blob: 0c3104cc97be4e8e2a40fa00adcdd225ba949c5d [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.io.gcp.bigquery_schema_tools &mdash; Apache Beam 2.53.0 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">
2.53.0
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.io.gcp.bigquery_schema_tools</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for apache_beam.io.gcp.bigquery_schema_tools</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;Tools used tool work with Schema types in the context of BigQuery.</span>
<span class="sd">Classes, constants and functions in this file are experimental and have no</span>
<span class="sd">backwards compatibility guarantees.</span>
<span class="sd">NOTHING IN THIS FILE HAS BACKWARDS COMPATIBILITY GUARANTEES.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">datetime</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">Sequence</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</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">import</span> <span class="nn">apache_beam.io.gcp.bigquery_tools</span>
<span class="kn">import</span> <span class="nn">apache_beam.typehints.schemas</span>
<span class="kn">import</span> <span class="nn">apache_beam.utils.proto_utils</span>
<span class="kn">import</span> <span class="nn">apache_beam.utils.timestamp</span>
<span class="kn">from</span> <span class="nn">apache_beam.io.gcp.internal.clients</span> <span class="kn">import</span> <span class="n">bigquery</span>
<span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">schema_pb2</span>
<span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="kn">import</span> <span class="n">DoFn</span>
<span class="c1"># BigQuery types as listed in</span>
<span class="c1"># https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types</span>
<span class="c1"># with aliases (RECORD, BOOLEAN, FLOAT, INTEGER) as defined in</span>
<span class="c1"># https://developers.google.com/resources/api-libraries/documentation/bigquery/v2/java/latest/com/google/api/services/bigquery/model/TableFieldSchema.html#setType-java.lang.String-</span>
<span class="n">BIG_QUERY_TO_PYTHON_TYPES</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;STRING&quot;</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
<span class="s2">&quot;INTEGER&quot;</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span>
<span class="s2">&quot;FLOAT64&quot;</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span>
<span class="s2">&quot;FLOAT&quot;</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span>
<span class="s2">&quot;BOOLEAN&quot;</span><span class="p">:</span> <span class="nb">bool</span><span class="p">,</span>
<span class="s2">&quot;BYTES&quot;</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span>
<span class="s2">&quot;TIMESTAMP&quot;</span><span class="p">:</span> <span class="n">apache_beam</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">timestamp</span><span class="o">.</span><span class="n">Timestamp</span>
<span class="c1">#TODO(https://github.com/apache/beam/issues/20810):</span>
<span class="c1"># Finish mappings for all BQ types</span>
<span class="p">}</span>
<div class="viewcode-block" id="generate_user_type_from_bq_schema"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.generate_user_type_from_bq_schema">[docs]</a><span class="k">def</span> <span class="nf">generate_user_type_from_bq_schema</span><span class="p">(</span><span class="n">the_table_schema</span><span class="p">,</span> <span class="n">selected_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1">#type: (bigquery.TableSchema) -&gt; type</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert a schema of type TableSchema into a pcollection element.</span>
<span class="sd"> Args:</span>
<span class="sd"> the_table_schema: A BQ schema of type TableSchema</span>
<span class="sd"> selected_fields: if not None, the subset of fields to consider</span>
<span class="sd"> Returns:</span>
<span class="sd"> type: type that can be used to work with pCollections.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">the_schema</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">gcp</span><span class="o">.</span><span class="n">bigquery_tools</span><span class="o">.</span><span class="n">get_dict_table_schema</span><span class="p">(</span>
<span class="n">the_table_schema</span><span class="p">)</span>
<span class="k">if</span> <span class="n">the_schema</span> <span class="o">==</span> <span class="p">{}:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Encountered an empty schema&quot;</span><span class="p">)</span>
<span class="n">field_names_and_types</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">the_schema</span><span class="p">[</span><span class="s1">&#39;fields&#39;</span><span class="p">]:</span>
<span class="k">if</span> <span class="n">selected_fields</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">field</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">selected_fields</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="n">field</span><span class="p">[</span><span class="s1">&#39;type&#39;</span><span class="p">]</span> <span class="ow">in</span> <span class="n">BIG_QUERY_TO_PYTHON_TYPES</span><span class="p">:</span>
<span class="n">typ</span> <span class="o">=</span> <span class="n">bq_field_to_type</span><span class="p">(</span><span class="n">field</span><span class="p">[</span><span class="s1">&#39;type&#39;</span><span class="p">],</span> <span class="n">field</span><span class="p">[</span><span class="s1">&#39;mode&#39;</span><span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Encountered &quot;</span>
<span class="sa">f</span><span class="s2">&quot;an unsupported type: </span><span class="si">{</span><span class="n">field</span><span class="p">[</span><span class="s1">&#39;type&#39;</span><span class="p">]</span><span class="si">!r}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="n">field_names_and_types</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">field</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">],</span> <span class="n">typ</span><span class="p">))</span>
<span class="n">sample_schema</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">schemas</span><span class="o">.</span><span class="n">named_fields_to_schema</span><span class="p">(</span>
<span class="n">field_names_and_types</span><span class="p">)</span>
<span class="n">usertype</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">schemas</span><span class="o">.</span><span class="n">named_tuple_from_schema</span><span class="p">(</span><span class="n">sample_schema</span><span class="p">)</span>
<span class="k">return</span> <span class="n">usertype</span></div>
<div class="viewcode-block" id="bq_field_to_type"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.bq_field_to_type">[docs]</a><span class="k">def</span> <span class="nf">bq_field_to_type</span><span class="p">(</span><span class="n">field</span><span class="p">,</span> <span class="n">mode</span><span class="p">):</span>
<span class="k">if</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;NULLABLE&#39;</span> <span class="ow">or</span> <span class="n">mode</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;&#39;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">Optional</span><span class="p">[</span><span class="n">BIG_QUERY_TO_PYTHON_TYPES</span><span class="p">[</span><span class="n">field</span><span class="p">]]</span>
<span class="k">elif</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;REPEATED&#39;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">BIG_QUERY_TO_PYTHON_TYPES</span><span class="p">[</span><span class="n">field</span><span class="p">]]</span>
<span class="k">elif</span> <span class="n">mode</span> <span class="o">==</span> <span class="s1">&#39;REQUIRED&#39;</span><span class="p">:</span>
<span class="k">return</span> <span class="n">BIG_QUERY_TO_PYTHON_TYPES</span><span class="p">[</span><span class="n">field</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Encountered an unsupported mode: </span><span class="si">{</span><span class="n">mode</span><span class="si">!r}</span><span class="s2">&quot;</span><span class="p">)</span></div>
<div class="viewcode-block" id="convert_to_usertype"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.convert_to_usertype">[docs]</a><span class="k">def</span> <span class="nf">convert_to_usertype</span><span class="p">(</span><span class="n">table_schema</span><span class="p">,</span> <span class="n">selected_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">usertype</span> <span class="o">=</span> <span class="n">generate_user_type_from_bq_schema</span><span class="p">(</span><span class="n">table_schema</span><span class="p">,</span> <span class="n">selected_fields</span><span class="p">)</span>
<span class="k">return</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">BeamSchemaConversionDoFn</span><span class="p">(</span><span class="n">usertype</span><span class="p">))</span></div>
<div class="viewcode-block" id="BeamSchemaConversionDoFn"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.BeamSchemaConversionDoFn">[docs]</a><span class="k">class</span> <span class="nc">BeamSchemaConversionDoFn</span><span class="p">(</span><span class="n">DoFn</span><span class="p">):</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll_val_ctor</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pcoll_val_ctor</span> <span class="o">=</span> <span class="n">pcoll_val_ctor</span>
<div class="viewcode-block" id="BeamSchemaConversionDoFn.process"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.BeamSchemaConversionDoFn.process">[docs]</a> <span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dict_of_tuples</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">dict_of_tuples</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="p">):</span>
<span class="n">dict_of_tuples</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">beam</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">timestamp</span><span class="o">.</span><span class="n">Timestamp</span><span class="o">.</span><span class="n">from_utc_datetime</span><span class="p">(</span><span class="n">v</span><span class="p">)</span>
<span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pcoll_val_ctor</span><span class="p">(</span><span class="o">**</span><span class="n">dict_of_tuples</span><span class="p">)</span></div>
<div class="viewcode-block" id="BeamSchemaConversionDoFn.infer_output_type"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_schema_tools.html#apache_beam.io.gcp.bigquery_schema_tools.BeamSchemaConversionDoFn.infer_output_type">[docs]</a> <span class="k">def</span> <span class="nf">infer_output_type</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_type</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pcoll_val_ctor</span></div>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_from_serialized_schema</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">schema_str</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">cls</span><span class="p">(</span>
<span class="n">apache_beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">schemas</span><span class="o">.</span><span class="n">named_tuple_from_schema</span><span class="p">(</span>
<span class="n">apache_beam</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">proto_utils</span><span class="o">.</span><span class="n">parse_Bytes</span><span class="p">(</span>
<span class="n">schema_str</span><span class="p">,</span> <span class="n">schema_pb2</span><span class="o">.</span><span class="n">Schema</span><span class="p">)))</span>
<span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># when pickling, use bytes representation of the schema.</span>
<span class="k">return</span> <span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_from_serialized_schema</span><span class="p">,</span>
<span class="p">(</span>
<span class="n">beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">schemas</span><span class="o">.</span><span class="n">named_tuple_to_schema</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pcoll_val_ctor</span><span class="p">)</span><span class="o">.</span><span class="n">SerializeToString</span><span class="p">(),</span> <span class="p">))</span></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>