| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>apache_beam.runners.interactive.sql.utils — Apache Beam 2.38.0 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"> |
| 2.38.0 |
| </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.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.runners.interactive.sql.utils</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.runners.interactive.sql.utils</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">"""Module of utilities for SQL magics.</span> |
| |
| <span class="sd">For internal use only; no backward-compatibility guarantees.</span> |
| <span class="sd">"""</span> |
| |
| <span class="c1"># pytype: skip-file</span> |
| |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">tempfile</span> |
| <span class="kn">from</span> <span class="nn">dataclasses</span> <span class="kn">import</span> <span class="n">dataclass</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span> |
| <span class="kn">from</span> <span class="nn">typing</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">Optional</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Type</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Union</span> |
| |
| <span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.io</span> <span class="kn">import</span> <span class="n">WriteToText</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">GoogleCloudOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">SetupOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.options.pipeline_options</span> <span class="kn">import</span> <span class="n">WorkerOptions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.utils</span> <span class="kn">import</span> <span class="n">create_var_in_main</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.interactive.utils</span> <span class="kn">import</span> <span class="n">progress_indicated</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="kn">import</span> <span class="n">create_runner</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints.native_type_compatibility</span> <span class="kn">import</span> <span class="n">match_is_named_tuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.utils.interactive_utils</span> <span class="kn">import</span> <span class="n">is_in_ipython</span> |
| |
| <span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="register_coder_for_schema"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.register_coder_for_schema">[docs]</a><span class="k">def</span> <span class="nf">register_coder_for_schema</span><span class="p">(</span> |
| <span class="n">schema</span><span class="p">:</span> <span class="n">NamedTuple</span><span class="p">,</span> <span class="n">verbose</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="sd">"""Registers a RowCoder for the given schema if hasn't.</span> |
| |
| <span class="sd"> Notifies the user of what code has been implicitly executed.</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">match_is_named_tuple</span><span class="p">(</span><span class="n">schema</span><span class="p">),</span> <span class="p">(</span> |
| <span class="s1">'Schema </span><span class="si">%s</span><span class="s1"> is not a typing.NamedTuple.'</span> <span class="o">%</span> <span class="n">schema</span><span class="p">)</span> |
| <span class="n">coder</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">get_coder</span><span class="p">(</span><span class="n">schema</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">coder</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">verbose</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span> |
| <span class="s1">'Schema </span><span class="si">%s</span><span class="s1"> has not been registered to use a RowCoder. '</span> |
| <span class="s1">'Automatically registering it by running: '</span> |
| <span class="s1">'beam.coders.registry.register_coder(</span><span class="si">%s</span><span class="s1">, '</span> |
| <span class="s1">'beam.coders.RowCoder)'</span><span class="p">,</span> |
| <span class="n">schema</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="n">schema</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span> |
| <span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">registry</span><span class="o">.</span><span class="n">register_coder</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">coders</span><span class="o">.</span><span class="n">RowCoder</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="find_pcolls"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.find_pcolls">[docs]</a><span class="k">def</span> <span class="nf">find_pcolls</span><span class="p">(</span> |
| <span class="n">sql</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">pcolls</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">PCollection</span><span class="p">],</span> |
| <span class="n">verbose</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">PCollection</span><span class="p">]:</span> |
| <span class="sd">"""Finds all PCollections used in the given sql query.</span> |
| |
| <span class="sd"> It does a simple word by word match and calls ib.collect for each PCollection</span> |
| <span class="sd"> found.</span> |
| <span class="sd"> """</span> |
| <span class="n">found</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">for</span> <span class="n">word</span> <span class="ow">in</span> <span class="n">sql</span><span class="o">.</span><span class="n">split</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">word</span> <span class="ow">in</span> <span class="n">pcolls</span><span class="p">:</span> |
| <span class="n">found</span><span class="p">[</span><span class="n">word</span><span class="p">]</span> <span class="o">=</span> <span class="n">pcolls</span><span class="p">[</span><span class="n">word</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">found</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">verbose</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Found PCollections used in the magic: </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> <span class="n">found</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Collecting data...'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">found</span></div> |
| |
| |
| <div class="viewcode-block" id="replace_single_pcoll_token"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.replace_single_pcoll_token">[docs]</a><span class="k">def</span> <span class="nf">replace_single_pcoll_token</span><span class="p">(</span><span class="n">sql</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">pcoll_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="sd">"""Replaces the pcoll_name used in the sql with 'PCOLLECTION'.</span> |
| |
| <span class="sd"> For sql query using only a single PCollection, the PCollection needs to be</span> |
| <span class="sd"> referred to as 'PCOLLECTION' instead of its variable/tag name.</span> |
| <span class="sd"> """</span> |
| <span class="n">words</span> <span class="o">=</span> <span class="n">sql</span><span class="o">.</span><span class="n">split</span><span class="p">()</span> |
| <span class="n">token_locations</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">for</span> <span class="n">word</span> <span class="ow">in</span> <span class="n">words</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">word</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s1">'from'</span><span class="p">:</span> |
| <span class="n">token_locations</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">2</span> |
| <span class="k">continue</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">for</span> <span class="n">token_location</span> <span class="ow">in</span> <span class="n">token_locations</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">token_location</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">words</span><span class="p">)</span> <span class="ow">and</span> <span class="n">words</span><span class="p">[</span><span class="n">token_location</span><span class="p">]</span> <span class="o">==</span> <span class="n">pcoll_name</span><span class="p">:</span> |
| <span class="n">words</span><span class="p">[</span><span class="n">token_location</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'PCOLLECTION'</span> |
| <span class="k">return</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">words</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="pformat_namedtuple"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.pformat_namedtuple">[docs]</a><span class="k">def</span> <span class="nf">pformat_namedtuple</span><span class="p">(</span><span class="n">schema</span><span class="p">:</span> <span class="n">NamedTuple</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">(</span><span class="si">{}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">schema</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> |
| <span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">([</span> |
| <span class="s1">'</span><span class="si">{}</span><span class="s1">: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="vm">__name__</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="n">schema</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="p">]))</span></div> |
| |
| |
| <div class="viewcode-block" id="pformat_dict"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.pformat_dict">[docs]</a><span class="k">def</span> <span class="nf">pformat_dict</span><span class="p">(</span><span class="n">raw_input</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">])</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'{{</span><span class="se">\n</span><span class="si">{}</span><span class="se">\n</span><span class="s1">}}'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="s1">',</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">'</span><span class="si">{}</span><span class="s1">: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</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="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">raw_input</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div> |
| |
| |
| <div class="viewcode-block" id="OptionsEntry"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsEntry">[docs]</a><span class="nd">@dataclass</span> |
| <span class="k">class</span> <span class="nc">OptionsEntry</span><span class="p">:</span> |
| <span class="sd">"""An entry of PipelineOptions that can be visualized through ipywidgets to</span> |
| <span class="sd"> take inputs in IPython notebooks interactively.</span> |
| |
| <span class="sd"> Attributes:</span> |
| <span class="sd"> label: The value of the Label widget.</span> |
| <span class="sd"> help: The help message of the entry, usually the same to the help in</span> |
| <span class="sd"> PipelineOptions.</span> |
| <span class="sd"> cls: The PipelineOptions class/subclass the options belong to.</span> |
| <span class="sd"> arg_builder: Builds the argument/option. If it's a str, this entry</span> |
| <span class="sd"> assigns the input ipywidget's value directly to the argument. If it's a</span> |
| <span class="sd"> Dict, use the corresponding Callable to assign the input value to each</span> |
| <span class="sd"> argument. If Callable is None, fallback to assign the input value</span> |
| <span class="sd"> directly. This allows building multiple similar PipelineOptions</span> |
| <span class="sd"> arguments from a single input, such as staging_location and</span> |
| <span class="sd"> temp_location in GoogleCloudOptions.</span> |
| <span class="sd"> default: The default value of the entry, None if absent.</span> |
| <span class="sd"> """</span> |
| <span class="n">label</span><span class="p">:</span> <span class="nb">str</span> |
| <span class="n">help</span><span class="p">:</span> <span class="nb">str</span> |
| <span class="bp">cls</span><span class="p">:</span> <span class="n">Type</span><span class="p">[</span><span class="n">PipelineOptions</span><span class="p">]</span> |
| <span class="n">arg_builder</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Callable</span><span class="p">]]]</span> |
| <span class="n">default</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> |
| |
| <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="c1"># The attribute holds an ipywidget, currently only supports Text.</span> |
| <span class="c1"># The str value can be accessed by self.input.value.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">input</span> <span class="o">=</span> <span class="kc">None</span></div> |
| |
| |
| <div class="viewcode-block" id="OptionsForm"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm">[docs]</a><span class="k">class</span> <span class="nc">OptionsForm</span><span class="p">:</span> |
| <span class="sd">"""A form visualized to take inputs from users in IPython Notebooks and</span> |
| <span class="sd"> generate PipelineOptions to run pipelines.</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="bp">self</span><span class="o">.</span><span class="n">options</span> <span class="o">=</span> <span class="n">PipelineOptions</span><span class="p">()</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">entries</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <div class="viewcode-block" id="OptionsForm.add"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">entry</span><span class="p">:</span> <span class="n">OptionsEntry</span><span class="p">)</span> <span class="o">-></span> <span class="s1">'OptionsForm'</span><span class="p">:</span> |
| <span class="sd">"""Adds an OptionsEntry to the form.</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">entries</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">entry</span><span class="p">)</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="OptionsForm.to_options"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm.to_options">[docs]</a> <span class="k">def</span> <span class="nf">to_options</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">PipelineOptions</span><span class="p">:</span> |
| <span class="sd">"""Builds the PipelineOptions based on user inputs.</span> |
| |
| <span class="sd"> Can only be invoked after display_for_input.</span> |
| <span class="sd"> """</span> |
| <span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">entries</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">entry</span><span class="o">.</span><span class="n">input</span><span class="p">,</span> <span class="p">(</span> |
| <span class="s1">'to_options invoked before display_for_input. '</span> |
| <span class="s1">'Wrong usage.'</span><span class="p">)</span> |
| <span class="n">view</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">entry</span><span class="o">.</span><span class="n">cls</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">entry</span><span class="o">.</span><span class="n">arg_builder</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="nb">setattr</span><span class="p">(</span><span class="n">view</span><span class="p">,</span> <span class="n">entry</span><span class="o">.</span><span class="n">arg_builder</span><span class="p">,</span> <span class="n">entry</span><span class="o">.</span><span class="n">input</span><span class="o">.</span><span class="n">value</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">arg</span><span class="p">,</span> <span class="n">builder</span> <span class="ow">in</span> <span class="n">entry</span><span class="o">.</span><span class="n">arg_builder</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">builder</span><span class="p">:</span> |
| <span class="nb">setattr</span><span class="p">(</span><span class="n">view</span><span class="p">,</span> <span class="n">arg</span><span class="p">,</span> <span class="n">builder</span><span class="p">(</span><span class="n">entry</span><span class="o">.</span><span class="n">input</span><span class="o">.</span><span class="n">value</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="nb">setattr</span><span class="p">(</span><span class="n">view</span><span class="p">,</span> <span class="n">arg</span><span class="p">,</span> <span class="n">entry</span><span class="o">.</span><span class="n">input</span><span class="o">.</span><span class="n">value</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">additional_options</span><span class="p">()</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">options</span></div> |
| |
| <div class="viewcode-block" id="OptionsForm.additional_options"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm.additional_options">[docs]</a> <span class="k">def</span> <span class="nf">additional_options</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Alters the self.options with additional config."""</span> |
| <span class="k">pass</span></div> |
| |
| <div class="viewcode-block" id="OptionsForm.display_for_input"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm.display_for_input">[docs]</a> <span class="k">def</span> <span class="nf">display_for_input</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="s1">'OptionsForm'</span><span class="p">:</span> |
| <span class="sd">"""Displays the widgets to take user inputs."""</span> |
| <span class="kn">from</span> <span class="nn">IPython.display</span> <span class="kn">import</span> <span class="n">display</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">GridBox</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Label</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Layout</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Text</span> |
| <span class="n">widgets</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">entries</span><span class="p">:</span> |
| <span class="n">text_label</span> <span class="o">=</span> <span class="n">Label</span><span class="p">(</span><span class="n">value</span><span class="o">=</span><span class="n">entry</span><span class="o">.</span><span class="n">label</span><span class="p">)</span> |
| <span class="n">text_input</span> <span class="o">=</span> <span class="n">entry</span><span class="o">.</span><span class="n">input</span> <span class="k">if</span> <span class="n">entry</span><span class="o">.</span><span class="n">input</span> <span class="k">else</span> <span class="n">Text</span><span class="p">(</span> |
| <span class="n">value</span><span class="o">=</span><span class="n">entry</span><span class="o">.</span><span class="n">default</span> <span class="k">if</span> <span class="n">entry</span><span class="o">.</span><span class="n">default</span> <span class="k">else</span> <span class="s1">''</span><span class="p">)</span> |
| <span class="n">text_help</span> <span class="o">=</span> <span class="n">Label</span><span class="p">(</span><span class="n">value</span><span class="o">=</span><span class="n">entry</span><span class="o">.</span><span class="n">help</span><span class="p">)</span> |
| <span class="n">entry</span><span class="o">.</span><span class="n">input</span> <span class="o">=</span> <span class="n">text_input</span> |
| <span class="n">widgets</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">text_label</span><span class="p">)</span> |
| <span class="n">widgets</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">text_input</span><span class="p">)</span> |
| <span class="n">widgets</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">text_help</span><span class="p">)</span> |
| <span class="n">grid</span> <span class="o">=</span> <span class="n">GridBox</span><span class="p">(</span><span class="n">widgets</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="n">Layout</span><span class="p">(</span><span class="n">grid_template_columns</span><span class="o">=</span><span class="s1">'1fr 2fr 6fr'</span><span class="p">))</span> |
| <span class="n">display</span><span class="p">(</span><span class="n">grid</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">display_actions</span><span class="p">()</span> |
| <span class="k">return</span> <span class="bp">self</span></div> |
| |
| <div class="viewcode-block" id="OptionsForm.display_actions"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.OptionsForm.display_actions">[docs]</a> <span class="k">def</span> <span class="nf">display_actions</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="sd">"""Displays actionable widgets to utilize the options, run pipelines and</span> |
| <span class="sd"> etc."""</span> |
| <span class="k">pass</span></div></div> |
| |
| |
| <div class="viewcode-block" id="DataflowOptionsForm"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.DataflowOptionsForm">[docs]</a><span class="k">class</span> <span class="nc">DataflowOptionsForm</span><span class="p">(</span><span class="n">OptionsForm</span><span class="p">):</span> |
| <span class="sd">"""A form to take inputs from users in IPython Notebooks to build</span> |
| <span class="sd"> PipelineOptions to run pipelines on Dataflow.</span> |
| |
| <span class="sd"> Only contains minimum fields needed.</span> |
| <span class="sd"> """</span> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_build_default_project</span><span class="p">()</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="sd">"""Builds a default project id."""</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># pylint: disable=c-extension-no-member</span> |
| <span class="kn">import</span> <span class="nn">google.auth</span> |
| <span class="k">return</span> <span class="n">google</span><span class="o">.</span><span class="n">auth</span><span class="o">.</span><span class="n">default</span><span class="p">()[</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">except</span> <span class="p">(</span><span class="ne">KeyboardInterrupt</span><span class="p">,</span> <span class="ne">SystemExit</span><span class="p">):</span> |
| <span class="k">raise</span> |
| <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">'There is some issue with your gcloud auth: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> |
| <span class="k">return</span> <span class="s1">'your-project-id'</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_build_req_file_from_pkgs</span><span class="p">(</span><span class="n">pkgs</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span> |
| <span class="sd">"""Builds a requirements file that contains all additional PYPI packages</span> |
| <span class="sd"> needed."""</span> |
| <span class="k">if</span> <span class="n">pkgs</span><span class="p">:</span> |
| <span class="n">deps</span> <span class="o">=</span> <span class="n">pkgs</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">','</span><span class="p">)</span> |
| <span class="n">req_file</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span> |
| <span class="n">tempfile</span><span class="o">.</span><span class="n">mkdtemp</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'beam-sql-dataflow-'</span><span class="p">),</span> <span class="s1">'req.txt'</span><span class="p">)</span> |
| <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">req_file</span><span class="p">,</span> <span class="s1">'a'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">dep</span> <span class="ow">in</span> <span class="n">deps</span><span class="p">:</span> |
| <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">dep</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="o">+</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">req_file</span> |
| <span class="k">return</span> <span class="kc">None</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">output_name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> |
| <span class="n">output_pcoll</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">PCollection</span><span class="p">,</span> |
| <span class="n">verbose</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""Inits the OptionsForm for setting up Dataflow jobs."""</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">p</span> <span class="o">=</span> <span class="n">output_pcoll</span><span class="o">.</span><span class="n">pipeline</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_name</span> <span class="o">=</span> <span class="n">output_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_pcoll</span> <span class="o">=</span> <span class="n">output_pcoll</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="o">=</span> <span class="n">verbose</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">notice_shown</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">add</span><span class="p">(</span> |
| <span class="n">OptionsEntry</span><span class="p">(</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Project Id'</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="s1">'Name of the Cloud project owning the Dataflow job.'</span><span class="p">,</span> |
| <span class="bp">cls</span><span class="o">=</span><span class="n">GoogleCloudOptions</span><span class="p">,</span> |
| <span class="n">arg_builder</span><span class="o">=</span><span class="s1">'project'</span><span class="p">,</span> |
| <span class="n">default</span><span class="o">=</span><span class="n">DataflowOptionsForm</span><span class="o">.</span><span class="n">_build_default_project</span><span class="p">())</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">add</span><span class="p">(</span> |
| <span class="n">OptionsEntry</span><span class="p">(</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Region'</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="s1">'The Google Compute Engine region for creating Dataflow job.'</span><span class="p">,</span> |
| <span class="bp">cls</span><span class="o">=</span><span class="n">GoogleCloudOptions</span><span class="p">,</span> |
| <span class="n">arg_builder</span><span class="o">=</span><span class="s1">'region'</span><span class="p">,</span> |
| <span class="n">default</span><span class="o">=</span><span class="s1">'us-central1'</span><span class="p">)</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">add</span><span class="p">(</span> |
| <span class="n">OptionsEntry</span><span class="p">(</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'GCS Bucket'</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span> |
| <span class="s1">'GCS path to stage code packages needed by workers and save '</span> |
| <span class="s1">'temporary workflow jobs.'</span><span class="p">),</span> |
| <span class="bp">cls</span><span class="o">=</span><span class="n">GoogleCloudOptions</span><span class="p">,</span> |
| <span class="n">arg_builder</span><span class="o">=</span><span class="p">{</span> |
| <span class="s1">'staging_location'</span><span class="p">:</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="s1">'/staging'</span><span class="p">,</span> |
| <span class="s1">'temp_location'</span><span class="p">:</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span> <span class="o">+</span> <span class="s1">'/temp'</span> |
| <span class="p">},</span> |
| <span class="n">default</span><span class="o">=</span><span class="s1">'gs://YOUR_GCS_BUCKET_HERE'</span><span class="p">)</span> |
| <span class="p">)</span><span class="o">.</span><span class="n">add</span><span class="p">(</span> |
| <span class="n">OptionsEntry</span><span class="p">(</span> |
| <span class="n">label</span><span class="o">=</span><span class="s1">'Additional Packages'</span><span class="p">,</span> |
| <span class="n">help</span><span class="o">=</span><span class="p">(</span> |
| <span class="s1">'PYPI packages installed, comma-separated. If None, leave '</span> |
| <span class="s1">'this field empty.'</span><span class="p">),</span> |
| <span class="bp">cls</span><span class="o">=</span><span class="n">SetupOptions</span><span class="p">,</span> |
| <span class="n">arg_builder</span><span class="o">=</span><span class="p">{</span> |
| <span class="s1">'requirements_file'</span><span class="p">:</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">DataflowOptionsForm</span><span class="o">.</span> |
| <span class="n">_build_req_file_from_pkgs</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="p">},</span> |
| <span class="n">default</span><span class="o">=</span><span class="s1">''</span><span class="p">))</span> |
| |
| <div class="viewcode-block" id="DataflowOptionsForm.additional_options"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.DataflowOptionsForm.additional_options">[docs]</a> <span class="k">def</span> <span class="nf">additional_options</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="c1"># Use the latest Java SDK by default.</span> |
| <span class="n">sdk_overrides</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span> |
| <span class="n">WorkerOptions</span><span class="p">)</span><span class="o">.</span><span class="n">sdk_harness_container_image_overrides</span> |
| <span class="n">override</span> <span class="o">=</span> <span class="s1">'.*java.*,apache/beam_java11_sdk:latest'</span> |
| <span class="k">if</span> <span class="n">sdk_overrides</span> <span class="ow">and</span> <span class="n">override</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">sdk_overrides</span><span class="p">:</span> |
| <span class="n">sdk_overrides</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">override</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span> |
| <span class="n">WorkerOptions</span><span class="p">)</span><span class="o">.</span><span class="n">sdk_harness_container_image_overrides</span> <span class="o">=</span> <span class="p">[</span><span class="n">override</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="DataflowOptionsForm.display_actions"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.sql.utils.html#apache_beam.runners.interactive.sql.utils.DataflowOptionsForm.display_actions">[docs]</a> <span class="k">def</span> <span class="nf">display_actions</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">IPython.display</span> <span class="kn">import</span> <span class="n">HTML</span> |
| <span class="kn">from</span> <span class="nn">IPython.display</span> <span class="kn">import</span> <span class="n">display</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Button</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">GridBox</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Layout</span> |
| <span class="kn">from</span> <span class="nn">ipywidgets</span> <span class="kn">import</span> <span class="n">Output</span> |
| <span class="n">options_output_area</span> <span class="o">=</span> <span class="n">Output</span><span class="p">()</span> |
| <span class="n">run_output_area</span> <span class="o">=</span> <span class="n">Output</span><span class="p">()</span> |
| <span class="n">run_btn</span> <span class="o">=</span> <span class="n">Button</span><span class="p">(</span> |
| <span class="n">description</span><span class="o">=</span><span class="s1">'Run on Dataflow'</span><span class="p">,</span> |
| <span class="n">button_style</span><span class="o">=</span><span class="s1">'success'</span><span class="p">,</span> |
| <span class="n">tooltip</span><span class="o">=</span><span class="p">(</span> |
| <span class="s1">'Submit to Dataflow for execution with the configured options. The '</span> |
| <span class="s1">'output PCollection</span><span class="se">\'</span><span class="s1">s data will be written to the GCS bucket you '</span> |
| <span class="s1">'configure.'</span><span class="p">))</span> |
| <span class="n">show_options_btn</span> <span class="o">=</span> <span class="n">Button</span><span class="p">(</span> |
| <span class="n">description</span><span class="o">=</span><span class="s1">'Show Options'</span><span class="p">,</span> |
| <span class="n">button_style</span><span class="o">=</span><span class="s1">'info'</span><span class="p">,</span> |
| <span class="n">tooltip</span><span class="o">=</span><span class="s1">'Show current pipeline options configured.'</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_run_on_dataflow</span><span class="p">(</span><span class="n">btn</span><span class="p">):</span> |
| <span class="k">with</span> <span class="n">run_output_area</span><span class="p">:</span> |
| <span class="n">run_output_area</span><span class="o">.</span><span class="n">clear_output</span><span class="p">()</span> |
| |
| <span class="nd">@progress_indicated</span> |
| <span class="k">def</span> <span class="nf">_inner</span><span class="p">():</span> |
| <span class="n">options</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_options</span><span class="p">()</span> |
| <span class="c1"># Caches the output_pcoll to a GCS bucket.</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">execution_count</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">if</span> <span class="n">is_in_ipython</span><span class="p">():</span> |
| <span class="kn">from</span> <span class="nn">IPython</span> <span class="kn">import</span> <span class="n">get_ipython</span> |
| <span class="n">execution_count</span> <span class="o">=</span> <span class="n">get_ipython</span><span class="p">()</span><span class="o">.</span><span class="n">execution_count</span> |
| <span class="n">output_location</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{}</span><span class="s1">/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span><span class="o">.</span><span class="n">staging_location</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">)</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_pcoll</span> <span class="o">|</span> <span class="s1">'WriteOuput</span><span class="si">{}</span><span class="s1">_</span><span class="si">{}</span><span class="s1">ToGCS'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">,</span> |
| <span class="n">execution_count</span><span class="p">)</span> <span class="o">>></span> <span class="n">WriteToText</span><span class="p">(</span><span class="n">output_location</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Data of output PCollection </span><span class="si">%s</span><span class="s1"> will be written to </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">,</span> |
| <span class="n">output_location</span><span class="p">)</span> |
| <span class="k">except</span> <span class="p">(</span><span class="ne">KeyboardInterrupt</span><span class="p">,</span> <span class="ne">SystemExit</span><span class="p">):</span> |
| <span class="k">raise</span> |
| <span class="k">except</span><span class="p">:</span> <span class="c1"># pylint: disable=bare-except</span> |
| <span class="c1"># The transform has been added before, noop.</span> |
| <span class="k">pass</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Running the pipeline on Dataflow with pipeline options </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> |
| <span class="n">pformat_dict</span><span class="p">(</span><span class="n">options</span><span class="o">.</span><span class="n">display_data</span><span class="p">()))</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">create_runner</span><span class="p">(</span><span class="s1">'DataflowRunner'</span><span class="p">)</span><span class="o">.</span><span class="n">run_pipeline</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span> |
| <span class="n">cloud_options</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">GoogleCloudOptions</span><span class="p">)</span> |
| <span class="n">url</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="s1">'https://console.cloud.google.com/dataflow/jobs/</span><span class="si">%s</span><span class="s1">/</span><span class="si">%s</span><span class="s1">?project=</span><span class="si">%s</span><span class="s1">'</span> |
| <span class="o">%</span> <span class="p">(</span><span class="n">cloud_options</span><span class="o">.</span><span class="n">region</span><span class="p">,</span> <span class="n">result</span><span class="o">.</span><span class="n">job_id</span><span class="p">(),</span> <span class="n">cloud_options</span><span class="o">.</span><span class="n">project</span><span class="p">))</span> |
| <span class="n">display</span><span class="p">(</span> |
| <span class="n">HTML</span><span class="p">(</span> |
| <span class="s1">'Click <a href="</span><span class="si">%s</span><span class="s1">" target="_new">here</a> for the details '</span> |
| <span class="s1">'of your Dataflow job.'</span> <span class="o">%</span> <span class="n">url</span><span class="p">))</span> |
| <span class="n">result_name</span> <span class="o">=</span> <span class="s1">'result_</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">)</span> |
| <span class="n">create_var_in_main</span><span class="p">(</span><span class="n">result_name</span><span class="p">,</span> <span class="n">result</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'The pipeline result of the run can be accessed from variable '</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">. The current status is </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> |
| <span class="n">result_name</span><span class="p">,</span> |
| <span class="n">result</span><span class="p">)</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">btn</span><span class="o">.</span><span class="n">disabled</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">_inner</span><span class="p">()</span> |
| <span class="k">finally</span><span class="p">:</span> |
| <span class="n">btn</span><span class="o">.</span><span class="n">disabled</span> <span class="o">=</span> <span class="kc">False</span> |
| |
| <span class="n">run_btn</span><span class="o">.</span><span class="n">on_click</span><span class="p">(</span><span class="n">_run_on_dataflow</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_show_options</span><span class="p">(</span><span class="n">btn</span><span class="p">):</span> |
| <span class="k">with</span> <span class="n">options_output_area</span><span class="p">:</span> |
| <span class="n">options_output_area</span><span class="o">.</span><span class="n">clear_output</span><span class="p">()</span> |
| <span class="n">options</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_options</span><span class="p">()</span> |
| <span class="n">options_name</span> <span class="o">=</span> <span class="s1">'options_</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">)</span> |
| <span class="n">create_var_in_main</span><span class="p">(</span><span class="n">options_name</span><span class="p">,</span> <span class="n">options</span><span class="p">)</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'The pipeline options configured is: </span><span class="si">%s</span><span class="s1">.'</span><span class="p">,</span> |
| <span class="n">pformat_dict</span><span class="p">(</span><span class="n">options</span><span class="o">.</span><span class="n">display_data</span><span class="p">()))</span> |
| |
| <span class="n">show_options_btn</span><span class="o">.</span><span class="n">on_click</span><span class="p">(</span><span class="n">_show_options</span><span class="p">)</span> |
| <span class="n">grid</span> <span class="o">=</span> <span class="n">GridBox</span><span class="p">([</span><span class="n">run_btn</span><span class="p">,</span> <span class="n">show_options_btn</span><span class="p">],</span> |
| <span class="n">layout</span><span class="o">=</span><span class="n">Layout</span><span class="p">(</span><span class="n">grid_template_columns</span><span class="o">=</span><span class="s1">'repeat(2, 200px)'</span><span class="p">))</span> |
| <span class="n">display</span><span class="p">(</span><span class="n">grid</span><span class="p">)</span> |
| |
| <span class="c1"># Implicitly initializes the options variable before 1st time showing</span> |
| <span class="c1"># options.</span> |
| <span class="n">options_name_inited</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">create_var_in_main</span><span class="p">(</span><span class="s1">'options_</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">output_name</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_options</span><span class="p">())</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">notice_shown</span><span class="p">:</span> |
| <span class="n">_LOGGER</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'The pipeline options can be configured through variable </span><span class="si">%s</span><span class="s1">. You '</span> |
| <span class="s1">'may also add additional options or sink transforms such as write '</span> |
| <span class="s1">'to BigQuery in other notebook cells. Come back to click "Run on '</span> |
| <span class="s1">'Dataflow" button once you complete additional configurations. '</span> |
| <span class="s1">'Optionally, you can chain more beam_sql magics with DataflowRunner '</span> |
| <span class="s1">'and click "Run on Dataflow" in their outputs.'</span><span class="p">,</span> |
| <span class="n">options_name_inited</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">notice_shown</span> <span class="o">=</span> <span class="kc">True</span> |
| |
| <span class="n">display</span><span class="p">(</span><span class="n">options_output_area</span><span class="p">)</span> |
| <span class="n">display</span><span class="p">(</span><span class="n">run_output_area</span><span class="p">)</span></div></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> |