blob: c43f1f4935efc4b7acd5bc42352ccbe66cfc2f04 [file] [log] [blame]
<!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.s3_to_gcs_operator &mdash; Airflow Documentation</title>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
<script src="../../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../../index.html" class="icon icon-home"> Airflow
</a>
<div 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 &amp; 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" 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>airflow.contrib.operators.s3_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.s3_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"># &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="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">airflow.contrib.hooks.gcs_hook</span> <span class="k">import</span> <span class="p">(</span><span class="n">GoogleCloudStorageHook</span><span class="p">,</span>
<span class="n">_parse_gcs_url</span><span class="p">)</span>
<span class="kn">from</span> <span class="nn">airflow.contrib.operators.s3_list_operator</span> <span class="k">import</span> <span class="n">S3ListOperator</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.hooks.S3_hook</span> <span class="k">import</span> <span class="n">S3Hook</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="S3ToGoogleCloudStorageOperator"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.s3_to_gcs_operator.S3ToGoogleCloudStorageOperator">[docs]</a><span class="k">class</span> <span class="nc">S3ToGoogleCloudStorageOperator</span><span class="p">(</span><span class="n">S3ListOperator</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Synchronizes an S3 key, possibly a prefix, with a Google Cloud Storage</span>
<span class="sd"> destination path.</span>
<span class="sd"> :param bucket: The S3 bucket where to find the objects. (templated)</span>
<span class="sd"> :type bucket: string</span>
<span class="sd"> :param prefix: Prefix string which filters objects whose name begin with</span>
<span class="sd"> such prefix. (templated)</span>
<span class="sd"> :type prefix: string</span>
<span class="sd"> :param delimiter: the delimiter marks key hierarchy. (templated)</span>
<span class="sd"> :type delimiter: string</span>
<span class="sd"> :param aws_conn_id: The source S3 connection</span>
<span class="sd"> :type aws_conn_id: string</span>
<span class="sd"> :param dest_gcs_conn_id: The destination connection ID to use</span>
<span class="sd"> when connecting to Google Cloud Storage.</span>
<span class="sd"> :type dest_gcs_conn_id: string</span>
<span class="sd"> :param dest_gcs: The destination Google Cloud Storage bucket and prefix</span>
<span class="sd"> where you want to store the files. (templated)</span>
<span class="sd"> :type dest_gcs: string</span>
<span class="sd"> :param delegate_to: The account to impersonate, if any.</span>
<span class="sd"> For this to work, the service account making the request must have</span>
<span class="sd"> domain-wide delegation enabled.</span>
<span class="sd"> :type delegate_to: string</span>
<span class="sd"> :param replace: Whether you want to replace existing destination files</span>
<span class="sd"> or not.</span>
<span class="sd"> :type replace: bool</span>
<span class="sd"> **Example**:</span>
<span class="sd"> .. code-block:: python</span>
<span class="sd"> s3_to_gcs_op = S3ToGoogleCloudStorageOperator(</span>
<span class="sd"> task_id=&#39;s3_to_gcs_example&#39;,</span>
<span class="sd"> bucket=&#39;my-s3-bucket&#39;,</span>
<span class="sd"> prefix=&#39;data/customers-201804&#39;,</span>
<span class="sd"> dest_gcs_conn_id=&#39;google_cloud_default&#39;,</span>
<span class="sd"> dest_gcs=&#39;gs://my.gcs.bucket/some/customers/&#39;,</span>
<span class="sd"> replace=False,</span>
<span class="sd"> dag=my-dag)</span>
<span class="sd"> Note that ``bucket``, ``prefix``, ``delimiter`` and ``dest_gcs`` are</span>
<span class="sd"> templated, so you can use variables in them if you wish.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;bucket&#39;</span><span class="p">,</span> <span class="s1">&#39;prefix&#39;</span><span class="p">,</span> <span class="s1">&#39;delimiter&#39;</span><span class="p">,</span> <span class="s1">&#39;dest_gcs&#39;</span><span class="p">)</span>
<span class="n">ui_color</span> <span class="o">=</span> <span class="s1">&#39;#e09411&#39;</span>
<span class="nd">@apply_defaults</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span>
<span class="n">bucket</span><span class="p">,</span>
<span class="n">prefix</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span>
<span class="n">aws_conn_id</span><span class="o">=</span><span class="s1">&#39;aws_default&#39;</span><span class="p">,</span>
<span class="n">dest_gcs_conn_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">dest_gcs</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="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="o">*</span><span class="n">args</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">S3ToGoogleCloudStorageOperator</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="n">bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span>
<span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span>
<span class="n">delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">,</span>
<span class="n">aws_conn_id</span><span class="o">=</span><span class="n">aws_conn_id</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">dest_gcs_conn_id</span> <span class="o">=</span> <span class="n">dest_gcs_conn_id</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span> <span class="o">=</span> <span class="n">dest_gcs</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">replace</span> <span class="o">=</span> <span class="n">replace</span>
<span class="k">if</span> <span class="n">dest_gcs</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_gcs_object_is_directory</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</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">&#39;Destination Google Cloud Storage path is not a valid &#39;</span>
<span class="s1">&#39;&quot;directory&quot;, define a path that ends with a slash &quot;/&quot; or &#39;</span>
<span class="s1">&#39;leave it empty for the root of the bucket.&#39;</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">&#39;The destination Google Cloud Storage path &#39;</span>
<span class="s1">&#39;must end with a slash &quot;/&quot; or be empty.&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="S3ToGoogleCloudStorageOperator.execute"><a class="viewcode-back" href="../../../../integration.html#airflow.contrib.operators.s3_to_gcs_operator.S3ToGoogleCloudStorageOperator.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="c1"># use the super method to list all the files in an S3 bucket/key</span>
<span class="n">files</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">S3ToGoogleCloudStorageOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">execute</span><span class="p">(</span><span class="n">context</span><span class="p">)</span>
<span class="n">gcs_hook</span> <span class="o">=</span> <span class="n">GoogleCloudStorageHook</span><span class="p">(</span>
<span class="n">google_cloud_storage_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs_conn_id</span><span class="p">,</span>
<span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">replace</span><span class="p">:</span>
<span class="c1"># if we are not replacing -&gt; list all files in the GCS bucket</span>
<span class="c1"># and only keep those files which are present in</span>
<span class="c1"># S3 and not in Google Cloud Storage</span>
<span class="n">bucket_name</span><span class="p">,</span> <span class="n">object_prefix</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span><span class="p">)</span>
<span class="n">existing_files_prefixed</span> <span class="o">=</span> <span class="n">gcs_hook</span><span class="o">.</span><span class="n">list</span><span class="p">(</span>
<span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">object_prefix</span><span class="p">)</span>
<span class="n">existing_files</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">if</span> <span class="n">existing_files_prefixed</span><span class="p">:</span>
<span class="c1"># Remove the object prefix itself, an empty directory was found</span>
<span class="k">if</span> <span class="n">object_prefix</span> <span class="ow">in</span> <span class="n">existing_files_prefixed</span><span class="p">:</span>
<span class="n">existing_files_prefixed</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">object_prefix</span><span class="p">)</span>
<span class="c1"># Remove the object prefix from all object string paths</span>
<span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">existing_files_prefixed</span><span class="p">:</span>
<span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">object_prefix</span><span class="p">):</span>
<span class="n">existing_files</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">f</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">object_prefix</span><span class="p">):])</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">existing_files</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="n">files</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="n">files</span><span class="p">)</span> <span class="o">-</span> <span class="nb">set</span><span class="p">(</span><span class="n">existing_files</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">files</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</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">&#39;</span><span class="si">{0}</span><span class="s1"> files are going to be synced: </span><span class="si">{1}</span><span class="s1">.&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="nb">len</span><span class="p">(</span><span class="n">files</span><span class="p">),</span> <span class="n">files</span><span class="p">))</span>
<span class="k">else</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">&#39;There are no new files to sync. Have a nice day!&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">files</span><span class="p">:</span>
<span class="n">hook</span> <span class="o">=</span> <span class="n">S3Hook</span><span class="p">(</span><span class="n">aws_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">aws_conn_id</span><span class="p">)</span>
<span class="k">for</span> <span class="n">file</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span>
<span class="c1"># GCS hook builds its own in-memory file so we have to create</span>
<span class="c1"># and pass the path</span>
<span class="n">file_object</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_key</span><span class="p">(</span><span class="n">file</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="k">with</span> <span class="n">NamedTemporaryFile</span><span class="p">(</span><span class="n">mode</span><span class="o">=</span><span class="s1">&#39;wb&#39;</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">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">file_object</span><span class="o">.</span><span class="n">download_fileobj</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
<span class="n">f</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span>
<span class="n">dest_gcs_bucket</span><span class="p">,</span> <span class="n">dest_gcs_object_prefix</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">dest_gcs</span><span class="p">)</span>
<span class="c1"># There will always be a &#39;/&#39; before file because it is</span>
<span class="c1"># enforced at instantiation time</span>
<span class="n">dest_gcs_object</span> <span class="o">=</span> <span class="n">dest_gcs_object_prefix</span> <span class="o">+</span> <span class="n">file</span>
<span class="c1"># Sync is sequential and the hook already logs too much</span>
<span class="c1"># so skip this for now</span>
<span class="c1"># self.log.info(</span>
<span class="c1"># &#39;Saving file {0} from S3 bucket {1} in GCS bucket {2}&#39;</span>
<span class="c1"># &#39; as object {3}&#39;.format(file, self.bucket,</span>
<span class="c1"># dest_gcs_bucket,</span>
<span class="c1"># dest_gcs_object))</span>
<span class="n">gcs_hook</span><span class="o">.</span><span class="n">upload</span><span class="p">(</span><span class="n">dest_gcs_bucket</span><span class="p">,</span> <span class="n">dest_gcs_object</span><span class="p">,</span> <span class="n">f</span><span class="o">.</span><span class="n">name</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="s2">&quot;All done, uploaded </span><span class="si">%d</span><span class="s2"> files to Google Cloud Storage&quot;</span><span class="p">,</span>
<span class="nb">len</span><span class="p">(</span><span class="n">files</span><span class="p">))</span>
<span class="k">else</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">&#39;In sync, no files needed to be uploaded to Google Cloud&#39;</span>
<span class="s1">&#39;Storage&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">files</span></div>
<span class="c1"># Following functionality may be better suited in</span>
<span class="c1"># airflow/contrib/hooks/gcs_hook.py</span>
<span class="k">def</span> <span class="nf">_gcs_object_is_directory</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">object</span><span class="p">):</span>
<span class="n">bucket</span><span class="p">,</span> <span class="n">blob</span> <span class="o">=</span> <span class="n">_parse_gcs_url</span><span class="p">(</span><span class="nb">object</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">blob</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">blob</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>