blob: 6032231063984caaa8cc4c6296fa7ce04dcd326d [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_avro_tools &mdash; Apache Beam 2.47.0 documentation</title>
<script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../../genindex.html" />
<link rel="search" title="Search" href="../../../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div class="version">
2.47.0
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.io.gcp.bigquery_avro_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_avro_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 Avro files 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="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_AVRO_TYPES</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;STRUCT&quot;</span><span class="p">:</span> <span class="s2">&quot;record&quot;</span><span class="p">,</span>
<span class="s2">&quot;RECORD&quot;</span><span class="p">:</span> <span class="s2">&quot;record&quot;</span><span class="p">,</span>
<span class="s2">&quot;STRING&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;BOOL&quot;</span><span class="p">:</span> <span class="s2">&quot;boolean&quot;</span><span class="p">,</span>
<span class="s2">&quot;BOOLEAN&quot;</span><span class="p">:</span> <span class="s2">&quot;boolean&quot;</span><span class="p">,</span>
<span class="s2">&quot;BYTES&quot;</span><span class="p">:</span> <span class="s2">&quot;bytes&quot;</span><span class="p">,</span>
<span class="s2">&quot;FLOAT64&quot;</span><span class="p">:</span> <span class="s2">&quot;double&quot;</span><span class="p">,</span>
<span class="s2">&quot;FLOAT&quot;</span><span class="p">:</span> <span class="s2">&quot;double&quot;</span><span class="p">,</span>
<span class="s2">&quot;INT64&quot;</span><span class="p">:</span> <span class="s2">&quot;long&quot;</span><span class="p">,</span>
<span class="s2">&quot;INTEGER&quot;</span><span class="p">:</span> <span class="s2">&quot;long&quot;</span><span class="p">,</span>
<span class="s2">&quot;TIME&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;long&quot;</span><span class="p">,</span>
<span class="s2">&quot;logicalType&quot;</span><span class="p">:</span> <span class="s2">&quot;time-micros&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;TIMESTAMP&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;long&quot;</span><span class="p">,</span>
<span class="s2">&quot;logicalType&quot;</span><span class="p">:</span> <span class="s2">&quot;timestamp-micros&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;DATE&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;int&quot;</span><span class="p">,</span>
<span class="s2">&quot;logicalType&quot;</span><span class="p">:</span> <span class="s2">&quot;date&quot;</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;DATETIME&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="s2">&quot;NUMERIC&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;bytes&quot;</span><span class="p">,</span>
<span class="s2">&quot;logicalType&quot;</span><span class="p">:</span> <span class="s2">&quot;decimal&quot;</span><span class="p">,</span>
<span class="c1"># https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#numeric-type</span>
<span class="s2">&quot;precision&quot;</span><span class="p">:</span> <span class="mi">38</span><span class="p">,</span>
<span class="s2">&quot;scale&quot;</span><span class="p">:</span> <span class="mi">9</span><span class="p">,</span>
<span class="p">},</span>
<span class="s2">&quot;GEOGRAPHY&quot;</span><span class="p">:</span> <span class="s2">&quot;string&quot;</span><span class="p">,</span>
<span class="p">}</span>
<div class="viewcode-block" id="get_record_schema_from_dict_table_schema"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_avro_tools.html#apache_beam.io.gcp.bigquery_avro_tools.get_record_schema_from_dict_table_schema">[docs]</a><span class="k">def</span> <span class="nf">get_record_schema_from_dict_table_schema</span><span class="p">(</span>
<span class="n">schema_name</span><span class="p">,</span> <span class="n">table_schema</span><span class="p">,</span> <span class="n">namespace</span><span class="o">=</span><span class="s2">&quot;apache_beam.io.gcp.bigquery&quot;</span><span class="p">):</span>
<span class="c1"># type: (Text, Dict[Text, Any], Text) -&gt; Dict[Text, Any] # noqa: F821</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert a table schema into an Avro schema.</span>
<span class="sd"> Args:</span>
<span class="sd"> schema_name (Text): The name of the record.</span>
<span class="sd"> table_schema (Dict[Text, Any]): A BigQuery table schema in dict form.</span>
<span class="sd"> namespace (Text): The namespace of the Avro schema.</span>
<span class="sd"> Returns:</span>
<span class="sd"> Dict[Text, Any]: The schema as an Avro RecordSchema.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">avro_fields</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">table_field_to_avro_field</span><span class="p">(</span><span class="n">field</span><span class="p">,</span> <span class="s2">&quot;.&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">((</span><span class="n">namespace</span><span class="p">,</span> <span class="n">schema_name</span><span class="p">)))</span>
<span class="k">for</span> <span class="n">field</span> <span class="ow">in</span> <span class="n">table_schema</span><span class="p">[</span><span class="s2">&quot;fields&quot;</span><span class="p">]</span>
<span class="p">]</span>
<span class="k">return</span> <span class="p">{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;record&quot;</span><span class="p">,</span>
<span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="n">schema_name</span><span class="p">,</span>
<span class="s2">&quot;fields&quot;</span><span class="p">:</span> <span class="n">avro_fields</span><span class="p">,</span>
<span class="s2">&quot;doc&quot;</span><span class="p">:</span> <span class="s2">&quot;Translated Avro Schema for </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">schema_name</span><span class="p">),</span>
<span class="s2">&quot;namespace&quot;</span><span class="p">:</span> <span class="n">namespace</span><span class="p">,</span>
<span class="p">}</span></div>
<div class="viewcode-block" id="table_field_to_avro_field"><a class="viewcode-back" href="../../../../apache_beam.io.gcp.bigquery_avro_tools.html#apache_beam.io.gcp.bigquery_avro_tools.table_field_to_avro_field">[docs]</a><span class="k">def</span> <span class="nf">table_field_to_avro_field</span><span class="p">(</span><span class="n">table_field</span><span class="p">,</span> <span class="n">namespace</span><span class="p">):</span>
<span class="c1"># type: (Dict[Text, Any], str) -&gt; Dict[Text, Any] # noqa: F821</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert a BigQuery field to an avro field.</span>
<span class="sd"> Args:</span>
<span class="sd"> table_field (Dict[Text, Any]): A BigQuery field in dict form.</span>
<span class="sd"> Returns:</span>
<span class="sd"> Dict[Text, Any]: An equivalent Avro field in dict form.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="s2">&quot;type&quot;</span> <span class="ow">in</span> <span class="n">table_field</span><span class="p">,</span> \
<span class="s2">&quot;Unable to get type for table field </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">table_field</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;type&quot;</span><span class="p">]</span> <span class="ow">in</span> <span class="n">BIG_QUERY_TO_AVRO_TYPES</span><span class="p">,</span> \
<span class="s2">&quot;Unable to map BigQuery field type </span><span class="si">{}</span><span class="s2"> to avro type&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;type&quot;</span><span class="p">])</span>
<span class="n">avro_type</span> <span class="o">=</span> <span class="n">BIG_QUERY_TO_AVRO_TYPES</span><span class="p">[</span><span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;type&quot;</span><span class="p">]]</span>
<span class="k">if</span> <span class="n">avro_type</span> <span class="o">==</span> <span class="s2">&quot;record&quot;</span><span class="p">:</span>
<span class="n">element_type</span> <span class="o">=</span> <span class="n">get_record_schema_from_dict_table_schema</span><span class="p">(</span>
<span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;name&quot;</span><span class="p">],</span>
<span class="n">table_field</span><span class="p">,</span>
<span class="n">namespace</span><span class="o">=</span><span class="s2">&quot;.&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">((</span><span class="n">namespace</span><span class="p">,</span> <span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;name&quot;</span><span class="p">])))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">element_type</span> <span class="o">=</span> <span class="n">avro_type</span>
<span class="n">field_mode</span> <span class="o">=</span> <span class="n">table_field</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;mode&quot;</span><span class="p">,</span> <span class="s2">&quot;NULLABLE&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">field_mode</span> <span class="ow">in</span> <span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="s2">&quot;NULLABLE&quot;</span><span class="p">):</span>
<span class="n">field_type</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;null&quot;</span><span class="p">,</span> <span class="n">element_type</span><span class="p">]</span>
<span class="k">elif</span> <span class="n">field_mode</span> <span class="o">==</span> <span class="s2">&quot;REQUIRED&quot;</span><span class="p">:</span>
<span class="n">field_type</span> <span class="o">=</span> <span class="n">element_type</span>
<span class="k">elif</span> <span class="n">field_mode</span> <span class="o">==</span> <span class="s2">&quot;REPEATED&quot;</span><span class="p">:</span>
<span class="n">field_type</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s2">&quot;array&quot;</span><span class="p">,</span> <span class="s2">&quot;items&quot;</span><span class="p">:</span> <span class="n">element_type</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="s2">&quot;Unkown BigQuery field mode: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">field_mode</span><span class="p">))</span>
<span class="n">avro_field</span> <span class="o">=</span> <span class="p">{</span><span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="n">field_type</span><span class="p">,</span> <span class="s2">&quot;name&quot;</span><span class="p">:</span> <span class="n">table_field</span><span class="p">[</span><span class="s2">&quot;name&quot;</span><span class="p">]}</span>
<span class="n">doc</span> <span class="o">=</span> <span class="n">table_field</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;description&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">doc</span><span class="p">:</span>
<span class="n">avro_field</span><span class="p">[</span><span class="s2">&quot;doc&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">doc</span>
<span class="k">return</span> <span class="n">avro_field</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>