| |
| |
| <!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.concat_source — 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.concat_source</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.concat_source</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">"""For internal use only; no backwards-compatibility guarantees.</span> |
| |
| <span class="sd">Concat Source, which reads the union of several other sources.</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">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| |
| <span class="kn">import</span> <span class="nn">bisect</span> |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">range</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="k">import</span> <span class="n">iobase</span> |
| |
| |
| <div class="viewcode-block" id="ConcatSource"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource">[docs]</a><span class="k">class</span> <span class="nc">ConcatSource</span><span class="p">(</span><span class="n">iobase</span><span class="o">.</span><span class="n">BoundedSource</span><span class="p">):</span> |
| <span class="sd">"""For internal use only; no backwards-compatibility guarantees.</span> |
| |
| <span class="sd"> A ``BoundedSource`` that can group a set of ``BoundedSources``.</span> |
| |
| <span class="sd"> Primarily for internal use, use the ``apache_beam.Flatten`` transform</span> |
| <span class="sd"> to create the union of several reads.</span> |
| <span class="sd"> """</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">sources</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span> <span class="o">=</span> <span class="p">[</span><span class="n">source</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="n">iobase</span><span class="o">.</span><span class="n">SourceBundle</span><span class="p">)</span> |
| <span class="k">else</span> <span class="n">iobase</span><span class="o">.</span><span class="n">SourceBundle</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">source</span> <span class="ow">in</span> <span class="n">sources</span><span class="p">]</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">sources</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="n">s</span><span class="o">.</span><span class="n">source</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">]</span> |
| |
| <div class="viewcode-block" id="ConcatSource.estimate_size"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource.estimate_size">[docs]</a> <span class="k">def</span> <span class="nf">estimate_size</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">s</span><span class="o">.</span><span class="n">source</span><span class="o">.</span><span class="n">estimate_size</span><span class="p">()</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ConcatSource.split"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource.split">[docs]</a> <span class="k">def</span> <span class="nf">split</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">desired_bundle_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">start_position</span> <span class="ow">or</span> <span class="n">stop_position</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Multi-level initial splitting is not supported. Expected start and '</span> |
| <span class="s1">'stop positions to be None. Received </span><span class="si">%r</span><span class="s1"> and </span><span class="si">%r</span><span class="s1"> respectively.'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">))</span> |
| |
| <span class="k">for</span> <span class="n">source</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">:</span> |
| <span class="c1"># We assume all sub-sources to produce bundles that specify weight using</span> |
| <span class="c1"># the same unit. For example, all sub-sources may specify the size in</span> |
| <span class="c1"># bytes as their weight.</span> |
| <span class="k">for</span> <span class="n">bundle</span> <span class="ow">in</span> <span class="n">source</span><span class="o">.</span><span class="n">source</span><span class="o">.</span><span class="n">split</span><span class="p">(</span> |
| <span class="n">desired_bundle_size</span><span class="p">,</span> <span class="n">source</span><span class="o">.</span><span class="n">start_position</span><span class="p">,</span> <span class="n">source</span><span class="o">.</span><span class="n">stop_position</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">bundle</span></div> |
| |
| <div class="viewcode-block" id="ConcatSource.get_range_tracker"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource.get_range_tracker">[docs]</a> <span class="k">def</span> <span class="nf">get_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">start_position</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">stop_position</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">start_position</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">start_position</span> <span class="o">=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">stop_position</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">stop_position</span> <span class="o">=</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">),</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">ConcatRangeTracker</span><span class="p">(</span> |
| <span class="n">start_position</span><span class="p">,</span> <span class="n">stop_position</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ConcatSource.read"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource.read">[docs]</a> <span class="k">def</span> <span class="nf">read</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">range_tracker</span><span class="p">):</span> |
| <span class="n">start_source</span><span class="p">,</span> <span class="n">_</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="n">stop_source</span><span class="p">,</span> <span class="n">stop_pos</span> <span class="o">=</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">stop_position</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">stop_pos</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">stop_source</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">for</span> <span class="n">source_ix</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">start_source</span><span class="p">,</span> <span class="n">stop_source</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">range_tracker</span><span class="o">.</span><span class="n">try_claim</span><span class="p">((</span><span class="n">source_ix</span><span class="p">,</span> <span class="kc">None</span><span class="p">)):</span> |
| <span class="k">break</span> |
| <span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span><span class="o">.</span><span class="n">source</span><span class="o">.</span><span class="n">read</span><span class="p">(</span> |
| <span class="n">range_tracker</span><span class="o">.</span><span class="n">sub_range_tracker</span><span class="p">(</span><span class="n">source_ix</span><span class="p">)):</span> |
| <span class="k">yield</span> <span class="n">record</span></div> |
| |
| <div class="viewcode-block" id="ConcatSource.default_output_coder"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatSource.default_output_coder">[docs]</a> <span class="k">def</span> <span class="nf">default_output_coder</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">:</span> |
| <span class="c1"># Getting coder from the first sub-sources. This assumes all sub-sources</span> |
| <span class="c1"># to produce the same coder.</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">source</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">(</span><span class="n">ConcatSource</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">default_output_coder</span><span class="p">()</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ConcatRangeTracker"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker">[docs]</a><span class="k">class</span> <span class="nc">ConcatRangeTracker</span><span class="p">(</span><span class="n">iobase</span><span class="o">.</span><span class="n">RangeTracker</span><span class="p">):</span> |
| <span class="sd">"""For internal use only; no backwards-compatibility guarantees.</span> |
| |
| <span class="sd"> Range tracker for ConcatSource"""</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">start</span><span class="p">,</span> <span class="n">end</span><span class="p">,</span> <span class="n">source_bundles</span><span class="p">):</span> |
| <span class="sd">"""Initializes ``ConcatRangeTracker``</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> start: start position, a tuple of (source_index, source_position)</span> |
| <span class="sd"> end: end position, a tuple of (source_index, source_position)</span> |
| <span class="sd"> source_bundles: the list of source bundles in the ConcatSource</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ConcatRangeTracker</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">_start</span> <span class="o">=</span> <span class="n">start</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_end</span> <span class="o">=</span> <span class="n">end</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span> <span class="o">=</span> <span class="n">source_bundles</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">RLock</span><span class="p">()</span> |
| <span class="c1"># Lazily-initialized list of RangeTrackers corresponding to each source.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_range_trackers</span> <span class="o">=</span> <span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">source_bundles</span><span class="p">)</span> |
| <span class="c1"># The currently-being-iterated-over (and latest claimed) source.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="c1"># Now compute cumulative progress through the sources for converting</span> |
| <span class="c1"># between global fractions and fractions within specific sources.</span> |
| <span class="c1"># TODO(robertwb): Implement fraction-at-position to properly scale</span> |
| <span class="c1"># partial start and end sources.</span> |
| <span class="c1"># Note, however, that in practice splits are typically on source</span> |
| <span class="c1"># boundaries anyways.</span> |
| <span class="n">last</span> <span class="o">=</span> <span class="n">end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="n">end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">start</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_cumulative_weights</span><span class="p">(</span><span class="n">source_bundles</span><span class="p">[</span><span class="n">start</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span><span class="n">last</span><span class="p">])</span> |
| <span class="o">+</span> <span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">source_bundles</span><span class="p">)</span> <span class="o">-</span> <span class="n">last</span> <span class="o">-</span> <span class="n">start</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_compute_cumulative_weights</span><span class="p">(</span><span class="n">source_bundles</span><span class="p">):</span> |
| <span class="c1"># Two adjacent sources must differ so that they can be uniquely</span> |
| <span class="c1"># identified by a single global fraction. Let min_diff be the</span> |
| <span class="c1"># smallest allowable difference between sources.</span> |
| <span class="n">min_diff</span> <span class="o">=</span> <span class="mf">1e-5</span> |
| <span class="c1"># For the computation below, we need weights for all sources.</span> |
| <span class="c1"># Substitute average weights for those whose weights are</span> |
| <span class="c1"># unspecified (or 1.0 for everything if none are known).</span> |
| <span class="n">known</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">weight</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">source_bundles</span> <span class="k">if</span> <span class="n">s</span><span class="o">.</span><span class="n">weight</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">]</span> |
| <span class="n">avg</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="n">known</span><span class="p">)</span> <span class="o">/</span> <span class="nb">len</span><span class="p">(</span><span class="n">known</span><span class="p">)</span> <span class="k">if</span> <span class="n">known</span> <span class="k">else</span> <span class="mf">1.0</span> |
| <span class="n">weights</span> <span class="o">=</span> <span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">weight</span> <span class="ow">or</span> <span class="n">avg</span> <span class="k">for</span> <span class="n">s</span> <span class="ow">in</span> <span class="n">source_bundles</span><span class="p">]</span> |
| |
| <span class="c1"># Now compute running totals of the percent done upon reaching</span> |
| <span class="c1"># each source, with respect to the start and end positions.</span> |
| <span class="c1"># E.g. if the weights were [100, 20, 3] we would produce</span> |
| <span class="c1"># [0.0, 100/123, 120/123, 1.0]</span> |
| <span class="n">total</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="nb">sum</span><span class="p">(</span><span class="n">weights</span><span class="p">))</span> |
| <span class="n">running_total</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">w</span> <span class="ow">in</span> <span class="n">weights</span><span class="p">:</span> |
| <span class="n">running_total</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="nb">max</span><span class="p">(</span><span class="n">min_diff</span><span class="p">,</span> <span class="nb">min</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">running_total</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="n">w</span> <span class="o">/</span> <span class="n">total</span><span class="p">)))</span> |
| <span class="n">running_total</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span> <span class="c1"># In case of rounding error.</span> |
| <span class="c1"># There are issues if, due to rouding error or greatly differing sizes,</span> |
| <span class="c1"># two adjacent running total weights are equal. Normalize this things so</span> |
| <span class="c1"># that this never happens.</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">running_total</span><span class="p">)):</span> |
| <span class="k">if</span> <span class="n">running_total</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">==</span> <span class="n">running_total</span><span class="p">[</span><span class="n">k</span> <span class="o">-</span> <span class="mi">1</span><span class="p">]:</span> |
| <span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">k</span><span class="p">):</span> |
| <span class="n">running_total</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> <span class="o">*=</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">min_diff</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">running_total</span> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.start_position"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.start_position">[docs]</a> <span class="k">def</span> <span class="nf">start_position</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">_start</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.stop_position"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.stop_position">[docs]</a> <span class="k">def</span> <span class="nf">stop_position</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">_end</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.try_claim"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.try_claim">[docs]</a> <span class="k">def</span> <span class="nf">try_claim</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pos</span><span class="p">):</span> |
| <span class="n">source_ix</span><span class="p">,</span> <span class="n">source_pos</span> <span class="o">=</span> <span class="n">pos</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">elif</span> <span class="n">source_ix</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">source_ix</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span> <span class="o">=</span> <span class="n">source_ix</span> |
| <span class="k">if</span> <span class="n">source_pos</span> <span class="ow">is</span> <span class="kc">None</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">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">sub_range_tracker</span><span class="p">(</span><span class="n">source_ix</span><span class="p">)</span><span class="o">.</span><span class="n">try_claim</span><span class="p">(</span><span class="n">source_pos</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.try_split"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.try_split">[docs]</a> <span class="k">def</span> <span class="nf">try_split</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pos</span><span class="p">):</span> |
| <span class="n">source_ix</span><span class="p">,</span> <span class="n">source_pos</span> <span class="o">=</span> <span class="n">pos</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span><span class="p">:</span> |
| <span class="c1"># Already claimed.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">elif</span> <span class="n">source_ix</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="c1"># After end.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">elif</span> <span class="n">source_ix</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># At/after end.</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span><span class="p">:</span> |
| <span class="c1"># Prefer to split on even boundary.</span> |
| <span class="n">split_pos</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">ratio</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># Split the current subsource.</span> |
| <span class="n">split</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">sub_range_tracker</span><span class="p">(</span><span class="n">source_ix</span><span class="p">)</span><span class="o">.</span><span class="n">try_split</span><span class="p">(</span> |
| <span class="n">source_pos</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">split</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">None</span> |
| <span class="n">split_pos</span><span class="p">,</span> <span class="n">frac</span> <span class="o">=</span> <span class="n">split</span> |
| <span class="n">ratio</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">local_to_global</span><span class="p">(</span><span class="n">source_ix</span><span class="p">,</span> <span class="n">frac</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_end</span> <span class="o">=</span> <span class="n">source_ix</span><span class="p">,</span> <span class="n">split_pos</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span> <span class="o">=</span> <span class="p">[</span><span class="nb">min</span><span class="p">(</span><span class="n">w</span> <span class="o">/</span> <span class="n">ratio</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">w</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">source_ix</span><span class="p">,</span> <span class="n">split_pos</span><span class="p">),</span> <span class="n">ratio</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.set_current_position"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.set_current_position">[docs]</a> <span class="k">def</span> <span class="nf">set_current_position</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pos</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">'Should only be called on sub-trackers'</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.position_at_fraction"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.position_at_fraction">[docs]</a> <span class="k">def</span> <span class="nf">position_at_fraction</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fraction</span><span class="p">):</span> |
| <span class="n">source_ix</span><span class="p">,</span> <span class="n">source_frac</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">global_to_local</span><span class="p">(</span><span class="n">fraction</span><span class="p">)</span> |
| <span class="n">last</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o">==</span> <span class="n">last</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">source_ix</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">source_ix</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">sub_range_tracker</span><span class="p">(</span><span class="n">source_ix</span><span class="p">)</span><span class="o">.</span><span class="n">position_at_fraction</span><span class="p">(</span> |
| <span class="n">source_frac</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.fraction_consumed"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.fraction_consumed">[docs]</a> <span class="k">def</span> <span class="nf">fraction_consumed</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">local_to_global</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">sub_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_claimed_source_ix</span><span class="p">)</span> |
| <span class="o">.</span><span class="n">fraction_consumed</span><span class="p">())</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.local_to_global"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.local_to_global">[docs]</a> <span class="k">def</span> <span class="nf">local_to_global</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_ix</span><span class="p">,</span> <span class="n">source_frac</span><span class="p">):</span> |
| <span class="n">cw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span> |
| <span class="c1"># The global fraction is the fraction to source_ix plus some portion of</span> |
| <span class="c1"># the way towards the next source.</span> |
| <span class="k">return</span> <span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> <span class="o">+</span> <span class="n">source_frac</span> <span class="o">*</span> <span class="p">(</span><span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span><span class="p">])</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.global_to_local"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.global_to_local">[docs]</a> <span class="k">def</span> <span class="nf">global_to_local</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">frac</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">frac</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="n">last</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">last</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">cw</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cumulative_weights</span> |
| <span class="c1"># Find the last source that starts at or before frac.</span> |
| <span class="n">source_ix</span> <span class="o">=</span> <span class="n">bisect</span><span class="o">.</span><span class="n">bisect</span><span class="p">(</span><span class="n">cw</span><span class="p">,</span> <span class="n">frac</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span> |
| <span class="c1"># Return this source, converting what's left of frac after starting</span> |
| <span class="c1"># this source into a value in [0.0, 1.0) representing how far we are</span> |
| <span class="c1"># towards the next source.</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">source_ix</span><span class="p">,</span> |
| <span class="p">(</span><span class="n">frac</span> <span class="o">-</span> <span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span><span class="p">])</span> <span class="o">/</span> <span class="p">(</span><span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> <span class="o">-</span> <span class="n">cw</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]))</span></div> |
| |
| <div class="viewcode-block" id="ConcatRangeTracker.sub_range_tracker"><a class="viewcode-back" href="../../../apache_beam.io.concat_source.html#apache_beam.io.concat_source.ConcatRangeTracker.sub_range_tracker">[docs]</a> <span class="k">def</span> <span class="nf">sub_range_tracker</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_ix</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><=</span> <span class="n">source_ix</span> <span class="o"><=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_range_trackers</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">_lock</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_range_trackers</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">source</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_source_bundles</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_start</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">start_position</span> |
| <span class="k">if</span> <span class="n">source_ix</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">stop</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_end</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">stop</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">stop_position</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_range_trackers</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span> <span class="o">=</span> <span class="n">source</span><span class="o">.</span><span class="n">source</span><span class="o">.</span><span class="n">get_range_tracker</span><span class="p">(</span> |
| <span class="n">start</span><span class="p">,</span> <span class="n">stop</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_range_trackers</span><span class="p">[</span><span class="n">source_ix</span><span class="p">]</span></div></div> |
| </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> |