blob: a1864a4bb41b588d1de9f90f8e129f013f122a46 [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>apache_beam.io.aws.s3io &mdash; Apache Beam 2.38.0 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 async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></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" />
</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"> Apache Beam
</a>
<div class="version">
2.38.0
</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="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</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">Apache Beam</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>apache_beam.io.aws.s3io</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 apache_beam.io.aws.s3io</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># 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, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="sd">&quot;&quot;&quot;AWS S3 client</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">import</span> <span class="nn">errno</span>
<span class="kn">import</span> <span class="nn">io</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">time</span>
<span class="kn">import</span> <span class="nn">traceback</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.aws.clients.s3</span> <span class="kn">import</span> <span class="n">messages</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">Downloader</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">DownloaderStream</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">Uploader</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystemio</span> <span class="kn">import</span> <span class="n">UploaderStream</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="kn">import</span> <span class="n">retry</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># pylint: disable=wrong-import-order, wrong-import-position</span>
<span class="c1"># pylint: disable=ungrouped-imports</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.aws.clients.s3</span> <span class="kn">import</span> <span class="n">boto3_client</span>
<span class="n">BOTO3_INSTALLED</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="n">BOTO3_INSTALLED</span> <span class="o">=</span> <span class="kc">False</span>
<span class="n">MAX_BATCH_OPERATION_SIZE</span> <span class="o">=</span> <span class="mi">100</span>
<div class="viewcode-block" id="parse_s3_path"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.parse_s3_path">[docs]</a><span class="k">def</span> <span class="nf">parse_s3_path</span><span class="p">(</span><span class="n">s3_path</span><span class="p">,</span> <span class="n">object_optional</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Return the bucket and object names of the given s3:// path.&quot;&quot;&quot;</span>
<span class="n">match</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="s1">&#39;^s3://([^/]+)/(.*)$&#39;</span><span class="p">,</span> <span class="n">s3_path</span><span class="p">)</span>
<span class="k">if</span> <span class="n">match</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="p">(</span><span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span> <span class="o">==</span> <span class="s1">&#39;&#39;</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">object_optional</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;S3 path must be in the form s3://&lt;bucket&gt;/&lt;object&gt;.&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="n">match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span></div>
<div class="viewcode-block" id="S3IO"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO">[docs]</a><span class="k">class</span> <span class="nc">S3IO</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;S3 I/O client.&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">client</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">options</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">client</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">options</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Must provide one of client or options&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">client</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">client</span>
<span class="k">elif</span> <span class="n">BOTO3_INSTALLED</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span> <span class="o">=</span> <span class="n">boto3_client</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="n">options</span><span class="o">=</span><span class="n">options</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">message</span> <span class="o">=</span> <span class="s1">&#39;AWS dependencies are not installed, and no alternative &#39;</span> \
<span class="s1">&#39;client was provided to S3IO.&#39;</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">message</span><span class="p">)</span>
<div class="viewcode-block" id="S3IO.open"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.open">[docs]</a> <span class="k">def</span> <span class="nf">open</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">filename</span><span class="p">,</span>
<span class="n">mode</span><span class="o">=</span><span class="s1">&#39;r&#39;</span><span class="p">,</span>
<span class="n">read_buffer_size</span><span class="o">=</span><span class="mi">16</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span><span class="p">,</span>
<span class="n">mime_type</span><span class="o">=</span><span class="s1">&#39;application/octet-stream&#39;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Open an S3 file path for reading or writing.</span>
<span class="sd"> Args:</span>
<span class="sd"> filename (str): S3 file path in the form ``s3://&lt;bucket&gt;/&lt;object&gt;``.</span>
<span class="sd"> mode (str): ``&#39;r&#39;`` for reading or ``&#39;w&#39;`` for writing.</span>
<span class="sd"> read_buffer_size (int): Buffer size to use during read operations.</span>
<span class="sd"> mime_type (str): Mime type to set for write operations.</span>
<span class="sd"> Returns:</span>
<span class="sd"> S3 file object.</span>
<span class="sd"> Raises:</span>
<span class="sd"> ValueError: Invalid open file mode.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;r&#39;</span> <span class="ow">or</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;rb&#39;</span><span class="p">:</span>
<span class="n">downloader</span> <span class="o">=</span> <span class="n">S3Downloader</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">buffer_size</span><span class="o">=</span><span class="n">read_buffer_size</span><span class="p">)</span>
<span class="k">return</span> <span class="n">io</span><span class="o">.</span><span class="n">BufferedReader</span><span class="p">(</span>
<span class="n">DownloaderStream</span><span class="p">(</span><span class="n">downloader</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">),</span> <span class="n">buffer_size</span><span class="o">=</span><span class="n">read_buffer_size</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;w&#39;</span> <span class="ow">or</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;wb&#39;</span><span class="p">:</span>
<span class="n">uploader</span> <span class="o">=</span> <span class="n">S3Uploader</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="p">,</span> <span class="n">filename</span><span class="p">,</span> <span class="n">mime_type</span><span class="p">)</span>
<span class="k">return</span> <span class="n">io</span><span class="o">.</span><span class="n">BufferedWriter</span><span class="p">(</span>
<span class="n">UploaderStream</span><span class="p">(</span><span class="n">uploader</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">),</span> <span class="n">buffer_size</span><span class="o">=</span><span class="mi">128</span> <span class="o">*</span> <span class="mi">1024</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Invalid file open mode: </span><span class="si">%s</span><span class="s1">.&#39;</span> <span class="o">%</span> <span class="n">mode</span><span class="p">)</span></div>
<div class="viewcode-block" id="S3IO.list_prefix"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.list_prefix">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">list_prefix</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Lists files matching the prefix.</span>
<span class="sd"> Args:</span>
<span class="sd"> path: S3 file path pattern in the form s3://&lt;bucket&gt;/[name].</span>
<span class="sd"> Returns:</span>
<span class="sd"> Dictionary of file name -&gt; size.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="n">prefix</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="n">object_optional</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">ListRequest</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">file_sizes</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">counter</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">start_time</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Starting the size estimation of the input&quot;</span><span class="p">)</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="c1">#The list operation will raise an exception</span>
<span class="c1">#when trying to list a nonexistent S3 path.</span>
<span class="c1">#This should not be an issue here.</span>
<span class="c1">#Ignore this exception or it will break the procedure.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">list</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="k">break</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">e</span>
<span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">response</span><span class="o">.</span><span class="n">items</span><span class="p">:</span>
<span class="n">file_name</span> <span class="o">=</span> <span class="s1">&#39;s3://</span><span class="si">%s</span><span class="s1">/</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">item</span><span class="o">.</span><span class="n">key</span><span class="p">)</span>
<span class="n">file_sizes</span><span class="p">[</span><span class="n">file_name</span><span class="p">]</span> <span class="o">=</span> <span class="n">item</span><span class="o">.</span><span class="n">size</span>
<span class="n">counter</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">if</span> <span class="n">counter</span> <span class="o">%</span> <span class="mi">10000</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Finished computing size of: </span><span class="si">%s</span><span class="s2"> files&quot;</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">file_sizes</span><span class="p">))</span>
<span class="k">if</span> <span class="n">response</span><span class="o">.</span><span class="n">next_token</span><span class="p">:</span>
<span class="n">request</span><span class="o">.</span><span class="n">continuation_token</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">next_token</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">break</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span>
<span class="s2">&quot;Finished listing </span><span class="si">%s</span><span class="s2"> files in </span><span class="si">%s</span><span class="s2"> seconds.&quot;</span><span class="p">,</span>
<span class="n">counter</span><span class="p">,</span>
<span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start_time</span><span class="p">)</span>
<span class="k">return</span> <span class="n">file_sizes</span></div>
<div class="viewcode-block" id="S3IO.checksum"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.checksum">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">checksum</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Looks up the checksum of an S3 object.</span>
<span class="sd"> Args:</span>
<span class="sd"> path: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">GetRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span><span class="p">)</span>
<span class="n">item</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_object_metadata</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">return</span> <span class="n">item</span><span class="o">.</span><span class="n">etag</span></div>
<div class="viewcode-block" id="S3IO.copy"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.copy">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">copy</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Copies a single S3 file object from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> src: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> dest: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> Raises:</span>
<span class="sd"> TimeoutError: on timeout.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">src_bucket</span><span class="p">,</span> <span class="n">src_key</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">src</span><span class="p">)</span>
<span class="n">dest_bucket</span><span class="p">,</span> <span class="n">dest_key</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">dest</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">CopyRequest</span><span class="p">(</span><span class="n">src_bucket</span><span class="p">,</span> <span class="n">src_key</span><span class="p">,</span> <span class="n">dest_bucket</span><span class="p">,</span> <span class="n">dest_key</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">request</span><span class="p">)</span></div>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.copy_paths"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.copy_paths">[docs]</a> <span class="k">def</span> <span class="nf">copy_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src_dest_pairs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Copies the given S3 objects from src to dest. This can handle directory</span>
<span class="sd"> or file paths.</span>
<span class="sd"> Args:</span>
<span class="sd"> src_dest_pairs: list of (src, dest) tuples of s3://&lt;bucket&gt;/&lt;name&gt; file</span>
<span class="sd"> paths to copy from src to dest</span>
<span class="sd"> Returns: List of tuples of (src, dest, exception) in the same order as the</span>
<span class="sd"> src_dest_pairs argument, where exception is None if the operation</span>
<span class="sd"> succeeded or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">src_dest_pairs</span><span class="p">:</span> <span class="k">return</span> <span class="p">[]</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span> <span class="ow">in</span> <span class="n">src_dest_pairs</span><span class="p">:</span>
<span class="c1"># Copy a directory with self.copy_tree</span>
<span class="k">if</span> <span class="n">src_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span> <span class="ow">and</span> <span class="n">dest_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">results</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy_tree</span><span class="p">(</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">)</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">err</span><span class="p">:</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">err</span><span class="p">))</span>
<span class="c1"># Copy individual files with self.copy</span>
<span class="k">elif</span> <span class="ow">not</span> <span class="n">src_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">dest_path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span>
<span class="n">src_bucket</span><span class="p">,</span> <span class="n">src_key</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">src_path</span><span class="p">)</span>
<span class="n">dest_bucket</span><span class="p">,</span> <span class="n">dest_key</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">dest_path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">CopyRequest</span><span class="p">(</span>
<span class="n">src_bucket</span><span class="p">,</span> <span class="n">src_key</span><span class="p">,</span> <span class="n">dest_bucket</span><span class="p">,</span> <span class="n">dest_key</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">err</span><span class="p">:</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">err</span><span class="p">))</span>
<span class="c1"># Mismatched paths (one directory, one non-directory) get an error result</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">e</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span><span class="p">(</span>
<span class="s2">&quot;Can&#39;t copy mismatched paths (one directory, one non-directory):&quot;</span> <span class="o">+</span>
<span class="s1">&#39; </span><span class="si">%s</span><span class="s1">, </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">),</span>
<span class="mi">400</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src_path</span><span class="p">,</span> <span class="n">dest_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span>
<span class="k">return</span> <span class="n">results</span></div>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.copy_tree"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.copy_tree">[docs]</a> <span class="k">def</span> <span class="nf">copy_tree</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Renames the given S3 directory and it&#39;s contents recursively</span>
<span class="sd"> from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> src: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> dest: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> Returns:</span>
<span class="sd"> List of tuples of (src, dest, exception) where exception is None if the</span>
<span class="sd"> operation succeeded or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="n">src</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">dest</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_prefix</span><span class="p">(</span><span class="n">src</span><span class="p">):</span>
<span class="n">rel_path</span> <span class="o">=</span> <span class="n">entry</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">src</span><span class="p">):]</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">)</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">entry</span><span class="p">,</span> <span class="n">dest</span> <span class="o">+</span> <span class="n">rel_path</span><span class="p">,</span> <span class="n">e</span><span class="p">))</span>
<span class="k">return</span> <span class="n">results</span></div>
<div class="viewcode-block" id="S3IO.delete"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.delete">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">delete</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Deletes a single S3 file object from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> src: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> dest: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> Returns:</span>
<span class="sd"> List of tuples of (src, dest, exception) in the same order as the</span>
<span class="sd"> src_dest_pairs argument, where exception is None if the operation</span>
<span class="sd"> succeeded or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">DeleteRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="k">return</span> <span class="c1"># Same behavior as GCS - don&#39;t surface a 404 error</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">&#39;HTTP error while deleting file </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">e</span></div>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.delete_paths"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.delete_paths">[docs]</a> <span class="k">def</span> <span class="nf">delete_paths</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">paths</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Deletes the given S3 objects from src to dest. This can handle directory</span>
<span class="sd"> or file paths.</span>
<span class="sd"> Args:</span>
<span class="sd"> src: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> dest: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;/.</span>
<span class="sd"> Returns:</span>
<span class="sd"> List of tuples of (src, dest, exception) in the same order as the</span>
<span class="sd"> src_dest_pairs argument, where exception is None if the operation</span>
<span class="sd"> succeeded or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">directories</span><span class="p">,</span> <span class="n">not_directories</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">:</span>
<span class="k">if</span> <span class="n">path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span> <span class="n">directories</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span> <span class="n">not_directories</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">directory</span> <span class="ow">in</span> <span class="n">directories</span><span class="p">:</span>
<span class="n">dir_result</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">delete_tree</span><span class="p">(</span><span class="n">directory</span><span class="p">))</span>
<span class="n">results</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">dir_result</span><span class="p">)</span>
<span class="n">not_directory_results</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">not_directories</span><span class="p">))</span>
<span class="n">results</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">not_directory_results</span><span class="p">)</span>
<span class="k">return</span> <span class="n">results</span></div>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.delete_files"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.delete_files">[docs]</a> <span class="k">def</span> <span class="nf">delete_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">paths</span><span class="p">,</span> <span class="n">max_batch_size</span><span class="o">=</span><span class="mi">1000</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Deletes the given S3 file object from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> paths: List of S3 file paths in the form s3://&lt;bucket&gt;/&lt;name&gt;</span>
<span class="sd"> max_batch_size: Largest number of keys to send to the client to be deleted</span>
<span class="sd"> simultaneously</span>
<span class="sd"> Returns: List of tuples of (path, exception) in the same order as the paths</span>
<span class="sd"> argument, where exception is None if the operation succeeded or</span>
<span class="sd"> the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">paths</span><span class="p">:</span> <span class="k">return</span> <span class="p">[]</span>
<span class="c1"># Sort paths into bucket: [keys]</span>
<span class="n">buckets</span><span class="p">,</span> <span class="n">keys</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="p">[</span><span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">])</span>
<span class="n">grouped_keys</span> <span class="o">=</span> <span class="p">{</span><span class="n">bucket</span><span class="p">:</span> <span class="p">[]</span> <span class="k">for</span> <span class="n">bucket</span> <span class="ow">in</span> <span class="n">buckets</span><span class="p">}</span>
<span class="k">for</span> <span class="n">bucket</span><span class="p">,</span> <span class="n">key</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">buckets</span><span class="p">,</span> <span class="n">keys</span><span class="p">):</span>
<span class="n">grouped_keys</span><span class="p">[</span><span class="n">bucket</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
<span class="c1"># For each bucket, delete minibatches of keys</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">bucket</span><span class="p">,</span> <span class="n">keys</span> <span class="ow">in</span> <span class="n">grouped_keys</span><span class="o">.</span><span class="n">items</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="mi">0</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">keys</span><span class="p">),</span> <span class="n">max_batch_size</span><span class="p">):</span>
<span class="n">minibatch_keys</span> <span class="o">=</span> <span class="n">keys</span><span class="p">[</span><span class="n">i</span><span class="p">:</span><span class="n">i</span> <span class="o">+</span> <span class="n">max_batch_size</span><span class="p">]</span>
<span class="n">results</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">_delete_minibatch</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">minibatch_keys</span><span class="p">))</span>
<span class="c1"># Organize final results</span>
<span class="n">final_results</span> <span class="o">=</span> <span class="p">[(</span><span class="n">path</span><span class="p">,</span> <span class="n">results</span><span class="p">[</span><span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)])</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">paths</span><span class="p">]</span>
<span class="k">return</span> <span class="n">final_results</span></div>
<span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_delete_minibatch</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">keys</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A helper method. Boto3 allows batch deletions</span>
<span class="sd"> for files within the same bucket.</span>
<span class="sd"> Args:</span>
<span class="sd"> bucket: String bucket name</span>
<span class="sd"> keys: List of keys to be deleted in the bucket</span>
<span class="sd"> Returns: dict of the form {(bucket, key): error}, where error is None if the</span>
<span class="sd"> operation succeeded</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">DeleteBatchRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">keys</span><span class="p">)</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">delete_batch</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">response</span><span class="o">.</span><span class="n">deleted</span><span class="p">:</span>
<span class="n">results</span><span class="p">[(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">key</span><span class="p">)]</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">error</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">failed</span><span class="p">,</span> <span class="n">response</span><span class="o">.</span><span class="n">errors</span><span class="p">):</span>
<span class="n">results</span><span class="p">[(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">key</span><span class="p">)]</span> <span class="o">=</span> <span class="n">error</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys</span><span class="p">:</span>
<span class="n">results</span><span class="p">[(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">key</span><span class="p">)]</span> <span class="o">=</span> <span class="n">e</span>
<span class="k">return</span> <span class="n">results</span>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.delete_tree"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.delete_tree">[docs]</a> <span class="k">def</span> <span class="nf">delete_tree</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">root</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Deletes all objects under the given S3 directory.</span>
<span class="sd"> Args:</span>
<span class="sd"> path: S3 root path in the form s3://&lt;bucket&gt;/&lt;name&gt;/ (ending with a &quot;/&quot;)</span>
<span class="sd"> Returns: List of tuples of (path, exception), where each path is an object</span>
<span class="sd"> under the given root. exception is None if the operation succeeded</span>
<span class="sd"> or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="n">root</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="n">paths</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_prefix</span><span class="p">(</span><span class="n">root</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">paths</span><span class="p">)</span></div>
<div class="viewcode-block" id="S3IO.size"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.size">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns the size of a single S3 object.</span>
<span class="sd"> This method does not perform glob expansion. Hence the given path must be</span>
<span class="sd"> for a single S3 object.</span>
<span class="sd"> Returns: size of the S3 object in bytes.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">GetRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="n">object_path</span><span class="p">)</span>
<span class="n">item</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_object_metadata</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">return</span> <span class="n">item</span><span class="o">.</span><span class="n">size</span></div>
<span class="c1"># We intentionally do not decorate this method with a retry, since the</span>
<span class="c1"># underlying copy and delete operations are already idempotent operations</span>
<span class="c1"># protected by retry decorators.</span>
<div class="viewcode-block" id="S3IO.rename"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.rename">[docs]</a> <span class="k">def</span> <span class="nf">rename</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Renames the given S3 object from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> src: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> dest: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">delete</span><span class="p">(</span><span class="n">src</span><span class="p">)</span></div>
<div class="viewcode-block" id="S3IO.last_updated"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.last_updated">[docs]</a> <span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">last_updated</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns the last updated epoch time of a single S3 object.</span>
<span class="sd"> This method does not perform glob expansion. Hence the given path must be</span>
<span class="sd"> for a single S3 object.</span>
<span class="sd"> Returns: last updated time of the S3 object in second.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">GetRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">)</span>
<span class="n">datetime</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_object_metadata</span><span class="p">(</span><span class="n">request</span><span class="p">)</span><span class="o">.</span><span class="n">last_modified</span>
<span class="k">return</span> <span class="p">(</span>
<span class="n">time</span><span class="o">.</span><span class="n">mktime</span><span class="p">(</span><span class="n">datetime</span><span class="o">.</span><span class="n">timetuple</span><span class="p">())</span> <span class="o">-</span> <span class="n">time</span><span class="o">.</span><span class="n">timezone</span> <span class="o">+</span>
<span class="n">datetime</span><span class="o">.</span><span class="n">microsecond</span> <span class="o">/</span> <span class="mf">1000000.0</span><span class="p">)</span></div>
<div class="viewcode-block" id="S3IO.exists"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.exists">[docs]</a> <span class="k">def</span> <span class="nf">exists</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Returns whether the given S3 object exists.</span>
<span class="sd"> Args:</span>
<span class="sd"> path: S3 file path pattern in the form s3://&lt;bucket&gt;/&lt;name&gt;.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">GetRequest</span><span class="p">(</span><span class="n">bucket</span><span class="p">,</span> <span class="nb">object</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">get_object_metadata</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="c1"># HTTP 404 indicates that the file did not exist</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># We re-raise all other exceptions</span>
<span class="k">raise</span></div>
<div class="viewcode-block" id="S3IO.rename_files"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3IO.rename_files">[docs]</a> <span class="k">def</span> <span class="nf">rename_files</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">src_dest_pairs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Renames the given S3 objects from src to dest.</span>
<span class="sd"> Args:</span>
<span class="sd"> src_dest_pairs: list of (src, dest) tuples of s3://&lt;bucket&gt;/&lt;name&gt; file</span>
<span class="sd"> paths to rename from src to dest</span>
<span class="sd"> Returns: List of tuples of (src, dest, exception) in the same order as the</span>
<span class="sd"> src_dest_pairs argument, where exception is None if the operation</span>
<span class="sd"> succeeded or the relevant exception if the operation failed.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">src_dest_pairs</span><span class="p">:</span> <span class="k">return</span> <span class="p">[]</span>
<span class="c1"># TODO: Throw value error if path has directory</span>
<span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span> <span class="ow">in</span> <span class="n">src_dest_pairs</span><span class="p">:</span>
<span class="k">if</span> <span class="n">src</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">)</span> <span class="ow">or</span> <span class="n">dest</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Cannot rename a directory&#39;</span><span class="p">)</span>
<span class="n">copy_results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy_paths</span><span class="p">(</span><span class="n">src_dest_pairs</span><span class="p">)</span>
<span class="n">paths_to_delete</span> <span class="o">=</span> <span class="p">[</span><span class="n">src</span> <span class="k">for</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">err</span><span class="p">)</span> <span class="ow">in</span> <span class="n">copy_results</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">delete_results</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">delete_files</span><span class="p">(</span><span class="n">paths_to_delete</span><span class="p">)</span>
<span class="n">delete_results_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">src</span><span class="p">:</span> <span class="n">err</span> <span class="k">for</span> <span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">err</span><span class="p">)</span> <span class="ow">in</span> <span class="n">delete_results</span><span class="p">}</span>
<span class="n">rename_results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">err</span> <span class="ow">in</span> <span class="n">copy_results</span><span class="p">:</span>
<span class="k">if</span> <span class="n">err</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> <span class="n">rename_results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">err</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">delete_results_dict</span><span class="p">[</span><span class="n">src</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">rename_results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="n">delete_results_dict</span><span class="p">[</span><span class="n">src</span><span class="p">]))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">rename_results</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">src</span><span class="p">,</span> <span class="n">dest</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span>
<span class="k">return</span> <span class="n">rename_results</span></div></div>
<div class="viewcode-block" id="S3Downloader"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3Downloader">[docs]</a><span class="k">class</span> <span class="nc">S3Downloader</span><span class="p">(</span><span class="n">Downloader</span><span class="p">):</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">client</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">buffer_size</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_client</span> <span class="o">=</span> <span class="n">client</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_path</span> <span class="o">=</span> <span class="n">path</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_buffer_size</span> <span class="o">=</span> <span class="n">buffer_size</span>
<span class="c1"># Get object state.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_get_request</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">messages</span><span class="o">.</span><span class="n">GetRequest</span><span class="p">(</span><span class="n">bucket</span><span class="o">=</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="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">))</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_object_metadata</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_request</span><span class="p">)</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="n">errno</span><span class="o">.</span><span class="n">ENOENT</span><span class="p">,</span> <span class="s1">&#39;Not found: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">&#39;HTTP error while requesting file </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span>
<span class="k">raise</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_size</span> <span class="o">=</span> <span class="n">metadata</span><span class="o">.</span><span class="n">size</span>
<span class="nd">@retry</span><span class="o">.</span><span class="n">with_exponential_backoff</span><span class="p">(</span>
<span class="n">retry_filter</span><span class="o">=</span><span class="n">retry</span><span class="o">.</span><span class="n">retry_on_server_errors_and_timeout_filter</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_get_object_metadata</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">get_request</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">get_object_metadata</span><span class="p">(</span><span class="n">get_request</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_size</span>
<div class="viewcode-block" id="S3Downloader.get_range"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3Downloader.get_range">[docs]</a> <span class="k">def</span> <span class="nf">get_range</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start</span><span class="p">,</span> <span class="n">end</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">get_range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_get_request</span><span class="p">,</span> <span class="n">start</span><span class="p">,</span> <span class="n">end</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="S3Uploader"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3Uploader">[docs]</a><span class="k">class</span> <span class="nc">S3Uploader</span><span class="p">(</span><span class="n">Uploader</span><span class="p">):</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">client</span><span class="p">,</span> <span class="n">path</span><span class="p">,</span> <span class="n">mime_type</span><span class="o">=</span><span class="s1">&#39;application/octet-stream&#39;</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_client</span> <span class="o">=</span> <span class="n">client</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_path</span> <span class="o">=</span> <span class="n">path</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">parse_s3_path</span><span class="p">(</span><span class="n">path</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mime_type</span> <span class="o">=</span> <span class="n">mime_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">part_number</span> <span class="o">=</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">&#39;&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_error</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">upload_id</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parts</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_start_upload</span><span class="p">()</span>
<span class="c1"># There is retry logic in the underlying transfer library but we should make</span>
<span class="c1"># it more explicit so we can control the retry parameters.</span>
<span class="nd">@retry</span><span class="o">.</span><span class="n">no_retries</span> <span class="c1"># Using no_retries marks this as an integration point.</span>
<span class="k">def</span> <span class="nf">_start_upload</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># The uploader by default transfers data in chunks of 1024 * 1024 bytes at</span>
<span class="c1"># a time, buffering writes until that size is reached.</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">UploadRequest</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mime_type</span><span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">create_multipart_upload</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">upload_id</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">upload_id</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="c1"># pylint: disable=broad-except</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
<span class="s1">&#39;Error in _start_upload while inserting file </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">,</span>
<span class="n">traceback</span><span class="o">.</span><span class="n">format_exc</span><span class="p">())</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_error</span> <span class="o">=</span> <span class="n">e</span>
<span class="k">raise</span> <span class="n">e</span>
<div class="viewcode-block" id="S3Uploader.put"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3Uploader.put">[docs]</a> <span class="k">def</span> <span class="nf">put</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
<span class="n">MIN_WRITE_SIZE</span> <span class="o">=</span> <span class="mi">5</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span>
<span class="n">MAX_WRITE_SIZE</span> <span class="o">=</span> <span class="mi">5</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span>
<span class="c1"># TODO: Byte strings might not be the most performant way to handle this</span>
<span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">+=</span> <span class="n">data</span><span class="o">.</span><span class="n">tobytes</span><span class="p">()</span>
<span class="k">while</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="n">MIN_WRITE_SIZE</span><span class="p">:</span>
<span class="c1"># Take the first chunk off the buffer and write it to S3</span>
<span class="n">chunk</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">[:</span><span class="n">MAX_WRITE_SIZE</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_write_to_s3</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
<span class="c1"># Remove the written chunk from the buffer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">[</span><span class="n">MAX_WRITE_SIZE</span><span class="p">:]</span></div>
<span class="k">def</span> <span class="nf">_write_to_s3</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">UploadPartRequest</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">upload_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">part_number</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">upload_part</span><span class="p">(</span><span class="n">request</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">parts</span><span class="o">.</span><span class="n">append</span><span class="p">({</span>
<span class="s1">&#39;ETag&#39;</span><span class="p">:</span> <span class="n">response</span><span class="o">.</span><span class="n">etag</span><span class="p">,</span> <span class="s1">&#39;PartNumber&#39;</span><span class="p">:</span> <span class="n">response</span><span class="o">.</span><span class="n">part_number</span>
<span class="p">})</span>
<span class="bp">self</span><span class="o">.</span><span class="n">part_number</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">part_number</span> <span class="o">+</span> <span class="mi">1</span>
<span class="k">except</span> <span class="n">messages</span><span class="o">.</span><span class="n">S3ClientError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">last_error</span> <span class="o">=</span> <span class="n">e</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">IOError</span><span class="p">(</span><span class="n">errno</span><span class="o">.</span><span class="n">ENOENT</span><span class="p">,</span> <span class="s1">&#39;Not found: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">&#39;HTTP error while requesting file </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_path</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span>
<span class="k">raise</span>
<div class="viewcode-block" id="S3Uploader.finish"><a class="viewcode-back" href="../../../../apache_beam.io.aws.s3io.html#apache_beam.io.aws.s3io.S3Uploader.finish">[docs]</a> <span class="k">def</span> <span class="nf">finish</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="c1"># writes with zero length or mid size files between</span>
<span class="c1"># MIN_WRITE_SIZE = 5 * 1024 * 1024</span>
<span class="c1"># MAX_WRITE_SIZE = 5 * 1024 * 1024 * 1024</span>
<span class="c1"># as we will reach this finish() with len(self.buffer) == 0</span>
<span class="c1"># which will fail</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_write_to_s3</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_error</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="bp">self</span><span class="o">.</span><span class="n">last_error</span> <span class="c1"># pylint: disable=raising-bad-type</span>
<span class="n">request</span> <span class="o">=</span> <span class="n">messages</span><span class="o">.</span><span class="n">CompleteMultipartUploadRequest</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bucket</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_name</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">upload_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">parts</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_client</span><span class="o">.</span><span class="n">complete_multipart_upload</span><span class="p">(</span><span class="n">request</span><span class="p">)</span></div></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</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>