blob: 4eb101168d3c9337192f9977bc03c468877f4bf4 [file] [log] [blame]
<!doctype html>
<html class="no-js" lang="en" data-content_root="./">
<head><meta charset="utf-8"/>
<meta name="viewport" content="width=device-width,initial-scale=1"/>
<meta name="color-scheme" content="light dark"><meta name="viewport" content="width=device-width, initial-scale=1" />
<link rel="index" title="Index" href="genindex.html" /><link rel="search" title="Search" href="search.html" /><link rel="next" title="C Data Interface" href="cdata.html" /><link rel="prev" title="Dataset" href="dataset.html" />
<!-- Generated with Sphinx 8.1.3 and Furo 2024.08.06 -->
<title>Substrait - arrow-java 18.1.0 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="_static/styles/furo.css?v=354aac6f" />
<link rel="stylesheet" type="text/css" href="_static/styles/furo-extensions.css?v=302659d7" />
<style>
body {
--color-code-background: #f8f8f8;
--color-code-foreground: black;
}
@media not print {
body[data-theme="dark"] {
--color-code-background: #202020;
--color-code-foreground: #d0d0d0;
}
@media (prefers-color-scheme: dark) {
body:not([data-theme="light"]) {
--color-code-background: #202020;
--color-code-foreground: #d0d0d0;
}
}
}
</style></head>
<body>
<script>
document.body.dataset.theme = localStorage.getItem("theme") || "auto";
</script>
<svg xmlns="http://www.w3.org/2000/svg" style="display: none;">
<symbol id="svg-toc" viewBox="0 0 24 24">
<title>Contents</title>
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 1024 1024">
<path d="M408 442h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8zm-8 204c0 4.4 3.6 8 8 8h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56zm504-486H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zm0 632H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zM115.4 518.9L271.7 642c5.8 4.6 14.4.5 14.4-6.9V388.9c0-7.4-8.5-11.5-14.4-6.9L115.4 505.1a8.74 8.74 0 0 0 0 13.8z"/>
</svg>
</symbol>
<symbol id="svg-menu" viewBox="0 0 24 24">
<title>Menu</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-menu">
<line x1="3" y1="12" x2="21" y2="12"></line>
<line x1="3" y1="6" x2="21" y2="6"></line>
<line x1="3" y1="18" x2="21" y2="18"></line>
</svg>
</symbol>
<symbol id="svg-arrow-right" viewBox="0 0 24 24">
<title>Expand</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-chevron-right">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
</symbol>
<symbol id="svg-sun" viewBox="0 0 24 24">
<title>Light mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="feather-sun">
<circle cx="12" cy="12" r="5"></circle>
<line x1="12" y1="1" x2="12" y2="3"></line>
<line x1="12" y1="21" x2="12" y2="23"></line>
<line x1="4.22" y1="4.22" x2="5.64" y2="5.64"></line>
<line x1="18.36" y1="18.36" x2="19.78" y2="19.78"></line>
<line x1="1" y1="12" x2="3" y2="12"></line>
<line x1="21" y1="12" x2="23" y2="12"></line>
<line x1="4.22" y1="19.78" x2="5.64" y2="18.36"></line>
<line x1="18.36" y1="5.64" x2="19.78" y2="4.22"></line>
</svg>
</symbol>
<symbol id="svg-moon" viewBox="0 0 24 24">
<title>Dark mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-moon">
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
<path d="M12 3c.132 0 .263 0 .393 0a7.5 7.5 0 0 0 7.92 12.446a9 9 0 1 1 -8.313 -12.454z" />
</svg>
</symbol>
<symbol id="svg-sun-with-moon" viewBox="0 0 24 24">
<title>Auto light/dark, in light mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round"
class="icon-custom-derived-from-feather-sun-and-tabler-moon">
<path style="opacity: 50%" d="M 5.411 14.504 C 5.471 14.504 5.532 14.504 5.591 14.504 C 3.639 16.319 4.383 19.569 6.931 20.352 C 7.693 20.586 8.512 20.551 9.25 20.252 C 8.023 23.207 4.056 23.725 2.11 21.184 C 0.166 18.642 1.702 14.949 4.874 14.536 C 5.051 14.512 5.231 14.5 5.411 14.5 L 5.411 14.504 Z"/>
<line x1="14.5" y1="3.25" x2="14.5" y2="1.25"/>
<line x1="14.5" y1="15.85" x2="14.5" y2="17.85"/>
<line x1="10.044" y1="5.094" x2="8.63" y2="3.68"/>
<line x1="19" y1="14.05" x2="20.414" y2="15.464"/>
<line x1="8.2" y1="9.55" x2="6.2" y2="9.55"/>
<line x1="20.8" y1="9.55" x2="22.8" y2="9.55"/>
<line x1="10.044" y1="14.006" x2="8.63" y2="15.42"/>
<line x1="19" y1="5.05" x2="20.414" y2="3.636"/>
<circle cx="14.5" cy="9.55" r="3.6"/>
</svg>
</symbol>
<symbol id="svg-moon-with-sun" viewBox="0 0 24 24">
<title>Auto light/dark, in dark mode</title>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round"
class="icon-custom-derived-from-feather-sun-and-tabler-moon">
<path d="M 8.282 7.007 C 8.385 7.007 8.494 7.007 8.595 7.007 C 5.18 10.184 6.481 15.869 10.942 17.24 C 12.275 17.648 13.706 17.589 15 17.066 C 12.851 22.236 5.91 23.143 2.505 18.696 C -0.897 14.249 1.791 7.786 7.342 7.063 C 7.652 7.021 7.965 7 8.282 7 L 8.282 7.007 Z"/>
<line style="opacity: 50%" x1="18" y1="3.705" x2="18" y2="2.5"/>
<line style="opacity: 50%" x1="18" y1="11.295" x2="18" y2="12.5"/>
<line style="opacity: 50%" x1="15.316" y1="4.816" x2="14.464" y2="3.964"/>
<line style="opacity: 50%" x1="20.711" y1="10.212" x2="21.563" y2="11.063"/>
<line style="opacity: 50%" x1="14.205" y1="7.5" x2="13.001" y2="7.5"/>
<line style="opacity: 50%" x1="21.795" y1="7.5" x2="23" y2="7.5"/>
<line style="opacity: 50%" x1="15.316" y1="10.184" x2="14.464" y2="11.036"/>
<line style="opacity: 50%" x1="20.711" y1="4.789" x2="21.563" y2="3.937"/>
<circle style="opacity: 50%" cx="18" cy="7.5" r="2.169"/>
</svg>
</symbol>
<symbol id="svg-pencil" viewBox="0 0 24 24">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-pencil-code">
<path d="M4 20h4l10.5 -10.5a2.828 2.828 0 1 0 -4 -4l-10.5 10.5v4" />
<path d="M13.5 6.5l4 4" />
<path d="M20 21l2 -2l-2 -2" />
<path d="M17 17l-2 2l2 2" />
</svg>
</symbol>
<symbol id="svg-eye" viewBox="0 0 24 24">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-eye-code">
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
<path d="M10 12a2 2 0 1 0 4 0a2 2 0 0 0 -4 0" />
<path
d="M11.11 17.958c-3.209 -.307 -5.91 -2.293 -8.11 -5.958c2.4 -4 5.4 -6 9 -6c3.6 0 6.6 2 9 6c-.21 .352 -.427 .688 -.647 1.008" />
<path d="M20 21l2 -2l-2 -2" />
<path d="M17 17l-2 2l2 2" />
</svg>
</symbol>
</svg>
<input type="checkbox" class="sidebar-toggle" name="__navigation" id="__navigation">
<input type="checkbox" class="sidebar-toggle" name="__toc" id="__toc">
<label class="overlay sidebar-overlay" for="__navigation">
<div class="visually-hidden">Hide navigation sidebar</div>
</label>
<label class="overlay toc-overlay" for="__toc">
<div class="visually-hidden">Hide table of contents sidebar</div>
</label>
<a class="skip-to-content muted-link" href="#furo-main-content">Skip to content</a>
<div class="page">
<header class="mobile-header">
<div class="header-left">
<label class="nav-overlay-icon" for="__navigation">
<div class="visually-hidden">Toggle site navigation sidebar</div>
<i class="icon"><svg><use href="#svg-menu"></use></svg></i>
</label>
</div>
<div class="header-center">
<a href="index.html"><div class="brand">arrow-java 18.1.0 documentation</div></a>
</div>
<div class="header-right">
<div class="theme-toggle-container theme-toggle-header">
<button class="theme-toggle">
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
<svg class="theme-icon-when-auto-light"><use href="#svg-sun-with-moon"></use></svg>
<svg class="theme-icon-when-auto-dark"><use href="#svg-moon-with-sun"></use></svg>
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
</button>
</div>
<label class="toc-overlay-icon toc-header-icon" for="__toc">
<div class="visually-hidden">Toggle table of contents sidebar</div>
<i class="icon"><svg><use href="#svg-toc"></use></svg></i>
</label>
</div>
</header>
<aside class="sidebar-drawer">
<div class="sidebar-container">
<div class="sidebar-sticky"><a class="sidebar-brand" href="index.html">
<span class="sidebar-brand-text">arrow-java 18.1.0 documentation</span>
</a><form class="sidebar-search-container" method="get" action="search.html" role="search">
<input class="sidebar-search" placeholder="Search" name="q" aria-label="Search">
<input type="hidden" name="check_keywords" value="yes">
<input type="hidden" name="area" value="default">
</form>
<div id="searchbox"></div><div class="sidebar-scroll"><div class="sidebar-tree">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="quickstartguide.html">Quick Start Guide</a></li>
<li class="toctree-l1"><a class="reference internal" href="overview.html">High-Level Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="install.html">Installing Java Modules</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="developers/index.html">Java Development</a><input class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" role="switch" type="checkbox"/><label for="toctree-checkbox-1"><div class="visually-hidden">Toggle navigation of Java Development</div><i class="icon"><svg><use href="#svg-arrow-right"></use></svg></i></label><ul>
<li class="toctree-l2"><a class="reference internal" href="developers/building.html">Building Arrow Java</a></li>
<li class="toctree-l2"><a class="reference internal" href="developers/development.html">Development Guidelines</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="memory.html">Memory Management</a></li>
<li class="toctree-l1"><a class="reference internal" href="vector.html">ValueVector</a></li>
<li class="toctree-l1"><a class="reference internal" href="vector_schema_root.html">Tabular Data</a></li>
<li class="toctree-l1"><a class="reference internal" href="table.html">Table</a></li>
<li class="toctree-l1"><a class="reference internal" href="ipc.html">Reading/Writing IPC formats</a></li>
<li class="toctree-l1"><a class="reference internal" href="algorithm.html">Java Algorithms</a></li>
<li class="toctree-l1"><a class="reference internal" href="flight.html">Arrow Flight RPC</a></li>
<li class="toctree-l1"><a class="reference internal" href="flight_sql.html">Arrow Flight SQL</a></li>
<li class="toctree-l1"><a class="reference internal" href="flight_sql_jdbc_driver.html">Arrow Flight SQL JDBC Driver</a></li>
<li class="toctree-l1"><a class="reference internal" href="dataset.html">Dataset</a></li>
<li class="toctree-l1 current current-page"><a class="current reference internal" href="#">Substrait</a></li>
<li class="toctree-l1"><a class="reference internal" href="cdata.html">C Data Interface</a></li>
<li class="toctree-l1"><a class="reference internal" href="jdbc.html">Arrow JDBC Adapter</a></li>
<li class="toctree-l1"><a class="reference internal" href="reference/index.html">Reference (javadoc)</a></li>
<li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/cookbook/java/">Cookbook</a></li>
</ul>
</div>
</div>
</div>
</div>
</aside>
<div class="main">
<div class="content">
<div class="article-container">
<a href="#" class="back-to-top muted-link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
<path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8v12z"></path>
</svg>
<span>Back to top</span>
</a>
<div class="content-icon-container">
<div class="view-this-page">
<a class="muted-link" href="_sources/substrait.rst.txt" title="View this page">
<svg><use href="#svg-eye"></use></svg>
<span class="visually-hidden">View this page</span>
</a>
</div>
<div class="theme-toggle-container theme-toggle-content">
<button class="theme-toggle">
<div class="visually-hidden">Toggle Light / Dark / Auto color theme</div>
<svg class="theme-icon-when-auto-light"><use href="#svg-sun-with-moon"></use></svg>
<svg class="theme-icon-when-auto-dark"><use href="#svg-moon-with-sun"></use></svg>
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
</button>
</div>
<label class="toc-overlay-icon toc-content-icon" for="__toc">
<div class="visually-hidden">Toggle table of contents sidebar</div>
<i class="icon"><svg><use href="#svg-toc"></use></svg></i>
</label>
</div>
<article role="main" id="furo-main-content">
<section id="substrait">
<h1>Substrait<a class="headerlink" href="#substrait" title="Link to this heading"></a></h1>
<p>The <code class="docutils literal notranslate"><span class="pre">arrow-dataset</span></code> module can execute <a class="reference external" href="https://substrait.io/">Substrait</a> plans via the <a class="reference external" href="https://arrow.apache.org/docs/cpp/streaming_execution.html" title="(in Apache Arrow v19.0.0)"><span class="xref std std-doc">Acero</span></a>
query engine.</p>
<section id="executing-queries-using-substrait-plans">
<h2>Executing Queries Using Substrait Plans<a class="headerlink" href="#executing-queries-using-substrait-plans" title="Link to this heading"></a></h2>
<p>Plans can reference data in files via URIs, or “named tables” that must be provided along with the plan.</p>
<p>Here is an example of a Java program that queries a Parquet file using Java Substrait
(this example use <a class="reference external" href="https://github.com/substrait-io/substrait-java">Substrait Java</a> project to compile a SQL query to a Substrait plan):</p>
<div class="highlight-Java notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">com.google.common.collect.ImmutableList</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">io.substrait.isthmus.SqlToSubstrait</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">io.substrait.proto.Plan</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.file.FileFormat</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.file.FileSystemDatasetFactory</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.jni.NativeMemoryPool</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.scanner.ScanOptions</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.scanner.Scanner</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.source.Dataset</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.source.DatasetFactory</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.substrait.AceroSubstraitConsumer</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.ipc.ArrowReader</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.calcite.sql.parser.SqlParseException</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.nio.ByteBuffer</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.util.HashMap</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.util.Map</span><span class="p">;</span>
<span class="kd">public</span><span class="w"> </span><span class="kd">class</span> <span class="nc">ClientSubstrait</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="kd">public</span><span class="w"> </span><span class="kd">static</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="n">String</span><span class="o">[]</span><span class="w"> </span><span class="n">args</span><span class="p">)</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">String</span><span class="w"> </span><span class="n">uri</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;file:///data/tpch_parquet/nation.parquet&quot;</span><span class="p">;</span>
<span class="w"> </span><span class="n">ScanOptions</span><span class="w"> </span><span class="n">options</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">ScanOptions</span><span class="p">(</span><span class="cm">/*batchSize*/</span><span class="w"> </span><span class="mi">32768</span><span class="p">);</span>
<span class="w"> </span><span class="k">try</span><span class="w"> </span><span class="p">(</span>
<span class="w"> </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="n">DatasetFactory</span><span class="w"> </span><span class="n">datasetFactory</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">FileSystemDatasetFactory</span><span class="p">(</span><span class="n">allocator</span><span class="p">,</span><span class="w"> </span><span class="n">NativeMemoryPool</span><span class="p">.</span><span class="na">getDefault</span><span class="p">(),</span>
<span class="w"> </span><span class="n">FileFormat</span><span class="p">.</span><span class="na">PARQUET</span><span class="p">,</span><span class="w"> </span><span class="n">uri</span><span class="p">);</span>
<span class="w"> </span><span class="n">Dataset</span><span class="w"> </span><span class="n">dataset</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">datasetFactory</span><span class="p">.</span><span class="na">finish</span><span class="p">();</span>
<span class="w"> </span><span class="n">Scanner</span><span class="w"> </span><span class="n">scanner</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">dataset</span><span class="p">.</span><span class="na">newScan</span><span class="p">(</span><span class="n">options</span><span class="p">);</span>
<span class="w"> </span><span class="n">ArrowReader</span><span class="w"> </span><span class="n">reader</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">scanner</span><span class="p">.</span><span class="na">scanBatches</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="c1">// map table to reader</span>
<span class="w"> </span><span class="n">Map</span><span class="o">&lt;</span><span class="n">String</span><span class="p">,</span><span class="w"> </span><span class="n">ArrowReader</span><span class="o">&gt;</span><span class="w"> </span><span class="n">mapTableToArrowReader</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">HashMap</span><span class="o">&lt;&gt;</span><span class="p">();</span>
<span class="w"> </span><span class="n">mapTableToArrowReader</span><span class="p">.</span><span class="na">put</span><span class="p">(</span><span class="s">&quot;NATION&quot;</span><span class="p">,</span><span class="w"> </span><span class="n">reader</span><span class="p">);</span>
<span class="w"> </span><span class="c1">// get binary plan</span>
<span class="w"> </span><span class="n">Plan</span><span class="w"> </span><span class="n">plan</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">getPlan</span><span class="p">();</span>
<span class="w"> </span><span class="n">ByteBuffer</span><span class="w"> </span><span class="n">substraitPlan</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">ByteBuffer</span><span class="p">.</span><span class="na">allocateDirect</span><span class="p">(</span><span class="n">plan</span><span class="p">.</span><span class="na">toByteArray</span><span class="p">().</span><span class="na">length</span><span class="p">);</span>
<span class="w"> </span><span class="n">substraitPlan</span><span class="p">.</span><span class="na">put</span><span class="p">(</span><span class="n">plan</span><span class="p">.</span><span class="na">toByteArray</span><span class="p">());</span>
<span class="w"> </span><span class="c1">// run query</span>
<span class="w"> </span><span class="k">try</span><span class="w"> </span><span class="p">(</span><span class="n">ArrowReader</span><span class="w"> </span><span class="n">arrowReader</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">AceroSubstraitConsumer</span><span class="p">(</span><span class="n">allocator</span><span class="p">).</span><span class="na">runQuery</span><span class="p">(</span>
<span class="w"> </span><span class="n">substraitPlan</span><span class="p">,</span>
<span class="w"> </span><span class="n">mapTableToArrowReader</span>
<span class="w"> </span><span class="p">))</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">while</span><span class="w"> </span><span class="p">(</span><span class="n">arrowReader</span><span class="p">.</span><span class="na">loadNextBatch</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">println</span><span class="p">(</span><span class="n">arrowReader</span><span class="p">.</span><span class="na">getVectorSchemaRoot</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="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="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="kd">static</span><span class="w"> </span><span class="n">Plan</span><span class="w"> </span><span class="nf">getPlan</span><span class="p">()</span><span class="w"> </span><span class="kd">throws</span><span class="w"> </span><span class="n">SqlParseException</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">String</span><span class="w"> </span><span class="n">sql</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;SELECT * from nation&quot;</span><span class="p">;</span>
<span class="w"> </span><span class="n">String</span><span class="w"> </span><span class="n">nation</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;CREATE TABLE NATION (N_NATIONKEY BIGINT NOT NULL, N_NAME CHAR(25), &quot;</span><span class="w"> </span><span class="o">+</span>
<span class="w"> </span><span class="s">&quot;N_REGIONKEY BIGINT NOT NULL, N_COMMENT VARCHAR(152))&quot;</span><span class="p">;</span>
<span class="w"> </span><span class="n">SqlToSubstrait</span><span class="w"> </span><span class="n">sqlToSubstrait</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">SqlToSubstrait</span><span class="p">();</span>
<span class="w"> </span><span class="n">Plan</span><span class="w"> </span><span class="n">plan</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">sqlToSubstrait</span><span class="p">.</span><span class="na">execute</span><span class="p">(</span><span class="n">sql</span><span class="p">,</span><span class="w"> </span><span class="n">ImmutableList</span><span class="p">.</span><span class="na">of</span><span class="p">(</span><span class="n">nation</span><span class="p">));</span>
<span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="n">plan</span><span class="p">;</span>
<span class="w"> </span><span class="p">}</span>
<span class="p">}</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>// Results example:
FieldPath(0) FieldPath(1) FieldPath(2) FieldPath(3)
0 ALGERIA 0 haggle. carefully final deposits detect slyly agai
1 ARGENTINA 1 al foxes promise slyly according to the regular accounts. bold requests alon
</pre></div>
</div>
</section>
<section id="executing-projections-and-filters-using-extended-expressions">
<h2>Executing Projections and Filters Using Extended Expressions<a class="headerlink" href="#executing-projections-and-filters-using-extended-expressions" title="Link to this heading"></a></h2>
<p>Dataset also supports projections and filters with Substrait’s <a class="reference external" href="https://github.com/substrait-io/substrait/blob/main/site/docs/expressions/extended_expression.md">Extended Expression</a>.
This requires the substrait-java library.</p>
<p>This Java program:</p>
<ul class="simple">
<li><p>Loads a Parquet file containing the “nation” table from the TPC-H benchmark.</p></li>
<li><dl class="simple">
<dt>Applies a filter:</dt><dd><ul>
<li><p><code class="docutils literal notranslate"><span class="pre">N_NATIONKEY</span> <span class="pre">&gt;</span> <span class="pre">18</span></code></p></li>
</ul>
</dd>
</dl>
</li>
<li><dl class="simple">
<dt>Projects two new columns:</dt><dd><ul>
<li><p><code class="docutils literal notranslate"><span class="pre">N_REGIONKEY</span> <span class="pre">+</span> <span class="pre">10</span></code></p></li>
<li><p><code class="docutils literal notranslate"><span class="pre">N_NAME</span> <span class="pre">||</span> <span class="pre">'</span> <span class="pre">-</span> <span class="pre">'</span> <span class="pre">||</span> <span class="pre">N_COMMENT</span></code></p></li>
</ul>
</dd>
</dl>
</li>
</ul>
<div class="highlight-Java notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span><span class="w"> </span><span class="nn">com.google.common.collect.ImmutableList</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">io.substrait.isthmus.SqlExpressionToSubstrait</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">io.substrait.proto.ExtendedExpression</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.file.FileFormat</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.file.FileSystemDatasetFactory</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.jni.NativeMemoryPool</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.scanner.ScanOptions</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.scanner.Scanner</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.source.Dataset</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.arrow.dataset.source.DatasetFactory</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.ipc.ArrowReader</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">org.apache.calcite.sql.parser.SqlParseException</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.nio.ByteBuffer</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.util.Base64</span><span class="p">;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">java.util.Optional</span><span class="p">;</span>
<span class="kd">public</span><span class="w"> </span><span class="kd">class</span> <span class="nc">ClientSubstraitExtendedExpressionsCookbook</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="kd">public</span><span class="w"> </span><span class="kd">static</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="nf">main</span><span class="p">(</span><span class="n">String</span><span class="o">[]</span><span class="w"> </span><span class="n">args</span><span class="p">)</span><span class="w"> </span><span class="kd">throws</span><span class="w"> </span><span class="n">SqlParseException</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">projectAndFilterDataset</span><span class="p">();</span>
<span class="w"> </span><span class="p">}</span>
<span class="w"> </span><span class="kd">private</span><span class="w"> </span><span class="kd">static</span><span class="w"> </span><span class="kt">void</span><span class="w"> </span><span class="nf">projectAndFilterDataset</span><span class="p">()</span><span class="w"> </span><span class="kd">throws</span><span class="w"> </span><span class="n">SqlParseException</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">String</span><span class="w"> </span><span class="n">uri</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="s">&quot;file:///Users/data/tpch_parquet/nation.parquet&quot;</span><span class="p">;</span>
<span class="w"> </span><span class="n">ScanOptions</span><span class="w"> </span><span class="n">options</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">ScanOptions</span><span class="p">.</span><span class="na">Builder</span><span class="p">(</span><span class="cm">/*batchSize*/</span><span class="w"> </span><span class="mi">32768</span><span class="p">)</span>
<span class="w"> </span><span class="p">.</span><span class="na">columns</span><span class="p">(</span><span class="n">Optional</span><span class="p">.</span><span class="na">empty</span><span class="p">())</span>
<span class="w"> </span><span class="p">.</span><span class="na">substraitFilter</span><span class="p">(</span><span class="n">getByteBuffer</span><span class="p">(</span><span class="k">new</span><span class="w"> </span><span class="n">String</span><span class="o">[]</span><span class="p">{</span><span class="s">&quot;N_NATIONKEY &gt; 18&quot;</span><span class="p">}))</span>
<span class="w"> </span><span class="p">.</span><span class="na">substraitProjection</span><span class="p">(</span><span class="n">getByteBuffer</span><span class="p">(</span><span class="k">new</span><span class="w"> </span><span class="n">String</span><span class="o">[]</span><span class="p">{</span><span class="s">&quot;N_REGIONKEY + 10&quot;</span><span class="p">,</span>
<span class="w"> </span><span class="s">&quot;N_NAME || CAST(&#39; - &#39; as VARCHAR) || N_COMMENT&quot;</span><span class="p">}))</span>
<span class="w"> </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">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="n">DatasetFactory</span><span class="w"> </span><span class="n">datasetFactory</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">FileSystemDatasetFactory</span><span class="p">(</span>
<span class="w"> </span><span class="n">allocator</span><span class="p">,</span><span class="w"> </span><span class="n">NativeMemoryPool</span><span class="p">.</span><span class="na">getDefault</span><span class="p">(),</span><span class="w"> </span><span class="n">FileFormat</span><span class="p">.</span><span class="na">PARQUET</span><span class="p">,</span><span class="w"> </span><span class="n">uri</span><span class="p">);</span>
<span class="w"> </span><span class="n">Dataset</span><span class="w"> </span><span class="n">dataset</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">datasetFactory</span><span class="p">.</span><span class="na">finish</span><span class="p">();</span>
<span class="w"> </span><span class="n">Scanner</span><span class="w"> </span><span class="n">scanner</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">dataset</span><span class="p">.</span><span class="na">newScan</span><span class="p">(</span><span class="n">options</span><span class="p">);</span>
<span class="w"> </span><span class="n">ArrowReader</span><span class="w"> </span><span class="n">reader</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">scanner</span><span class="p">.</span><span class="na">scanBatches</span><span class="p">())</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="k">while</span><span class="w"> </span><span class="p">(</span><span class="n">reader</span><span class="p">.</span><span class="na">loadNextBatch</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">println</span><span class="p">(</span><span class="n">reader</span><span class="p">.</span><span class="na">getVectorSchemaRoot</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="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="k">throw</span><span class="w"> </span><span class="k">new</span><span class="w"> </span><span class="n">RuntimeException</span><span class="p">(</span><span class="n">e</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="kd">private</span><span class="w"> </span><span class="kd">static</span><span class="w"> </span><span class="n">ByteBuffer</span><span class="w"> </span><span class="nf">getByteBuffer</span><span class="p">(</span><span class="n">String</span><span class="o">[]</span><span class="w"> </span><span class="n">sqlExpression</span><span class="p">)</span><span class="w"> </span><span class="kd">throws</span><span class="w"> </span><span class="n">SqlParseException</span><span class="w"> </span><span class="p">{</span>
<span class="w"> </span><span class="n">String</span><span class="w"> </span><span class="n">schema</span><span class="w"> </span><span class="o">=</span>
<span class="w"> </span><span class="s">&quot;CREATE TABLE NATION (N_NATIONKEY INT NOT NULL, N_NAME VARCHAR, &quot;</span>
<span class="w"> </span><span class="o">+</span><span class="w"> </span><span class="s">&quot;N_REGIONKEY INT NOT NULL, N_COMMENT VARCHAR)&quot;</span><span class="p">;</span>
<span class="w"> </span><span class="n">SqlExpressionToSubstrait</span><span class="w"> </span><span class="n">expressionToSubstrait</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">SqlExpressionToSubstrait</span><span class="p">();</span>
<span class="w"> </span><span class="n">ExtendedExpression</span><span class="w"> </span><span class="n">expression</span><span class="w"> </span><span class="o">=</span>
<span class="w"> </span><span class="n">expressionToSubstrait</span><span class="p">.</span><span class="na">convert</span><span class="p">(</span><span class="n">sqlExpression</span><span class="p">,</span><span class="w"> </span><span class="n">ImmutableList</span><span class="p">.</span><span class="na">of</span><span class="p">(</span><span class="n">schema</span><span class="p">));</span>
<span class="w"> </span><span class="kt">byte</span><span class="o">[]</span><span class="w"> </span><span class="n">expressionToByte</span><span class="w"> </span><span class="o">=</span>
<span class="w"> </span><span class="n">Base64</span><span class="p">.</span><span class="na">getDecoder</span><span class="p">().</span><span class="na">decode</span><span class="p">(</span><span class="n">Base64</span><span class="p">.</span><span class="na">getEncoder</span><span class="p">().</span><span class="na">encodeToString</span><span class="p">(</span><span class="n">expression</span><span class="p">.</span><span class="na">toByteArray</span><span class="p">()));</span>
<span class="w"> </span><span class="n">ByteBuffer</span><span class="w"> </span><span class="n">byteBuffer</span><span class="w"> </span><span class="o">=</span><span class="w"> </span><span class="n">ByteBuffer</span><span class="p">.</span><span class="na">allocateDirect</span><span class="p">(</span><span class="n">expressionToByte</span><span class="p">.</span><span class="na">length</span><span class="p">);</span>
<span class="w"> </span><span class="n">byteBuffer</span><span class="p">.</span><span class="na">put</span><span class="p">(</span><span class="n">expressionToByte</span><span class="p">);</span>
<span class="w"> </span><span class="k">return</span><span class="w"> </span><span class="n">byteBuffer</span><span class="p">;</span>
<span class="w"> </span><span class="p">}</span>
<span class="p">}</span>
</pre></div>
</div>
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>column-1 column-2
13 ROMANIA - ular asymptotes are about the furious multipliers. express dependencies nag above the ironically ironic account
14 SAUDI ARABIA - ts. silent requests haggle. closely express packages sleep across the blithely
12 VIETNAM - hely enticingly express accounts. even, final
13 RUSSIA - requests against the platelets use never according to the quickly regular pint
13 UNITED KINGDOM - eans boost carefully special requests. accounts are. carefull
11 UNITED STATES - y final packages. slow foxes cajole quickly. quickly silent platelets breach ironic accounts. unusual pinto be
</pre></div>
</div>
</section>
</section>
</article>
</div>
<footer>
<div class="related-pages">
<a class="next-page" href="cdata.html">
<div class="page-info">
<div class="context">
<span>Next</span>
</div>
<div class="title">C Data Interface</div>
</div>
<svg class="furo-related-icon"><use href="#svg-arrow-right"></use></svg>
</a>
<a class="prev-page" href="dataset.html">
<svg class="furo-related-icon"><use href="#svg-arrow-right"></use></svg>
<div class="page-info">
<div class="context">
<span>Previous</span>
</div>
<div class="title">Dataset</div>
</div>
</a>
</div>
<div class="bottom-of-page">
<div class="left-details">
<div class="copyright">
Copyright &#169; 2025, Apache Arrow Developers
</div>
Made with <a href="https://www.sphinx-doc.org/">Sphinx</a> and <a class="muted-link" href="https://pradyunsg.me">@pradyunsg</a>'s
<a href="https://github.com/pradyunsg/furo">Furo</a>
</div>
<div class="right-details">
</div>
</div>
</footer>
</div>
<aside class="toc-drawer">
<div class="toc-sticky toc-scroll">
<div class="toc-title-container">
<span class="toc-title">
On this page
</span>
</div>
<div class="toc-tree-container">
<div class="toc-tree">
<ul>
<li><a class="reference internal" href="#">Substrait</a><ul>
<li><a class="reference internal" href="#executing-queries-using-substrait-plans">Executing Queries Using Substrait Plans</a></li>
<li><a class="reference internal" href="#executing-projections-and-filters-using-extended-expressions">Executing Projections and Filters Using Extended Expressions</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div>
</aside>
</div>
</div><script src="_static/documentation_options.js?v=c4c92189"></script>
<script src="_static/doctools.js?v=9bcbadda"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/scripts/furo.js?v=5fa4622c"></script>
</body>
</html>