<span class="n">temp_file</span> <span class="o">=</span> <span class="n">NamedTemporaryFile</span><span class="p">()</span>
<span class="k">return</span> <span class="n">temp_file</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
<div class="footer">This page uses <a href="https://analytics.google.com/">
Google Analytics</a> to collect statistics. You can disable it by blocking
the JavaScript coming from www.google-analytics.com. Check our
<a href="../../../../privacy_notice.html">Privacy Policy</a>
for more details.
</div>
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
<!-- Theme Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-140539454-1', 'auto');
ga('send', 'pageview');
</script>
</body>
</html>