| |
| |
| <!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.avroio — 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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.io.avroio</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.avroio</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 "License"); 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 "AS IS" 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">"""``PTransforms`` for reading from and writing to Avro files.</span> |
| |
| <span class="sd">Provides two read ``PTransform``s, ``ReadFromAvro`` and ``ReadAllFromAvro``,</span> |
| <span class="sd">that produces a ``PCollection`` of records.</span> |
| <span class="sd">Each record of this ``PCollection`` will contain a single record read from</span> |
| <span class="sd">an Avro file. Records that are of simple types will be mapped into</span> |
| <span class="sd">corresponding Python types. Records that are of Avro type 'RECORD' will be</span> |
| <span class="sd">mapped to Python dictionaries that comply with the schema contained in the</span> |
| <span class="sd">Avro file that contains those records. In this case, keys of each dictionary</span> |
| <span class="sd">will contain the corresponding field names and will be of type ``string``</span> |
| <span class="sd">while the values of the dictionary will be of the type defined in the</span> |
| <span class="sd">corresponding Avro schema.</span> |
| |
| <span class="sd">For example, if schema of the Avro file is the following.</span> |
| <span class="sd">{"namespace": "example.avro","type": "record","name": "User","fields":</span> |
| <span class="sd">[{"name": "name", "type": "string"},</span> |
| <span class="sd">{"name": "favorite_number", "type": ["int", "null"]},</span> |
| <span class="sd">{"name": "favorite_color", "type": ["string", "null"]}]}</span> |
| |
| <span class="sd">Then records generated by read transforms will be dictionaries of the</span> |
| <span class="sd">following form.</span> |
| <span class="sd">{u'name': u'Alyssa', u'favorite_number': 256, u'favorite_color': None}).</span> |
| |
| <span class="sd">Additionally, this module provides a write ``PTransform`` ``WriteToAvro``</span> |
| <span class="sd">that can be used to write a given ``PCollection`` of Python objects to an</span> |
| <span class="sd">Avro file.</span> |
| <span class="sd">"""</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">io</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">zlib</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">avro</span> |
| <span class="kn">from</span> <span class="nn">avro</span> <span class="k">import</span> <span class="n">io</span> <span class="k">as</span> <span class="n">avroio</span> |
| <span class="kn">from</span> <span class="nn">avro</span> <span class="k">import</span> <span class="n">datafile</span> |
| <span class="kn">from</span> <span class="nn">avro</span> <span class="k">import</span> <span class="n">schema</span> |
| <span class="kn">from</span> <span class="nn">fastavro.read</span> <span class="k">import</span> <span class="n">block_reader</span> |
| <span class="kn">from</span> <span class="nn">fastavro.write</span> <span class="k">import</span> <span class="n">Writer</span> |
| |
| <span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</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</span> <span class="k">import</span> <span class="n">filebasedsource</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="k">import</span> <span class="n">iobase</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.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">'ReadFromAvro'</span><span class="p">,</span> <span class="s1">'ReadAllFromAvro'</span><span class="p">,</span> <span class="s1">'WriteToAvro'</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="ReadFromAvro"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.ReadFromAvro">[docs]</a><span class="k">class</span> <span class="nc">ReadFromAvro</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A :class:`~apache_beam.transforms.ptransform.PTransform` for reading avro</span> |
| <span class="sd"> files."""</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="o">=</span><span class="kc">None</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">validate</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="n">use_fastavro</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""Initializes :class:`ReadFromAvro`.</span> |
| |
| <span class="sd"> Uses source :class:`~apache_beam.io._AvroSource` to read a set of Avro</span> |
| <span class="sd"> files defined by a given file pattern.</span> |
| |
| <span class="sd"> If ``/mypath/myavrofiles*`` is a file-pattern that points to a set of Avro</span> |
| <span class="sd"> files, a :class:`~apache_beam.pvalue.PCollection` for the records in</span> |
| <span class="sd"> these Avro files can be created in the following manner.</span> |
| |
| <span class="sd"> .. testcode::</span> |
| |
| <span class="sd"> with beam.Pipeline() as p:</span> |
| <span class="sd"> records = p | 'Read' >> beam.io.ReadFromAvro('/mypath/myavrofiles*')</span> |
| |
| <span class="sd"> .. NOTE: We're not actually interested in this error; but if we get here,</span> |
| <span class="sd"> it means that the way of calling this transform hasn't changed.</span> |
| |
| <span class="sd"> .. testoutput::</span> |
| <span class="sd"> :hide:</span> |
| |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> IOError: No files found based on the file pattern</span> |
| |
| <span class="sd"> Each record of this :class:`~apache_beam.pvalue.PCollection` will contain</span> |
| <span class="sd"> a single record read from a source. Records that are of simple types will be</span> |
| <span class="sd"> mapped into corresponding Python types. Records that are of Avro type</span> |
| <span class="sd"> ``RECORD`` will be mapped to Python dictionaries that comply with the schema</span> |
| <span class="sd"> contained in the Avro file that contains those records. In this case, keys</span> |
| <span class="sd"> of each dictionary will contain the corresponding field names and will be of</span> |
| <span class="sd"> type :class:`str` while the values of the dictionary will be of the type</span> |
| <span class="sd"> defined in the corresponding Avro schema.</span> |
| |
| <span class="sd"> For example, if schema of the Avro file is the following. ::</span> |
| |
| <span class="sd"> {</span> |
| <span class="sd"> "namespace": "example.avro",</span> |
| <span class="sd"> "type": "record",</span> |
| <span class="sd"> "name": "User",</span> |
| <span class="sd"> "fields": [</span> |
| |
| <span class="sd"> {"name": "name",</span> |
| <span class="sd"> "type": "string"},</span> |
| |
| <span class="sd"> {"name": "favorite_number",</span> |
| <span class="sd"> "type": ["int", "null"]},</span> |
| |
| <span class="sd"> {"name": "favorite_color",</span> |
| <span class="sd"> "type": ["string", "null"]}</span> |
| |
| <span class="sd"> ]</span> |
| <span class="sd"> }</span> |
| |
| <span class="sd"> Then records generated by :class:`~apache_beam.io._AvroSource` will be</span> |
| <span class="sd"> dictionaries of the following form. ::</span> |
| |
| <span class="sd"> {u'name': u'Alyssa', u'favorite_number': 256, u'favorite_color': None}).</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> file_pattern (str): the file glob to read</span> |
| <span class="sd"> min_bundle_size (int): the minimum size in bytes, to be considered when</span> |
| <span class="sd"> splitting the input into bundles.</span> |
| <span class="sd"> validate (bool): flag to verify that the files exist during the pipeline</span> |
| <span class="sd"> creation time.</span> |
| <span class="sd"> use_fastavro (bool); when set, use the `fastavro` library for IO, which</span> |
| <span class="sd"> is significantly faster, and will likely become the default</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ReadFromAvro</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="bp">self</span><span class="o">.</span><span class="n">_source</span> <span class="o">=</span> <span class="n">_create_avro_source</span><span class="p">(</span> |
| <span class="n">file_pattern</span><span class="p">,</span> |
| <span class="n">min_bundle_size</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="n">use_fastavro</span><span class="o">=</span><span class="n">use_fastavro</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="ReadFromAvro.expand"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.ReadFromAvro.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 class="viewcode-block" id="ReadFromAvro.display_data"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.ReadFromAvro.display_data">[docs]</a> <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{</span><span class="s1">'source_dd'</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> |
| |
| |
| <div class="viewcode-block" id="ReadAllFromAvro"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.ReadAllFromAvro">[docs]</a><span class="k">class</span> <span class="nc">ReadAllFromAvro</span><span class="p">(</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A ``PTransform`` for reading ``PCollection`` of Avro files.</span> |
| |
| <span class="sd"> Uses source '_AvroSource' to read a ``PCollection`` of Avro files or</span> |
| <span class="sd"> file patterns and produce a ``PCollection`` of Avro records.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">DEFAULT_DESIRED_BUNDLE_SIZE</span> <span class="o">=</span> <span class="mi">64</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span> <span class="c1"># 64MB</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">min_bundle_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="n">desired_bundle_size</span><span class="o">=</span><span class="n">DEFAULT_DESIRED_BUNDLE_SIZE</span><span class="p">,</span> |
| <span class="n">use_fastavro</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'ReadAllFiles'</span><span class="p">):</span> |
| <span class="sd">"""Initializes ``ReadAllFromAvro``.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> min_bundle_size: the minimum size in bytes, to be considered when</span> |
| <span class="sd"> splitting the input into bundles.</span> |
| <span class="sd"> desired_bundle_size: the desired size in bytes, to be considered when</span> |
| <span class="sd"> splitting the input into bundles.</span> |
| <span class="sd"> """</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_avro_source</span><span class="p">,</span> |
| <span class="n">min_bundle_size</span><span class="o">=</span><span class="n">min_bundle_size</span><span class="p">,</span> |
| <span class="n">use_fastavro</span><span class="o">=</span><span class="n">use_fastavro</span> |
| <span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_read_all_files</span> <span class="o">=</span> <span class="n">filebasedsource</span><span class="o">.</span><span class="n">ReadAllFiles</span><span class="p">(</span> |
| <span class="kc">True</span><span class="p">,</span> <span class="n">CompressionTypes</span><span class="o">.</span><span class="n">AUTO</span><span class="p">,</span> <span class="n">desired_bundle_size</span><span class="p">,</span> <span class="n">min_bundle_size</span><span class="p">,</span> |
| <span class="n">source_from_file</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">=</span> <span class="n">label</span> |
| |
| <div class="viewcode-block" id="ReadAllFromAvro.expand"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.ReadAllFromAvro.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="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">>></span> <span class="bp">self</span><span class="o">.</span><span class="n">_read_all_files</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_AvroUtils</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">read_meta_data_from_file</span><span class="p">(</span><span class="n">f</span><span class="p">):</span> |
| <span class="sd">"""Reads metadata from a given Avro file.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> f: Avro file to read.</span> |
| <span class="sd"> Returns:</span> |
| <span class="sd"> a tuple containing the codec, schema, and the sync marker of the Avro</span> |
| <span class="sd"> file.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ValueError: if the file does not start with the byte sequence defined in</span> |
| <span class="sd"> the specification.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| <span class="n">decoder</span> <span class="o">=</span> <span class="n">avroio</span><span class="o">.</span><span class="n">BinaryDecoder</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| <span class="n">header</span> <span class="o">=</span> <span class="n">avroio</span><span class="o">.</span><span class="n">DatumReader</span><span class="p">()</span><span class="o">.</span><span class="n">read_data</span><span class="p">(</span><span class="n">datafile</span><span class="o">.</span><span class="n">META_SCHEMA</span><span class="p">,</span> |
| <span class="n">datafile</span><span class="o">.</span><span class="n">META_SCHEMA</span><span class="p">,</span> <span class="n">decoder</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">header</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'magic'</span><span class="p">)</span> <span class="o">!=</span> <span class="n">datafile</span><span class="o">.</span><span class="n">MAGIC</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Not an Avro file. File header should start with </span><span class="si">%s</span><span class="s1"> but'</span> |
| <span class="s1">'started with </span><span class="si">%s</span><span class="s1"> instead.'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">datafile</span><span class="o">.</span><span class="n">MAGIC</span><span class="p">,</span> <span class="n">header</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'magic'</span><span class="p">)))</span> |
| |
| <span class="n">meta</span> <span class="o">=</span> <span class="n">header</span><span class="p">[</span><span class="s1">'meta'</span><span class="p">]</span> |
| |
| <span class="k">if</span> <span class="n">datafile</span><span class="o">.</span><span class="n">CODEC_KEY</span> <span class="ow">in</span> <span class="n">meta</span><span class="p">:</span> |
| <span class="n">codec</span> <span class="o">=</span> <span class="n">meta</span><span class="p">[</span><span class="n">datafile</span><span class="o">.</span><span class="n">CODEC_KEY</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">codec</span> <span class="o">=</span> <span class="s1">'null'</span> |
| |
| <span class="n">schema_string</span> <span class="o">=</span> <span class="n">meta</span><span class="p">[</span><span class="n">datafile</span><span class="o">.</span><span class="n">SCHEMA_KEY</span><span class="p">]</span> |
| <span class="n">sync_marker</span> <span class="o">=</span> <span class="n">header</span><span class="p">[</span><span class="s1">'sync'</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="n">codec</span><span class="p">,</span> <span class="n">schema_string</span><span class="p">,</span> <span class="n">sync_marker</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">read_block_from_file</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">codec</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">expected_sync_marker</span><span class="p">):</span> |
| <span class="sd">"""Reads a block from a given Avro file.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> f: Avro file to read.</span> |
| <span class="sd"> codec: The codec to use for block-level decompression.</span> |
| <span class="sd"> Supported codecs: 'null', 'deflate', 'snappy'</span> |
| <span class="sd"> schema: Avro Schema definition represented as JSON string.</span> |
| <span class="sd"> expected_sync_marker: Avro synchronization marker. If the block's sync</span> |
| <span class="sd"> marker does not match with this parameter then ValueError is thrown.</span> |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A single _AvroBlock.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> ValueError: If the block cannot be read properly because the file doesn't</span> |
| <span class="sd"> match the specification.</span> |
| <span class="sd"> """</span> |
| <span class="n">offset</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> |
| <span class="n">decoder</span> <span class="o">=</span> <span class="n">avroio</span><span class="o">.</span><span class="n">BinaryDecoder</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| <span class="n">num_records</span> <span class="o">=</span> <span class="n">decoder</span><span class="o">.</span><span class="n">read_long</span><span class="p">()</span> |
| <span class="n">block_size</span> <span class="o">=</span> <span class="n">decoder</span><span class="o">.</span><span class="n">read_long</span><span class="p">()</span> |
| <span class="n">block_bytes</span> <span class="o">=</span> <span class="n">decoder</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">block_size</span><span class="p">)</span> |
| <span class="n">sync_marker</span> <span class="o">=</span> <span class="n">decoder</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">expected_sync_marker</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">sync_marker</span> <span class="o">!=</span> <span class="n">expected_sync_marker</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unexpected sync marker (actual "</span><span class="si">%s</span><span class="s1">" vs expected "</span><span class="si">%s</span><span class="s1">"). '</span> |
| <span class="s1">'Maybe the underlying avro file is corrupted?'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">sync_marker</span><span class="p">,</span> <span class="n">expected_sync_marker</span><span class="p">))</span> |
| <span class="n">size</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> <span class="o">-</span> <span class="n">offset</span> |
| <span class="k">return</span> <span class="n">_AvroBlock</span><span class="p">(</span><span class="n">block_bytes</span><span class="p">,</span> <span class="n">num_records</span><span class="p">,</span> <span class="n">codec</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">offset</span><span class="p">,</span> <span class="n">size</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">advance_file_past_next_sync_marker</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">sync_marker</span><span class="p">):</span> |
| <span class="n">buf_size</span> <span class="o">=</span> <span class="mi">10000</span> |
| |
| <span class="n">data</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">buf_size</span><span class="p">)</span> |
| <span class="k">while</span> <span class="n">data</span><span class="p">:</span> |
| <span class="n">pos</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">pos</span> <span class="o">>=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="c1"># Adjusting the current position to the ending position of the sync</span> |
| <span class="c1"># marker.</span> |
| <span class="n">backtrack</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> <span class="o">-</span> <span class="n">pos</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">)</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span> <span class="o">*</span> <span class="n">backtrack</span><span class="p">,</span> <span class="n">os</span><span class="o">.</span><span class="n">SEEK_CUR</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> <span class="o">>=</span> <span class="nb">len</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">):</span> |
| <span class="c1"># Backtracking in case we partially read the sync marker during the</span> |
| <span class="c1"># previous read. We only have to backtrack if there are at least</span> |
| <span class="c1"># len(sync_marker) bytes before current position. We only have to</span> |
| <span class="c1"># backtrack (len(sync_marker) - 1) bytes.</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span> <span class="o">*</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">),</span> <span class="n">os</span><span class="o">.</span><span class="n">SEEK_CUR</span><span class="p">)</span> |
| <span class="n">data</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">buf_size</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_create_avro_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">min_bundle_size</span><span class="o">=</span><span class="kc">None</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="n">use_fastavro</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="k">return</span> \ |
| <span class="n">_FastAvroSource</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">min_bundle_size</span><span class="o">=</span><span class="n">min_bundle_size</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="k">if</span> <span class="n">use_fastavro</span> \ |
| <span class="k">else</span> \ |
| <span class="n">_AvroSource</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">min_bundle_size</span><span class="o">=</span><span class="n">min_bundle_size</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="k">class</span> <span class="nc">_AvroBlock</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Represents a block of an Avro file."""</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">block_bytes</span><span class="p">,</span> <span class="n">num_records</span><span class="p">,</span> <span class="n">codec</span><span class="p">,</span> <span class="n">schema_string</span><span class="p">,</span> |
| <span class="n">offset</span><span class="p">,</span> <span class="n">size</span><span class="p">):</span> |
| <span class="c1"># Decompress data early on (if needed) and thus decrease the number of</span> |
| <span class="c1"># parallel copies of the data in memory at any given time during block</span> |
| <span class="c1"># iteration.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_decompressed_block_bytes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_decompress_bytes</span><span class="p">(</span><span class="n">block_bytes</span><span class="p">,</span> <span class="n">codec</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_num_records</span> <span class="o">=</span> <span class="n">num_records</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_schema</span> <span class="o">=</span> <span class="n">schema</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">schema_string</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_offset</span> <span class="o">=</span> <span class="n">offset</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_size</span> <span class="o">=</span> <span class="n">size</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> |
| |
| <span class="k">def</span> <span class="nf">offset</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">_offset</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_decompress_bytes</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">codec</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">codec</span> <span class="o">==</span> <span class="s1">'null'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">data</span> |
| <span class="k">elif</span> <span class="n">codec</span> <span class="o">==</span> <span class="s1">'deflate'</span><span class="p">:</span> |
| <span class="c1"># zlib.MAX_WBITS is the window size. '-' sign indicates that this is</span> |
| <span class="c1"># raw data (without headers). See zlib and Avro documentations for more</span> |
| <span class="c1"># details.</span> |
| <span class="k">return</span> <span class="n">zlib</span><span class="o">.</span><span class="n">decompress</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="o">-</span><span class="n">zlib</span><span class="o">.</span><span class="n">MAX_WBITS</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">codec</span> <span class="o">==</span> <span class="s1">'snappy'</span><span class="p">:</span> |
| <span class="c1"># Snappy is an optional avro codec.</span> |
| <span class="c1"># See Snappy and Avro documentation for more details.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">snappy</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Snappy does not seem to be installed.'</span><span class="p">)</span> |
| |
| <span class="c1"># Compressed data includes a 4-byte CRC32 checksum which we verify.</span> |
| <span class="c1"># We take care to avoid extra copies of data while slicing large objects</span> |
| <span class="c1"># by use of a memoryview.</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">snappy</span><span class="o">.</span><span class="n">decompress</span><span class="p">(</span><span class="nb">memoryview</span><span class="p">(</span><span class="n">data</span><span class="p">)[:</span><span class="o">-</span><span class="mi">4</span><span class="p">])</span> |
| <span class="n">avroio</span><span class="o">.</span><span class="n">BinaryDecoder</span><span class="p">(</span><span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="o">-</span><span class="mi">4</span><span class="p">:]))</span><span class="o">.</span><span class="n">check_crc32</span><span class="p">(</span><span class="n">result</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</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">'Unknown codec: </span><span class="si">%r</span><span class="s1">'</span> <span class="o">%</span> <span class="n">codec</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">num_records</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">_num_records</span> |
| |
| <span class="k">def</span> <span class="nf">records</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">decoder</span> <span class="o">=</span> <span class="n">avroio</span><span class="o">.</span><span class="n">BinaryDecoder</span><span class="p">(</span> |
| <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_decompressed_block_bytes</span><span class="p">))</span> |
| <span class="n">reader</span> <span class="o">=</span> <span class="n">avroio</span><span class="o">.</span><span class="n">DatumReader</span><span class="p">(</span> |
| <span class="n">writers_schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_schema</span><span class="p">,</span> <span class="n">readers_schema</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_schema</span><span class="p">)</span> |
| |
| <span class="n">current_record</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">while</span> <span class="n">current_record</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_records</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">reader</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="n">decoder</span><span class="p">)</span> |
| <span class="n">current_record</span> <span class="o">+=</span> <span class="mi">1</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_AvroSource</span><span class="p">(</span><span class="n">filebasedsource</span><span class="o">.</span><span class="n">FileBasedSource</span><span class="p">):</span> |
| <span class="sd">"""A source for reading Avro files.</span> |
| |
| <span class="sd"> ``_AvroSource`` is implemented using the file-based source framework available</span> |
| <span class="sd"> in module 'filebasedsource'. Hence please refer to module 'filebasedsource'</span> |
| <span class="sd"> to fully understand how this source implements operations common to all</span> |
| <span class="sd"> file-based sources such as file-pattern expansion and splitting into bundles</span> |
| <span class="sd"> for parallel processing.</span> |
| <span class="sd"> """</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">range_tracker</span><span class="p">):</span> |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| |
| <span class="k">def</span> <span class="nf">split_points_unclaimed</span><span class="p">(</span><span class="n">stop_position</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">next_block_start</span> <span class="o">>=</span> <span class="n">stop_position</span><span class="p">:</span> |
| <span class="c1"># Next block starts at or after the suggested stop position. Hence</span> |
| <span class="c1"># there will not be split points to be claimed for the range ending at</span> |
| <span class="c1"># suggested stop position.</span> |
| <span class="k">return</span> <span class="mi">0</span> |
| |
| <span class="k">return</span> <span class="n">iobase</span><span class="o">.</span><span class="n">RangeTracker</span><span class="o">.</span><span class="n">SPLIT_POINTS_UNKNOWN</span> |
| |
| <span class="n">range_tracker</span><span class="o">.</span><span class="n">set_split_points_unclaimed_callback</span><span class="p">(</span><span class="n">split_points_unclaimed</span><span class="p">)</span> |
| |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">start_offset</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="mi">0</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">f</span><span class="p">:</span> |
| <span class="n">codec</span><span class="p">,</span> <span class="n">schema_string</span><span class="p">,</span> <span class="n">sync_marker</span> <span class="o">=</span> \ |
| <span class="n">_AvroUtils</span><span class="o">.</span><span class="n">read_meta_data_from_file</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| |
| <span class="c1"># We have to start at current position if previous bundle ended at the</span> |
| <span class="c1"># end of a sync marker.</span> |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">start_offset</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">))</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="n">start_offset</span><span class="p">)</span> |
| <span class="n">_AvroUtils</span><span class="o">.</span><span class="n">advance_file_past_next_sync_marker</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">sync_marker</span><span class="p">)</span> |
| |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> |
| |
| <span class="k">while</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">try_claim</span><span class="p">(</span><span class="n">next_block_start</span><span class="p">):</span> |
| <span class="n">block</span> <span class="o">=</span> <span class="n">_AvroUtils</span><span class="o">.</span><span class="n">read_block_from_file</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">codec</span><span class="p">,</span> <span class="n">schema_string</span><span class="p">,</span> |
| <span class="n">sync_marker</span><span class="p">)</span> |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="n">block</span><span class="o">.</span><span class="n">offset</span><span class="p">()</span> <span class="o">+</span> <span class="n">block</span><span class="o">.</span><span class="n">size</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="n">block</span><span class="o">.</span><span class="n">records</span><span class="p">():</span> |
| <span class="k">yield</span> <span class="n">record</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_FastAvroSource</span><span class="p">(</span><span class="n">filebasedsource</span><span class="o">.</span><span class="n">FileBasedSource</span><span class="p">):</span> |
| <span class="sd">"""A source for reading Avro files using the `fastavro` library.</span> |
| |
| <span class="sd"> ``_FastAvroSource`` is implemented using the file-based source framework</span> |
| <span class="sd"> available in module 'filebasedsource'. Hence please refer to module</span> |
| <span class="sd"> 'filebasedsource' to fully understand how this source implements operations</span> |
| <span class="sd"> common to all file-based sources such as file-pattern expansion and splitting</span> |
| <span class="sd"> into bundles for parallel processing.</span> |
| |
| <span class="sd"> TODO: remove ``_AvroSource`` in favor of using ``_FastAvroSource``</span> |
| <span class="sd"> everywhere once it has been more widely tested</span> |
| <span class="sd"> """</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">range_tracker</span><span class="p">):</span> |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> |
| |
| <span class="k">def</span> <span class="nf">split_points_unclaimed</span><span class="p">(</span><span class="n">stop_position</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">next_block_start</span> <span class="o">>=</span> <span class="n">stop_position</span><span class="p">:</span> |
| <span class="c1"># Next block starts at or after the suggested stop position. Hence</span> |
| <span class="c1"># there will not be split points to be claimed for the range ending at</span> |
| <span class="c1"># suggested stop position.</span> |
| <span class="k">return</span> <span class="mi">0</span> |
| |
| <span class="k">return</span> <span class="n">iobase</span><span class="o">.</span><span class="n">RangeTracker</span><span class="o">.</span><span class="n">SPLIT_POINTS_UNKNOWN</span> |
| |
| <span class="n">range_tracker</span><span class="o">.</span><span class="n">set_split_points_unclaimed_callback</span><span class="p">(</span><span class="n">split_points_unclaimed</span><span class="p">)</span> |
| |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">start_position</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">start_offset</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="mi">0</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">f</span><span class="p">:</span> |
| <span class="n">blocks</span> <span class="o">=</span> <span class="n">block_reader</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> |
| <span class="n">sync_marker</span> <span class="o">=</span> <span class="n">blocks</span><span class="o">.</span><span class="n">_header</span><span class="p">[</span><span class="s1">'sync'</span><span class="p">]</span> |
| |
| <span class="c1"># We have to start at current position if previous bundle ended at the</span> |
| <span class="c1"># end of a sync marker.</span> |
| <span class="n">start_offset</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">start_offset</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="n">sync_marker</span><span class="p">))</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="n">start_offset</span><span class="p">)</span> |
| <span class="n">_AvroUtils</span><span class="o">.</span><span class="n">advance_file_past_next_sync_marker</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">sync_marker</span><span class="p">)</span> |
| |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">tell</span><span class="p">()</span> |
| |
| <span class="k">while</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">try_claim</span><span class="p">(</span><span class="n">next_block_start</span><span class="p">):</span> |
| <span class="n">block</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">blocks</span><span class="p">)</span> |
| <span class="n">next_block_start</span> <span class="o">=</span> <span class="n">block</span><span class="o">.</span><span class="n">offset</span> <span class="o">+</span> <span class="n">block</span><span class="o">.</span><span class="n">size</span> |
| <span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="n">block</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">record</span> |
| |
| |
| <div class="viewcode-block" id="WriteToAvro"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.WriteToAvro">[docs]</a><span class="k">class</span> <span class="nc">WriteToAvro</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A ``PTransform`` for writing avro files."""</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">schema</span><span class="p">,</span> |
| <span class="n">codec</span><span class="o">=</span><span class="s1">'deflate'</span><span class="p">,</span> |
| <span class="n">file_name_suffix</span><span class="o">=</span><span class="s1">''</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">mime_type</span><span class="o">=</span><span class="s1">'application/x-avro'</span><span class="p">,</span> |
| <span class="n">use_fastavro</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""Initialize a WriteToAvro 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. In most cases,</span> |
| <span class="sd"> only this argument is specified and num_shards, shard_name_template, and</span> |
| <span class="sd"> file_name_suffix use default values.</span> |
| <span class="sd"> schema: The schema to use, as returned by avro.schema.parse</span> |
| <span class="sd"> codec: The codec to use for block-level compression. Any string supported</span> |
| <span class="sd"> by the Avro specification is accepted (for example 'null').</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"> service will decide on the optimal number of shards.</span> |
| <span class="sd"> Constraining the number of shards is likely to reduce</span> |
| <span class="sd"> the performance of a pipeline. Setting this value is not recommended</span> |
| <span class="sd"> unless you require a specific number of output files.</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 'S' and 'N' are</span> |
| <span class="sd"> replaced with the 0-padded shard number and shard count respectively.</span> |
| <span class="sd"> This argument can be '' 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 '-SSSSS-of-NNNNN' if None is passed as the shard_name_template.</span> |
| <span class="sd"> mime_type: The MIME type to use for the produced files, if the filesystem</span> |
| <span class="sd"> supports specifying MIME types.</span> |
| <span class="sd"> use_fastavro: when set, use the `fastavro` library for IO</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A WriteToAvro transform usable for writing.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sink</span> <span class="o">=</span> \ |
| <span class="n">_create_avro_sink</span><span class="p">(</span> |
| <span class="n">file_path_prefix</span><span class="p">,</span> |
| <span class="n">schema</span><span class="p">,</span> |
| <span class="n">codec</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">mime_type</span><span class="p">,</span> |
| <span class="n">use_fastavro</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="WriteToAvro.expand"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.WriteToAvro.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">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">iobase</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 class="viewcode-block" id="WriteToAvro.display_data"><a class="viewcode-back" href="../../../apache_beam.io.avroio.html#apache_beam.io.avroio.WriteToAvro.display_data">[docs]</a> <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{</span><span class="s1">'sink_dd'</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> |
| |
| |
| <span class="k">def</span> <span class="nf">_create_avro_sink</span><span class="p">(</span><span class="n">file_path_prefix</span><span class="p">,</span> |
| <span class="n">schema</span><span class="p">,</span> |
| <span class="n">codec</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">mime_type</span><span class="p">,</span> |
| <span class="n">use_fastavro</span><span class="p">):</span> |
| <span class="k">return</span> \ |
| <span class="n">_FastAvroSink</span><span class="p">(</span> |
| <span class="n">file_path_prefix</span><span class="p">,</span> |
| <span class="n">schema</span><span class="p">,</span> |
| <span class="n">codec</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">mime_type</span> |
| <span class="p">)</span> \ |
| <span class="k">if</span> <span class="n">use_fastavro</span> \ |
| <span class="k">else</span> \ |
| <span class="n">_AvroSink</span><span class="p">(</span> |
| <span class="n">file_path_prefix</span><span class="p">,</span> |
| <span class="n">schema</span><span class="p">,</span> |
| <span class="n">codec</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">mime_type</span> |
| <span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_AvroSink</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">"""A sink for avro files."""</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">schema</span><span class="p">,</span> |
| <span class="n">codec</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">mime_type</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_AvroSink</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="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">coder</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">mime_type</span><span class="o">=</span><span class="n">mime_type</span><span class="p">,</span> |
| <span class="c1"># Compression happens at the block level using the supplied codec, and</span> |
| <span class="c1"># not at the file level.</span> |
| <span class="n">compression_type</span><span class="o">=</span><span class="n">CompressionTypes</span><span class="o">.</span><span class="n">UNCOMPRESSED</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_schema</span> <span class="o">=</span> <span class="n">schema</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_codec</span> <span class="o">=</span> <span class="n">codec</span> |
| |
| <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">temp_path</span><span class="p">):</span> |
| <span class="n">file_handle</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">_AvroSink</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">avro</span><span class="o">.</span><span class="n">datafile</span><span class="o">.</span><span class="n">DataFileWriter</span><span class="p">(</span> |
| <span class="n">file_handle</span><span class="p">,</span> <span class="n">avro</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">DatumWriter</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_schema</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_codec</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">write_record</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">writer</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="n">writer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">res</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">_AvroSink</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">display_data</span><span class="p">()</span> |
| <span class="n">res</span><span class="p">[</span><span class="s1">'codec'</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_codec</span><span class="p">)</span> |
| <span class="n">res</span><span class="p">[</span><span class="s1">'schema'</span><span class="p">]</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_schema</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">res</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_FastAvroSink</span><span class="p">(</span><span class="n">_AvroSink</span><span class="p">):</span> |
| <span class="sd">"""A sink for avro files that uses the `fastavro` library"""</span> |
| <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">temp_path</span><span class="p">):</span> |
| <span class="n">file_handle</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">_AvroSink</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">temp_path</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">Writer</span><span class="p">(</span><span class="n">file_handle</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_schema</span><span class="o">.</span><span class="n">to_json</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_codec</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">write_record</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">writer</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span> |
| <span class="n">writer</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">value</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">close</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">writer</span><span class="p">):</span> |
| <span class="n">writer</span><span class="o">.</span><span class="n">flush</span><span class="p">()</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_FastAvroSink</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">close</span><span class="p">(</span><span class="n">writer</span><span class="o">.</span><span class="n">fo</span><span class="p">)</span> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © 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> |