You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2014/07/01 23:42:51 UTC
svn commit: r1607200 [2/2] - in /spark: ./ _layouts/ images/ news/_posts/
site/ site/graphx/ site/images/ site/mllib/ site/news/ site/releases/
site/screencasts/ site/sql/ site/streaming/ sql/
Added: spark/site/sql/index.html
URL: http://svn.apache.org/viewvc/spark/site/sql/index.html?rev=1607200&view=auto
==============================================================================
--- spark/site/sql/index.html (added)
+++ spark/site/sql/index.html Tue Jul 1 21:42:50 2014
@@ -0,0 +1,346 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="utf-8">
+ <meta http-equiv="X-UA-Compatible" content="IE=edge">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+ <title>
+ Spark SQL | Apache Spark
+
+ </title>
+
+
+
+ <!-- Bootstrap core CSS -->
+ <link href="/css/cerulean.min.css" rel="stylesheet">
+ <link href="/css/custom.css" rel="stylesheet">
+
+ <script type="text/javascript">
+ <!-- Google Analytics initialization -->
+ 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);
+ })();
+
+ <!-- Adds slight delay to links to allow async reporting -->
+ function trackOutboundLink(link, category, action) {
+ try {
+ _gaq.push(['_trackEvent', category , action]);
+ } catch(err){}
+
+ setTimeout(function() {
+ document.location.href = link.href;
+ }, 100);
+ }
+ </script>
+
+ <!-- HTML5 shim and Respond.js IE8 support of HTML5 elements and media queries -->
+ <!--[if lt IE 9]>
+ <script src="https://oss.maxcdn.com/libs/html5shiv/3.7.0/html5shiv.js"></script>
+ <script src="https://oss.maxcdn.com/libs/respond.js/1.3.0/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+<body>
+
+<div class="container" style="max-width: 1200px;">
+
+<div class="masthead">
+
+ <p class="lead">
+ <a href="/">
+ <img src="/images/spark-logo.png"
+ style="height:100px; width:auto; vertical-align: bottom; margin-top: 20px;"></a>
+ <a href="#"><span class="subproject">
+ SQL
+ </span></a>
+ </p>
+
+</div>
+
+<nav class="navbar navbar-default" role="navigation">
+ <!-- Brand and toggle get grouped for better mobile display -->
+ <div class="navbar-header">
+ <button type="button" class="navbar-toggle" data-toggle="collapse"
+ data-target="#navbar-collapse-1">
+ <span class="sr-only">Toggle navigation</span>
+ <span class="icon-bar"></span>
+ <span class="icon-bar"></span>
+ <span class="icon-bar"></span>
+ </button>
+ </div>
+
+ <!-- Collect the nav links, forms, and other content for toggling -->
+ <div class="collapse navbar-collapse" id="navbar-collapse-1">
+ <ul class="nav navbar-nav">
+ <li><a href="/downloads.html">Download</a></li>
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">
+ Related Projects <b class="caret"></b>
+ </a>
+ <ul class="dropdown-menu">
+
+ <li><a href="/">Apache Spark</a></li>
+
+ <li><a href="/sql/">Spark SQL</a></li>
+ <li><a href="/streaming/">Spark Streaming</a></li>
+ <li><a href="/mllib/">MLlib (machine learning)</a></li>
+ <li><a href="/graphx/">GraphX (graph)</a></li>
+ </ul>
+ </li>
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">
+ Documentation <b class="caret"></b>
+ </a>
+ <ul class="dropdown-menu">
+ <li><a href="/documentation.html">Overview</a></li>
+ <li><a href="/docs/latest/">Latest Release (Spark 1.0)</a></li>
+ <li><a href="/examples.html">Examples</a></li>
+ </ul>
+ </li>
+ <li class="dropdown">
+ <a href="#" class="dropdown-toggle" data-toggle="dropdown">
+ Community <b class="caret"></b>
+ </a>
+ <ul class="dropdown-menu">
+ <li><a href="/community.html">Mailing Lists</a></li>
+ <li><a href="/community.html#events">Events and Meetups</a></li>
+ <li><a href="/community.html#history">Project History</a></li>
+ <li><a href="https://cwiki.apache.org/confluence/display/SPARK/Powered+By+Spark">Powered By</a></li>
+ </ul>
+ </li>
+ <li><a href="/faq.html">FAQ</a></li>
+ </ul>
+ </div>
+ <!-- /.navbar-collapse -->
+</nav>
+
+
+<div class="row">
+ <div class="col-md-3 col-md-push-9">
+ <div class="news" style="margin-bottom: 20px;">
+ <h5>Latest News</h5>
+ <ul class="list-unstyled">
+
+ <li><a href="/news/two-weeks-to-spark-summit-2014.html">Two weeks to Spark Summit 2014</a>
+ <span class="small">(Jun 16, 2014)</span></li>
+
+ <li><a href="/news/spark-1-0-0-released.html">Spark 1.0.0 released</a>
+ <span class="small">(May 30, 2014)</span></li>
+
+ <li><a href="/news/spark-summit-agenda-posted.html">Spark Summit agenda posted</a>
+ <span class="small">(May 11, 2014)</span></li>
+
+ <li><a href="/news/spark-0-9-1-released.html">Spark 0.9.1 released</a>
+ <span class="small">(Apr 09, 2014)</span></li>
+
+ </ul>
+ <p class="small" style="text-align: right;"><a href="/news/index.html">Archive</a></p>
+ </div>
+ <div class="hidden-xs hidden-sm">
+ <a href="/downloads.html" class="btn btn-success btn-lg btn-block" style="margin-bottom: 30px;">
+ Download Spark
+ </a>
+ <p style="font-size: 16px; font-weight: 500; color: #555;">
+ Related Projects:
+ </p>
+ <ul class="list-narrow">
+
+ <li><a href="/">Apache Spark</a></li>
+
+ <li><a href="/sql/">Spark SQL</a></li>
+ <li><a href="/streaming/">Spark Streaming</a></li>
+ <li><a href="/mllib/">MLlib (machine learning)</a></li>
+ <li><a href="/graphx/">GraphX (graph)</a></li>
+ </ul>
+ </div>
+ </div>
+
+ <div class="col-md-9 col-md-pull-3">
+ <div class="jumbotron">
+ <b>Spark SQL</b> unifies access to structured data.
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Integrated</h2>
+ <p class="lead">
+ Seemlessly mix SQL queries with Spark programs.
+ </p>
+ <p>
+ Spark SQL lets you query structured data as a distributed dataset (RDD) in Spark, with integrated APIs in Python, Scala and Java.
+ This tight integration makes it easy to run SQL queries alongside complex analytic algorithms.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+
+ <div style="margin-top: 15px; text-align: left; display: inline-block;">
+ <div class="code">
+ sqlCtx = new <span class="sparkop">HiveContext</span>(sc)<br />
+ results = sqlCtx.<span class="sparkop">sql</span>(<br /> <span class="closure">"SELECT * FROM people"</span>)<br />
+ names = results.<span class="sparkop">map</span>(<span class="closure">lambda p: p.name</span>)
+ </div>
+ <div class="caption">Apply functions to results of SQL queries.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Unified Data Access</h2>
+ <p class="lead">
+ Load and query data from a variety of sources.
+ </p>
+ <p>
+ SchemaRDDs provide a single interface for efficiently working with structured data, including Apache Hive tables, parquet files and JSON files.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="margin-top: 15px; text-align: left; display: inline-block;">
+ <div class="code">
+ sqlCtx.<span class="sparkop">jsonFile</span>(<span class="closure">"s3n://..."</span>)<br /> .registerAsTable("json")<br />
+ schema_rdd = sqlCtx.<span class="sparkop">sql</span>(<span class="closure">"""<br />
+ SELECT * <br />
+ FROM hiveTable<br />
+ JOIN json ..."""</span>)<br />
+ </div>
+ <div class="caption">Query and join different data sources.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Hive Compatibility</h2>
+ <p class="lead">
+ Run unmodified Hive queries on existing warehouses.
+ </p>
+ <p>
+ Spark SQL reuses the Hive frontend and metastore, giving you full compatibility with
+ existing Hive data, queries, and UDFs. Simply install it alongside Hive.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 323px; display: inline-block">
+ <img src="/images/sql-hive-arch.png" style="width: 100%; max-width: 323px;" />
+ <div class="caption">Spark SQL can use existing Hive metastores, SerDes, and UDFs.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Standard Connectivity</h2>
+ <p class="lead">
+ Connect through JDBC or ODBC.
+ </p>
+ <p>
+ Spark SQL includes a server mode with industry standard JDBC and ODBC connectivity.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 323px; display: inline-block">
+ <img src="/images/jdbc.png" style="width: 75%; max-width: 323px;" />
+ <div class="caption">Use your existing BI tools to query big data.</div>
+ </div>
+ </div>
+</div>
+
+<!--
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Speed</h2>
+ <p class="lead">
+ Optimized to execute on Spark.
+ </p>
+ <p>
+ Spark SQL was built using the Catalyst optimizer, which automatically rewrites your queries to execute more efficiently.
+ By leveraging advanced techniques like runtime code generation, Spark SQL makes it easier to write lightning-fast analytic applications.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 272px; display: inline-block; text-align: center;">
+ <img src="/images/sqlperf.png" style="width: 100%; max-width: 250px;">
+ <div class="caption" style="min-width: 272px;">Performance comparison between Shark and Spark SQL</div>
+ </div>
+ </div>
+</div>
+-->
+
+
+ </div>
+</div>
+
+
+
+<div class="row">
+ <div class="col-md-4 col-padded">
+ <h3>Scalability</h3>
+ <p>
+ Use the same engine for both interactive and long queries.
+ </p>
+ <p>
+ Spark SQL takes advantage of the RDD model to support mid-query fault tolerance, letting it scale to large jobs too.
+ Don't worry about using a different engine for historical data.
+ </p>
+ </div>
+
+ <div class="col-md-4 col-padded">
+ <h3>Community</h3>
+ <p>
+ Spark SQL is developed as part of Apache Spark. It thus gets
+ tested and updated with each Spark release.
+ </p>
+ <p>
+ If you have questions about the system, ask on the
+ <a href="/community.html#mailing-lists">Spark mailing lists</a>.
+ </p>
+ <p>
+ The Spark SQL developers welcome contributions. If you'd like to help out,
+ read <a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">how to
+ contribute to Spark</a>, and send us a patch!
+ </p>
+ </div>
+
+ <div class="col-md-4 col-padded">
+ <h3>Getting Started</h3>
+ <p>
+ To get started with Spark SQL:
+ </p>
+ <ul class="list-narrow">
+ <li><a href="/downloads.html">Download Spark</a>. It includes Spark SQL as a module.</li>
+ <li>Read the <a href="/docs/latest/sql-programming-guide.html">Spark SQL programming guide</a>, which includes a examples of common use cases.</li>
+ </ul>
+ </div>
+</div>
+
+<div class="row">
+ <div class="col-sm-12 col-center">
+ <a href="/downloads.html" class="btn btn-success btn-lg btn-multiline">
+ Download Spark<br /><span class="small">Includes Spark SQL</span>
+ </a>
+ </div>
+</div>
+
+
+
+
+<footer class="small">
+ <hr>
+ Apache Spark, Spark, Apache, and the Spark logo are trademarks of
+ <a href="http://www.apache.org">The Apache Software Foundation</a>.
+</footer>
+
+</div>
+
+<script src="https://code.jquery.com/jquery.js"></script>
+<script src="//netdna.bootstrapcdn.com/bootstrap/3.0.3/js/bootstrap.min.js"></script>
+<script src="/js/lang-tabs.js"></script>
+
+</body>
+</html>
Modified: spark/site/streaming/index.html
URL: http://svn.apache.org/viewvc/spark/site/streaming/index.html?rev=1607200&r1=1607199&r2=1607200&view=diff
==============================================================================
--- spark/site/streaming/index.html (original)
+++ spark/site/streaming/index.html Tue Jul 1 21:42:50 2014
@@ -87,7 +87,7 @@
<li><a href="/">Apache Spark</a></li>
- <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li>
+ <li><a href="/sql/">Spark SQL</a></li>
<li><a href="/streaming/">Spark Streaming</a></li>
<li><a href="/mllib/">MLlib (machine learning)</a></li>
<li><a href="/graphx/">GraphX (graph)</a></li>
@@ -153,7 +153,7 @@
<li><a href="/">Apache Spark</a></li>
- <li><a href="http://shark.cs.berkeley.edu">Shark (SQL)</a></li>
+ <li><a href="/sql/">Spark SQL</a></li>
<li><a href="/streaming/">Spark Streaming</a></li>
<li><a href="/mllib/">MLlib (machine learning)</a></li>
<li><a href="/graphx/">GraphX (graph)</a></li>
Added: spark/sql/index.md
URL: http://svn.apache.org/viewvc/spark/sql/index.md?rev=1607200&view=auto
==============================================================================
--- spark/sql/index.md (added)
+++ spark/sql/index.md Tue Jul 1 21:42:50 2014
@@ -0,0 +1,172 @@
+---
+layout: global
+type: "page singular"
+title: Spark SQL
+subproject: SQL
+---
+
+
+<div class="jumbotron">
+ <b>Spark SQL</b> unifies access to structured data.
+</div>
+
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Integrated</h2>
+ <p class="lead">
+ Seemlessly mix SQL queries with Spark programs.
+ </p>
+ <p>
+ Spark SQL lets you query structured data as a distributed dataset (RDD) in Spark, with integrated APIs in Python, Scala and Java.
+ This tight integration makes it easy to run SQL queries alongside complex analytic algorithms.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+
+ <div style="margin-top: 15px; text-align: left; display: inline-block;">
+ <div class="code">
+ sqlCtx = new <span class="sparkop">HiveContext</span>(sc)<br/>
+ results = sqlCtx.<span class="sparkop">sql</span>(<br/> <span class="closure">"SELECT * FROM people"</span>)<br/>
+ names = results.<span class="sparkop">map</span>(<span class="closure">lambda p: p.name</span>)</br>
+ </div>
+ <div class="caption">Apply functions to results of SQL queries.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Unified Data Access</h2>
+ <p class="lead">
+ Load and query data from a variety of sources.
+ </p>
+ <p>
+ SchemaRDDs provide a single interface for efficiently working with structured data, including Apache Hive tables, parquet files and JSON files.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="margin-top: 15px; text-align: left; display: inline-block;">
+ <div class="code">
+ sqlCtx.<span class="sparkop">jsonFile</span>(<span class="closure">"s3n://..."</span>)<br/> .registerAsTable("json")<br/>
+ schema_rdd = sqlCtx.<span class="sparkop">sql</span>(<span class="closure">"""<br/>
+ SELECT * <br/>
+ FROM hiveTable<br/>
+ JOIN json ..."""</span>)<br/>
+ </div>
+ <div class="caption">Query and join different data sources.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Hive Compatibility</h2>
+ <p class="lead">
+ Run unmodified Hive queries on existing warehouses.
+ </p>
+ <p>
+ Spark SQL reuses the Hive frontend and metastore, giving you full compatibility with
+ existing Hive data, queries, and UDFs. Simply install it alongside Hive.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 323px; display: inline-block">
+ <img src="{{site.url}}images/sql-hive-arch.png" style="width: 100%; max-width: 323px;">
+ <div class="caption">Spark SQL can use existing Hive metastores, SerDes, and UDFs.</div>
+ </div>
+ </div>
+</div>
+
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Standard Connectivity</h2>
+ <p class="lead">
+ Connect through JDBC or ODBC.
+ </p>
+ <p>
+ Spark SQL includes a server mode with industry standard JDBC and ODBC connectivity.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 323px; display: inline-block">
+ <img src="{{site.url}}images/jdbc.png" style="width: 75%; max-width: 323px;">
+ <div class="caption">Use your existing BI tools to query big data.</div>
+ </div>
+ </div>
+</div>
+
+<!--
+<div class="row row-padded">
+ <div class="col-md-7 col-sm-7">
+ <h2>Speed</h2>
+ <p class="lead">
+ Optimized to execute on Spark.
+ </p>
+ <p>
+ Spark SQL was built using the Catalyst optimizer, which automatically rewrites your queries to execute more efficiently.
+ By leveraging advanced techniques like runtime code generation, Spark SQL makes it easier to write lightning-fast analytic applications.
+ </p>
+ </div>
+ <div class="col-md-5 col-sm-5 col-padded-top col-center">
+ <div style="width: 100%; max-width: 272px; display: inline-block; text-align: center;">
+ <img src="{{site.url}}images/sqlperf.png" style="width: 100%; max-width: 250px;">
+ <div class="caption" style="min-width: 272px;">Performance comparison between Shark and Spark SQL</div>
+ </div>
+ </div>
+</div>
+-->
+
+{% extra %}
+
+
+<div class="row">
+ <div class="col-md-4 col-padded">
+ <h3>Scalability</h3>
+ <p>
+ Use the same engine for both interactive and long queries.
+ </p>
+ <p>
+ Spark SQL takes advantage of the RDD model to support mid-query fault tolerance, letting it scale to large jobs too.
+ Don't worry about using a different engine for historical data.
+ </p>
+ </div>
+
+ <div class="col-md-4 col-padded">
+ <h3>Community</h3>
+ <p>
+ Spark SQL is developed as part of Apache Spark. It thus gets
+ tested and updated with each Spark release.
+ </p>
+ <p>
+ If you have questions about the system, ask on the
+ <a href="{{site.url}}community.html#mailing-lists">Spark mailing lists</a>.
+ </p>
+ <p>
+ The Spark SQL developers welcome contributions. If you'd like to help out,
+ read <a href="https://cwiki.apache.org/confluence/display/SPARK/Contributing+to+Spark">how to
+ contribute to Spark</a>, and send us a patch!
+ </p>
+ </div>
+
+ <div class="col-md-4 col-padded">
+ <h3>Getting Started</h3>
+ <p>
+ To get started with Spark SQL:
+ </p>
+ <ul class="list-narrow">
+ <li><a href="{{site.url}}downloads.html">Download Spark</a>. It includes Spark SQL as a module.</li>
+ <li>Read the <a href="{{site.url}}docs/latest/sql-programming-guide.html">Spark SQL programming guide</a>, which includes a examples of common use cases.</li>
+ </ul>
+ </div>
+</div>
+
+<div class="row">
+ <div class="col-sm-12 col-center">
+ <a href="{{site.url}}downloads.html" class="btn btn-success btn-lg btn-multiline">
+ Download Spark<br/><span class="small">Includes Spark SQL</span>
+ </a>
+ </div>
+</div>
+
+{% endextra %}