blob: 3a5038bd58a6b20a406786fe73acec36d0cb2f02 [file] [log] [blame]
<!DOCTYPE html>
<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<title>LOAD DATA - Spark 3.0.1 Documentation</title>
<link rel="stylesheet" href="css/bootstrap.min.css">
<style>
body {
padding-top: 60px;
padding-bottom: 40px;
}
</style>
<meta name="viewport" content="width=device-width">
<link rel="stylesheet" href="css/bootstrap-responsive.min.css">
<link rel="stylesheet" href="css/main.css">
<script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script>
<link rel="stylesheet" href="css/pygments-default.css">
<!-- Google analytics script -->
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-32518208-2']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
</head>
<body>
<!--[if lt IE 7]>
<p class="chromeframe">You are using an outdated browser. <a href="https://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p>
<![endif]-->
<!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html -->
<div class="navbar navbar-fixed-top" id="topbar">
<div class="navbar-inner">
<div class="container">
<div class="brand"><a href="index.html">
<img src="img/spark-logo-hd.png" style="height:50px;"/></a><span class="version">3.0.1</span>
</div>
<ul class="nav">
<!--TODO(andyk): Add class="active" attribute to li some how.-->
<li><a href="index.html">Overview</a></li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Programming Guides<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="quick-start.html">Quick Start</a></li>
<li><a href="rdd-programming-guide.html">RDDs, Accumulators, Broadcasts Vars</a></li>
<li><a href="sql-programming-guide.html">SQL, DataFrames, and Datasets</a></li>
<li><a href="structured-streaming-programming-guide.html">Structured Streaming</a></li>
<li><a href="streaming-programming-guide.html">Spark Streaming (DStreams)</a></li>
<li><a href="ml-guide.html">MLlib (Machine Learning)</a></li>
<li><a href="graphx-programming-guide.html">GraphX (Graph Processing)</a></li>
<li><a href="sparkr.html">SparkR (R on Spark)</a></li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">API Docs<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="api/scala/org/apache/spark/index.html">Scala</a></li>
<li><a href="api/java/index.html">Java</a></li>
<li><a href="api/python/index.html">Python</a></li>
<li><a href="api/R/index.html">R</a></li>
<li><a href="api/sql/index.html">SQL, Built-in Functions</a></li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Deploying<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="cluster-overview.html">Overview</a></li>
<li><a href="submitting-applications.html">Submitting Applications</a></li>
<li class="divider"></li>
<li><a href="spark-standalone.html">Spark Standalone</a></li>
<li><a href="running-on-mesos.html">Mesos</a></li>
<li><a href="running-on-yarn.html">YARN</a></li>
<li><a href="running-on-kubernetes.html">Kubernetes</a></li>
</ul>
</li>
<li class="dropdown">
<a href="api.html" class="dropdown-toggle" data-toggle="dropdown">More<b class="caret"></b></a>
<ul class="dropdown-menu">
<li><a href="configuration.html">Configuration</a></li>
<li><a href="monitoring.html">Monitoring</a></li>
<li><a href="tuning.html">Tuning Guide</a></li>
<li><a href="job-scheduling.html">Job Scheduling</a></li>
<li><a href="security.html">Security</a></li>
<li><a href="hardware-provisioning.html">Hardware Provisioning</a></li>
<li><a href="migration-guide.html">Migration Guide</a></li>
<li class="divider"></li>
<li><a href="building-spark.html">Building Spark</a></li>
<li><a href="https://spark.apache.org/contributing.html">Contributing to Spark</a></li>
<li><a href="https://spark.apache.org/third-party-projects.html">Third Party Projects</a></li>
</ul>
</li>
</ul>
<!--<p class="navbar-text pull-right"><span class="version-text">v3.0.1</span></p>-->
</div>
</div>
</div>
<div class="container-wrapper">
<div class="left-menu-wrapper">
<div class="left-menu">
<h3><a href="sql-programming-guide.html">Spark SQL Guide</a></h3>
<ul>
<li>
<a href="sql-getting-started.html">
Getting Started
</a>
</li>
<li>
<a href="sql-data-sources.html">
Data Sources
</a>
</li>
<li>
<a href="sql-performance-tuning.html">
Performance Tuning
</a>
</li>
<li>
<a href="sql-distributed-sql-engine.html">
Distributed SQL Engine
</a>
</li>
<li>
<a href="sql-pyspark-pandas-with-arrow.html">
PySpark Usage Guide for Pandas with Apache Arrow
</a>
</li>
<li>
<a href="sql-migration-old.html">
Migration Guide
</a>
</li>
<li>
<a href="sql-ref.html">
SQL Reference
</a>
</li>
<ul>
<li>
<a href="sql-ref-ansi-compliance.html">
ANSI Compliance
</a>
</li>
<li>
<a href="sql-ref-datatypes.html">
Data Types
</a>
</li>
<li>
<a href="sql-ref-datetime-pattern.html">
Datetime Pattern
</a>
</li>
<li>
<a href="sql-ref-functions.html">
Functions
</a>
</li>
<li>
<a href="sql-ref-identifier.html">
Identifiers
</a>
</li>
<li>
<a href="sql-ref-literals.html">
Literals
</a>
</li>
<li>
<a href="sql-ref-null-semantics.html">
Null Semantics
</a>
</li>
<li>
<a href="sql-ref-syntax.html">
SQL Syntax
</a>
</li>
<ul>
<li>
<a href="sql-ref-syntax-ddl.html">
Data Definition Statements
</a>
</li>
<li>
<a href="sql-ref-syntax-dml.html">
Data Manipulation Statements
</a>
</li>
<ul>
<li>
<a href="sql-ref-syntax-dml-insert.html">
INSERT
</a>
</li>
<li>
<a href="sql-ref-syntax-dml-load.html">
<b>LOAD</b>
</a>
</li>
</ul>
<li>
<a href="sql-ref-syntax-qry.html">
Data Retrieval(Queries)
</a>
</li>
<li>
<a href="sql-ref-syntax-aux.html">
Auxiliary Statements
</a>
</li>
</ul>
</ul>
</ul>
</div>
</div>
<input id="nav-trigger" class="nav-trigger" checked type="checkbox">
<label for="nav-trigger"></label>
<div class="content-with-sidebar" id="content">
<h1 class="title">LOAD DATA</h1>
<h3 id="description">Description</h3>
<p><code class="highlighter-rouge">LOAD DATA</code> statement loads the data into a Hive serde table from the user specified directory or file. If a directory is specified then all the files from the directory are loaded. If a file is specified then only the single file is loaded. Additionally the <code class="highlighter-rouge">LOAD DATA</code> statement takes an optional partition specification. When a partition is specified, the data files (when input source is a directory) or the single file (when input source is a file) are loaded into the partition of the target table.</p>
<h3 id="syntax">Syntax</h3>
<div class="language-sql highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">LOAD</span> <span class="k">DATA</span> <span class="p">[</span> <span class="k">LOCAL</span> <span class="p">]</span> <span class="n">INPATH</span> <span class="n">path</span> <span class="p">[</span> <span class="n">OVERWRITE</span> <span class="p">]</span> <span class="k">INTO</span> <span class="k">TABLE</span> <span class="n">table_identifier</span> <span class="p">[</span> <span class="n">partition_spec</span> <span class="p">]</span>
</code></pre></div></div>
<h3 id="parameters">Parameters</h3>
<ul>
<li>
<p><strong>path</strong></p>
<p>Path of the file system. It can be either an absolute or a relative path.</p>
</li>
<li>
<p><strong>table_identifier</strong></p>
<p>Specifies a table name, which may be optionally qualified with a database name.</p>
<p><strong>Syntax:</strong> <code class="highlighter-rouge">[ database_name. ] table_name</code></p>
</li>
<li>
<p><strong>partition_spec</strong></p>
<p>An optional parameter that specifies a comma separated list of key and value pairs
for partitions.</p>
<p><strong>Syntax:</strong> <code class="highlighter-rouge">PARTITION ( partition_col_name = partition_col_val [ , ... ] )</code></p>
</li>
<li>
<p><strong>LOCAL</strong></p>
<p>If specified, it causes the <code class="highlighter-rouge">INPATH</code> to be resolved against the local file system, instead of the default file system, which is typically a distributed storage.</p>
</li>
<li>
<p><strong>OVERWRITE</strong></p>
<p>By default, new data is appended to the table. If <code class="highlighter-rouge">OVERWRITE</code> is used, the table is instead overwritten with new data.</p>
</li>
</ul>
<h3 id="examples">Examples</h3>
<div class="language-sql highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="c1">-- Example without partition specification.</span>
<span class="c1">-- Assuming the students table has already been created and populated.</span>
<span class="k">SELECT</span> <span class="o">*</span> <span class="k">FROM</span> <span class="n">students</span><span class="p">;</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="o">|</span> <span class="n">name</span><span class="o">|</span> <span class="n">address</span><span class="o">|</span><span class="n">student_id</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="o">|</span><span class="n">Amy</span> <span class="n">Smith</span><span class="o">|</span><span class="mi">123</span> <span class="n">Park</span> <span class="n">Ave</span><span class="p">,</span> <span class="n">San</span> <span class="n">Jose</span><span class="o">|</span> <span class="mi">111111</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">test_load</span> <span class="p">(</span><span class="n">name</span> <span class="nb">VARCHAR</span><span class="p">(</span><span class="mi">64</span><span class="p">),</span> <span class="n">address</span> <span class="nb">VARCHAR</span><span class="p">(</span><span class="mi">64</span><span class="p">),</span> <span class="n">student_id</span> <span class="nb">INT</span><span class="p">)</span> <span class="k">USING</span> <span class="n">HIVE</span><span class="p">;</span>
<span class="c1">-- Assuming the students table is in '/user/hive/warehouse/'</span>
<span class="k">LOAD</span> <span class="k">DATA</span> <span class="k">LOCAL</span> <span class="n">INPATH</span> <span class="s1">'/user/hive/warehouse/students'</span> <span class="n">OVERWRITE</span> <span class="k">INTO</span> <span class="k">TABLE</span> <span class="n">test_load</span><span class="p">;</span>
<span class="k">SELECT</span> <span class="o">*</span> <span class="k">FROM</span> <span class="n">test_load</span><span class="p">;</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="o">|</span> <span class="n">name</span><span class="o">|</span> <span class="n">address</span><span class="o">|</span><span class="n">student_id</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="o">|</span><span class="n">Amy</span> <span class="n">Smith</span><span class="o">|</span><span class="mi">123</span> <span class="n">Park</span> <span class="n">Ave</span><span class="p">,</span> <span class="n">San</span> <span class="n">Jose</span><span class="o">|</span> <span class="mi">111111</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---------+----------------------+----------+</span>
<span class="c1">-- Example with partition specification.</span>
<span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">test_partition</span> <span class="p">(</span><span class="n">c1</span> <span class="nb">INT</span><span class="p">,</span> <span class="n">c2</span> <span class="nb">INT</span><span class="p">,</span> <span class="n">c3</span> <span class="nb">INT</span><span class="p">)</span> <span class="n">PARTITIONED</span> <span class="k">BY</span> <span class="p">(</span><span class="n">c2</span><span class="p">,</span> <span class="n">c3</span><span class="p">);</span>
<span class="k">INSERT</span> <span class="k">INTO</span> <span class="n">test_partition</span> <span class="n">PARTITION</span> <span class="p">(</span><span class="n">c2</span> <span class="o">=</span> <span class="mi">2</span><span class="p">,</span> <span class="n">c3</span> <span class="o">=</span> <span class="mi">3</span><span class="p">)</span> <span class="k">VALUES</span> <span class="p">(</span><span class="mi">1</span><span class="p">);</span>
<span class="k">INSERT</span> <span class="k">INTO</span> <span class="n">test_partition</span> <span class="n">PARTITION</span> <span class="p">(</span><span class="n">c2</span> <span class="o">=</span> <span class="mi">5</span><span class="p">,</span> <span class="n">c3</span> <span class="o">=</span> <span class="mi">6</span><span class="p">)</span> <span class="k">VALUES</span> <span class="p">(</span><span class="mi">4</span><span class="p">);</span>
<span class="k">INSERT</span> <span class="k">INTO</span> <span class="n">test_partition</span> <span class="n">PARTITION</span> <span class="p">(</span><span class="n">c2</span> <span class="o">=</span> <span class="mi">8</span><span class="p">,</span> <span class="n">c3</span> <span class="o">=</span> <span class="mi">9</span><span class="p">)</span> <span class="k">VALUES</span> <span class="p">(</span><span class="mi">7</span><span class="p">);</span>
<span class="k">SELECT</span> <span class="o">*</span> <span class="k">FROM</span> <span class="n">test_partition</span><span class="p">;</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
<span class="o">|</span> <span class="n">c1</span><span class="o">|</span> <span class="n">c2</span><span class="o">|</span> <span class="n">c3</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
<span class="o">|</span> <span class="mi">1</span><span class="o">|</span> <span class="mi">2</span><span class="o">|</span> <span class="mi">3</span><span class="o">|</span>
<span class="o">|</span> <span class="mi">4</span><span class="o">|</span> <span class="mi">5</span><span class="o">|</span> <span class="mi">6</span><span class="o">|</span>
<span class="o">|</span> <span class="mi">7</span><span class="o">|</span> <span class="mi">8</span><span class="o">|</span> <span class="mi">9</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
<span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">test_load_partition</span> <span class="p">(</span><span class="n">c1</span> <span class="nb">INT</span><span class="p">,</span> <span class="n">c2</span> <span class="nb">INT</span><span class="p">,</span> <span class="n">c3</span> <span class="nb">INT</span><span class="p">)</span> <span class="k">USING</span> <span class="n">HIVE</span> <span class="n">PARTITIONED</span> <span class="k">BY</span> <span class="p">(</span><span class="n">c2</span><span class="p">,</span> <span class="n">c3</span><span class="p">);</span>
<span class="c1">-- Assuming the test_partition table is in '/user/hive/warehouse/'</span>
<span class="k">LOAD</span> <span class="k">DATA</span> <span class="k">LOCAL</span> <span class="n">INPATH</span> <span class="s1">'/user/hive/warehouse/test_partition/c2=2/c3=3'</span>
<span class="n">OVERWRITE</span> <span class="k">INTO</span> <span class="k">TABLE</span> <span class="n">test_load_partition</span> <span class="n">PARTITION</span> <span class="p">(</span><span class="n">c2</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">c3</span><span class="o">=</span><span class="mi">3</span><span class="p">);</span>
<span class="k">SELECT</span> <span class="o">*</span> <span class="k">FROM</span> <span class="n">test_load_partition</span><span class="p">;</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
<span class="o">|</span> <span class="n">c1</span><span class="o">|</span> <span class="n">c2</span><span class="o">|</span> <span class="n">c3</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
<span class="o">|</span> <span class="mi">1</span><span class="o">|</span> <span class="mi">2</span><span class="o">|</span> <span class="mi">3</span><span class="o">|</span>
<span class="o">+</span><span class="c1">---+---+---+</span>
</code></pre></div></div>
</div>
<!-- /container -->
</div>
<script src="js/vendor/jquery-3.4.1.min.js"></script>
<script src="js/vendor/bootstrap.min.js"></script>
<script src="js/vendor/anchor.min.js"></script>
<script src="js/main.js"></script>
<!-- MathJax Section -->
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
TeX: { equationNumbers: { autoNumber: "AMS" } }
});
</script>
<script>
// Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS.
// We could use "//cdn.mathjax...", but that won't support "file://".
(function(d, script) {
script = d.createElement('script');
script.type = 'text/javascript';
script.async = true;
script.onload = function(){
MathJax.Hub.Config({
tex2jax: {
inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ],
displayMath: [ ["$$","$$"], ["\\[", "\\]"] ],
processEscapes: true,
skipTags: ['script', 'noscript', 'style', 'textarea', 'pre']
}
});
};
script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') +
'cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js' +
'?config=TeX-AMS-MML_HTMLorMML';
d.getElementsByTagName('head')[0].appendChild(script);
}(document));
</script>
</body>
</html>