blob: 1b5e86f78b9ebbb6dd32d628bad2f5764fb93806 [file] [log] [blame]
<!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 &mdash; 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> &raquo;</li>
<li><a href="../../../../index.html">Module code</a> &raquo;</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">&quot;&quot;&quot;Module of utilities for SQL magics.</span>
<span class="sd">For internal use only; no backward-compatibility guarantees.</span>
<span class="sd">&quot;&quot;&quot;</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">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Registers a RowCoder for the given schema if hasn&#39;t.</span>
<span class="sd"> Notifies the user of what code has been implicitly executed.</span>
<span class="sd"> &quot;&quot;&quot;</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">&#39;Schema </span><span class="si">%s</span><span class="s1"> is not a typing.NamedTuple.&#39;</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">&#39;Schema </span><span class="si">%s</span><span class="s1"> has not been registered to use a RowCoder. &#39;</span>
<span class="s1">&#39;Automatically registering it by running: &#39;</span>
<span class="s1">&#39;beam.coders.registry.register_coder(</span><span class="si">%s</span><span class="s1">, &#39;</span>
<span class="s1">&#39;beam.coders.RowCoder)&#39;</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">-&gt;</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">&quot;&quot;&quot;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"> &quot;&quot;&quot;</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">&#39;Found PCollections used in the magic: </span><span class="si">%s</span><span class="s1">.&#39;</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">&#39;Collecting data...&#39;</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">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Replaces the pcoll_name used in the sql with &#39;PCOLLECTION&#39;.</span>
<span class="sd"> For sql query using only a single PCollection, the PCollection needs to be</span>
<span class="sd"> referred to as &#39;PCOLLECTION&#39; instead of its variable/tag name.</span>
<span class="sd"> &quot;&quot;&quot;</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">&#39;from&#39;</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">&lt;</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">&#39;PCOLLECTION&#39;</span>
<span class="k">return</span> <span class="s1">&#39; &#39;</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">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="k">return</span> <span class="s1">&#39;</span><span class="si">{}</span><span class="s1">(</span><span class="si">{}</span><span class="s1">)&#39;</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">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span>
<span class="s1">&#39;</span><span class="si">{}</span><span class="s1">: </span><span class="si">{}</span><span class="s1">&#39;</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">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="k">return</span> <span class="s1">&#39;{{</span><span class="se">\n</span><span class="si">{}</span><span class="se">\n</span><span class="s1">}}&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="s1">&#39;,</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39;</span><span class="si">{}</span><span class="s1">: </span><span class="si">{}</span><span class="s1">&#39;</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">&quot;&quot;&quot;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&#39;s a str, this entry</span>
<span class="sd"> assigns the input ipywidget&#39;s value directly to the argument. If it&#39;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"> &quot;&quot;&quot;</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">&quot;&quot;&quot;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"> &quot;&quot;&quot;</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">-&gt;</span> <span class="s1">&#39;OptionsForm&#39;</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Adds an OptionsEntry to the form.</span>
<span class="sd"> &quot;&quot;&quot;</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">-&gt;</span> <span class="n">PipelineOptions</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Builds the PipelineOptions based on user inputs.</span>
<span class="sd"> Can only be invoked after display_for_input.</span>
<span class="sd"> &quot;&quot;&quot;</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">&#39;to_options invoked before display_for_input. &#39;</span>
<span class="s1">&#39;Wrong usage.&#39;</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">&quot;&quot;&quot;Alters the self.options with additional config.&quot;&quot;&quot;</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">-&gt;</span> <span class="s1">&#39;OptionsForm&#39;</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Displays the widgets to take user inputs.&quot;&quot;&quot;</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">&#39;&#39;</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">&#39;1fr 2fr 6fr&#39;</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">&quot;&quot;&quot;Displays actionable widgets to utilize the options, run pipelines and</span>
<span class="sd"> etc.&quot;&quot;&quot;</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">&quot;&quot;&quot;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"> &quot;&quot;&quot;</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">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="sd">&quot;&quot;&quot;Builds a default project id.&quot;&quot;&quot;</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">&#39;There is some issue with your gcloud auth: </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
<span class="k">return</span> <span class="s1">&#39;your-project-id&#39;</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">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
<span class="sd">&quot;&quot;&quot;Builds a requirements file that contains all additional PYPI packages</span>
<span class="sd"> needed.&quot;&quot;&quot;</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">&#39;,&#39;</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">&#39;beam-sql-dataflow-&#39;</span><span class="p">),</span> <span class="s1">&#39;req.txt&#39;</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">&#39;a&#39;</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">&#39;</span><span class="se">\n</span><span class="s1">&#39;</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">&quot;&quot;&quot;Inits the OptionsForm for setting up Dataflow jobs.&quot;&quot;&quot;</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">&#39;Project Id&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Name of the Cloud project owning the Dataflow job.&#39;</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">&#39;project&#39;</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">&#39;Region&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;The Google Compute Engine region for creating Dataflow job.&#39;</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">&#39;region&#39;</span><span class="p">,</span>
<span class="n">default</span><span class="o">=</span><span class="s1">&#39;us-central1&#39;</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">&#39;GCS Bucket&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="p">(</span>
<span class="s1">&#39;GCS path to stage code packages needed by workers and save &#39;</span>
<span class="s1">&#39;temporary workflow jobs.&#39;</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">&#39;staging_location&#39;</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">&#39;/staging&#39;</span><span class="p">,</span>
<span class="s1">&#39;temp_location&#39;</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">&#39;/temp&#39;</span>
<span class="p">},</span>
<span class="n">default</span><span class="o">=</span><span class="s1">&#39;gs://YOUR_GCS_BUCKET_HERE&#39;</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">&#39;Additional Packages&#39;</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="p">(</span>
<span class="s1">&#39;PYPI packages installed, comma-separated. If None, leave &#39;</span>
<span class="s1">&#39;this field empty.&#39;</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">&#39;requirements_file&#39;</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">&#39;&#39;</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">&#39;.*java.*,apache/beam_java11_sdk:latest&#39;</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">&#39;Run on Dataflow&#39;</span><span class="p">,</span>
<span class="n">button_style</span><span class="o">=</span><span class="s1">&#39;success&#39;</span><span class="p">,</span>
<span class="n">tooltip</span><span class="o">=</span><span class="p">(</span>
<span class="s1">&#39;Submit to Dataflow for execution with the configured options. The &#39;</span>
<span class="s1">&#39;output PCollection</span><span class="se">\&#39;</span><span class="s1">s data will be written to the GCS bucket you &#39;</span>
<span class="s1">&#39;configure.&#39;</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">&#39;Show Options&#39;</span><span class="p">,</span>
<span class="n">button_style</span><span class="o">=</span><span class="s1">&#39;info&#39;</span><span class="p">,</span>
<span class="n">tooltip</span><span class="o">=</span><span class="s1">&#39;Show current pipeline options configured.&#39;</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">&#39;</span><span class="si">{}</span><span class="s1">/</span><span class="si">{}</span><span class="s1">&#39;</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">&#39;WriteOuput</span><span class="si">{}</span><span class="s1">_</span><span class="si">{}</span><span class="s1">ToGCS&#39;</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">&gt;&gt;</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">&#39;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">&#39;</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">&#39;Running the pipeline on Dataflow with pipeline options </span><span class="si">%s</span><span class="s1">.&#39;</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">&#39;DataflowRunner&#39;</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">&#39;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">&#39;</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">&#39;Click &lt;a href=&quot;</span><span class="si">%s</span><span class="s1">&quot; target=&quot;_new&quot;&gt;here&lt;/a&gt; for the details &#39;</span>
<span class="s1">&#39;of your Dataflow job.&#39;</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">&#39;result_</span><span class="si">{}</span><span class="s1">&#39;</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">&#39;The pipeline result of the run can be accessed from variable &#39;</span>
<span class="s1">&#39;</span><span class="si">%s</span><span class="s1">. The current status is </span><span class="si">%s</span><span class="s1">.&#39;</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">&#39;options_</span><span class="si">{}</span><span class="s1">&#39;</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">&#39;The pipeline options configured is: </span><span class="si">%s</span><span class="s1">.&#39;</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">&#39;repeat(2, 200px)&#39;</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">&#39;options_</span><span class="si">{}</span><span class="s1">&#39;</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">&#39;The pipeline options can be configured through variable </span><span class="si">%s</span><span class="s1">. You &#39;</span>
<span class="s1">&#39;may also add additional options or sink transforms such as write &#39;</span>
<span class="s1">&#39;to BigQuery in other notebook cells. Come back to click &quot;Run on &#39;</span>
<span class="s1">&#39;Dataflow&quot; button once you complete additional configurations. &#39;</span>
<span class="s1">&#39;Optionally, you can chain more beam_sql magics with DataflowRunner &#39;</span>
<span class="s1">&#39;and click &quot;Run on Dataflow&quot; in their outputs.&#39;</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>
&copy; 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>