blob: ffabf312d3e2c52a4c131abd1c9e6353d59344ed [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.transforms.enrichment_handlers.bigquery module &mdash; Apache Beam 2.57.0 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" />
<link rel="next" title="apache_beam.transforms.enrichment_handlers.bigtable module" href="apache_beam.transforms.enrichment_handlers.bigtable.html" />
<link rel="prev" title="apache_beam.transforms.enrichment_handlers package" href="apache_beam.transforms.enrichment_handlers.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">
2.57.0
</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 class="current">
<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 current"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a><ul class="current">
<li class="toctree-l2 current"><a class="reference internal" href="apache_beam.transforms.html#subpackages">Subpackages</a><ul class="current">
<li class="toctree-l3 current"><a class="reference internal" href="apache_beam.transforms.enrichment_handlers.html">apache_beam.transforms.enrichment_handlers package</a><ul class="current">
<li class="toctree-l4 current"><a class="reference internal" href="apache_beam.transforms.enrichment_handlers.html#submodules">Submodules</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.xlang.html">apache_beam.transforms.xlang package</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="apache_beam.transforms.html#submodules">Submodules</a></li>
</ul>
</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="apache_beam.transforms.html">apache_beam.transforms package</a> &raquo;</li>
<li><a href="apache_beam.transforms.enrichment_handlers.html">apache_beam.transforms.enrichment_handlers package</a> &raquo;</li>
<li>apache_beam.transforms.enrichment_handlers.bigquery module</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/apache_beam.transforms.enrichment_handlers.bigquery.rst.txt" rel="nofollow"> View page source</a>
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="module-apache_beam.transforms.enrichment_handlers.bigquery">
<span id="apache-beam-transforms-enrichment-handlers-bigquery-module"></span><h1>apache_beam.transforms.enrichment_handlers.bigquery module<a class="headerlink" href="#module-apache_beam.transforms.enrichment_handlers.bigquery" title="Permalink to this headline"></a></h1>
<dl class="class">
<dt id="apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler">
<em class="property">class </em><code class="descclassname">apache_beam.transforms.enrichment_handlers.bigquery.</code><code class="descname">BigQueryEnrichmentHandler</code><span class="sig-paren">(</span><em>project: str, *, table_name: str = '', row_restriction_template: str = '', fields: Optional[List[str]] = None, column_names: Optional[List[str]] = None, condition_value_fn: Optional[Callable[[apache_beam.pvalue.Row], List[Any]]] = None, query_fn: Optional[Callable[[apache_beam.pvalue.Row], str]] = None, min_batch_size: int = 1, max_batch_size: int = 10000, **kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/enrichment_handlers/bigquery.html#BigQueryEnrichmentHandler"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.enrichment.html#apache_beam.transforms.enrichment.EnrichmentSourceHandler" title="apache_beam.transforms.enrichment.EnrichmentSourceHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.enrichment.EnrichmentSourceHandler</span></code></a></p>
<p>Enrichment handler for Google Cloud BigQuery.</p>
<p>Use this handler with <a class="reference internal" href="apache_beam.transforms.enrichment.html#apache_beam.transforms.enrichment.Enrichment" title="apache_beam.transforms.enrichment.Enrichment"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.enrichment.Enrichment</span></code></a>
transform.</p>
<dl class="docutils">
<dt>To use this handler you need either of the following combinations:</dt>
<dd><ul class="first last simple">
<li><cite>table_name</cite>, <cite>row_restriction_template</cite>, <cite>fields</cite></li>
<li><cite>table_name</cite>, <cite>row_restriction_template</cite>, <cite>condition_value_fn</cite></li>
<li><cite>query_fn</cite></li>
</ul>
</dd>
</dl>
<p>By default, the handler pulls all columns from the BigQuery table.
To override this, use the <cite>column_name</cite> parameter to specify a list of column
names to fetch.</p>
<p>This handler pulls data from BigQuery per element by default. To change this
behavior, set the <cite>min_batch_size</cite> and <cite>max_batch_size</cite> parameters.
These min and max values for batch size are sent to the
<code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.utils.BatchElements</span></code> transform.</p>
<p>NOTE: Elements cannot be batched when using the <cite>query_fn</cite> parameter.</p>
<dl class="docutils">
<dt>Example Usage:</dt>
<dd><dl class="first last docutils">
<dt>handler = BigQueryEnrichmentHandler(project=project_name,</dt>
<dd>row_restriction=”id=’{}’”,
table_name=’project.dataset.table’,
fields=fields,
min_batch_size=2,
max_batch_size=100)</dd>
</dl>
</dd>
</dl>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple">
<li><strong>project</strong> – Google Cloud project ID for the BigQuery table.</li>
<li><strong>table_name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><em>str</em></a>) – Fully qualified BigQuery table name
in the format <cite>project.dataset.table</cite>.</li>
<li><strong>row_restriction_template</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.12)"><em>str</em></a>) – A template string for the <cite>WHERE</cite> clause
in the BigQuery query with placeholders (<cite>{}</cite>) to dynamically filter
rows based on input data.</li>
<li><strong>fields</strong> – (Optional[List[str]]) List of field names present in the input
<cite>beam.Row</cite>. These are used to construct the WHERE clause
(if <cite>condition_value_fn</cite> is not provided).</li>
<li><strong>column_names</strong> – (Optional[List[str]]) Names of columns to select from the
BigQuery table. If not provided, all columns (<cite>*</cite>) are selected.</li>
<li><strong>condition_value_fn</strong> – (Optional[Callable[[beam.Row], Any]]) A function
that takes a <cite>beam.Row</cite> and returns a list of value to populate in the
placeholder <cite>{}</cite> of <cite>WHERE</cite> clause in the query.</li>
<li><strong>query_fn</strong> – (Optional[Callable[[beam.Row], str]]) A function that takes a
<cite>beam.Row</cite> and returns a complete BigQuery SQL query string.</li>
<li><strong>min_batch_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Minimum number of rows to batch together when
querying BigQuery. Defaults to 1 if <cite>query_fn</cite> is not specified.</li>
<li><strong>max_batch_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.12)"><em>int</em></a>) – Maximum number of rows to batch together.
Defaults to 10,000 if <cite>query_fn</cite> is not specified.</li>
<li><strong>**kwargs</strong> – Additional keyword arguments to pass to <cite>bigquery.Client</cite>.</li>
</ul>
</td>
</tr>
</tbody>
</table>
<div class="admonition note">
<p class="first admonition-title">Note</p>
<ul class="last simple">
<li><cite>min_batch_size</cite> and <cite>max_batch_size</cite> cannot be defined if the
<cite>query_fn</cite> is provided.</li>
<li>Either <cite>fields</cite> or <cite>condition_value_fn</cite> must be provided for query
construction if <cite>query_fn</cite> is not provided.</li>
<li>Ensure appropriate permissions are granted for BigQuery access.</li>
</ul>
</div>
<dl class="method">
<dt id="apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler.get_cache_key">
<code class="descname">get_cache_key</code><span class="sig-paren">(</span><em>request: Union[apache_beam.pvalue.Row, List[apache_beam.pvalue.Row]]</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/enrichment_handlers/bigquery.html#BigQueryEnrichmentHandler.get_cache_key"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler.get_cache_key" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler.batch_elements_kwargs">
<code class="descname">batch_elements_kwargs</code><span class="sig-paren">(</span><span class="sig-paren">)</span> &#x2192; Mapping[str, Any]<a class="reference internal" href="_modules/apache_beam/transforms/enrichment_handlers/bigquery.html#BigQueryEnrichmentHandler.batch_elements_kwargs"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.transforms.enrichment_handlers.bigquery.BigQueryEnrichmentHandler.batch_elements_kwargs" title="Permalink to this definition"></a></dt>
<dd><p>Returns a kwargs suitable for <cite>beam.BatchElements</cite>.</p>
</dd></dl>
</dd></dl>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="apache_beam.transforms.enrichment_handlers.bigtable.html" class="btn btn-neutral float-right" title="apache_beam.transforms.enrichment_handlers.bigtable module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="apache_beam.transforms.enrichment_handlers.html" class="btn btn-neutral float-left" title="apache_beam.transforms.enrichment_handlers package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<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>