| |
| |
| <!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.transforms.external — Apache Beam 2.47.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 2.47.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing 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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.yaml.html">apache_beam.yaml 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="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.transforms.external</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.transforms.external</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">"""Defines Transform whose expansion is implemented elsewhere.</span> |
| |
| <span class="sd">No backward compatibility guarantees. Everything in this module is experimental.</span> |
| <span class="sd">"""</span> |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span> <span class="nn">contextlib</span> |
| <span class="kn">import</span> <span class="nn">copy</span> |
| <span class="kn">import</span> <span class="nn">functools</span> |
| <span class="kn">import</span> <span class="nn">glob</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">threading</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">OrderedDict</span> |
| <span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">namedtuple</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span> |
| |
| <span class="kn">import</span> <span class="nn">grpc</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">pvalue</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.coders</span> <span class="kn">import</span> <span class="n">RowCoder</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability</span> <span class="kn">import</span> <span class="n">common_urns</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">beam_artifact_api_pb2_grpc</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">beam_expansion_api_pb2</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">beam_expansion_api_pb2_grpc</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">beam_runner_api_pb2</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">external_transforms_pb2</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners</span> <span class="kn">import</span> <span class="n">pipeline_context</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.portability</span> <span class="kn">import</span> <span class="n">artifact_service</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">ptransform</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="kn">import</span> <span class="n">WithTypeHints</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="kn">import</span> <span class="n">native_type_compatibility</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="kn">import</span> <span class="n">row_type</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.schemas</span> <span class="kn">import</span> <span class="n">named_fields_to_schema</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.schemas</span> <span class="kn">import</span> <span class="n">named_tuple_from_schema</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.schemas</span> <span class="kn">import</span> <span class="n">named_tuple_to_schema</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.trivial_inference</span> <span class="kn">import</span> <span class="n">instance_to_type</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.typehints</span> <span class="kn">import</span> <span class="n">Union</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.typehints</span> <span class="kn">import</span> <span class="n">UnionConstraint</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils</span> <span class="kn">import</span> <span class="n">subprocess_server</span> |
| |
| <span class="n">DEFAULT_EXPANSION_SERVICE</span> <span class="o">=</span> <span class="s1">'localhost:8097'</span> |
| |
| |
| <div class="viewcode-block" id="convert_to_typing_type"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.convert_to_typing_type">[docs]</a><span class="k">def</span> <span class="nf">convert_to_typing_type</span><span class="p">(</span><span class="n">type_</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">type_</span><span class="p">,</span> <span class="n">row_type</span><span class="o">.</span><span class="n">RowTypeConstraint</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">named_fields_to_schema</span><span class="p">(</span><span class="n">type_</span><span class="o">.</span><span class="n">_fields</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">native_type_compatibility</span><span class="o">.</span><span class="n">convert_to_typing_type</span><span class="p">(</span><span class="n">type_</span><span class="p">)</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_is_optional_or_none</span><span class="p">(</span><span class="n">typehint</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span> <span class="ow">in</span> <span class="n">typehint</span><span class="o">.</span><span class="n">union_types</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span> |
| <span class="n">typehint</span><span class="p">,</span> <span class="n">UnionConstraint</span><span class="p">)</span> <span class="k">else</span> <span class="n">typehint</span> <span class="ow">is</span> <span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">))</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_strip_optional</span><span class="p">(</span><span class="n">typehint</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">_is_optional_or_none</span><span class="p">(</span><span class="n">typehint</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">typehint</span> |
| <span class="n">new_types</span> <span class="o">=</span> <span class="n">typehint</span><span class="o">.</span><span class="n">union_types</span><span class="o">.</span><span class="n">difference</span><span class="p">({</span><span class="nb">type</span><span class="p">(</span><span class="kc">None</span><span class="p">)})</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">new_types</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="n">new_types</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">Union</span><span class="p">[</span><span class="n">new_types</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="iter_urns"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.iter_urns">[docs]</a><span class="k">def</span> <span class="nf">iter_urns</span><span class="p">(</span><span class="n">coder</span><span class="p">,</span> <span class="n">context</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">coder</span><span class="o">.</span><span class="n">to_runner_api_parameter</span><span class="p">(</span><span class="n">context</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">for</span> <span class="n">child</span> <span class="ow">in</span> <span class="n">coder</span><span class="o">.</span><span class="n">_get_component_coders</span><span class="p">():</span> |
| <span class="k">for</span> <span class="n">urn</span> <span class="ow">in</span> <span class="n">iter_urns</span><span class="p">(</span><span class="n">child</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">urn</span></div> |
| |
| |
| <div class="viewcode-block" id="PayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.PayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">PayloadBuilder</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract base class for building payloads to pass to ExternalTransform.</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="PayloadBuilder.build"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.PayloadBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> :return: ExternalConfigurationPayload</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="PayloadBuilder.payload"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.PayloadBuilder.payload">[docs]</a> <span class="k">def</span> <span class="nf">payload</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> The serialized ExternalConfigurationPayload</span> |
| |
| <span class="sd"> :return: bytes</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">build</span><span class="p">()</span><span class="o">.</span><span class="n">SerializeToString</span><span class="p">()</span></div> |
| |
| <span class="k">def</span> <span class="nf">_get_schema_proto_and_payload</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="n">named_fields</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">fields_to_values</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span> |
| |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">key</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Parameter name cannot be empty'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">value</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Received value None for key </span><span class="si">%s</span><span class="s1">. None values are currently not '</span> |
| <span class="s1">'supported'</span> <span class="o">%</span> <span class="n">key</span><span class="p">)</span> |
| <span class="n">named_fields</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">convert_to_typing_type</span><span class="p">(</span><span class="n">instance_to_type</span><span class="p">(</span><span class="n">value</span><span class="p">))))</span> |
| <span class="n">fields_to_values</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span> |
| |
| <span class="n">schema_proto</span> <span class="o">=</span> <span class="n">named_fields_to_schema</span><span class="p">(</span><span class="n">named_fields</span><span class="p">)</span> |
| <span class="n">row</span> <span class="o">=</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">schema_proto</span><span class="p">)(</span><span class="o">**</span><span class="n">fields_to_values</span><span class="p">)</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_tuple_to_schema</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">row</span><span class="p">))</span> |
| |
| <span class="n">payload</span> <span class="o">=</span> <span class="n">RowCoder</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">row</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">schema_proto</span><span class="p">,</span> <span class="n">payload</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="SchemaBasedPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaBasedPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">SchemaBasedPayloadBuilder</span><span class="p">(</span><span class="n">PayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Base class for building payloads based on a schema that provides</span> |
| <span class="sd"> type information for each configuration value to encode.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">_get_named_tuple_instance</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">()</span> |
| |
| <div class="viewcode-block" id="SchemaBasedPayloadBuilder.build"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaBasedPayloadBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">row</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_named_tuple_instance</span><span class="p">()</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_tuple_to_schema</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">row</span><span class="p">))</span> |
| <span class="k">return</span> <span class="n">external_transforms_pb2</span><span class="o">.</span><span class="n">ExternalConfigurationPayload</span><span class="p">(</span> |
| <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> <span class="n">payload</span><span class="o">=</span><span class="n">RowCoder</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">row</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ImplicitSchemaPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ImplicitSchemaPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">ImplicitSchemaPayloadBuilder</span><span class="p">(</span><span class="n">SchemaBasedPayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Build a payload that generates a schema from the provided values.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">values</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_values</span> <span class="o">=</span> <span class="n">values</span> |
| |
| <span class="k">def</span> <span class="nf">_get_named_tuple_instance</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="c1"># omit fields with value=None since we can't infer their type</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">key</span><span class="p">:</span> <span class="n">value</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_values</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="n">value</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> |
| <span class="p">}</span> |
| |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_fields_to_schema</span><span class="p">([</span> |
| <span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">convert_to_typing_type</span><span class="p">(</span><span class="n">instance_to_type</span><span class="p">(</span><span class="n">value</span><span class="p">)))</span> <span class="k">for</span> <span class="n">key</span><span class="p">,</span> |
| <span class="n">value</span> <span class="ow">in</span> <span class="n">values</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">])</span> |
| <span class="k">return</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)(</span><span class="o">**</span><span class="n">values</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="NamedTupleBasedPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.NamedTupleBasedPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">NamedTupleBasedPayloadBuilder</span><span class="p">(</span><span class="n">SchemaBasedPayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Build a payload based on a NamedTuple schema.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tuple_instance</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> :param tuple_instance: an instance of a typing.NamedTuple</span> |
| <span class="sd"> """</span> |
| <span class="nb">super</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">_tuple_instance</span> <span class="o">=</span> <span class="n">tuple_instance</span> |
| |
| <span class="k">def</span> <span class="nf">_get_named_tuple_instance</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">_tuple_instance</span></div> |
| |
| |
| <div class="viewcode-block" id="SchemaTransformPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaTransformPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">SchemaTransformPayloadBuilder</span><span class="p">(</span><span class="n">PayloadBuilder</span><span class="p">):</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">identifier</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_identifier</span> <span class="o">=</span> <span class="n">identifier</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span> |
| |
| <div class="viewcode-block" id="SchemaTransformPayloadBuilder.build"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaTransformPayloadBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">schema_proto</span><span class="p">,</span> <span class="n">payload</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_schema_proto_and_payload</span><span class="p">(</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span> |
| <span class="n">payload</span> <span class="o">=</span> <span class="n">external_transforms_pb2</span><span class="o">.</span><span class="n">SchemaTransformPayload</span><span class="p">(</span> |
| <span class="n">identifier</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_identifier</span><span class="p">,</span> |
| <span class="n">configuration_schema</span><span class="o">=</span><span class="n">schema_proto</span><span class="p">,</span> |
| <span class="n">configuration_row</span><span class="o">=</span><span class="n">payload</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">payload</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JavaClassLookupPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaClassLookupPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">JavaClassLookupPayloadBuilder</span><span class="p">(</span><span class="n">PayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Builds a payload for directly instantiating a Java transform using a</span> |
| <span class="sd"> constructor and builder methods.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">IGNORED_ARG_FORMAT</span> <span class="o">=</span> <span class="s1">'ignore</span><span class="si">%d</span><span class="s1">'</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">class_name</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> :param class_name: fully qualified name of the transform class.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">class_name</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Class name must not be empty'</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_class_name</span> <span class="o">=</span> <span class="n">class_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_method</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_args</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_builder_methods_and_params</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">_args_to_named_fields</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span> |
| <span class="n">next_field_id</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">named_fields</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">args</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">value</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Received value None. None values are currently not supported'</span><span class="p">)</span> |
| <span class="n">named_fields</span><span class="p">[(</span> |
| <span class="n">JavaClassLookupPayloadBuilder</span><span class="o">.</span><span class="n">IGNORED_ARG_FORMAT</span> <span class="o">%</span> |
| <span class="n">next_field_id</span><span class="p">)]</span> <span class="o">=</span> <span class="n">value</span> |
| <span class="n">next_field_id</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">named_fields</span> |
| |
| <div class="viewcode-block" id="JavaClassLookupPayloadBuilder.build"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaClassLookupPayloadBuilder.build">[docs]</a> <span class="k">def</span> <span class="nf">build</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">all_constructor_param_kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_args_to_named_fields</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_args</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span><span class="p">:</span> |
| <span class="n">all_constructor_param_kwargs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span><span class="p">)</span> |
| <span class="n">constructor_schema</span><span class="p">,</span> <span class="n">constructor_payload</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_get_schema_proto_and_payload</span><span class="p">(</span><span class="o">**</span><span class="n">all_constructor_param_kwargs</span><span class="p">))</span> |
| <span class="n">payload</span> <span class="o">=</span> <span class="n">external_transforms_pb2</span><span class="o">.</span><span class="n">JavaClassLookupPayload</span><span class="p">(</span> |
| <span class="n">class_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_class_name</span><span class="p">,</span> |
| <span class="n">constructor_schema</span><span class="o">=</span><span class="n">constructor_schema</span><span class="p">,</span> |
| <span class="n">constructor_payload</span><span class="o">=</span><span class="n">constructor_payload</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_method</span><span class="p">:</span> |
| <span class="n">payload</span><span class="o">.</span><span class="n">constructor_method</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_method</span> |
| |
| <span class="k">for</span> <span class="n">builder_method_name</span><span class="p">,</span> <span class="n">params</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_builder_methods_and_params</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">builder_method_args</span><span class="p">,</span> <span class="n">builder_method_kwargs</span> <span class="o">=</span> <span class="n">params</span> |
| <span class="n">all_builder_method_kwargs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_args_to_named_fields</span><span class="p">(</span> |
| <span class="n">builder_method_args</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">builder_method_kwargs</span><span class="p">:</span> |
| <span class="n">all_builder_method_kwargs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">builder_method_kwargs</span><span class="p">)</span> |
| <span class="n">builder_method_schema</span><span class="p">,</span> <span class="n">builder_method_payload</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_get_schema_proto_and_payload</span><span class="p">(</span><span class="o">**</span><span class="n">all_builder_method_kwargs</span><span class="p">))</span> |
| <span class="n">builder_method</span> <span class="o">=</span> <span class="n">external_transforms_pb2</span><span class="o">.</span><span class="n">BuilderMethod</span><span class="p">(</span> |
| <span class="n">name</span><span class="o">=</span><span class="n">builder_method_name</span><span class="p">,</span> |
| <span class="n">schema</span><span class="o">=</span><span class="n">builder_method_schema</span><span class="p">,</span> |
| <span class="n">payload</span><span class="o">=</span><span class="n">builder_method_payload</span><span class="p">)</span> |
| <span class="n">builder_method</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">builder_method_name</span> |
| <span class="n">payload</span><span class="o">.</span><span class="n">builder_methods</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">builder_method</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">payload</span></div> |
| |
| <div class="viewcode-block" id="JavaClassLookupPayloadBuilder.with_constructor"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaClassLookupPayloadBuilder.with_constructor">[docs]</a> <span class="k">def</span> <span class="nf">with_constructor</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Specifies the Java constructor to use.</span> |
| <span class="sd"> Arguments provided using args and kwargs will be applied to the Java</span> |
| <span class="sd"> transform constructor in the specified order.</span> |
| |
| <span class="sd"> :param args: parameter values of the constructor.</span> |
| <span class="sd"> :param kwargs: parameter names and values of the constructor.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_has_constructor</span><span class="p">():</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Constructor or constructor method can only be specified once'</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_args</span> <span class="o">=</span> <span class="n">args</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span></div> |
| |
| <div class="viewcode-block" id="JavaClassLookupPayloadBuilder.with_constructor_method"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaClassLookupPayloadBuilder.with_constructor_method">[docs]</a> <span class="k">def</span> <span class="nf">with_constructor_method</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">method_name</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Specifies the Java constructor method to use.</span> |
| <span class="sd"> Arguments provided using args and kwargs will be applied to the Java</span> |
| <span class="sd"> transform constructor method in the specified order.</span> |
| |
| <span class="sd"> :param method_name: name of the constructor method.</span> |
| <span class="sd"> :param args: parameter values of the constructor method.</span> |
| <span class="sd"> :param kwargs: parameter names and values of the constructor method.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_has_constructor</span><span class="p">():</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Constructor or constructor method can only be specified once'</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_method</span> <span class="o">=</span> <span class="n">method_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_args</span> <span class="o">=</span> <span class="n">args</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span></div> |
| |
| <div class="viewcode-block" id="JavaClassLookupPayloadBuilder.add_builder_method"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaClassLookupPayloadBuilder.add_builder_method">[docs]</a> <span class="k">def</span> <span class="nf">add_builder_method</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">method_name</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Specifies a Java builder method to be invoked after instantiating the Java</span> |
| <span class="sd"> transform class. Specified builder method will be applied in order.</span> |
| <span class="sd"> Arguments provided using args and kwargs will be applied to the Java</span> |
| <span class="sd"> transform builder method in the specified order.</span> |
| |
| <span class="sd"> :param method_name: name of the builder method.</span> |
| <span class="sd"> :param args: parameter values of the builder method.</span> |
| <span class="sd"> :param kwargs: parameter names and values of the builder method.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_builder_methods_and_params</span><span class="p">[</span><span class="n">method_name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_has_constructor</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="bp">self</span><span class="o">.</span><span class="n">_constructor_method</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_args</span> <span class="ow">or</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_constructor_param_kwargs</span><span class="p">)</span></div> |
| |
| |
| <span class="c1"># Information regarding a SchemaTransform available in an external SDK.</span> |
| <span class="n">SchemaTransformsConfig</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span> |
| <span class="s1">'SchemaTransformsConfig'</span><span class="p">,</span> |
| <span class="p">[</span><span class="s1">'identifier'</span><span class="p">,</span> <span class="s1">'configuration_schema'</span><span class="p">,</span> <span class="s1">'inputs'</span><span class="p">,</span> <span class="s1">'outputs'</span><span class="p">])</span> |
| |
| |
| <div class="viewcode-block" id="SchemaAwareExternalTransform"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaAwareExternalTransform">[docs]</a><span class="k">class</span> <span class="nc">SchemaAwareExternalTransform</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A proxy transform for SchemaTransforms implemented in external SDKs.</span> |
| |
| <span class="sd"> This allows Python pipelines to directly use existing SchemaTransforms</span> |
| <span class="sd"> available to the expansion service without adding additional code in external</span> |
| <span class="sd"> SDKs.</span> |
| |
| <span class="sd"> :param identifier: unique identifier of the SchemaTransform.</span> |
| <span class="sd"> :param expansion_service: an expansion service to use. This should already be</span> |
| <span class="sd"> available and the Schema-aware transforms to be used must already be</span> |
| <span class="sd"> deployed.</span> |
| <span class="sd"> :param classpath: (Optional) A list paths to additional jars to place on the</span> |
| <span class="sd"> expansion service classpath.</span> |
| <span class="sd"> :kwargs: field name to value mapping for configuring the schema transform.</span> |
| <span class="sd"> keys map to the field names of the schema of the SchemaTransform</span> |
| <span class="sd"> (in-order).</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">identifier</span><span class="p">,</span> <span class="n">expansion_service</span><span class="p">,</span> <span class="n">classpath</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span> <span class="o">=</span> <span class="n">SchemaTransformPayloadBuilder</span><span class="p">(</span><span class="n">identifier</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="o">=</span> <span class="n">classpath</span> |
| |
| <div class="viewcode-block" id="SchemaAwareExternalTransform.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaAwareExternalTransform.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">pcolls</span><span class="p">):</span> |
| <span class="c1"># Expand the transform using the expansion service.</span> |
| <span class="k">return</span> <span class="n">pcolls</span> <span class="o">|</span> <span class="n">ExternalTransform</span><span class="p">(</span> |
| <span class="n">common_urns</span><span class="o">.</span><span class="n">schematransform_based_expand</span><span class="o">.</span><span class="n">urn</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SchemaAwareExternalTransform.discover"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaAwareExternalTransform.discover">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">discover</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Discover all SchemaTransforms available to the given expansion service.</span> |
| |
| <span class="sd"> :return: a list of SchemaTransformsConfigs that represent the discovered</span> |
| <span class="sd"> SchemaTransforms.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">with</span> <span class="n">ExternalTransform</span><span class="o">.</span><span class="n">service</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">)</span> <span class="k">as</span> <span class="n">service</span><span class="p">:</span> |
| <span class="n">discover_response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">DiscoverSchemaTransform</span><span class="p">(</span> |
| <span class="n">beam_expansion_api_pb2</span><span class="o">.</span><span class="n">DiscoverSchemaTransformRequest</span><span class="p">())</span> |
| |
| <span class="k">for</span> <span class="n">identifier</span> <span class="ow">in</span> <span class="n">discover_response</span><span class="o">.</span><span class="n">schema_transform_configs</span><span class="p">:</span> |
| <span class="n">proto_config</span> <span class="o">=</span> <span class="n">discover_response</span><span class="o">.</span><span class="n">schema_transform_configs</span><span class="p">[</span><span class="n">identifier</span><span class="p">]</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">proto_config</span><span class="o">.</span><span class="n">config_schema</span><span class="p">)</span> |
| |
| <span class="k">yield</span> <span class="n">SchemaTransformsConfig</span><span class="p">(</span> |
| <span class="n">identifier</span><span class="o">=</span><span class="n">identifier</span><span class="p">,</span> |
| <span class="n">configuration_schema</span><span class="o">=</span><span class="n">schema</span><span class="p">,</span> |
| <span class="n">inputs</span><span class="o">=</span><span class="n">proto_config</span><span class="o">.</span><span class="n">input_pcollection_names</span><span class="p">,</span> |
| <span class="n">outputs</span><span class="o">=</span><span class="n">proto_config</span><span class="o">.</span><span class="n">output_pcollection_names</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SchemaAwareExternalTransform.discover_config"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.SchemaAwareExternalTransform.discover_config">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">discover_config</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Discover one SchemaTransform by name in the given expansion service.</span> |
| |
| <span class="sd"> :return: one SchemaTransformConfig that represents the discovered</span> |
| <span class="sd"> SchemaTransform</span> |
| |
| <span class="sd"> :raises:</span> |
| <span class="sd"> ValueError: if more than one SchemaTransform is discovered, or if none</span> |
| <span class="sd"> are discovered</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">schematransforms</span> <span class="o">=</span> <span class="n">SchemaAwareExternalTransform</span><span class="o">.</span><span class="n">discover</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">)</span> |
| <span class="n">matched</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">for</span> <span class="n">st</span> <span class="ow">in</span> <span class="n">schematransforms</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">st</span><span class="o">.</span><span class="n">identifier</span><span class="p">:</span> |
| <span class="n">matched</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">st</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">matched</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Did not discover any SchemaTransforms resembling the name '</span><span class="si">%s</span><span class="s2">'"</span> <span class="o">%</span> |
| <span class="n">name</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">matched</span><span class="p">)</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Found multiple SchemaTransforms with the name '</span><span class="si">%s</span><span class="s2">':</span><span class="se">\n</span><span class="si">%s</span><span class="se">\n</span><span class="s2">"</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="p">[</span><span class="n">st</span><span class="o">.</span><span class="n">identifier</span> <span class="k">for</span> <span class="n">st</span> <span class="ow">in</span> <span class="n">matched</span><span class="p">]))</span> |
| |
| <span class="k">return</span> <span class="n">matched</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JavaExternalTransform"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaExternalTransform">[docs]</a><span class="k">class</span> <span class="nc">JavaExternalTransform</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""A proxy for Java-implemented external transforms.</span> |
| |
| <span class="sd"> One builds these transforms just as one would in Java, e.g.::</span> |
| |
| <span class="sd"> transform = JavaExternalTransform('fully.qualified.ClassName'</span> |
| <span class="sd"> )(contructorArg, ... ).builderMethod(...)</span> |
| |
| <span class="sd"> or::</span> |
| |
| <span class="sd"> JavaExternalTransform('fully.qualified.ClassName').staticConstructor(</span> |
| <span class="sd"> ...).builderMethod1(...).builderMethod2(...)</span> |
| |
| <span class="sd"> :param class_name: fully qualified name of the java class</span> |
| <span class="sd"> :param expansion_service: (Optional) an expansion service to use. If none is</span> |
| <span class="sd"> provided, a default expansion service will be started.</span> |
| <span class="sd"> :param classpath: (Optional) A list paths to additional jars to place on the</span> |
| <span class="sd"> expansion service classpath.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">class_name</span><span class="p">,</span> <span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">classpath</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">expansion_service</span> <span class="ow">and</span> <span class="n">classpath</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s1">'Only one of expansion_service (</span><span class="si">{</span><span class="n">expansion_service</span><span class="si">}</span><span class="s1">) '</span> |
| <span class="sa">f</span><span class="s1">'or classpath (</span><span class="si">{</span><span class="n">classpath</span><span class="si">}</span><span class="s1">) may be provided.'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span> <span class="o">=</span> <span class="n">JavaClassLookupPayloadBuilder</span><span class="p">(</span><span class="n">class_name</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="o">=</span> <span class="n">classpath</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span> |
| <span class="c1"># Beam explicitly looks for following attributes. Hence adding</span> |
| <span class="c1"># 'None' values here to prevent '__getattr__' from being called.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">inputs</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_fn_api_payload</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="o">.</span><span class="n">with_constructor</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span> |
| |
| <span class="k">def</span> <span class="fm">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> |
| <span class="c1"># Don't try to emulate special methods.</span> |
| <span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'__'</span><span class="p">)</span> <span class="ow">and</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'__'</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__getattr__</span><span class="p">(</span><span class="n">name</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> |
| <span class="c1"># Use directly for keywords or attribute conflicts.</span> |
| <span class="k">def</span> <span class="nf">construct</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="o">.</span><span class="n">_has_constructor</span><span class="p">():</span> |
| <span class="n">builder_method</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="o">.</span><span class="n">add_builder_method</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">builder_method</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="o">.</span><span class="n">with_constructor_method</span> |
| <span class="n">builder_method</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span> |
| |
| <span class="k">return</span> <span class="n">construct</span> |
| |
| <div class="viewcode-block" id="JavaExternalTransform.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaExternalTransform.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">pcolls</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span> <span class="o">=</span> <span class="n">BeamJarExpansionService</span><span class="p">(</span> |
| <span class="s1">':sdks:java:expansion-service:app:shadowJar'</span><span class="p">,</span> |
| <span class="n">extra_args</span><span class="o">=</span><span class="p">[</span><span class="s1">'{{PORT}}'</span><span class="p">,</span> <span class="s1">'--javaClassLookupAllowlistFile=*'</span><span class="p">],</span> |
| <span class="n">classpath</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">pcolls</span> <span class="o">|</span> <span class="n">ExternalTransform</span><span class="p">(</span> |
| <span class="n">common_urns</span><span class="o">.</span><span class="n">java_class_lookup</span><span class="o">.</span><span class="n">urn</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload_builder</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="AnnotationBasedPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.AnnotationBasedPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">AnnotationBasedPayloadBuilder</span><span class="p">(</span><span class="n">SchemaBasedPayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Build a payload based on an external transform's type annotations.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transform</span><span class="p">,</span> <span class="o">**</span><span class="n">values</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> :param transform: a PTransform instance or class. type annotations will</span> |
| <span class="sd"> be gathered from its __init__ method</span> |
| <span class="sd"> :param values: values to encode</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform</span> <span class="o">=</span> <span class="n">transform</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_values</span> <span class="o">=</span> <span class="n">values</span> |
| |
| <span class="k">def</span> <span class="nf">_get_named_tuple_instance</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_fields_to_schema</span><span class="p">([</span> |
| <span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">convert_to_typing_type</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> |
| <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_transform</span><span class="o">.</span><span class="fm">__init__</span><span class="o">.</span><span class="vm">__annotations__</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">k</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_values</span> |
| <span class="p">])</span> |
| <span class="k">return</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)(</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_values</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="DataclassBasedPayloadBuilder"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.DataclassBasedPayloadBuilder">[docs]</a><span class="k">class</span> <span class="nc">DataclassBasedPayloadBuilder</span><span class="p">(</span><span class="n">SchemaBasedPayloadBuilder</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Build a payload based on an external transform that uses dataclasses.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> :param transform: a dataclass-decorated PTransform instance from which to</span> |
| <span class="sd"> gather type annotations and values</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_transform</span> <span class="o">=</span> <span class="n">transform</span> |
| |
| <span class="k">def</span> <span class="nf">_get_named_tuple_instance</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="kn">import</span> <span class="nn">dataclasses</span> |
| <span class="n">schema</span> <span class="o">=</span> <span class="n">named_fields_to_schema</span><span class="p">([</span> |
| <span class="p">(</span><span class="n">field</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">convert_to_typing_type</span><span class="p">(</span><span class="n">field</span><span class="o">.</span><span class="n">type</span><span class="p">))</span> |
| <span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">dataclasses</span><span class="o">.</span><span class="n">fields</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_transform</span><span class="p">)</span> |
| <span class="p">])</span> |
| <span class="k">return</span> <span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">schema</span><span class="p">)(</span> |
| <span class="o">**</span><span class="n">dataclasses</span><span class="o">.</span><span class="n">asdict</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_transform</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="ExternalTransform"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform">[docs]</a><span class="k">class</span> <span class="nc">ExternalTransform</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> External provides a cross-language transform via expansion services in</span> |
| <span class="sd"> foreign SDKs.</span> |
| |
| <span class="sd"> Experimental; no backwards compatibility guarantees.</span> |
| <span class="sd"> """</span> |
| <span class="n">_namespace_counter</span> <span class="o">=</span> <span class="mi">0</span> |
| |
| <span class="c1"># Variable name _namespace conflicts with DisplayData._namespace so we use</span> |
| <span class="c1"># name _external_namespace here.</span> |
| <span class="n">_external_namespace</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">local</span><span class="p">()</span> |
| |
| <span class="n">_IMPULSE_PREFIX</span> <span class="o">=</span> <span class="s1">'impulse'</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">urn</span><span class="p">,</span> <span class="n">payload</span><span class="p">,</span> <span class="n">expansion_service</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Wrapper for an external transform with the given urn and payload.</span> |
| |
| <span class="sd"> :param urn: the unique beam identifier for this transform</span> |
| <span class="sd"> :param payload: the payload, either as a byte string or a PayloadBuilder</span> |
| <span class="sd"> :param expansion_service: an expansion service implementing the beam</span> |
| <span class="sd"> ExpansionService protocol, either as an object with an Expand method</span> |
| <span class="sd"> or an address (as a str) to a grpc server that provides this method.</span> |
| <span class="sd"> """</span> |
| <span class="n">expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span> <span class="ow">or</span> <span class="n">DEFAULT_EXPANSION_SERVICE</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">urn</span> <span class="ow">and</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">payload</span><span class="p">,</span> <span class="n">JavaClassLookupPayloadBuilder</span><span class="p">):</span> |
| <span class="n">urn</span> <span class="o">=</span> <span class="n">common_urns</span><span class="o">.</span><span class="n">java_class_lookup</span><span class="o">.</span><span class="n">urn</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_urn</span> <span class="o">=</span> <span class="n">urn</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_payload</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">payload</span><span class="o">.</span><span class="n">payload</span><span class="p">()</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">payload</span><span class="p">,</span> <span class="n">PayloadBuilder</span><span class="p">)</span> <span class="k">else</span> <span class="n">payload</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span> <span class="o">=</span> <span class="n">expansion_service</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_fresh_namespace</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="p">{}</span> <span class="c1"># type: Dict[str, pvalue.PCollection]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_outputs</span> <span class="o">=</span> <span class="p">{}</span> <span class="c1"># type: Dict[str, pvalue.PCollection]</span> |
| |
| <div class="viewcode-block" id="ExternalTransform.with_output_types"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.with_output_types">[docs]</a> <span class="k">def</span> <span class="nf">with_output_types</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">WithTypeHints</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ExternalTransform.replace_named_inputs"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.replace_named_inputs">[docs]</a> <span class="k">def</span> <span class="nf">replace_named_inputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">named_inputs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="n">named_inputs</span></div> |
| |
| <div class="viewcode-block" id="ExternalTransform.replace_named_outputs"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.replace_named_outputs">[docs]</a> <span class="k">def</span> <span class="nf">replace_named_outputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">named_outputs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_outputs</span> <span class="o">=</span> <span class="n">named_outputs</span></div> |
| |
| <span class="k">def</span> <span class="nf">__post_init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">expansion_service</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> This will only be invoked if ExternalTransform is used as a base class</span> |
| <span class="sd"> for a class decorated with dataclasses.dataclass</span> |
| <span class="sd"> """</span> |
| <span class="n">ExternalTransform</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">URN</span><span class="p">,</span> <span class="n">DataclassBasedPayloadBuilder</span><span class="p">(</span><span class="bp">self</span><span class="p">),</span> <span class="n">expansion_service</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ExternalTransform.default_label"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.default_label">[docs]</a> <span class="k">def</span> <span class="nf">default_label</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">(</span><span class="si">%s</span><span class="s1">)'</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_urn</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ExternalTransform.get_local_namespace"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.get_local_namespace">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">get_local_namespace</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">,</span> <span class="s1">'value'</span><span class="p">,</span> <span class="s1">'external'</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ExternalTransform.outer_namespace"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.outer_namespace">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span> |
| <span class="k">def</span> <span class="nf">outer_namespace</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">namespace</span><span class="p">):</span> |
| <span class="n">prev</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">get_local_namespace</span><span class="p">()</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_external_namespace</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">namespace</span> |
| <span class="k">yield</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_external_namespace</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">prev</span></div> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_fresh_namespace</span><span class="p">(</span><span class="bp">cls</span><span class="p">):</span> |
| <span class="c1"># type: () -> str</span> |
| <span class="n">ExternalTransform</span><span class="o">.</span><span class="n">_namespace_counter</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">_</span><span class="si">%d</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">get_local_namespace</span><span class="p">(),</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_namespace_counter</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ExternalTransform.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.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">pvalueish</span><span class="p">):</span> |
| <span class="c1"># type: (pvalue.PCollection) -> pvalue.PCollection</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pvalueish</span><span class="p">,</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">PBegin</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pvalueish</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="p">{</span><span class="nb">str</span><span class="p">(</span><span class="n">ix</span><span class="p">):</span> <span class="n">pvalue</span> <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">pvalue</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">pvalueish</span><span class="p">)}</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">pvalueish</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="n">pvalueish</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'input'</span><span class="p">:</span> <span class="n">pvalueish</span><span class="p">}</span> |
| <span class="n">pipeline</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="nb">next</span><span class="p">(</span><span class="nb">iter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span><span class="o">.</span><span class="n">values</span><span class="p">()))</span><span class="o">.</span><span class="n">pipeline</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span> <span class="k">else</span> <span class="n">pvalueish</span><span class="o">.</span><span class="n">pipeline</span><span class="p">)</span> |
| <span class="n">context</span> <span class="o">=</span> <span class="n">pipeline_context</span><span class="o">.</span><span class="n">PipelineContext</span><span class="p">(</span> |
| <span class="n">component_id_map</span><span class="o">=</span><span class="n">pipeline</span><span class="o">.</span><span class="n">component_id_map</span><span class="p">)</span> |
| <span class="n">transform_proto</span> <span class="o">=</span> <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">PTransform</span><span class="p">(</span> |
| <span class="n">unique_name</span><span class="o">=</span><span class="n">pipeline</span><span class="o">.</span><span class="n">_current_transform</span><span class="p">()</span><span class="o">.</span><span class="n">full_label</span><span class="p">,</span> |
| <span class="n">spec</span><span class="o">=</span><span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">FunctionSpec</span><span class="p">(</span> |
| <span class="n">urn</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_urn</span><span class="p">,</span> <span class="n">payload</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_payload</span><span class="p">))</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> <span class="n">pcoll</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">transform_proto</span><span class="o">.</span><span class="n">inputs</span><span class="p">[</span><span class="n">tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_id</span><span class="p">(</span><span class="n">pcoll</span><span class="p">)</span> |
| <span class="c1"># Conversion to/from proto assumes producers.</span> |
| <span class="c1"># TODO: Possibly loosen this.</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_IMPULSE_PREFIX</span><span class="p">,</span> <span class="n">tag</span><span class="p">),</span> |
| <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">PTransform</span><span class="p">(</span> |
| <span class="n">unique_name</span><span class="o">=</span><span class="s1">'</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_IMPULSE_PREFIX</span><span class="p">,</span> <span class="n">tag</span><span class="p">),</span> |
| <span class="n">spec</span><span class="o">=</span><span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">FunctionSpec</span><span class="p">(</span> |
| <span class="n">urn</span><span class="o">=</span><span class="n">common_urns</span><span class="o">.</span><span class="n">primitives</span><span class="o">.</span><span class="n">IMPULSE</span><span class="o">.</span><span class="n">urn</span><span class="p">),</span> |
| <span class="n">outputs</span><span class="o">=</span><span class="p">{</span><span class="s1">'out'</span><span class="p">:</span> <span class="n">transform_proto</span><span class="o">.</span><span class="n">inputs</span><span class="p">[</span><span class="n">tag</span><span class="p">]}))</span> |
| <span class="n">output_coders</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_type_hints</span><span class="o">.</span><span class="n">output_types</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_type_hints</span><span class="o">.</span><span class="n">output_types</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="n">output_coders</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span> |
| <span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">k</span><span class="p">),</span> <span class="n">context</span><span class="o">.</span><span class="n">coder_id_from_element_type</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| <span class="k">for</span> <span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_type_hints</span><span class="o">.</span><span class="n">output_types</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_type_hints</span><span class="o">.</span><span class="n">output_types</span><span class="p">[</span><span class="mi">1</span><span class="p">]:</span> |
| <span class="n">output_coders</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">k</span><span class="p">:</span> <span class="n">context</span><span class="o">.</span><span class="n">coder_id_from_element_type</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> |
| <span class="k">for</span> <span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_type_hints</span><span class="o">.</span><span class="n">output_types</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">}</span> |
| <span class="n">components</span> <span class="o">=</span> <span class="n">context</span><span class="o">.</span><span class="n">to_runner_api</span><span class="p">()</span> |
| <span class="n">request</span> <span class="o">=</span> <span class="n">beam_expansion_api_pb2</span><span class="o">.</span><span class="n">ExpansionRequest</span><span class="p">(</span> |
| <span class="n">components</span><span class="o">=</span><span class="n">components</span><span class="p">,</span> |
| <span class="n">namespace</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">,</span> |
| <span class="n">transform</span><span class="o">=</span><span class="n">transform_proto</span><span class="p">,</span> |
| <span class="n">output_coder_requests</span><span class="o">=</span><span class="n">output_coders</span><span class="p">)</span> |
| |
| <span class="k">with</span> <span class="n">ExternalTransform</span><span class="o">.</span><span class="n">service</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_expansion_service</span><span class="p">)</span> <span class="k">as</span> <span class="n">service</span><span class="p">:</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">service</span><span class="o">.</span><span class="n">Expand</span><span class="p">(</span><span class="n">request</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">response</span><span class="o">.</span><span class="n">error</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">error</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">components</span> |
| <span class="k">if</span> <span class="nb">any</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">dependencies</span> |
| <span class="k">for</span> <span class="n">env</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">environments</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_resolve_artifacts</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="p">,</span> |
| <span class="n">service</span><span class="o">.</span><span class="n">artifact_service</span><span class="p">(),</span> |
| <span class="n">pipeline</span><span class="o">.</span><span class="n">local_tempdir</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">transform</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_requirements</span> <span class="o">=</span> <span class="n">response</span><span class="o">.</span><span class="n">requirements</span> |
| <span class="n">result_context</span> <span class="o">=</span> <span class="n">pipeline_context</span><span class="o">.</span><span class="n">PipelineContext</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">components</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">fix_output</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">tag</span><span class="p">):</span> |
| <span class="n">pcoll</span><span class="o">.</span><span class="n">pipeline</span> <span class="o">=</span> <span class="n">pipeline</span> |
| <span class="n">pcoll</span><span class="o">.</span><span class="n">tag</span> <span class="o">=</span> <span class="n">tag</span> |
| <span class="k">return</span> <span class="n">pcoll</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_outputs</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="n">tag</span><span class="p">:</span> <span class="n">fix_output</span><span class="p">(</span><span class="n">result_context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_by_id</span><span class="p">(</span><span class="n">pcoll_id</span><span class="p">),</span> <span class="n">tag</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">pcoll_id</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">outputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">}</span> |
| |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_output_to_pvalueish</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_outputs</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ExternalTransform.service"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.service">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span> |
| <span class="k">def</span> <span class="nf">service</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">channel_options</span> <span class="o">=</span> <span class="p">[(</span><span class="s2">"grpc.max_receive_message_length"</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">),</span> |
| <span class="p">(</span><span class="s2">"grpc.max_send_message_length"</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">grpc</span><span class="p">,</span> <span class="s1">'local_channel_credentials'</span><span class="p">):</span> |
| <span class="c1"># Some environments may not support insecure channels. Hence use a</span> |
| <span class="c1"># secure channel with local credentials here.</span> |
| <span class="c1"># TODO: update this to support secure non-local channels.</span> |
| <span class="n">channel_factory_fn</span> <span class="o">=</span> <span class="n">functools</span><span class="o">.</span><span class="n">partial</span><span class="p">(</span> |
| <span class="n">grpc</span><span class="o">.</span><span class="n">secure_channel</span><span class="p">,</span> |
| <span class="n">expansion_service</span><span class="p">,</span> |
| <span class="n">grpc</span><span class="o">.</span><span class="n">local_channel_credentials</span><span class="p">(),</span> |
| <span class="n">options</span><span class="o">=</span><span class="n">channel_options</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># local_channel_credentials is an experimental API which is unsupported</span> |
| <span class="c1"># by older versions of grpc which may be pulled in due to other project</span> |
| <span class="c1"># dependencies.</span> |
| <span class="n">channel_factory_fn</span> <span class="o">=</span> <span class="n">functools</span><span class="o">.</span><span class="n">partial</span><span class="p">(</span> |
| <span class="n">grpc</span><span class="o">.</span><span class="n">insecure_channel</span><span class="p">,</span> <span class="n">expansion_service</span><span class="p">,</span> <span class="n">options</span><span class="o">=</span><span class="n">channel_options</span><span class="p">)</span> |
| <span class="k">with</span> <span class="n">channel_factory_fn</span><span class="p">()</span> <span class="k">as</span> <span class="n">channel</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">ExpansionAndArtifactRetrievalStub</span><span class="p">(</span><span class="n">channel</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">expansion_service</span><span class="p">,</span> <span class="s1">'Expand'</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">expansion_service</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">with</span> <span class="n">expansion_service</span> <span class="k">as</span> <span class="n">stub</span><span class="p">:</span> |
| <span class="k">yield</span> <span class="n">stub</span></div> |
| |
| <span class="k">def</span> <span class="nf">_resolve_artifacts</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">components</span><span class="p">,</span> <span class="n">service</span><span class="p">,</span> <span class="n">dest</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">env</span> <span class="ow">in</span> <span class="n">components</span><span class="o">.</span><span class="n">environments</span><span class="o">.</span><span class="n">values</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">env</span><span class="o">.</span><span class="n">dependencies</span><span class="p">:</span> |
| <span class="n">resolved</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span> |
| <span class="n">artifact_service</span><span class="o">.</span><span class="n">resolve_artifacts</span><span class="p">(</span><span class="n">env</span><span class="o">.</span><span class="n">dependencies</span><span class="p">,</span> <span class="n">service</span><span class="p">,</span> <span class="n">dest</span><span class="p">))</span> |
| <span class="k">del</span> <span class="n">env</span><span class="o">.</span><span class="n">dependencies</span><span class="p">[:]</span> |
| <span class="n">env</span><span class="o">.</span><span class="n">dependencies</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">resolved</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">components</span> |
| |
| <span class="k">def</span> <span class="nf">_output_to_pvalueish</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">output_dict</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">output_dict</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">next</span><span class="p">(</span><span class="nb">iter</span><span class="p">(</span><span class="n">output_dict</span><span class="o">.</span><span class="n">values</span><span class="p">()))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">output_dict</span> |
| |
| <div class="viewcode-block" id="ExternalTransform.to_runner_api_transform"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExternalTransform.to_runner_api_transform">[docs]</a> <span class="k">def</span> <span class="nf">to_runner_api_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">,</span> <span class="n">full_label</span><span class="p">):</span> |
| <span class="n">pcoll_renames</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="n">renamed_tag_seen</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> <span class="n">pcoll</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">tag</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">inputs</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">renamed_tag_seen</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span> |
| <span class="s1">'Ambiguity due to non-preserved tags: </span><span class="si">%s</span><span class="s1"> vs </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span> |
| <span class="nb">sorted</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">inputs</span><span class="o">.</span><span class="n">keys</span><span class="p">()),</span> |
| <span class="nb">sorted</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_inputs</span><span class="o">.</span><span class="n">keys</span><span class="p">())))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">renamed_tag_seen</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">tag</span><span class="p">,</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">inputs</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span> |
| <span class="n">pcoll_renames</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">inputs</span><span class="p">[</span><span class="n">tag</span><span class="p">]]</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_id</span><span class="p">(</span><span class="n">pcoll</span><span class="p">))</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> <span class="n">pcoll</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_outputs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">pcoll_renames</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">outputs</span><span class="p">[</span><span class="n">tag</span><span class="p">]]</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">get_id</span><span class="p">(</span><span class="n">pcoll</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">_equivalent</span><span class="p">(</span><span class="n">coder1</span><span class="p">,</span> <span class="n">coder2</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">coder1</span> <span class="o">==</span> <span class="n">coder2</span> <span class="ow">or</span> <span class="n">_normalize</span><span class="p">(</span><span class="n">coder1</span><span class="p">)</span> <span class="o">==</span> <span class="n">_normalize</span><span class="p">(</span><span class="n">coder2</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_normalize</span><span class="p">(</span><span class="n">coder_proto</span><span class="p">):</span> |
| <span class="n">normalized</span> <span class="o">=</span> <span class="n">copy</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">coder_proto</span><span class="p">)</span> |
| <span class="n">normalized</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">environment_id</span> <span class="o">=</span> <span class="s1">''</span> |
| <span class="c1"># TODO(robertwb): Normalize components as well.</span> |
| <span class="k">return</span> <span class="n">normalized</span> |
| |
| <span class="k">for</span> <span class="nb">id</span><span class="p">,</span> <span class="n">proto</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">):</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">proto</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">id</span> <span class="ow">in</span> <span class="n">context</span><span class="o">.</span><span class="n">coders</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">_equivalent</span><span class="p">(</span><span class="n">context</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">_id_to_proto</span><span class="p">[</span><span class="nb">id</span><span class="p">],</span> <span class="n">proto</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span> |
| <span class="s1">'Re-used coder id: </span><span class="si">%s</span><span class="se">\n</span><span class="si">%s</span><span class="se">\n</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">context</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">_id_to_proto</span><span class="p">[</span><span class="nb">id</span><span class="p">],</span> <span class="n">proto</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">proto</span><span class="p">)</span> |
| <span class="k">for</span> <span class="nb">id</span><span class="p">,</span> <span class="n">proto</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">):</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">windowing_strategies</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">proto</span><span class="p">)</span> |
| <span class="k">for</span> <span class="nb">id</span><span class="p">,</span> <span class="n">proto</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">environments</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">):</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">environments</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">proto</span><span class="p">)</span> |
| <span class="k">for</span> <span class="nb">id</span><span class="p">,</span> <span class="n">proto</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="nb">id</span> <span class="o">=</span> <span class="n">pcoll_renames</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="nb">id</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">_id_to_obj</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">pcollections</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">proto</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="nb">id</span><span class="p">,</span> <span class="n">proto</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_components</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_IMPULSE_PREFIX</span><span class="p">):</span> |
| <span class="c1"># Our fake inputs.</span> |
| <span class="k">continue</span> |
| <span class="k">assert</span> <span class="nb">id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">),</span> <span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_external_namespace</span><span class="p">)</span> |
| <span class="n">new_proto</span> <span class="o">=</span> <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">PTransform</span><span class="p">(</span> |
| <span class="n">unique_name</span><span class="o">=</span><span class="n">proto</span><span class="o">.</span><span class="n">unique_name</span><span class="p">,</span> |
| <span class="c1"># If URN is not set this is an empty spec.</span> |
| <span class="n">spec</span><span class="o">=</span><span class="n">proto</span><span class="o">.</span><span class="n">spec</span> <span class="k">if</span> <span class="n">proto</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">urn</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">subtransforms</span><span class="o">=</span><span class="n">proto</span><span class="o">.</span><span class="n">subtransforms</span><span class="p">,</span> |
| <span class="n">inputs</span><span class="o">=</span><span class="p">{</span> |
| <span class="n">tag</span><span class="p">:</span> <span class="n">pcoll_renames</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">pcoll</span> <span class="ow">in</span> <span class="n">proto</span><span class="o">.</span><span class="n">inputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">},</span> |
| <span class="n">outputs</span><span class="o">=</span><span class="p">{</span> |
| <span class="n">tag</span><span class="p">:</span> <span class="n">pcoll_renames</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">pcoll</span> <span class="ow">in</span> <span class="n">proto</span><span class="o">.</span><span class="n">outputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">},</span> |
| <span class="n">display_data</span><span class="o">=</span><span class="n">proto</span><span class="o">.</span><span class="n">display_data</span><span class="p">,</span> |
| <span class="n">environment_id</span><span class="o">=</span><span class="n">proto</span><span class="o">.</span><span class="n">environment_id</span><span class="p">)</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">put_proto</span><span class="p">(</span><span class="nb">id</span><span class="p">,</span> <span class="n">new_proto</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">requirement</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_requirements</span><span class="p">:</span> |
| <span class="n">context</span><span class="o">.</span><span class="n">add_requirement</span><span class="p">(</span><span class="n">requirement</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">beam_runner_api_pb2</span><span class="o">.</span><span class="n">PTransform</span><span class="p">(</span> |
| <span class="n">unique_name</span><span class="o">=</span><span class="n">full_label</span><span class="p">,</span> |
| <span class="n">spec</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">spec</span><span class="p">,</span> |
| <span class="n">subtransforms</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">subtransforms</span><span class="p">,</span> |
| <span class="n">inputs</span><span class="o">=</span><span class="p">{</span> |
| <span class="n">tag</span><span class="p">:</span> <span class="n">pcoll_renames</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">pcoll</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">inputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">},</span> |
| <span class="n">outputs</span><span class="o">=</span><span class="p">{</span> |
| <span class="n">tag</span><span class="p">:</span> <span class="n">pcoll_renames</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">tag</span><span class="p">,</span> |
| <span class="n">pcoll</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">outputs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="p">},</span> |
| <span class="n">environment_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_expanded_transform</span><span class="o">.</span><span class="n">environment_id</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="ExpansionAndArtifactRetrievalStub"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExpansionAndArtifactRetrievalStub">[docs]</a><span class="k">class</span> <span class="nc">ExpansionAndArtifactRetrievalStub</span><span class="p">(</span> |
| <span class="n">beam_expansion_api_pb2_grpc</span><span class="o">.</span><span class="n">ExpansionServiceStub</span><span class="p">):</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">channel</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_channel</span> <span class="o">=</span> <span class="n">channel</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span> |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">channel</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ExpansionAndArtifactRetrievalStub.artifact_service"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExpansionAndArtifactRetrievalStub.artifact_service">[docs]</a> <span class="k">def</span> <span class="nf">artifact_service</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">beam_artifact_api_pb2_grpc</span><span class="o">.</span><span class="n">ArtifactRetrievalServiceStub</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_channel</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="ExpansionAndArtifactRetrievalStub.ready"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.ExpansionAndArtifactRetrievalStub.ready">[docs]</a> <span class="k">def</span> <span class="nf">ready</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">timeout_sec</span><span class="p">):</span> |
| <span class="n">grpc</span><span class="o">.</span><span class="n">channel_ready_future</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_channel</span><span class="p">)</span><span class="o">.</span><span class="n">result</span><span class="p">(</span><span class="n">timeout</span><span class="o">=</span><span class="n">timeout_sec</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JavaJarExpansionService"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.JavaJarExpansionService">[docs]</a><span class="k">class</span> <span class="nc">JavaJarExpansionService</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""An expansion service based on an Java Jar file.</span> |
| |
| <span class="sd"> This can be passed into an ExternalTransform as the expansion_service</span> |
| <span class="sd"> argument which will spawn a subprocess using this jar to expand the</span> |
| <span class="sd"> transform.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> path_to_jar: the path to a locally available executable jar file to be used</span> |
| <span class="sd"> to start up the expansion service.</span> |
| <span class="sd"> extra_args: arguments to be provided when starting up the</span> |
| <span class="sd"> expansion service using the jar file. These arguments will replace the</span> |
| <span class="sd"> default arguments.</span> |
| <span class="sd"> classpath: Additional dependencies to be added to the classpath.</span> |
| <span class="sd"> append_args: arguments to be provided when starting up the</span> |
| <span class="sd"> expansion service using the jar file. These arguments will be appended to</span> |
| <span class="sd"> the default arguments.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">path_to_jar</span><span class="p">,</span> <span class="n">extra_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">classpath</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">append_args</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">extra_args</span> <span class="ow">and</span> <span class="n">append_args</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Only one of extra_args or append_args may be provided'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span> <span class="o">=</span> <span class="n">path_to_jar</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_extra_args</span> <span class="o">=</span> <span class="n">extra_args</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="o">=</span> <span class="n">classpath</span> <span class="ow">or</span> <span class="p">[]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service_count</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_append_args</span> <span class="o">=</span> <span class="n">append_args</span> <span class="ow">or</span> <span class="p">[]</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_expand_jars</span><span class="p">(</span><span class="n">jar</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">glob</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="n">jar</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">glob</span><span class="o">.</span><span class="n">glob</span><span class="p">(</span><span class="n">jar</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">jar</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span> <span class="ow">and</span> <span class="p">(</span><span class="n">jar</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'http://'</span><span class="p">)</span> <span class="ow">or</span> |
| <span class="n">jar</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'https://'</span><span class="p">)):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">local_jar</span><span class="p">(</span><span class="n">jar</span><span class="p">)]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># If the input JAR is not a local glob, nor an http/https URL, then</span> |
| <span class="c1"># we assume that it's a gradle-style Java artifact in Maven Central,</span> |
| <span class="c1"># in the form group:artifact:version, so we attempt to parse that way.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">group_id</span><span class="p">,</span> <span class="n">artifact_id</span><span class="p">,</span> <span class="n">version</span> <span class="o">=</span> <span class="n">jar</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="c1"># If we are not able to find a JAR, nor a JAR artifact, nor a URL for</span> |
| <span class="c1"># a JAR path, we still choose to include it in the path.</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">'Unable to parse </span><span class="si">%s</span><span class="s1"> into group:artifact:version.'</span><span class="p">,</span> <span class="n">jar</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">jar</span><span class="p">]</span> |
| <span class="n">path</span> <span class="o">=</span> <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">local_jar</span><span class="p">(</span> |
| <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">path_to_maven_jar</span><span class="p">(</span> |
| <span class="n">artifact_id</span><span class="p">,</span> <span class="n">group_id</span><span class="p">,</span> <span class="n">version</span><span class="p">))</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">path</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">_default_args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Default arguments to be used by `JavaJarExpansionService`."""</span> |
| |
| <span class="n">to_stage</span> <span class="o">=</span> <span class="s1">','</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span><span class="p">]</span> <span class="o">+</span> <span class="nb">sum</span><span class="p">((</span> |
| <span class="n">JavaJarExpansionService</span><span class="o">.</span><span class="n">_expand_jars</span><span class="p">(</span><span class="n">jar</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">jar</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="ow">or</span> <span class="p">[]),</span> <span class="p">[]))</span> |
| <span class="k">return</span> <span class="p">[</span><span class="s1">'{{PORT}}'</span><span class="p">,</span> <span class="sa">f</span><span class="s1">'--filesToStage=</span><span class="si">{</span><span class="n">to_stage</span><span class="si">}</span><span class="s1">'</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="fm">__enter__</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">_service_count</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span> <span class="o">=</span> <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">local_jar</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_extra_args</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_extra_args</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_default_args</span><span class="p">()</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_append_args</span> |
| <span class="c1"># Consider memoizing these servers (with some timeout).</span> |
| <span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Starting a JAR-based expansion service from JAR </span><span class="si">%s</span><span class="s1"> '</span> <span class="o">+</span> <span class="p">(</span> |
| <span class="s1">'and with classpath: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> <span class="k">else</span> <span class="s1">''</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span><span class="p">)</span> |
| <span class="n">classpath_urls</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">local_jar</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">jar</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_classpath</span> |
| <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">JavaJarExpansionService</span><span class="o">.</span><span class="n">_expand_jars</span><span class="p">(</span><span class="n">jar</span><span class="p">)</span> |
| <span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service_provider</span> <span class="o">=</span> <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="p">(</span> |
| <span class="n">ExpansionAndArtifactRetrievalStub</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_path_to_jar</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_extra_args</span><span class="p">,</span> |
| <span class="n">classpath</span><span class="o">=</span><span class="n">classpath_urls</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_service_provider</span><span class="o">.</span><span class="fm">__enter__</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service_count</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_service</span> |
| |
| <span class="k">def</span> <span class="fm">__exit__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service_count</span> <span class="o">-=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_service_count</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_service_provider</span><span class="o">.</span><span class="fm">__exit__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="BeamJarExpansionService"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.BeamJarExpansionService">[docs]</a><span class="k">class</span> <span class="nc">BeamJarExpansionService</span><span class="p">(</span><span class="n">JavaJarExpansionService</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""An expansion service based on an Beam Java Jar file.</span> |
| |
| <span class="sd"> Attempts to use a locally-built copy of the jar based on the gradle target,</span> |
| <span class="sd"> if it exists, otherwise attempts to download and cache the released artifact</span> |
| <span class="sd"> corresponding to this version of Beam from the apache maven repository.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> gradle_target: Beam Gradle target for building an executable jar which will</span> |
| <span class="sd"> be used to start the expansion service.</span> |
| <span class="sd"> extra_args: arguments to be provided when starting up the</span> |
| <span class="sd"> expansion service using the jar file. These arguments will replace the</span> |
| <span class="sd"> default arguments.</span> |
| <span class="sd"> gradle_appendix: Gradle appendix of the artifact.</span> |
| <span class="sd"> classpath: Additional dependencies to be added to the classpath.</span> |
| <span class="sd"> append_args: arguments to be provided when starting up the</span> |
| <span class="sd"> expansion service using the jar file. These arguments will be appended to</span> |
| <span class="sd"> the default arguments.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">gradle_target</span><span class="p">,</span> |
| <span class="n">extra_args</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">gradle_appendix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">classpath</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">append_args</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">path_to_jar</span> <span class="o">=</span> <span class="n">subprocess_server</span><span class="o">.</span><span class="n">JavaJarServer</span><span class="o">.</span><span class="n">path_to_beam_jar</span><span class="p">(</span> |
| <span class="n">gradle_target</span><span class="p">,</span> <span class="n">gradle_appendix</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">path_to_jar</span><span class="p">,</span> <span class="n">extra_args</span><span class="p">,</span> <span class="n">classpath</span><span class="o">=</span><span class="n">classpath</span><span class="p">,</span> <span class="n">append_args</span><span class="o">=</span><span class="n">append_args</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="memoize"><a class="viewcode-back" href="../../../apache_beam.transforms.external.html#apache_beam.transforms.external.memoize">[docs]</a><span class="k">def</span> <span class="nf">memoize</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="n">cache</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">def</span> <span class="nf">wrapper</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">args</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">cache</span><span class="p">:</span> |
| <span class="n">cache</span><span class="p">[</span><span class="n">args</span><span class="p">]</span> <span class="o">=</span> <span class="n">func</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">cache</span><span class="p">[</span><span class="n">args</span><span class="p">]</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span></div> |
| </pre></div> |
| |
| </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/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> |