Google Git
Sign in
apache / beam-site / refs/heads/updates_release_2.15.0 / . / pydoc / 2.15.0 / _modules / apache_beam / io / tfrecordio.html
blob: 869f57dd52cd17b4f16049c2bfe4be20d7a38351 [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.tfrecordio &mdash; Apache Beam documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="Apache Beam documentation" href="../../../index.html"/>
<link rel="up" title="Module code" href="../../index.html"/>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search">
<a href="../../../index.html" class="icon icon-home"> Apache Beam
</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="../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.internal.html">apache_beam.internal 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.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.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.tools.html">apache_beam.tools 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>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.version.html">apache_beam.version module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">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.tfrecordio</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.tfrecordio</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;TFRecord sources and sinks.&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span>
<span class="kn">import</span> <span class="nn">codecs</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">struct</span>
<span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span>
<span class="kn">from</span> <span class="nn">functools</span> <span class="k">import</span> <span class="n">partial</span>
<span class="kn">import</span> <span class="nn">crcmod</span>
<span class="kn">from</span> <span class="nn">apache_beam</span> <span class="k">import</span> <span class="n">coders</span>
<span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="k">import</span> <span class="n">filebasedsink</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filebasedsource</span> <span class="k">import</span> <span class="n">FileBasedSource</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filebasedsource</span> <span class="k">import</span> <span class="n">ReadAllFiles</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.filesystem</span> <span class="k">import</span> <span class="n">CompressionTypes</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.iobase</span> <span class="k">import</span> <span class="n">Read</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.iobase</span> <span class="k">import</span> <span class="n">Write</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">PTransform</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;ReadFromTFRecord&#39;</span><span class="p">,</span> <span class="s1">&#39;WriteToTFRecord&#39;</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">_default_crc32c_fn</span><span class="p">(</span><span class="n">value</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Calculates crc32c of a bytes object using either snappy or crcmod.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">snappy</span> <span class="c1"># pylint: disable=import-error</span>
<span class="c1"># Support multiple versions of python-snappy:</span>
<span class="c1"># https://github.com/andrix/python-snappy/pull/53</span>
<span class="k">if</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">snappy</span><span class="p">,</span> <span class="s1">&#39;_crc32c&#39;</span><span class="p">,</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span> <span class="o">=</span> <span class="n">snappy</span><span class="o">.</span><span class="n">_crc32c</span> <span class="c1"># pylint: disable=protected-access</span>
<span class="k">elif</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">snappy</span><span class="p">,</span> <span class="s1">&#39;_snappy&#39;</span><span class="p">,</span> <span class="kc">None</span><span class="p">):</span>
<span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span> <span class="o">=</span> <span class="n">snappy</span><span class="o">.</span><span class="n">_snappy</span><span class="o">.</span><span class="n">_crc32c</span> <span class="c1"># pylint: disable=protected-access</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">pass</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;Couldn</span><span class="se">\&#39;</span><span class="s1">t find python-snappy so the implementation of &#39;</span>
<span class="s1">&#39;_TFRecordUtil._masked_crc32c is not as fast as it could &#39;</span>
<span class="s1">&#39;be.&#39;</span><span class="p">)</span>
<span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span> <span class="o">=</span> <span class="n">crcmod</span><span class="o">.</span><span class="n">predefined</span><span class="o">.</span><span class="n">mkPredefinedCrcFun</span><span class="p">(</span><span class="s1">&#39;crc-32c&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
<span class="n">_default_crc32c_fn</span><span class="o">.</span><span class="n">fn</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">class</span> <span class="nc">_TFRecordUtil</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Provides basic TFRecord encoding/decoding with consistency checks.</span>
<span class="sd"> For detailed TFRecord format description see:</span>
<span class="sd"> https://www.tensorflow.org/versions/r1.11/api_guides/python/python_io#TFRecords_Format_Details</span>
<span class="sd"> Note that masks and length are represented in LittleEndian order.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_masked_crc32c</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">crc32c_fn</span><span class="o">=</span><span class="n">_default_crc32c_fn</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Compute a masked crc32c checksum for a value.</span>
<span class="sd"> Args:</span>
<span class="sd"> value: A bytes object for which we compute the crc.</span>
<span class="sd"> crc32c_fn: A function that can compute a crc32c.</span>
<span class="sd"> This is a performance hook that also helps with testing. Callers are</span>
<span class="sd"> not expected to make use of it directly.</span>
<span class="sd"> Returns:</span>
<span class="sd"> Masked crc32c checksum.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">crc</span> <span class="o">=</span> <span class="n">crc32c_fn</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
<span class="k">return</span> <span class="p">(((</span><span class="n">crc</span> <span class="o">&gt;&gt;</span> <span class="mi">15</span><span class="p">)</span> <span class="o">|</span> <span class="p">(</span><span class="n">crc</span> <span class="o">&lt;&lt;</span> <span class="mi">17</span><span class="p">))</span> <span class="o">+</span> <span class="mh">0xa282ead8</span><span class="p">)</span> <span class="o">&amp;</span> <span class="mh">0xffffffff</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">encoded_num_bytes</span><span class="p">(</span><span class="n">record</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Return the number of bytes consumed by a record in its encoded form.&quot;&quot;&quot;</span>
<span class="c1"># 16 = 8 (Length) + 4 (crc of length) + 4 (crc of data)</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">record</span><span class="p">)</span> <span class="o">+</span> <span class="mi">16</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">write_record</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">file_handle</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Encode a value as a TFRecord.</span>
<span class="sd"> Args:</span>
<span class="sd"> file_handle: The file to write to.</span>
<span class="sd"> value: A bytes object representing content of the record.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">encoded_length</span> <span class="o">=</span> <span class="n">struct</span><span class="o">.</span><span class="n">pack</span><span class="p">(</span><span class="sa">b</span><span class="s1">&#39;&lt;Q&#39;</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">value</span><span class="p">))</span>
<span class="n">file_handle</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span>
<span class="n">encoded_length</span><span class="p">,</span>
<span class="n">struct</span><span class="o">.</span><span class="n">pack</span><span class="p">(</span><span class="sa">b</span><span class="s1">&#39;&lt;I&#39;</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_masked_crc32c</span><span class="p">(</span><span class="n">encoded_length</span><span class="p">)),</span>
<span class="n">value</span><span class="p">,</span>
<span class="n">struct</span><span class="o">.</span><span class="n">pack</span><span class="p">(</span><span class="sa">b</span><span class="s1">&#39;&lt;I&#39;</span><span class="p">,</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_masked_crc32c</span><span class="p">(</span><span class="n">value</span><span class="p">))</span>
<span class="p">]))</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">read_record</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">file_handle</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Read a record from a TFRecords file.</span>
<span class="sd"> Args:</span>
<span class="sd"> file_handle: The file to read from.</span>
<span class="sd"> Returns:</span>
<span class="sd"> None if EOF is reached; the paylod of the record otherwise.</span>
<span class="sd"> Raises:</span>
<span class="sd"> ValueError: If file appears to not be a valid TFRecords file.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">buf_length_expected</span> <span class="o">=</span> <span class="mi">12</span>
<span class="n">buf</span> <span class="o">=</span> <span class="n">file_handle</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">buf_length_expected</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">buf</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">None</span> <span class="c1"># EOF Reached.</span>
<span class="c1"># Validate all length related payloads.</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> <span class="o">!=</span> <span class="n">buf_length_expected</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Not a valid TFRecord. Fewer than </span><span class="si">%d</span><span class="s1"> bytes: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="n">buf_length_expected</span><span class="p">,</span> <span class="n">codecs</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">buf</span><span class="p">,</span> <span class="s1">&#39;hex&#39;</span><span class="p">)))</span>
<span class="n">length</span><span class="p">,</span> <span class="n">length_mask_expected</span> <span class="o">=</span> <span class="n">struct</span><span class="o">.</span><span class="n">unpack</span><span class="p">(</span><span class="s1">&#39;&lt;QI&#39;</span><span class="p">,</span> <span class="n">buf</span><span class="p">)</span>
<span class="n">length_mask_actual</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_masked_crc32c</span><span class="p">(</span><span class="n">buf</span><span class="p">[:</span><span class="mi">8</span><span class="p">])</span>
<span class="k">if</span> <span class="n">length_mask_actual</span> <span class="o">!=</span> <span class="n">length_mask_expected</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Not a valid TFRecord. Mismatch of length mask: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="n">codecs</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">buf</span><span class="p">,</span> <span class="s1">&#39;hex&#39;</span><span class="p">))</span>
<span class="c1"># Validate all data related payloads.</span>
<span class="n">buf_length_expected</span> <span class="o">=</span> <span class="n">length</span> <span class="o">+</span> <span class="mi">4</span>
<span class="n">buf</span> <span class="o">=</span> <span class="n">file_handle</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">buf_length_expected</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> <span class="o">!=</span> <span class="n">buf_length_expected</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Not a valid TFRecord. Fewer than </span><span class="si">%d</span><span class="s1"> bytes: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="p">(</span><span class="n">buf_length_expected</span><span class="p">,</span> <span class="n">codecs</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">buf</span><span class="p">,</span> <span class="s1">&#39;hex&#39;</span><span class="p">)))</span>
<span class="n">data</span><span class="p">,</span> <span class="n">data_mask_expected</span> <span class="o">=</span> <span class="n">struct</span><span class="o">.</span><span class="n">unpack</span><span class="p">(</span><span class="s1">&#39;&lt;</span><span class="si">%d</span><span class="s1">sI&#39;</span> <span class="o">%</span> <span class="n">length</span><span class="p">,</span> <span class="n">buf</span><span class="p">)</span>
<span class="n">data_mask_actual</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_masked_crc32c</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="k">if</span> <span class="n">data_mask_actual</span> <span class="o">!=</span> <span class="n">data_mask_expected</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Not a valid TFRecord. Mismatch of data mask: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="n">codecs</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">buf</span><span class="p">,</span> <span class="s1">&#39;hex&#39;</span><span class="p">))</span>
<span class="c1"># All validation checks passed.</span>
<span class="k">return</span> <span class="n">data</span>
<span class="k">class</span> <span class="nc">_TFRecordSource</span><span class="p">(</span><span class="n">FileBasedSource</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A File source for reading files of TFRecords.</span>
<span class="sd"> For detailed TFRecords format description see:</span>
<span class="sd"> https://www.tensorflow.org/versions/r1.11/api_guides/python/python_io#TFRecords_Format_Details</span>
<span class="sd"> &quot;&quot;&quot;</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">file_pattern</span><span class="p">,</span>
<span class="n">coder</span><span class="p">,</span>
<span class="n">compression_type</span><span class="p">,</span>
<span class="n">validate</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize a TFRecordSource. See ReadFromTFRecord for details.&quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_TFRecordSource</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">file_pattern</span><span class="o">=</span><span class="n">file_pattern</span><span class="p">,</span>
<span class="n">compression_type</span><span class="o">=</span><span class="n">compression_type</span><span class="p">,</span>
<span class="n">splittable</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">validate</span><span class="o">=</span><span class="n">validate</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_coder</span> <span class="o">=</span> <span class="n">coder</span>
<span class="k">def</span> <span class="nf">read_records</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_name</span><span class="p">,</span> <span class="n">offset_range_tracker</span><span class="p">):</span>
<span class="k">if</span> <span class="n">offset_range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">():</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Start position not 0:</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span>
<span class="n">offset_range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">())</span>
<span class="n">current_offset</span> <span class="o">=</span> <span class="n">offset_range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">()</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">open_file</span><span class="p">(</span><span class="n">file_name</span><span class="p">)</span> <span class="k">as</span> <span class="n">file_handle</span><span class="p">:</span>
<span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">offset_range_tracker</span><span class="o">.</span><span class="n">try_claim</span><span class="p">(</span><span class="n">current_offset</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">&#39;Unable to claim position: </span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="n">current_offset</span><span class="p">)</span>
<span class="n">record</span> <span class="o">=</span> <span class="n">_TFRecordUtil</span><span class="o">.</span><span class="n">read_record</span><span class="p">(</span><span class="n">file_handle</span><span class="p">)</span>
<span class="k">if</span> <span class="n">record</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="c1"># Reached EOF</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">current_offset</span> <span class="o">+=</span> <span class="n">_TFRecordUtil</span><span class="o">.</span><span class="n">encoded_num_bytes</span><span class="p">(</span><span class="n">record</span><span class="p">)</span>
<span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">_coder</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="n">record</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_create_tfrecordio_source</span><span class="p">(</span>
<span class="n">file_pattern</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">compression_type</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># We intentionally disable validation for ReadAll pattern so that reading does</span>
<span class="c1"># not fail for globs (elements) that are empty.</span>
<span class="k">return</span> <span class="n">_TFRecordSource</span><span class="p">(</span><span class="n">file_pattern</span><span class="p">,</span> <span class="n">coder</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">,</span>
<span class="n">validate</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">ReadAllFromTFRecord</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A ``PTransform`` for reading a ``PCollection`` of TFRecord files.&quot;&quot;&quot;</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">coder</span><span class="o">=</span><span class="n">coders</span><span class="o">.</span><span class="n">BytesCoder</span><span class="p">(),</span>
<span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize the ``ReadAllFromTFRecord`` transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> coder: Coder used to decode each record.</span>
<span class="sd"> compression_type: Used to handle compressed input files. Default value</span>
<span class="sd"> is CompressionTypes.AUTO, in which case the file_path&#39;s extension will</span>
<span class="sd"> be used to detect the compression.</span>
<span class="sd"> **kwargs: optional args dictionary. These are passed through to parent</span>
<span class="sd"> constructor.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ReadAllFromTFRecord</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">source_from_file</span> <span class="o">=</span> <span class="n">partial</span><span class="p">(</span>
<span class="n">_create_tfrecordio_source</span><span class="p">,</span> <span class="n">compression_type</span><span class="o">=</span><span class="n">compression_type</span><span class="p">,</span>
<span class="n">coder</span><span class="o">=</span><span class="n">coder</span><span class="p">)</span>
<span class="c1"># Desired and min bundle sizes do not matter since TFRecord files are</span>
<span class="c1"># unsplittable.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_read_all_files</span> <span class="o">=</span> <span class="n">ReadAllFiles</span><span class="p">(</span>
<span class="n">splittable</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">compression_type</span><span class="o">=</span><span class="n">compression_type</span><span class="p">,</span>
<span class="n">desired_bundle_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">min_bundle_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">source_from_file</span><span class="o">=</span><span class="n">source_from_file</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pvalue</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pvalue</span> <span class="o">|</span> <span class="s1">&#39;ReadAllFiles&#39;</span> <span class="o">&gt;&gt;</span> <span class="bp">self</span><span class="o">.</span><span class="n">_read_all_files</span>
<div class="viewcode-block" id="ReadFromTFRecord"><a class="viewcode-back" href="../../../apache_beam.io.tfrecordio.html#apache_beam.io.tfrecordio.ReadFromTFRecord">[docs]</a><span class="k">class</span> <span class="nc">ReadFromTFRecord</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Transform for reading TFRecord sources.&quot;&quot;&quot;</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">file_pattern</span><span class="p">,</span>
<span class="n">coder</span><span class="o">=</span><span class="n">coders</span><span class="o">.</span><span class="n">BytesCoder</span><span class="p">(),</span>
<span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">,</span>
<span class="n">validate</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize a ReadFromTFRecord transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> file_pattern: A file glob pattern to read TFRecords from.</span>
<span class="sd"> coder: Coder used to decode each record.</span>
<span class="sd"> compression_type: Used to handle compressed input files. Default value</span>
<span class="sd"> is CompressionTypes.AUTO, in which case the file_path&#39;s extension will</span>
<span class="sd"> be used to detect the compression.</span>
<span class="sd"> validate: Boolean flag to verify that the files exist during the pipeline</span>
<span class="sd"> creation time.</span>
<span class="sd"> **kwargs: optional args dictionary. These are passed through to parent</span>
<span class="sd"> constructor.</span>
<span class="sd"> Returns:</span>
<span class="sd"> A ReadFromTFRecord transform object.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ReadFromTFRecord</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_source</span> <span class="o">=</span> <span class="n">_TFRecordSource</span><span class="p">(</span><span class="n">file_pattern</span><span class="p">,</span> <span class="n">coder</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">,</span>
<span class="n">validate</span><span class="p">)</span>
<div class="viewcode-block" id="ReadFromTFRecord.expand"><a class="viewcode-back" href="../../../apache_beam.io.tfrecordio.html#apache_beam.io.tfrecordio.ReadFromTFRecord.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pvalue</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">|</span> <span class="n">Read</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_source</span><span class="p">)</span></div></div>
<span class="k">class</span> <span class="nc">_TFRecordSink</span><span class="p">(</span><span class="n">filebasedsink</span><span class="o">.</span><span class="n">FileBasedSink</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Sink for writing TFRecords files.</span>
<span class="sd"> For detailed TFRecord format description see:</span>
<span class="sd"> https://www.tensorflow.org/versions/r1.11/api_guides/python/python_io#TFRecords_Format_Details</span>
<span class="sd"> &quot;&quot;&quot;</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">file_path_prefix</span><span class="p">,</span> <span class="n">coder</span><span class="p">,</span> <span class="n">file_name_suffix</span><span class="p">,</span> <span class="n">num_shards</span><span class="p">,</span>
<span class="n">shard_name_template</span><span class="p">,</span> <span class="n">compression_type</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize a TFRecordSink. See WriteToTFRecord for details.&quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_TFRecordSink</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">file_path_prefix</span><span class="o">=</span><span class="n">file_path_prefix</span><span class="p">,</span>
<span class="n">coder</span><span class="o">=</span><span class="n">coder</span><span class="p">,</span>
<span class="n">file_name_suffix</span><span class="o">=</span><span class="n">file_name_suffix</span><span class="p">,</span>
<span class="n">num_shards</span><span class="o">=</span><span class="n">num_shards</span><span class="p">,</span>
<span class="n">shard_name_template</span><span class="o">=</span><span class="n">shard_name_template</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="n">compression_type</span><span class="o">=</span><span class="n">compression_type</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">write_encoded_record</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">file_handle</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="n">_TFRecordUtil</span><span class="o">.</span><span class="n">write_record</span><span class="p">(</span><span class="n">file_handle</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
<div class="viewcode-block" id="WriteToTFRecord"><a class="viewcode-back" href="../../../apache_beam.io.tfrecordio.html#apache_beam.io.tfrecordio.WriteToTFRecord">[docs]</a><span class="k">class</span> <span class="nc">WriteToTFRecord</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Transform for writing to TFRecord sinks.&quot;&quot;&quot;</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">file_path_prefix</span><span class="p">,</span>
<span class="n">coder</span><span class="o">=</span><span class="n">coders</span><span class="o">.</span><span class="n">BytesCoder</span><span class="p">(),</span>
<span class="n">file_name_suffix</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span>
<span class="n">num_shards</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">shard_name_template</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize WriteToTFRecord transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> file_path_prefix: The file path to write to. The files written will begin</span>
<span class="sd"> with this prefix, followed by a shard identifier (see num_shards), and</span>
<span class="sd"> end in a common extension, if given by file_name_suffix.</span>
<span class="sd"> coder: Coder used to encode each record.</span>
<span class="sd"> file_name_suffix: Suffix for the files written.</span>
<span class="sd"> num_shards: The number of files (shards) used for output. If not set, the</span>
<span class="sd"> default value will be used.</span>
<span class="sd"> shard_name_template: A template string containing placeholders for</span>
<span class="sd"> the shard number and shard count. When constructing a filename for a</span>
<span class="sd"> particular shard number, the upper-case letters &#39;S&#39; and &#39;N&#39; are</span>
<span class="sd"> replaced with the 0-padded shard number and shard count respectively.</span>
<span class="sd"> This argument can be &#39;&#39; in which case it behaves as if num_shards was</span>
<span class="sd"> set to 1 and only one file will be generated. The default pattern used</span>
<span class="sd"> is &#39;-SSSSS-of-NNNNN&#39; if None is passed as the shard_name_template.</span>
<span class="sd"> compression_type: Used to handle compressed output files. Typical value</span>
<span class="sd"> is CompressionTypes.AUTO, in which case the file_path&#39;s extension will</span>
<span class="sd"> be used to detect the compression.</span>
<span class="sd"> **kwargs: Optional args dictionary. These are passed through to parent</span>
<span class="sd"> constructor.</span>
<span class="sd"> Returns:</span>
<span class="sd"> A WriteToTFRecord transform object.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">WriteToTFRecord</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_sink</span> <span class="o">=</span> <span class="n">_TFRecordSink</span><span class="p">(</span><span class="n">file_path_prefix</span><span class="p">,</span> <span class="n">coder</span><span class="p">,</span> <span class="n">file_name_suffix</span><span class="p">,</span>
<span class="n">num_shards</span><span class="p">,</span> <span class="n">shard_name_template</span><span class="p">,</span>
<span class="n">compression_type</span><span class="p">)</span>
<div class="viewcode-block" id="WriteToTFRecord.expand"><a class="viewcode-back" href="../../../apache_beam.io.tfrecordio.html#apache_beam.io.tfrecordio.WriteToTFRecord.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">Write</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_sink</span><span class="p">)</span></div></div>
</pre></div>
</div>
<div class="articleComments">
</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/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.StickyNav.enable();
});
</script>
</body>
</html>