blob: dc6568608c11677c9038a689c57591e2b3aa98e4 [file] [log] [blame]
<!DOCTYPE html>
<html lang="en" data-content_root="./">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Avro &#8212; Apache Arrow Java Cookbook documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=d1102ebc" />
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=49eeb2a1" />
<script src="_static/documentation_options.js?v=5929fcd5"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="icon" href="_static/favicon.ico"/>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="Arrow JDBC Adapter" href="jdbc.html" />
<link rel="prev" title="Data manipulation" href="data.html" />
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
<!-- Matomo -->
<script>
var _paq = window._paq = window._paq || [];
/* tracker methods like "setCustomDimension" should be called before "trackPageView" */
/* We explicitly disable cookie tracking to avoid privacy issues */
_paq.push(['disableCookies']);
_paq.push(['trackPageView']);
_paq.push(['enableLinkTracking']);
(function() {
var u="https://analytics.apache.org/";
_paq.push(['setTrackerUrl', u+'matomo.php']);
_paq.push(['setSiteId', '20']);
var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
})();
</script>
<!-- End Matomo Code -->
</head><body>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<section id="avro">
<span id="arrow-avro"></span><h1><a class="toc-backref" href="#id1" role="doc-backlink">Avro</a><a class="headerlink" href="#avro" title="Link to this heading"></a></h1>
<p>Avro encoded data can be converted into Arrow format.</p>
<nav class="contents" id="contents">
<p class="topic-title">Contents</p>
<ul class="simple">
<li><p><a class="reference internal" href="#avro" id="id1">Avro</a></p>
<ul>
<li><p><a class="reference internal" href="#avro-to-arrow" id="id2">Avro to Arrow</a></p></li>
</ul>
</li>
</ul>
</nav>
<section id="avro-to-arrow">
<h2><a class="toc-backref" href="#id2" role="doc-backlink">Avro to Arrow</a><a class="headerlink" href="#avro-to-arrow" title="Link to this heading"></a></h2>
<p>The example assumes that the Avro schema is stored separately from the Avro data itself.</p>
<div class="highlight-java notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.adapter.avro.AvroToArrow</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.adapter.avro.AvroToArrowConfig</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.adapter.avro.AvroToArrowConfigBuilder</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.adapter.avro.AvroToArrowVectorIterator</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.memory.BufferAllocator</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.memory.RootAllocator</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.vector.VectorSchemaRoot</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.avro.Schema</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.avro.io.BinaryDecoder</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.avro.io.DecoderFactory</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.io.File</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.io.FileInputStream</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.io.FileNotFoundException</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.io.IOException</span><span class="p">;</span>
<span class="k">try</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">BinaryDecoder</span><span class="w"> </span><span class="n">decoder</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="k">new</span><span class="w"> </span><span class="n">DecoderFactory</span><span class="p">().</span><span class="na">binaryDecoder</span><span class="p">(</span><span class="k">new</span><span class="w"> </span><span class="n">FileInputStream</span><span class="p">(</span><span class="s">&quot;./thirdpartydeps/avro/users.avro&quot;</span><span class="p">),</span><span class="w"> </span><span class="kc">null</span><span class="p">);</span>
<span class="w"> </span><span class="n">Schema</span><span class="w"> </span><span class="n">schema</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="k">new</span><span class="w"> </span><span class="n">Schema</span><span class="p">.</span><span class="na">Parser</span><span class="p">().</span><span class="na">parse</span><span class="p">(</span><span class="k">new</span><span class="w"> </span><span class="n">File</span><span class="p">(</span><span class="s">&quot;./thirdpartydeps/avro/user.avsc&quot;</span><span class="p">));</span>
<span class="w"> </span><span class="k">try</span><span class="w"> </span><span class="p">(</span><span class="n">BufferAllocator</span><span class="w"> </span><span class="n">allocator</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="k">new</span><span class="w"> </span><span class="n">RootAllocator</span><span class="p">())</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">AvroToArrowConfig</span><span class="w"> </span><span class="n">config</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="k">new</span><span class="w"> </span><span class="n">AvroToArrowConfigBuilder</span><span class="p">(</span><span class="n">allocator</span><span class="p">).</span><span class="na">build</span><span class="p">();</span>
<span class="w"> </span><span class="k">try</span><span class="w"> </span><span class="p">(</span><span class="n">AvroToArrowVectorIterator</span><span class="w"> </span><span class="n">avroToArrowVectorIterator</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">AvroToArrow</span><span class="p">.</span><span class="na">avroToArrowIterator</span><span class="p">(</span><span class="n">schema</span><span class="p">,</span><span class="w"> </span><span class="n">decoder</span><span class="p">,</span><span class="w"> </span><span class="n">config</span><span class="p">))</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">while</span><span class="p">(</span><span class="n">avroToArrowVectorIterator</span><span class="p">.</span><span class="na">hasNext</span><span class="p">())</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">try</span><span class="w"> </span><span class="p">(</span><span class="n">VectorSchemaRoot</span><span class="w"> </span><span class="n">root</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">avroToArrowVectorIterator</span><span class="p">.</span><span class="na">next</span><span class="p">())</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">System</span><span class="p">.</span><span class="na">out</span><span class="p">.</span><span class="na">print</span><span class="p">(</span><span class="n">root</span><span class="p">.</span><span class="na">contentToTSVString</span><span class="p">());</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">}</span>
<span class="p">}</span><span class="w"> </span><span class="k">catch</span><span class="w"> </span><span class="p">(</span><span class="n">Exception</span><span class="w"> </span><span class="n">e</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">e</span><span class="p">.</span><span class="na">printStackTrace</span><span class="p">();</span>
<span class="p">}</span>
</pre></div>
</div>
<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>name favorite_number favorite_color
Alyssa 256 null
Ben 7 red
</pre></div>
</div>
</section>
</section>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo">
<a href="index.html">
<img class="logo" src="_static/arrow-logo_vertical_black-txt_transparent-bg.svg" alt="Logo" />
</a>
</p>
<p>
<iframe src="https://ghbtns.com/github-btn.html?user=apache&repo=arrow-cookbook&type=none&count=true&size=large&v=2"
allowtransparency="true" frameborder="0" scrolling="0" width="200px" height="35px"></iframe>
</p>
<h3>Navigation</h3>
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="create.html">Creating Arrow Objects</a></li>
<li class="toctree-l1"><a class="reference internal" href="schema.html">Working with Schema</a></li>
<li class="toctree-l1"><a class="reference internal" href="io.html">Reading and writing data</a></li>
<li class="toctree-l1"><a class="reference internal" href="flight.html">Arrow Flight</a></li>
<li class="toctree-l1"><a class="reference internal" href="dataset.html">Dataset</a></li>
<li class="toctree-l1"><a class="reference internal" href="substrait.html">Substrait</a></li>
<li class="toctree-l1"><a class="reference internal" href="data.html">Data manipulation</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Avro</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#avro-to-arrow">Avro to Arrow</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="jdbc.html">Arrow JDBC Adapter</a></li>
</ul>
<hr />
<ul>
<li class="toctree-l1"><a href="https://arrow.apache.org/docs/java/index.html">User Guide</a></li>
<li class="toctree-l1"><a href="https://arrow.apache.org/docs/java/reference/index.html">API Reference</a></li>
</ul>
<div class="relations">
<h3>Related Topics</h3>
<ul>
<li><a href="index.html">Documentation overview</a><ul>
<li>Previous: <a href="data.html" title="previous chapter">Data manipulation</a></li>
<li>Next: <a href="jdbc.html" title="next chapter">Arrow JDBC Adapter</a></li>
</ul></li>
</ul>
</div>
<div id="searchbox" style="display: none" role="search">
<h3 id="searchlabel">Quick search</h3>
<div class="searchformwrapper">
<form class="search" action="search.html" method="get">
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="Go" />
</form>
</div>
</div>
<script>document.getElementById('searchbox').style.display = "block"</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer">
&#169;2022, Apache Software Foundation.
|
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 7.2.6</a>
&amp; <a href="https://alabaster.readthedocs.io">Alabaster 0.7.16</a>
|
<a href="_sources/avro.rst.txt"
rel="nofollow">Page source</a>
</div>
</body>
</html>