| |
| |
| <!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.runners.interactive.pipeline_instrument module — Apache Beam documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script> |
| <script type="text/javascript" src="_static/jquery.js"></script> |
| <script type="text/javascript" src="_static/underscore.js"></script> |
| <script type="text/javascript" src="_static/doctools.js"></script> |
| <script type="text/javascript" src="_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.runners.interactive.recording_manager module" href="apache_beam.runners.interactive.recording_manager.html" /> |
| <link rel="prev" title="apache_beam.runners.interactive.pipeline_fragment module" href="apache_beam.runners.interactive.pipeline_fragment.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| |
| |
| |
| <div 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 class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.runners.html#subpackages">Subpackages</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.runners.dataflow.html">apache_beam.runners.dataflow package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.runners.direct.html">apache_beam.runners.direct package</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="apache_beam.runners.interactive.html">apache_beam.runners.interactive package</a><ul class="current"> |
| <li class="toctree-l4"><a class="reference internal" href="apache_beam.runners.interactive.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.runners.interactive.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.runners.job.html">apache_beam.runners.job package</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="apache_beam.runners.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="index.html">Docs</a> »</li> |
| |
| <li><a href="apache_beam.runners.html">apache_beam.runners package</a> »</li> |
| |
| <li><a href="apache_beam.runners.interactive.html">apache_beam.runners.interactive package</a> »</li> |
| |
| <li>apache_beam.runners.interactive.pipeline_instrument module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.runners.interactive.pipeline_instrument.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="module-apache_beam.runners.interactive.pipeline_instrument"> |
| <span id="apache-beam-runners-interactive-pipeline-instrument-module"></span><h1>apache_beam.runners.interactive.pipeline_instrument module<a class="headerlink" href="#module-apache_beam.runners.interactive.pipeline_instrument" title="Permalink to this headline">¶</a></h1> |
| <p>Module to instrument interactivity to the given pipeline.</p> |
| <p>For internal use only; no backwards-compatibility guarantees. |
| This module accesses current interactive environment and analyzes given pipeline |
| to transform original pipeline into a one-shot pipeline with interactivity.</p> |
| <dl class="class"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument"> |
| <em class="property">class </em><code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">PipelineInstrument</code><span class="sig-paren">(</span><em>pipeline</em>, <em>options=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.9)"><code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></a></p> |
| <p>A pipeline instrument for pipeline to be executed by interactive runner.</p> |
| <p>This module should never depend on underlying runner that interactive runner |
| delegates. It instruments the original instance of pipeline directly by |
| appending or replacing transforms with help of cache. It provides |
| interfaces to recover states of original pipeline. It’s the interactive |
| runner’s responsibility to coordinate supported underlying runners to run |
| the pipeline instrumented and recover the original pipeline states if needed.</p> |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.instrumented_pipeline_proto"> |
| <code class="descname">instrumented_pipeline_proto</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.instrumented_pipeline_proto"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.instrumented_pipeline_proto" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Always returns a new instance of portable instrumented proto.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.prune_subgraph_for"> |
| <code class="descname">prune_subgraph_for</code><span class="sig-paren">(</span><em>pipeline</em>, <em>required_transform_ids</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.prune_subgraph_for"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.prune_subgraph_for" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.background_caching_pipeline_proto"> |
| <code class="descname">background_caching_pipeline_proto</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.background_caching_pipeline_proto"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.background_caching_pipeline_proto" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns the background caching pipeline.</p> |
| <p>This method creates a background caching pipeline by: adding writes to cache |
| from each unbounded source (done in the instrument method), and cutting out |
| all components (transform, PCollections, coders, windowing strategies) that |
| are not the unbounded sources or writes to cache (or subtransforms thereof).</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.has_unbounded_sources"> |
| <code class="descname">has_unbounded_sources</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.has_unbounded_sources" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns whether the pipeline has any recordable sources.</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cacheables"> |
| <code class="descname">cacheables</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cacheables" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Finds cacheable PCollections from the pipeline.</p> |
| <p>The function only treats the result as cacheables since there is no |
| guarantee whether PCollections that need to be cached have been cached or |
| not. A PCollection needs to be cached when it’s bound to a user defined |
| variable in the source code. Otherwise, the PCollection is not reusable |
| nor introspectable which nullifies the need of cache.</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.pcolls_to_pcoll_id"> |
| <code class="descname">pcolls_to_pcoll_id</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.pcolls_to_pcoll_id" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a dict mapping str(PCollection)s to IDs.</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.original_pipeline_proto"> |
| <code class="descname">original_pipeline_proto</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.original_pipeline_proto" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a snapshot of the pipeline proto before instrumentation.</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.user_pipeline"> |
| <code class="descname">user_pipeline</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.user_pipeline" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a reference to the pipeline instance defined by the user. If a |
| pipeline has no cacheable PCollection and the user pipeline cannot be |
| found, return None indicating there is nothing to be cached in the user |
| pipeline.</p> |
| <p>The pipeline given for instrumenting and mutated in this class is not |
| necessarily the pipeline instance defined by the user. From the watched |
| scopes, this class figures out what the user pipeline instance is. |
| This metadata can be used for tracking pipeline results.</p> |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.runner_pcoll_to_user_pcoll"> |
| <code class="descname">runner_pcoll_to_user_pcoll</code><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.runner_pcoll_to_user_pcoll" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns cacheable PCollections correlated from instances in the runner |
| pipeline to instances in the user pipeline.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.instrument"> |
| <code class="descname">instrument</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.instrument"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.instrument" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Instruments original pipeline with cache.</p> |
| <p>For cacheable output PCollection, if cache for the key doesn’t exist, do |
| _write_cache(); for cacheable input PCollection, if cache for the key |
| exists, do _read_cache(). No instrument in any other situation.</p> |
| <dl class="docutils"> |
| <dt>Modifies:</dt> |
| <dd>self._pipeline</dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.preprocess"> |
| <code class="descname">preprocess</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.preprocess"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.preprocess" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Pre-processes the pipeline.</p> |
| <p>Since the pipeline instance in the class might not be the same instance |
| defined in the user code, the pre-process will figure out the relationship |
| of cacheable PCollections between these 2 instances by replacing ‘pcoll’ |
| fields in the cacheable dictionary with ones from the running instance.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cache_key"> |
| <code class="descname">cache_key</code><span class="sig-paren">(</span><em>pcoll</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.cache_key"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cache_key" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Gets the identifier of a cacheable PCollection in cache.</p> |
| <p>If the pcoll is not a cacheable, return ‘’. |
| The key is what the pcoll would use as identifier if it’s materialized in |
| cache. It doesn’t mean that there would definitely be such cache already. |
| Also, the pcoll can come from the original user defined pipeline object or |
| an equivalent pcoll from a transformed copy of the original pipeline.</p> |
| <p>‘pcoll_id’ of cacheable is not stable for cache_key, thus not included in |
| cache key. A combination of ‘var’, ‘version’ and ‘producer_version’ is |
| sufficient to identify a cached PCollection.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cacheable_var_by_pcoll_id"> |
| <code class="descname">cacheable_var_by_pcoll_id</code><span class="sig-paren">(</span><em>pcoll_id</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#PipelineInstrument.cacheable_var_by_pcoll_id"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.PipelineInstrument.cacheable_var_by_pcoll_id" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Retrieves the variable name of a PCollection.</p> |
| <p>In source code, PCollection variables are defined in the user pipeline. When |
| it’s converted to the runner api representation, each PCollection referenced |
| in the user pipeline is assigned a unique-within-pipeline pcoll_id. Given |
| such pcoll_id, retrieves the str variable name defined in user pipeline for |
| that referenced PCollection. If the PCollection is not watched, return None.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.build_pipeline_instrument"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">build_pipeline_instrument</code><span class="sig-paren">(</span><em>pipeline</em>, <em>options=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#build_pipeline_instrument"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.build_pipeline_instrument" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Creates PipelineInstrument for a pipeline and its options with cache.</p> |
| <p>Throughout the process, the returned PipelineInstrument snapshots the given |
| pipeline and then mutates the pipeline. It’s invoked by interactive components |
| such as the InteractiveRunner and the given pipeline should be implicitly |
| created runner pipelines instead of pipeline instances defined by the user.</p> |
| <p>This is the shorthand for doing 3 steps: 1) compute once for metadata of the |
| given runner pipeline and everything watched from user pipelines; 2) associate |
| info between the runner pipeline and its corresponding user pipeline, |
| eliminate data from other user pipelines if there are any; 3) mutate the |
| runner pipeline to apply interactivity.</p> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.cacheables"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">cacheables</code><span class="sig-paren">(</span><em>pcolls_to_pcoll_id</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#cacheables"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.cacheables" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Finds PCollections that need to be cached for analyzed PCollections.</p> |
| <p>The function only treats the result as cacheables since there is no guarantee |
| whether PCollections that need to be cached have been cached or not. A |
| PCollection needs to be cached when it’s bound to a user defined variable in |
| the source code. Otherwise, the PCollection is not reusable nor introspectable |
| which nullifies the need of cache. There might be multiple pipelines defined |
| and watched, this will only return for PCollections with pcolls_to_pcoll_id |
| analyzed. The check is not strict because pcoll_id is not unique across |
| multiple pipelines. Additional check needs to be done during instrument.</p> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.cacheable_key"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">cacheable_key</code><span class="sig-paren">(</span><em>pcoll</em>, <em>pcolls_to_pcoll_id</em>, <em>pcoll_version_map=None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#cacheable_key"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.cacheable_key" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.has_unbounded_sources"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">has_unbounded_sources</code><span class="sig-paren">(</span><em>pipeline</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#has_unbounded_sources"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.has_unbounded_sources" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Checks if a given pipeline has recordable sources.</p> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.unbounded_sources"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">unbounded_sources</code><span class="sig-paren">(</span><em>pipeline</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#unbounded_sources"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.unbounded_sources" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a pipeline’s recordable sources.</p> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.pcolls_to_pcoll_id"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">pcolls_to_pcoll_id</code><span class="sig-paren">(</span><em>pipeline</em>, <em>original_context</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#pcolls_to_pcoll_id"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.pcolls_to_pcoll_id" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a dict mapping PCollections string to PCollection IDs.</p> |
| <p>Using a PipelineVisitor to iterate over every node in the pipeline, |
| records the mapping from PCollections to PCollections IDs. This mapping |
| will be used to query cached PCollections.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">(dict from str to str) a dict mapping str(pcoll) to pcoll_id.</td> |
| </tr> |
| </tbody> |
| </table> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.runners.interactive.pipeline_instrument.watch_sources"> |
| <code class="descclassname">apache_beam.runners.interactive.pipeline_instrument.</code><code class="descname">watch_sources</code><span class="sig-paren">(</span><em>pipeline</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/runners/interactive/pipeline_instrument.html#watch_sources"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.runners.interactive.pipeline_instrument.watch_sources" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Watches the unbounded sources in the pipeline.</p> |
| <p>Sources can output to a PCollection without a user variable reference. In |
| this case the source is not cached. We still want to cache the data so we |
| synthetically create a variable to the intermediate PCollection.</p> |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="apache_beam.runners.interactive.recording_manager.html" class="btn btn-neutral float-right" title="apache_beam.runners.interactive.recording_manager module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.runners.interactive.pipeline_fragment.html" class="btn btn-neutral float-left" title="apache_beam.runners.interactive.pipeline_fragment module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <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/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |