tajo-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hyun...@apache.org
Subject svn commit: r1583596 [3/19] - in /tajo/site: ./ docs/0.8.0/ docs/0.8.0/_sources/ docs/0.8.0/_sources/configuration/ docs/0.8.0/_sources/functions/ docs/0.8.0/_sources/getting_started/ docs/0.8.0/_sources/table_management/ docs/0.8.0/_static/ docs/0.8.0...
Date Tue, 01 Apr 2014 10:22:26 GMT
Added: tajo/site/docs/0.8.0/table_management/sequencefile.html
URL: http://svn.apache.org/viewvc/tajo/site/docs/0.8.0/table_management/sequencefile.html?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/0.8.0/table_management/sequencefile.html (added)
+++ tajo/site/docs/0.8.0/table_management/sequencefile.html Tue Apr  1 10:22:23 2014
@@ -0,0 +1,324 @@
+
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
+<head>
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  
+  <title>SequenceFile &mdash; Apache Tajo 0.8.0 documentation</title>
+  
+
+  
+  
+
+  
+  <link href='https://fonts.googleapis.com/css?family=Lato:400,700|Roboto+Slab:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>
+
+  
+  
+    
+
+  
+
+  
+  
+    <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
+  
+
+  
+    <link rel="top" title="Apache Tajo 0.8.0 documentation" href="../index.html"/>
+        <link rel="up" title="File Formats" href="file_formats.html"/>
+        <link rel="next" title="Compression" href="compression.html"/>
+        <link rel="prev" title="Parquet" href="parquet.html"/> 
+
+  
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/modernizr/2.6.2/modernizr.min.js"></script>
+
+</head>
+
+<body class="wy-body-for-nav" role="document">
+
+  <div class="wy-grid-for-nav">
+
+    
+    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
+      <div class="wy-side-nav-search">
+        <a href="../index.html" class="fa fa-home"> Apache Tajo</a>
+        <div role="search">
+  <form id ="rtd-search-form" class="wy-form" action="../search.html" method="get">
+    <input type="text" name="q" placeholder="Search docs" />
+    <input type="hidden" name="check_keywords" value="yes" />
+    <input type="hidden" name="area" value="default" />
+  </form>
+</div>
+      </div>
+
+      <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
+        
+        
+            <ul class="current">
+<li class="toctree-l1"><a class="reference internal" href="../introduction.html">Introduction</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../getting_started.html">Getting Started</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../getting_started/prerequisites.html">Prerequisites</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../getting_started/downloading_source.html">Dowload and unpack the source code of Apache Tajo</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../getting_started/building.html">Build source code</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../getting_started/local_setup.html">Setting up a local Tajo cluster</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../getting_started/first_query.html">First query execution</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../configuration.html">Configuration</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/preliminary.html">Preliminary</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/cluster_setup.html">Cluster Setup</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/tajo_master_configuration.html">Tajo Master Configuration</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/worker_configuration.html">Worker Configuration</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/catalog_configuration.html">Catalog Configuration</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../configuration/configuration_defaults.html">Configuration Defaults</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../cli.html">Tajo Shell (TSQL)</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../cli.html#synopsis">Synopsis</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../cli.html#entering-tsql-shell">Entering tsql shell</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../cli.html#meta-commands">Meta Commands</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../sql_language.html">SQL Language</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/data_model.html">Data Model</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/ddl.html">Data Definition Language</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/insert.html">INSERT (OVERWRITE) INTO</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/queries.html">Queries</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/sql_expression.html">SQL Expressions</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../sql_language/predicates.html">Predicates</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../functions.html">Functions</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../functions/math_func_and_operators.html">Math Functions and Operators</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../functions/string_func_and_operators.html">String Functions and Operators</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../functions/datetime_func_and_operators.html">DateTime Functions and Operators</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../functions/network_func_and_operators.html">Network Functions and Operators</a></li>
+</ul>
+</li>
+<li class="toctree-l1 current"><a class="reference internal" href="../table_management.html">Table Management</a><ul class="current">
+<li class="toctree-l2 current"><a class="reference internal" href="file_formats.html">File Formats</a></li>
+<li class="toctree-l2"><a class="reference internal" href="compression.html">Compression</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../table_partitioning.html">Table Partitioning</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../partitioning/intro_to_partitioning.html">Introduction to Partitioning</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../partitioning/column_partitioning.html">Column Partitioning</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../partitioning/range_partitioning.html">Range Partitioning</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../partitioning/hash_partitioning.html">Hash Partitioning</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../backup_and_restore.html">Backup and Restore</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../backup_and_restore/catalog.html">Backup and Restore Catalog</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../hcatalog_integration.html">HCatalog Integration</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../jdbc_driver.html">Tajo JDBC Driver</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="../jdbc_driver.html#how-to-get-jdbc-driver">How to get JDBC driver</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../jdbc_driver.html#setting-the-classpath">Setting the CLASSPATH</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../jdbc_driver.html#an-example-jdbc-client">An Example JDBC Client</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../jdbc_driver.html#appendix">Appendix</a></li>
+<li class="toctree-l2"><a class="reference internal" href="../jdbc_driver.html#faq">FAQ</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="../tajo_client_api.html">Tajo Client API</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../faq.html">FAQ</a></li>
+</ul>
+
+        
+      </div>
+      &nbsp;
+    </nav>
+
+    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
+
+      
+      <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
+        <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
+        <a href="../index.html">Apache Tajo</a>
+      </nav>
+
+
+      
+      <div class="wy-nav-content">
+        <div class="rst-content">
+          <div role="navigation" aria-label="breadcrumbs navigation">
+  <ul class="wy-breadcrumbs">
+    <li><a href="../index.html">Docs</a> &raquo;</li>
+      
+          <li><a href="../table_management.html">Table Management</a> &raquo;</li>
+      
+          <li><a href="file_formats.html">File Formats</a> &raquo;</li>
+      
+    <li>SequenceFile</li>
+      <li class="wy-breadcrumbs-aside">
+        
+          <a href="../_sources/table_management/sequencefile.txt" rel="nofollow"> View page source</a>
+        
+      </li>
+  </ul>
+  <hr/>
+</div>
+          <div role="main">
+            
+  <div class="section" id="sequencefile">
+<h1>SequenceFile<a class="headerlink" href="#sequencefile" title="Permalink to this headline">¶</a></h1>
+<div class="section" id="introduce">
+<h2>Introduce<a class="headerlink" href="#introduce" title="Permalink to this headline">¶</a></h2>
+<p>SequenceFiles are flat files consisting of binary key/value pairs.
+SequenceFile is basic file format which provided by Hadoop, and Hive also provides it to create a table.</p>
+<p>The <tt class="docutils literal"><span class="pre">USING</span> <span class="pre">sequencefile</span></tt> keywords let you create a SequecneFile. Here is an example statement to create a table using <tt class="docutils literal"><span class="pre">SequecneFile</span></tt>:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="nb">text</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="nb">text</span><span class="p">)</span>
+<span class="k">USING</span> <span class="n">sequencefile</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>Also Tajo provides Hive compatibility for SequenceFile. The above statement can be written in Hive as follows:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="n">string</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="n">string</span><span class="p">)</span>
+<span class="n">STORED</span> <span class="k">AS</span> <span class="n">sequencefile</span><span class="p">;</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="serializerdeserializer-serde">
+<h2>SerializerDeserializer (SerDe)<a class="headerlink" href="#serializerdeserializer-serde" title="Permalink to this headline">¶</a></h2>
+<p>There are two SerDe for SequenceFile as follows:</p>
+<blockquote>
+<div><ul class="simple">
+<li>TextSerializerDeserializer: This class can read and write data in plain text file format.</li>
+<li>BinarySerializerDeserializer: This class can read and write data in binary file format.</li>
+</ul>
+</div></blockquote>
+<p>The default is the SerDe for plain text file in Tajo. The above example statement created the table using TextSerializerDeserializer.If you want to use BinarySerializerDeserializer, you can specify it by <tt class="docutils literal"><span class="pre">sequencefile.serde</span></tt> keywords:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="nb">text</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="nb">text</span><span class="p">)</span>
+<span class="k">USING</span> <span class="n">sequencefile</span> <span class="k">with</span> <span class="p">(</span><span class="s1">&#39;sequencefile.serde&#39;</span><span class="o">=</span><span class="s1">&#39;org.apache.tajo.storage.BinarySerializerDeserializer&#39;</span><span class="p">)</span>
+</pre></div>
+</div>
+<p>In Hive, the above statement can be written in Hive as follows:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="n">string</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="n">string</span><span class="p">)</span>
+<span class="k">ROW</span> <span class="n">FORMAT</span> <span class="n">SERDE</span>
+ <span class="s1">&#39;org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe&#39;</span>
+<span class="n">STORED</span> <span class="k">AS</span> <span class="n">sequencefile</span><span class="p">;</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="writer">
+<h2>Writer<a class="headerlink" href="#writer" title="Permalink to this headline">¶</a></h2>
+<p>There are three SequenceFile Writers based on the SequenceFile.CompressionType used to compress key/value pairs:</p>
+<blockquote>
+<div><ul class="simple">
+<li>Writer : Uncompressed records.</li>
+<li>RecordCompressWriter : Record-compressed files, only compress values.</li>
+<li>BlockCompressWriter : Block-compressed files, both keys &amp; values are collected in &#8216;blocks&#8217; separately and compressed. The size of the &#8216;block&#8217; is configurable.</li>
+</ul>
+</div></blockquote>
+<p>The default is Uncompressed Writer in Tajo. If you want to use RecordCompressWriter, you can specify it by <tt class="docutils literal"><span class="pre">compression.type</span></tt> keywords and  <tt class="docutils literal"><span class="pre">compression.codec</span></tt> keywords:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="nb">text</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="nb">text</span><span class="p">)</span>
+<span class="k">USING</span> <span class="n">sequencefile</span> <span class="k">with</span> <span class="p">(</span><span class="s1">&#39;compression.type&#39;</span><span class="o">=</span><span class="s1">&#39;RECORD&#39;</span><span class="p">,</span><span class="s1">&#39;compression.codec&#39;</span><span class="o">=</span><span class="s1">&#39;org.apache.hadoop.io.compress.SnappyCodec&#39;</span><span class="p">)</span>
+</pre></div>
+</div>
+<p>In hive, you need to specify settings as follows:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">hive</span><span class="p">.</span><span class="k">exec</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="k">output</span> <span class="o">=</span> <span class="k">true</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="k">type</span> <span class="o">=</span> <span class="n">RECORD</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="n">codec</span> <span class="o">=</span> <span class="n">org</span><span class="p">.</span><span class="n">apache</span><span class="p">.</span><span class="n">hadoop</span><span class="p">.</span><span class="n">io</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="n">SnappyCodec</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="n">string</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="n">string</span><span class="p">)</span> <span class="n">STORED</span> <span class="k">AS</span> <span class="n">sequencefile</span><span class="p">;;</span>
+</pre></div>
+</div>
+<p>And if you want to use BlockCompressWriter, you can specify it by <tt class="docutils literal"><span class="pre">compression.type</span></tt> keywords and  <tt class="docutils literal"><span class="pre">compression.codec</span></tt> keywords:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="nb">text</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="nb">text</span><span class="p">)</span>
+<span class="k">USING</span> <span class="n">sequencefile</span> <span class="k">with</span> <span class="p">(</span><span class="s1">&#39;compression.type&#39;</span><span class="o">=</span><span class="s1">&#39;BLOCK&#39;</span><span class="p">,</span><span class="s1">&#39;compression.codec&#39;</span><span class="o">=</span><span class="s1">&#39;org.apache.hadoop.io.compress.SnappyCodec&#39;</span><span class="p">)</span>
+</pre></div>
+</div>
+<p>In hive, you need to specify settings as follows:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">hive</span><span class="p">.</span><span class="k">exec</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="k">output</span> <span class="o">=</span> <span class="k">true</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="k">type</span> <span class="o">=</span> <span class="n">BLOCK</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="n">codec</span> <span class="o">=</span> <span class="n">org</span><span class="p">.</span><span class="n">apache</span><span class="p">.</span><span class="n">hadoop</span><span class="p">.</span><span class="n">io</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="n">SnappyCodec</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="n">string</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="n">string</span><span class="p">)</span> <span class="n">STORED</span> <span class="k">AS</span> <span class="n">sequencefile</span><span class="p">;;</span>
+</pre></div>
+</div>
+<p>For reference, you can use TextSerDe or BinarySerDe with compression keywords.
+Here is an example statement for this case.</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="nb">text</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="nb">text</span><span class="p">)</span>
+<span class="k">USING</span> <span class="n">sequencefile</span> <span class="k">with</span> <span class="p">(</span><span class="s1">&#39;sequencefile.serde&#39;</span><span class="o">=</span><span class="s1">&#39;org.apache.tajo.storage.BinarySerializerDeserializer&#39;</span><span class="p">,</span> <span class="s1">&#39;compression.type&#39;</span><span class="o">=</span><span class="s1">&#39;BLOCK&#39;</span><span class="p">,</span><span class="s1">&#39;compression.codec&#39;</span><span class="o">=</span><span class="s1">&#39;org.apache.hadoop.io.compress.SnappyCodec&#39;</span><span class="p">)</span>
+</pre></div>
+</div>
+<p>In hive, you need to specify settings as follows:</p>
+<div class="highlight-sql"><div class="highlight"><pre><span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">hive</span><span class="p">.</span><span class="k">exec</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="k">output</span> <span class="o">=</span> <span class="k">true</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="k">type</span> <span class="o">=</span> <span class="n">BLOCK</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">SET</span> <span class="n">mapred</span><span class="p">.</span><span class="k">output</span><span class="p">.</span><span class="n">compression</span><span class="p">.</span><span class="n">codec</span> <span class="o">=</span> <span class="n">org</span><span class="p">.</span><span class="n">apache</span><span class="p">.</span><span class="n">hadoop</span><span class="p">.</span><span class="n">io</span><span class="p">.</span><span class="n">compress</span><span class="p">.</span><span class="n">SnappyCodec</span><span class="p">;</span>
+<span class="n">hive</span><span class="o">&gt;</span> <span class="k">CREATE</span> <span class="k">TABLE</span> <span class="n">table1</span> <span class="p">(</span><span class="n">id</span> <span class="nb">int</span><span class="p">,</span> <span class="n">name</span> <span class="n">string</span><span class="p">,</span> <span class="n">score</span> <span class="nb">float</span><span class="p">,</span> <span class="k">type</span> <span class="n">string</span><span class="p">)</span>
+      <span class="k">ROW</span> <span class="n">FORMAT</span> <span class="n">SERDE</span>
+        <span class="s1">&#39;org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe&#39;</span>
+      <span class="n">STORED</span> <span class="k">AS</span> <span class="n">sequencefile</span><span class="p">;;</span>
+</pre></div>
+</div>
+</div>
+</div>
+
+
+          </div>
+          <footer>
+  
+    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
+      
+        <a href="compression.html" class="btn btn-neutral float-right" title="Compression"/>Next <span class="fa fa-arrow-circle-right"></span></a>
+      
+      
+        <a href="parquet.html" class="btn btn-neutral" title="Parquet"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+      
+    </div>
+  
+
+  <hr/>
+
+  <div role="contentinfo">
+    <p>
+        &copy; Copyright 2014, Apache Tajo Team.
+    </p>
+  </div>
+
+  <a href="https://github.com/snide/sphinx_rtd_theme">Sphinx theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>
+</footer>
+        </div>
+      </div>
+
+    </section>
+
+  </div>
+  
+
+
+  
+
+    <script type="text/javascript">
+        var DOCUMENTATION_OPTIONS = {
+            URL_ROOT:'../',
+            VERSION:'0.8.0',
+            COLLAPSE_INDEX:false,
+            FILE_SUFFIX:'.html',
+            HAS_SOURCE:  true
+        };
+    </script>
+      <script type="text/javascript" src="../_static/jquery.js"></script>
+      <script type="text/javascript" src="../_static/underscore.js"></script>
+      <script type="text/javascript" src="../_static/doctools.js"></script>
+
+  
+
+  
+  
+    <script type="text/javascript" src="../_static/js/theme.js"></script>
+  
+
+  
+  
+  <script type="text/javascript">
+      jQuery(function () {
+          SphinxRtdTheme.StickyNav.enable();
+      });
+  </script>
+   
+
+</body>
+</html>
\ No newline at end of file

Added: tajo/site/docs/current/.buildinfo
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/.buildinfo?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/.buildinfo (added)
+++ tajo/site/docs/current/.buildinfo Tue Apr  1 10:22:23 2014
@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: bc2afd991aacbe812db57707c3398b4e
+tags: 645f666f9bcd5a90fca523b33c5a78b7

Added: tajo/site/docs/current/_sources/backup_and_restore.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/backup_and_restore.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/backup_and_restore.txt (added)
+++ tajo/site/docs/current/_sources/backup_and_restore.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,8 @@
+************************
+Backup and Restore
+************************
+
+.. toctree::
+    :maxdepth: 1
+
+    backup_and_restore/catalog

Added: tajo/site/docs/current/_sources/backup_and_restore/catalog.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/backup_and_restore/catalog.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/backup_and_restore/catalog.txt (added)
+++ tajo/site/docs/current/_sources/backup_and_restore/catalog.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,48 @@
+***************************
+Backup and Restore Catalog
+***************************
+
+Now, Tajo supports a two backup methods for 
+
+* SQL dump
+* Database-level backup 
+
+==========
+SQL dump 
+==========
+
+SQL dump is an easy and strong way. If you use this approach, you don't need to concern database-level compatiblities. If you want to backup your catalog, just use bin/tajo_dump command. The basic usage of this command is: ::
+
+  $ tajo_dump table_name > outfile
+
+For example, if you want to backup a table customer, you should type a command as follows: ::
+
+  $ bin/tajo_dump customer > table_backup.sql
+  $
+  $ cat table_backup.sql
+  -- Tajo database dump
+  -- Dump date: 10/04/2013 16:28:03
+  --
+
+  --
+  -- Name: customer; Type: TABLE; Storage: CSV
+  -- Path: file:/home/hyunsik/tpch/customer
+  --
+  CREATE EXTERNAL TABLE customer (c_custkey INT8, c_name TEXT, c_address TEXT, c_nationkey INT8, c_phone TEXT, c_acctbal FLOAT8, c_mktsegment TEXT, c_comment TEXT) USING CSV LOCATION 'file:/home/hyunsik/tpch/customer';
+  
+
+If you want to restore the catalog from the SQL dump file, please type the below command: ::
+
+  $ bin/tsql -f table_backup.sql
+
+
+If you use an option '-a', tajo_dump will dump all table DDLs. ::
+
+  $ bin/tajo_dump -a > all_backup.sql
+
+=======================
+Database-level backup
+=======================
+
+.. todo::
+

Added: tajo/site/docs/current/_sources/cli.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/cli.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/cli.txt (added)
+++ tajo/site/docs/current/_sources/cli.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,159 @@
+*****************************
+Tajo Shell (TSQL)
+*****************************
+
+==========
+Synopsis
+==========
+
+.. code-block:: bash
+
+  bin/tsql [options] [database name]
+
+If a *database_name* is given, tsql connects to the database at startup time. Otherwise, tsql connects to ``default`` database.
+
+Options
+
+* ``-c "quoted sql"`` : Execute quoted sql statements, and then the shell will exist.
+* ``-f filename (--file filename)`` : Use the file named filename as the source of commands instead of interactive shell.
+* ``-h hostname (--host hostname)`` : Specifies the host name of the machine on which the Tajo master is running.
+* ``-p port (--port port)`` : Specifies the TCP port. If it is not set, the port will be 26002 in default. 
+
+===================
+Entering tsql shell
+===================
+
+If the hostname and the port num are not given, tsql will try to connect the Tajo master specified in ${TAJO_HOME}/conf/tajo-site.xml. ::
+
+  bin/tsql
+
+  default>
+
+If you want to connect a specified TajoMaster, you should use '-h' and (or) 'p' options as follows: ::
+
+  bin/tsql -h localhost -p 9004
+
+  default> 
+
+The prompt indicates the current database.
+
+===================
+ Meta Commands
+===================
+
+In tsql, anything command that begins with an unquoted backslash ('\') is a tsql meta-command that is processed by tsql itself.
+
+In the current implementation, there are meta commands as follows: ::
+
+  default> \?
+
+  General
+    \copyright  show Apache License 2.0
+    \version    show Tajo version
+    \?          show help
+    \q          quit tsql
+
+
+  Informational
+    \l           list databases
+    \c           show current database
+    \c [DBNAME]  connect to new database
+    \d           list tables
+    \d [TBNAME]  describe table
+    \df          list functions
+    \df NAME     describe function
+
+
+  Variables
+    \set [[NAME] [VALUE]  set session variable or list session variables
+    \unset NAME           unset session variable
+
+
+  Documentations
+    tsql guide        http://tajo.apache.org/docs/0.8.0/cli.html
+    Query language    http://tajo.apache.org/docs/0.8.0/sql_language.html
+    Functions         http://tajo.apache.org/docs/0.8.0/functions.html
+    Backup & restore  http://tajo.apache.org/docs/0.8.0/backup_and_restore.html
+    Configuration     http://tajo.apache.org/docs/0.8.0/configuration.html
+
+-----------------------------------------------
+Basic usages
+-----------------------------------------------
+
+``\l`` command shows a list of all databases.
+
+.. code-block:: sql
+
+  default> \l
+  default
+  tpch
+  work1
+  default> 
+
+``\d`` command shows a list of tables in the current database as follows: ..
+
+  default> \d
+  customer
+  lineitem
+  nation
+  orders
+  part
+  partsupp
+  region
+  supplier
+
+``\d [table name]`` command also shows a table description.
+
+  default> \d orders
+
+  table name: orders
+  table path: hdfs:/xxx/xxx/tpch/orders
+  store type: CSV
+  number of rows: 0
+  volume (bytes): 172.0 MB
+  schema: 
+  o_orderkey      INT8
+  o_custkey       INT8
+  o_orderstatus   TEXT
+  o_totalprice    FLOAT8
+  o_orderdate     TEXT
+  o_orderpriority TEXT
+  o_clerk TEXT
+  o_shippriority  INT4
+  o_comment       TEXT
+
+The prompt ``default>`` indicates the current database. Basically, all SQL statements and meta commands work in the current database. Also, you can change the current database with ``\c`` command.
+
+.. code-block:: sql
+
+  default> \c work1
+  You are now connected to database "test" as user "hyunsik".
+  work1>
+
+-----------------------------------------------
+Session Variables
+-----------------------------------------------
+
+Each client connection to TajoMaster creates a unique session, and the client and TajoMaster uses the session until disconnect. A session provides session variables which are used for various configs per session.
+
+``tsql`` provides the meta command ``\set`` to manipulate session variables. Just ``\set`` command shows all session variables. ::
+
+  default> \set
+  'name1'='val1'
+  'name2'='val2'
+  'name3'='val3'
+       ...
+
+``\set key val`` will set the session variable named *key* with the value *val*. ::
+
+  default> \set
+  'CURRENT_DATABASE'='default'
+  
+  default> \set key1 val1
+
+  default> \set
+  'CURRENT_DATABASE'='default'
+  'key1'='val1'
+
+
+Also, ``\unset key`` will unset the session variable named *key*.
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration.txt (added)
+++ tajo/site/docs/current/_sources/configuration.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,13 @@
+************************
+Configuration
+************************
+
+.. toctree::
+    :maxdepth: 1
+
+    configuration/preliminary
+    configuration/cluster_setup
+    configuration/tajo_master_configuration
+    configuration/worker_configuration
+    configuration/catalog_configuration
+    configuration/configuration_defaults
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration/catalog_configuration.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/catalog_configuration.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/catalog_configuration.txt (added)
+++ tajo/site/docs/current/_sources/configuration/catalog_configuration.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,108 @@
+******************************
+Catalog Configuration
+******************************
+
+If you want to customize the catalog service, copy ``$TAJO_HOME/conf/catalog-site.xml.template`` to ``catalog-site.xml``. Then, add the following configs to catalog-site.xml. Note that the default configs are enough to launch Tajo cluster in most cases.
+
+* tajo.catalog.master.addr - If you want to launch a Tajo cluster in distributed mode, you must specify this address. For more detail information, see [Default Ports](#DefaultPorts).
+* tajo.catalog.store.class - If you want to change the persistent storage of the catalog server, specify the class name. Its default value is tajo.catalog.store.DerbyStore. In the current version, Tajo provides three persistent storage classes as follows:
+
++-----------------------------------+------------------------------------------------+
+| Driver Class                      | Descriptions                                   |
++===================================+================================================+
+| tajo.catalog.store.DerbyStore     | this storage class uses Apache Derby.          |
++-----------------------------------+------------------------------------------------+
+| tajo.catalog.store.MySQLStore     | this storage class uses MySQL.                 |
++-----------------------------------+------------------------------------------------+
+| tajo.catalog.store.MemStore       | this is the in-memory storage. It is only used |
+|                                   | in unit tests to shorten the duration of unit  |
+|                                   | tests.                                         |
++-----------------------------------+------------------------------------------------+
+| tajo.catalog.store.HCatalogStore  | this storage class uses HiveMetaStore.         |
++-----------------------------------+------------------------------------------------+
+
+=========================
+MySQLStore Configuration
+=========================
+
+In order to use MySQLStore, you need to create database and user on MySQL for Tajo.
+
+.. code-block:: sh
+  
+  mysql> create user 'tajo'@'localhost' identified by 'xxxxxx';
+  Query OK, 0 rows affected (0.00 sec)
+
+  mysql> create database tajo;
+  Query OK, 1 row affected (0.00 sec)  
+
+  mysql> grant all on tajo.* to 'tajo'@'localhost';
+  Query OK, 0 rows affected (0.01 sec)
+
+
+And then, you need to prepare MySQL JDBC driver on the machine which can be ran TajoMaster. If you do, you should set ``TAJO_CLASSPATH`` variable in ``conf/tajo-env.sh`` with it as follows:
+
+.. code-block:: sh
+
+  export TAJO_CLASSPATH=/usr/local/mysql/lib/mysql-connector-java-x.x.x.jar
+
+Or you just can copy jdbc driver into $TAJO_HOME/lib.
+
+Finally, you should add the following config to `conf/catalog-site.xml` :
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.catalog.store.class</name>
+    <value>org.apache.tajo.catalog.store.MySQLStore</value>
+  </property>
+  <property>
+    <name>tajo.catalog.jdbc.connection.id</name>
+    <value><mysql user name></value>
+  </property>
+  <property>
+    <name>tajo.catalog.jdbc.connection.password</name>
+    <value><mysql user password></value>
+  </property>
+    <property>
+    <name>tajo.catalog.jdbc.uri</name>
+    <value>jdbc:mysql://<mysql host name>:<mysql port>/<database name for tajo>?createDatabaseIfNotExist=true</value>
+  </property>
+
+
+----------------------------------
+  HCatalogStore Configuration
+----------------------------------
+
+Tajo support HCatalogStore to integrate with hive. If you want to use HCatalogStore, you just do as follows.
+
+First, you must compile source code and get a binary archive as follows:
+
+.. code-block:: sh
+
+  $ git clone https://git-wip-us.apache.org/repos/asf/tajo.git tajo
+  $ mvn clean package -DskipTests -Pdist -Dtar -Phcatalog-0.1x.0
+  $ ls tajo-dist/target/tajo-0.8.0-SNAPSHOT.tar.gz
+
+Tajo support to build based on hive 0.11.0 and hive 0.12.0. If you use hive 0.11.0, you have to set ``-Phcatalog-0.11.0``. And if you use hive 0.12.0, you have to set ``-Phcatalog-0.12.0``.
+
+Second, you must set your hive home directory to HIVE_HOME variable in ``conf/tajo-env.sh`` with it as follows:
+
+.. code-block:: sh
+
+  export HIVE_HOME=/path/to/your/hive/directory
+
+Third, if you need to use jdbc to connect HiveMetaStore, you have to prepare mysql jdbc driver on host which can be ran TajoMaster. If you prepare it, you should set jdbc driver file path to ``HIVE_JDBC_DRIVER_DIR`` variable in conf/tajo-env.sh with it as follows:
+
+.. code-block:: sh
+
+  export HIVE_JDBC_DRIVER_DIR=/path/to/your/mysql_jdbc_driver/mysql-connector-java-x.x.x-bin.jar
+
+
+Lastly, you should add the following config to ``conf/catalog-site.xml`` :
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.catalog.store.class</name>
+    <value>org.apache.tajo.catalog.store.HCatalogStore</value>
+  </property>
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration/cluster_setup.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/cluster_setup.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/cluster_setup.txt (added)
+++ tajo/site/docs/current/_sources/configuration/cluster_setup.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,66 @@
+*******************************************
+Cluster Setup
+*******************************************
+
+Fully Distributed Mode
+==========================================
+A fully distributed mode enables a Tajo instance to run on `Hadoop Distributed File System (HDFS) <http://wiki.apache.org/hadoop/HDFS>`_. In this mode, a number of Tajo workers run across a number of the physical nodes where HDFS data nodes run.
+
+
+In this section, we explain how to setup the cluster mode. 
+
+
+Settings
+--------------------------------------------------------
+
+Please add the following configs to tajo-site.xml file:
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.rootdir</name>
+    <value>hdfs://hostname:port/tajo</value>
+  </property>
+
+  <property>
+    <name>tajo.master.umbilical-rpc.address</name>
+    <value>hostname:26001</value>
+  </property>
+
+  <property>
+    <name>tajo.master.client-rpc.address</name>
+    <value>hostname:26002</value>
+  </property>
+
+  <property>
+    <name>tajo.catalog.client-rpc.address</name>
+    <value>hostname:26005</value>
+  </property>
+
+
+Make base directories and set permissions
+--------------------------------------------------------
+
+If you want to know Tajo’s configuration in more detail, see Configuration page.
+Before launching the tajo, you should create the tajo root dir and set the permission as follows: ::
+
+  $ $HADOOP_HOME/bin/hadoop fs -mkdir       /tajo
+  $ $HADOOP_HOME/bin/hadoop fs -chmod g+w   /tajo
+
+
+Launch a Tajo cluster
+--------------------------------------------------------
+
+Then, execute ``start-tajo.sh`` ::
+
+  $ $TAJO_HOME/bin/start-tajo.sh
+
+.. note::
+
+  In default, each worker is set to very little resource capacity. In order to increase parallel degree, please read 
+  :doc:`/configuration/worker_configuration`.
+
+.. note::
+
+  In default, TajoMaster listens on 127.0.0.1 for clients. To allow remote clients to access TajoMaster, please set tajo.master.client-rpc.address config to tajo-site.xml. In order to know how to change the listen port, please refer :doc:`/configuration/configuration_defaults`.
+

Added: tajo/site/docs/current/_sources/configuration/configuration_defaults.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/configuration_defaults.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/configuration_defaults.txt (added)
+++ tajo/site/docs/current/_sources/configuration/configuration_defaults.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,27 @@
+**********************
+Configuration Defaults
+**********************
+
+Tajo Master Configuration Defaults
+====================================
+
+============================  ==============================================================  ===========   ===============  
+  Service Name                Config Property Name                                            Description   default address 
+============================  ==============================================================  ===========   ===============  
+Tajo Master Umbilical Rpc     tajo.master.umbilical-rpc.address                                             localhost:26001 
+Tajo Master Client Rpc        tajo.master.client-rpc.address                                                localhost:26002 
+Tajo Master Info Http         tajo.master.info-http.address                                                 0.0.0.0:26080   
+Tajo Catalog Client Rpc       tajo.catalog.client-rpc.address                                               localhost:26005
+============================  ==============================================================  ===========   ===============  
+
+====================================
+Tajo Worker Configuration Defaults
+====================================
+
+============================  ==============================================================  ===========   ===============  
+  Service Name                Config Property Name                                            Description   default address 
+============================  ==============================================================  ===========   ===============  
+Tajo Worker Peer Rpc          tajo.worker.peer-rpc.address                                                  0.0.0.0:28091   
+Tajo Worker Client Rpc        tajo.worker.client-rpc.address                                                0.0.0.0:28092   
+Tajo Worker Info Http         tajo.worker.info-http.address                                                 0.0.0.0:28080   
+============================  ==============================================================  ===========   ===============  
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration/preliminary.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/preliminary.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/preliminary.txt (added)
+++ tajo/site/docs/current/_sources/configuration/preliminary.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,40 @@
+***************
+Preliminary
+***************
+
+===================================
+catalog-site.xml and tajo-site.xml
+===================================
+Tajo's configuration is based on Hadoop's configuration system. Tajo uses two config files:
+
+* catalog-site.xml - configuration for the catalog server.
+* tajo-site.xml - configuration for other tajo modules. 
+
+Each config consists of a pair of a name and a value. If you want to set the config name ``a.b.c`` with the value ``123``, add the following element to an appropriate file.
+
+.. code-block:: xml
+
+  <property>
+    <name>a.b.c</name>
+    <value>123</value>
+  </property>
+
+Tajo has a variety of internal configs. If you don't set some config explicitly, the default config will be used for for that config. Tajo is designed to use only a few of configs in usual cases. You may not be concerned with the configuration.
+
+In default, there is no ``tajo-site.xml`` in ``${TAJO}/conf`` directory. If you set some configs, first copy ``$TAJO_HOME/conf/tajo-site.xml.templete`` to ``tajo-site.xml``. Then, add the configs to your tajo-site.
+
+============
+tajo-env.sh
+============
+
+tajo-env.sh is a shell script file. The main purpose of this file is to set shell environment variables for TajoMaster and TajoWorker java program. So, you can set some variable as follows:
+
+.. code-block:: sh
+
+  VARIABLE=value
+
+If a value is a literal string, type this as follows:
+
+.. code-block:: sh
+
+  VARIABLE='value'
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration/tajo_master_configuration.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/tajo_master_configuration.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/tajo_master_configuration.txt (added)
+++ tajo/site/docs/current/_sources/configuration/tajo_master_configuration.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,32 @@
+**************************
+Tajo Master Configuration
+**************************
+
+================================================
+  Tajo Rootdir
+================================================
+
+Tajo uses HDFS as a primary storage layer. So, one Tajo cluster instance should have one tajo rootdir. A user is allowed to specific your tajo rootdir as follows:
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.rootdir</name>
+    <value>hdfs://namenode_hostname:port/path</value>
+  </property>
+
+Tajo rootdir must be a url form like ``scheme://hostname:port/path``. The current implementaion only supports ``hdfs://`` and ``file://`` schemes. The default value is ``file:///tmp/tajo-${user.name}/``.
+
+================================================
+TajoMaster Heap Memory Size
+================================================
+
+The environment variable TAJO_MASTER_HEAPSIZE in conf/tajo-env.sh allow Tajo Master to use the specified heap memory size.
+
+If you want to adjust heap memory size, set ``TAJO_MASTER_HEAPSIZE`` variable in ``conf/tajo-env.sh`` with a proper size as follows:
+
+.. code-block:: sh
+
+  TAJO_MASTER_HEAPSIZE=2000
+
+The default size is 1000 (1GB). 
\ No newline at end of file

Added: tajo/site/docs/current/_sources/configuration/worker_configuration.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/configuration/worker_configuration.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/configuration/worker_configuration.txt (added)
+++ tajo/site/docs/current/_sources/configuration/worker_configuration.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,105 @@
+*********************
+Worker Configuration
+*********************
+
+========================
+Worker Heap Memory Size
+========================
+
+The environment variable ``TAJO_WORKER_HEAPSIZE`` in ``conf/tajo-env.sh`` allow Tajo Worker to use the specified heap memory size.
+
+If you want to adjust heap memory size, set ``TAJO_WORKER_HEAPSIZE`` variable in ``conf/tajo-env.sh`` with a proper size as follows:
+
+.. code-block:: bash
+
+  TAJO_WORKER_HEAPSIZE=8000
+
+The default size is 1000 (1GB).
+
+========================
+Temporary Data Directory
+========================
+
+TajoWorker stores temporary data on local file system due to out-of-core algorithms. It is possible to specify one or more temporary data directories where temporary data will be stored.
+
+``tajo-site.xml``
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.worker.tmpdir.locations</name>
+    <value>/disk1/tmpdir,/disk2/tmpdir,/disk3/tmpdir</value>
+  </property>
+  
+
+==========================================================
+Maximum number of parallel running tasks for each worker
+==========================================================
+
+In Tajo, the capacity of running tasks in parallel are determined by available resources and workload of running queries. In order to specify it, please see [Worker Resources] (#ResourceConfiguration) section.
+
+==========================================================
+Worker Resources
+==========================================================
+
+Each worker can execute multiple tasks simultaneously.
+In Tajo, users can specify the total size of memory and the number of disks for each worker. Available resources affect how many tasks are executed simultaneously.
+
+In order to specify the resource capacity of each worker, you should add the following configs to ``tajo-site.xml`` :
+
+=================================  ==========================  ===================   =========================
+  property name                     description                value type            default value            
+=================================  ==========================  ===================   =========================
+  tajo.worker.resource.cpu-cores    the number of cpu cores    integer               1                        
+  tajo.worker.resource.memory-mb    memory size (MB)           integer               1024                     
+  tajo.worker.resource.disks        the number of disks        integer               1                        
+=================================  ==========================  ===================   =========================
+
+.. note:: 
+  
+  Currently, QueryMaster requests 512MB memory and 1.0 disk per task for the backward compatibility.
+
+------------
+ Example
+------------
+
+Assume that you want to give 5120 MB memory, 6.0 disks, and 24 cores on each worker. The example configuration is as follows:
+
+``tajo-site.xml``
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.worker.resource.tajo.worker.resource.cpu-cores</name>
+    <value>24</value>
+  </property>
+  
+   <property>
+    <name>tajo.worker.resource.memory-mb</name>
+    <value>5120</value>
+  </property>
+  
+  <property>
+    <name>tajo.worker.resource.tajo.worker.resource.disks</name>
+    <value>6.0</value>
+  </property>  
+
+--------------------
+ Dedicated Mode
+--------------------
+Tajo provides a dedicated mode that allows each worker in a Tajo cluster to use whole available system resources including cpu-cores, memory, and disks. For this mode, a user should add the following config to ``tajo-site.xml`` : 
+
+.. code-block:: xml
+
+  <property>
+    <name>tajo.worker.resource.dedicated</name>
+    <value>true</value>
+  </property>
+
+In addition, it can limit the memory capacity used for Tajo worker as follows:
+
+===============================================  ================================================   ===================   =======================
+  property name                                  description                                        value type            default value           
+===============================================  ================================================   ===================   =======================
+  tajo.worker.resource.dedicated-memory-ratio    how much memory to be used in whole memory         float                 0.8                     
+===============================================  ================================================   ===================   =======================
\ No newline at end of file

Added: tajo/site/docs/current/_sources/faq.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/faq.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/faq.txt (added)
+++ tajo/site/docs/current/_sources/faq.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,5 @@
+*************************************
+FAQ
+*************************************
+
+.. todo::
\ No newline at end of file

Added: tajo/site/docs/current/_sources/functions.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/functions.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/functions.txt (added)
+++ tajo/site/docs/current/_sources/functions.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,11 @@
+******************
+Functions
+******************
+
+.. toctree::
+    :maxdepth: 1
+
+    functions/math_func_and_operators
+    functions/string_func_and_operators
+    functions/datetime_func_and_operators
+    functions/network_func_and_operators
\ No newline at end of file

Added: tajo/site/docs/current/_sources/functions/datetime_func_and_operators.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/functions/datetime_func_and_operators.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/functions/datetime_func_and_operators.txt (added)
+++ tajo/site/docs/current/_sources/functions/datetime_func_and_operators.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,42 @@
+********************************
+DateTime Functions and Operators
+********************************
+
+.. function:: utc_usec_to (string text , long timestamp , int dayOfWeek)
+
+  * If the **first parameter** is 'day'.
+
+    Shifts and return a UNIX timestamp in microseconds to the beginning of the day it occurs in.
+    For example, if unix_timestamp occurs on May 19th at 08:58, this function returns a UNIX timestamp for May 19th at 00:00 (midnight).
+
+  * If the **first parameter** is 'hour'.
+
+    Shifts and return a UNIX timestamp in microseconds to the beginning of the hour it occurs in.
+    For example, if unix_timestamp occurs at 08:58, this function returns a UNIX timestamp for 08:00 on the same day.
+
+  * If the **first parameter** is 'month'.
+
+    Shifts and return a UNIX timestamp in microseconds to the beginning of the month it occurs in.
+    For example, if unix_timestamp occurs on March 19th, this function returns a UNIX timestamp for March 1st of the same year.
+
+  * If the **first parameter** is 'year'.
+
+    Returns a UNIX timestamp in microseconds that represents the year of the unix_timestamp argument.
+    For example, if unix_timestamp occurs in 2010, the function returns 1274259481071200, the microsecond representation of 2010-01-01 00:00.
+
+  * If the **first parameter** is 'week' and **third parameter** is 2 i.e (TUESDAY)
+
+    Returns a UNIX timestamp in microseconds that represents a day in the week of the
+    For example, if unix_timestamp occurs on Friday, 2008-04-11, and you set day_of_week to 2 (Tuesday), the function returns a UNIX timestamp for Tuesday, 2008-04-08.
+
+  :param string: could be 'day' 'hour' 'month' 'year' 'week'
+  :param long: unix timestamp in microseconds
+  :param int: day of the week from 0 (Sunday) to 6 (Saturday).Optional parameter required only if first parameter is 'week'
+  :rtype: long
+  :alias: utc_usec_to
+  :example:
+
+  .. code-block:: sql
+
+    SELECT utc_usec_to('day', 1274259481071200);
+    > 1274227200000000
\ No newline at end of file

Added: tajo/site/docs/current/_sources/functions/math_func_and_operators.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/functions/math_func_and_operators.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/functions/math_func_and_operators.txt (added)
+++ tajo/site/docs/current/_sources/functions/math_func_and_operators.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,5 @@
+*****************************
+Math Functions and Operators
+*****************************
+
+.. todo::
\ No newline at end of file

Added: tajo/site/docs/current/_sources/functions/network_func_and_operators.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/functions/network_func_and_operators.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/functions/network_func_and_operators.txt (added)
+++ tajo/site/docs/current/_sources/functions/network_func_and_operators.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,78 @@
+*******************************
+Network Functions and Operators
+*******************************
+
+=============
+Prerequisites
+=============
+
+Apache Tajo provides network functions and operations using GeoIP databases.
+To use these functions and operations, the GeoIP database should be precedently installed in local disks of
+all the workers.
+(Please refer the install instruction in http://dev.maxmind.com/geoip/legacy/downloadable/)
+
+Once the GeoIP database is installed, you should specify the install location in ``conf/tajo-site.xml``
+as follows. ::
+
+  <property>
+    <name>tajo.function.geoip-database-location</name>
+    <value>/path/to/geoip/database/file</value>
+  </property>
+
+===================
+Supported Functions
+===================
+
+.. function:: geoip_country_code (string addr)
+
+  Convert an ipv4 address string to a geoip country code.
+
+  :param addr: ipv4 address string
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select geoip_country_code('163.152.71.31')
+    > 'KR'
+
+.. function:: geoip_country_code (inet4 addr)
+
+  Convert an ipv4 address to a geoip country code.
+
+  :param addr: ipv4 address
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select geoip_country_code(163.152.71.31)
+    > 'KR'
+
+.. function:: geoip_in_country (string addr, string code)
+
+  If the given country code is same with the country code of the given address, it returns true. Otherwise, returns false.
+
+  :param addr: ipv4 address string
+  :param code: country code
+  :rtype: boolean
+  :example:
+
+  .. code-block:: sql
+
+    select geoip_in_country('163.152.71.31', 'KR')
+    > true
+
+.. function:: geoip_in_country (inet4 addr, string code)
+
+  If the given country code is same with the country code of the given address, it returns true. Otherwise, returns false.
+
+  :param addr: ipv4 address
+  :param code: country code
+  :rtype: boolean
+  :example:
+
+  .. code-block:: sql
+
+    select geoip_in_country(163.152.71.31, 'KR')
+    > true
\ No newline at end of file

Added: tajo/site/docs/current/_sources/functions/string_func_and_operators.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/functions/string_func_and_operators.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/functions/string_func_and_operators.txt (added)
+++ tajo/site/docs/current/_sources/functions/string_func_and_operators.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,154 @@
+*******************************
+String Functions and Operators
+*******************************
+
+.. function:: str1 || str2
+
+  Returns the concatnenated string of both side strings ``str1`` and ``str2``.
+
+  :param str1: first string
+  :param str2: second string
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select ‘Ta’ || ‘jo’; 
+    > 'Tajo'
+  
+
+.. function:: char_length (string text)
+
+  Returns Number of characters in string
+
+  :param string: to be counted
+  :rtype: int4
+  :alias: character_length
+  :example:
+
+  .. code-block:: sql
+
+    select char_length(‘Tajo’);
+    > 4
+
+
+.. function:: trim([leading | trailing | both] [characters] from string)
+
+  Removes the characters (a space by default) from the start/end/both ends of the string
+
+  :param string: 
+  :param characters: 
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select trim(both ‘x’ from ‘xTajoxx’);
+    > Tajo   
+
+
+.. function:: btrim(string text, [characters text])
+
+  Removes the characters (a space by default) from the both ends of the string
+  
+  :param string: 
+  :param characters: 
+  :rtype: text
+  :alias: trim
+  :example:
+
+  .. code-block:: sql
+
+    select btrim(‘xTajoxx’, ‘x’);
+    > Tajo 
+
+
+.. function:: ltrim(string text, [characters text])
+
+  Removes the characters (a space by default) from the start ends of the string
+
+  :param string: 
+  :param characters: 
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select ltrim(‘xxTajo’, ‘x’);
+    > Tajo 
+
+
+.. function:: rtrim(string text, [characters text])
+
+  Removes the characters (a space by default) from the end ends of the string
+
+  :param string: 
+  :param characters: 
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select rtrim('Tajoxx', 'x');
+    > Tajo 
+
+
+.. function:: split_part(string text, delimiter text, field int)
+
+  Splits a string on delimiter and return the given field (counting from one)
+
+  :param string: 
+  :param delimiter: 
+  :param field: 
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select split_part(‘ab_bc_cd’,‘_’,2);   
+    > bc 
+
+
+
+.. function:: regexp_replace(string text, pattern text, replacement text)
+
+  Replaces substrings matched to a given regular expression pattern
+
+  :param string: 
+  :param pattern: 
+  :param replacement: 
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select regexp_replace(‘abcdef’, ‘(ˆab|ef$)’, ‘–’); 
+    > –cd–
+
+
+.. function:: upper(string text)
+
+  makes an input text to be upper case
+
+  :param string:
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select upper('tajo');
+    > TAJO
+
+
+.. function:: lower(string text)
+
+  makes an input text to be lower case
+
+  :param string:
+  :rtype: text
+  :example:
+
+  .. code-block:: sql
+
+    select lower('TAJO');
+    > tajo

Added: tajo/site/docs/current/_sources/getting_started.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started.txt (added)
+++ tajo/site/docs/current/_sources/getting_started.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,14 @@
+***************
+Getting Started
+***************
+
+In this section, we explain setup of a standalone Tajo instance. It will run against the local filesystem. In later sections, we will present how to run Tajo cluster instance on Apache Hadoop's HDFS, a distributed filesystem. This section shows you how to start up a Tajo cluster, create tables in your Tajo cluster, submit SQL queries via Tajo shell, and shutting down your Tajo cluster instance. The below exercise should take no more than ten minutes.
+
+.. toctree::
+  :maxdepth: 1
+
+  getting_started/prerequisites
+  getting_started/downloading_source
+  getting_started/building
+  getting_started/local_setup
+  getting_started/first_query
\ No newline at end of file

Added: tajo/site/docs/current/_sources/getting_started/building.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started/building.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started/building.txt (added)
+++ tajo/site/docs/current/_sources/getting_started/building.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,22 @@
+*****************
+Build source code
+*****************
+
+You prepare the prerequisites and the source code, you can build the source code now.
+
+The first step of the installation procedure is to configure the source tree for your system and choose the options you would like. This is done by running the configure script. For a default installation simply enter:
+
+You can compile source code and get a binary archive as follows:
+
+.. code-block:: bash
+
+  $ cd tajo-x.y.z
+  $ mvn clean package -DskipTests -Pdist -Dtar
+  $ ls tajo-dist/target/tajo-x.y.z-SNAPSHOT.tar.gz
+
+Then, after you move some proper directory, discompress the tar.gz file as follows:
+
+.. code-block:: bash
+
+  $ cd [a directory to be parent of tajo binary]
+  $ tar xzvf ${TAJO_SRC}/tajo-dist/target/tajo-x.y.z-SNAPSHOT.tar.gz
\ No newline at end of file

Added: tajo/site/docs/current/_sources/getting_started/downloading_source.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started/downloading_source.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started/downloading_source.txt (added)
+++ tajo/site/docs/current/_sources/getting_started/downloading_source.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,32 @@
+****************************************************
+Dowload and unpack the source code of Apache Tajo
+****************************************************
+
+You can get either the source code release of Apache Tajo or check out the development code base from Git.
+
+================================================
+Dowload the latest source release
+================================================
+
+Choose a download site from this list of `Apache Download Mirrors <http://www.apache.org/dyn/closer.cgi/incubator/tajo>`_.
+Click on the suggested mirror link. This will take you to a mirror of Tajo Releases. 
+Download the file that ends in .tar.gz to your local filesystem; e.g. tajo-0.8.0-incubating.tar.gz. 
+
+Decompress and untar your download and then change into the unpacked directory. ::
+
+  tar xzvf tajo-0.8.0-incubating.tar.gz
+
+================================================
+Get the source code via Git
+================================================
+
+The development codebase can also be downloaded from `the Apache git repository <https://git-wip-us.apache.org/repos/asf/tajo.git>`_ as follows: ::
+
+  git clone https://git-wip-us.apache.org/repos/asf/tajo.git
+
+A read-only git repository is also mirrored on `Github <https://github.com/apache/tajo>`_.
+
+Once you have downloaded Tajo, follow the `getting started instructions <http://tajo.apache.org/tajo-0.8.0-doc.html#GettingStarted>`_, and take a look at the rest of the Tajo documentation.
+
+
+

Added: tajo/site/docs/current/_sources/getting_started/first_query.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started/first_query.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started/first_query.txt (added)
+++ tajo/site/docs/current/_sources/getting_started/first_query.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,78 @@
+************************
+First query execution
+************************
+
+First of all, we need to prepare some table for query execution. For example, you can make a simple text-based table as follows: 
+
+.. code-block:: bash
+
+  $ mkdir /home/x/table1
+  $ cd /home/x/table1
+  $ cat > data.csv
+  1|abc|1.1|a
+  2|def|2.3|b
+  3|ghi|3.4|c
+  4|jkl|4.5|d
+  5|mno|5.6|e
+  <CTRL + D>
+
+
+Apache Tajo™ provides a SQL shell which allows users to interactively submit SQL queries. In order to use this shell, please execute ``bin/tsql`` ::
+
+  $ $TAJO_HOME/bin/tsql
+  tajo>
+
+In order to load the table we created above, we should think of a schema of the table.
+Here, we assume the schema as (int, text, float, text). ::
+
+  $ $TAJO_HOME/bin/tsql
+  tajo> create external table table1 (
+        id int,
+        name text, 
+        score float, 
+        type text) 
+        using csv with ('csvfile.delimiter'='|') location 'file:/home/x/table1';
+
+To load an external table, you need to use ‘create external table’ statement. 
+In the location clause, you should use the absolute directory path with an appropriate scheme. 
+If the table resides in HDFS, you should use ‘hdfs’ instead of ‘file’.
+
+If you want to know DDL statements in more detail, please see Query Language. ::
+
+  tajo> \d
+  table1
+
+ ``\d`` command shows the list of tables. ::
+
+  tajo> \d table1
+
+  table name: table1
+  table path: file:/home/x/table1
+  store type: CSV
+  number of rows: 0
+  volume (bytes): 78 B
+  schema:
+  id      INT
+  name    TEXT
+  score   FLOAT
+  type    TEXT
+
+``\d [table name]`` command shows the description of a given table.
+
+Also, you can execute SQL queries as follows: ::
+
+  tajo> select * from table1 where id > 2;
+  final state: QUERY_SUCCEEDED, init time: 0.069 sec, response time: 0.397 sec
+  result: file:/tmp/tajo-hadoop/staging/q_1363768615503_0001_000001/RESULT, 3 rows ( 35B)
+
+  id,  name,  score,  type
+  - - - - - - - - - -  - - -
+  3,  ghi,  3.4,  c
+  4,  jkl,  4.5,  d
+  5,  mno,  5.6,  e
+
+  tajo> exit
+  bye
+
+Feel free to enjoy Tajo with SQL standards. 
+If you want to know more explanation for SQL supported by Tajo, please refer :doc:`/sql_language`.
\ No newline at end of file

Added: tajo/site/docs/current/_sources/getting_started/local_setup.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started/local_setup.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started/local_setup.txt (added)
+++ tajo/site/docs/current/_sources/getting_started/local_setup.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,25 @@
+**********************************
+Setting up a local Tajo cluster
+**********************************
+
+Apache Tajo™ provides two run modes: local mode and fully distributed mode. Here, we explain only the local mode where a Tajo instance runs on a local file system. A local mode Tajo instance can start up with very simple configurations.
+
+First of all, you need to add the environment variables to conf/tajo-env.sh.
+
+.. code-block:: bash
+
+  # Hadoop home. Required
+  export HADOOP_HOME= ...
+
+  # The java implementation to use.  Required.
+  export JAVA_HOME= ...
+
+To launch the tajo master, execute start-tajo.sh.
+
+.. code-block:: bash
+
+  $ $TAJO_HOME/bin/start-tajo.sh
+
+.. note::
+
+  If you want to how to setup a fully distributed mode of Tajo, please see :doc:`/configuration/cluster_setup`.

Added: tajo/site/docs/current/_sources/getting_started/prerequisites.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/getting_started/prerequisites.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/getting_started/prerequisites.txt (added)
+++ tajo/site/docs/current/_sources/getting_started/prerequisites.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,7 @@
+**********************
+Prerequisites
+**********************
+
+ * Hadoop 2.2.0 or higher
+ * Java 1.6 or higher
+ * Protocol buffer 2.5.0
\ No newline at end of file

Added: tajo/site/docs/current/_sources/hcatalog_integration.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/hcatalog_integration.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/hcatalog_integration.txt (added)
+++ tajo/site/docs/current/_sources/hcatalog_integration.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,39 @@
+*************************************
+HCatalog Integration
+*************************************
+
+Apache Tajo™ catalog supports HCatalogStore driver to integrate with Apache Hive™. 
+This integration allows Tajo to access all tables used in Apache Hive. 
+Depending on your purpose, you can execute either SQL queries or HiveQL queries on the 
+same tables managed in Apache Hive.
+
+In order to use this feature, you need to build Tajo with a specified maven profile 
+and then add some configs into ``conf/tajo-env.sh`` and ``conf/catalog-site.xml``. 
+This section describes how to setup HCatalog integration. 
+This instruction would take no more than ten minutes.
+
+First, you need to compile the source code with hcatalog profile. 
+Currently, Tajo supports hcatalog-0.11.0 and hcatalog-0.12.0 profile.
+So, if you want to use Hive 0.11.0, you need to set ``-Phcatalog-0.11.0`` as the maven profile ::
+
+  $ mvn clean package -DskipTests -Pdist -Dtar -Phcatalog-0.11.0
+
+Or, if you want to use Hive 0.12.0, you need to set ``-Phcatalog-0.12.0`` as the maven profile ::
+
+  $ mvn clean package -DskipTests -Pdist -Dtar -Phcatalog-0.12.0
+
+Then, you need to set your Hive home directory to the environment variable ``HIVE_HOME`` in conf/tajo-env.sh as follows: ::
+
+  export HIVE_HOME=/path/to/your/hive/directory
+
+If you need to use jdbc to connect HiveMetaStore, you have to prepare MySQL jdbc driver.
+Next, you should set the path of MySQL JDBC driver jar file to the environment variable HIVE_JDBC_DRIVER_DIR in conf/tajo-env.sh as follows: ::
+
+  export HIVE_JDBC_DRIVER_DIR==/path/to/your/mysql_jdbc_driver/mysql-connector-java-x.x.x-bin.jar
+
+Finally, you should specify HCatalogStore as Tajo catalog driver class in ``conf/catalog-site.xml`` as follows: ::
+
+  <property>
+    <name>tajo.catalog.store.class</name>
+    <value>org.apache.tajo.catalog.store.HCatalogStore</value>
+  </property>

Added: tajo/site/docs/current/_sources/index.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/index.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/index.txt (added)
+++ tajo/site/docs/current/_sources/index.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,46 @@
+.. Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+.. http://www.apache.org/licenses/LICENSE-2.0
+
+.. Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+.. Apache Tajo documentation master file, created by
+   sphinx-quickstart on Thu Feb 27 08:29:11 2014.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Apache Tajo™ 0.8.0 (dev) - User documentation
+===========================================================================
+
+Table of Contents:
+
+.. toctree::
+   :maxdepth: 3
+
+   introduction
+   getting_started
+   configuration
+   cli
+   sql_language
+   functions
+   table_management
+   table_partitioning
+   backup_and_restore
+   hcatalog_integration
+   jdbc_driver   
+   tajo_client_api
+   faq
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

Added: tajo/site/docs/current/_sources/introduction.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/introduction.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/introduction.txt (added)
+++ tajo/site/docs/current/_sources/introduction.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,13 @@
+***************
+Introduction
+***************
+
+The main goal of Apache Tajo project is to build an advanced open source
+data warehouse system in Hadoop for processing web-scale data sets. 
+Basically, Tajo provides SQL standard as a query language.
+Tajo is designed for both interactive and batch queries on data sets
+stored on HDFS and other data sources. Without hurting query response
+times, Tajo provides fault-tolerance and dynamic load balancing which
+are necessary for long-running queries. Tajo employs a cost-based and
+progressive query optimization techniques for reoptimizing running
+queries in order to avoid the worst query plans.
\ No newline at end of file

Added: tajo/site/docs/current/_sources/jdbc_driver.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/jdbc_driver.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/jdbc_driver.txt (added)
+++ tajo/site/docs/current/_sources/jdbc_driver.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,139 @@
+*************************************
+Tajo JDBC Driver
+*************************************
+
+Apache Tajo™ provides JDBC driver
+which enables Java applciations to easily access Apache Tajo in a RDBMS-like manner.
+In this section, we explain how to get JDBC driver and an example code.
+
+How to get JDBC driver
+=======================
+
+Tajo provides some necesssary jar files packaged by maven. In order get the jar files, 
+please follow the below commands.
+
+.. code-block:: bash
+
+  $ cd tajo-x.y.z-incubating
+  $ mvn clean package -DskipTests -Pdist -Dtar
+  $ ls -l tajo-dist/target/tajo-x.y.z-incubating/share/jdbc-dist
+
+
+Setting the CLASSPATH
+=======================
+
+In order to use the JDBC driver, you should set the jar files included in 
+``tajo-dist/target/tajo-x.y.z-incubating/share/jdbc-dist`` to your ``CLASSPATH``.
+In addition, you should add hadoop clsspath into your ``CLASSPATH``.
+So, ``CLASSPATH`` will be set as follows:
+
+.. code-block:: bash
+
+  CLASSPATH=path/to/tajo-jdbc/*:${TAJO_HOME}/conf:$(hadoop classpath)
+
+.. note::
+
+  You can get ${hadoop classpath} by executing  the command ``bin/hadoop classpath`` in your hadoop cluster.
+
+.. note::
+
+  You may want to a minimal set of JAR files. If so, please refer :ref:`minimal_jar_files`.
+
+An Example JDBC Client
+=======================
+
+The JDBC driver class name is ``org.apache.tajo.jdbc.TajoDriver``.
+You can get the driver ``Class.forName("org.apache.tajo.jdbc.TajoDriver").newInstance()``.
+The connection url should be ``jdbc:tajo://<TajoMaster hostname>:<TajoMaster client rpc port>``.
+The default TajoMaster client rpc port is ``26002``.
+If you want to change the listening port, please refer :doc:`/configuration/configuration_defaults`.
+
+.. note::
+  
+  Currently, Tajo does not support the concept of database and namespace. 
+  All tables are contained in ``default`` database. So, you don't need to specify any database name.
+
+The following shows an example of JDBC Client.
+
+.. code-block:: java
+
+  import java.sql.Connection;
+  import java.sql.ResultSet;
+  import java.sql.Statement;
+  import java.sql.DriverManager;
+
+  public class TajoJDBCClient {
+    
+    ....
+
+    public static void main(String[] args) throws Exception {
+      Class.forName("org.apache.tajo.jdbc.TajoDriver").newInstance();
+      Connection conn = DriverManager.getConnection("jdbc:tajo://127.0.0.1:26002");
+
+      Statement stmt = null;
+      ResultSet rs = null;
+      try {
+        stmt = conn.createStatement();
+        rs = stmt.executeQuery("select * from table1");
+        while (rs.next()) {
+          System.out.println(rs.getString(1) + "," + rs.getString(3));
+        }
+      } finally {
+        if (rs != null) rs.close();
+        if (stmt != null) stmt.close();
+        if (conn != null) conn.close();
+      }
+    }
+  }
+
+
+Appendix
+===========================================
+
+.. _minimal_jar_files:
+
+Minimal JAR file list
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The following JAR files are necessary minimal JAR file list.
+We've tested JDBC drivers with the following JAR files for
+usual SQL queries. But, they does not guarantee that they are 
+fully tested for all operations. So, you may need additional JAR files.
+In addition to the following JAR files, please don't forgot including
+``${HADOOP_HOME}/eta/hadoop`` and ``${TAJO_HOME}/conf`` in your ``CLASSPATH``.
+
+  * hadoop-annotations-2.2.0.jar
+  * hadoop-auth-2.2.0.jar
+  * hadoop-common-2.2.0.jar
+  * hadoop-hdfs-2.2.0.jar
+  * joda-time-2.3.jar
+  * tajo-catalog-common-0.8.0-SNAPSHOT.jar
+  * tajo-client-0.8.0-SNAPSHOT.jar
+  * tajo-common-0.8.0-SNAPSHOT.jar
+  * tajo-jdbc-0.8.0-SNAPSHOT.jar
+  * tajo-rpc-0.8.0-SNAPSHOT.jar
+  * tajo-storage-0.8.0-SNAPSHOT.jar
+  * log4j-1.2.17.jar
+  * commons-logging-1.1.1.jar
+  * guava-11.0.2.jar
+  * protobuf-java-2.5.0.jar
+  * netty-3.6.6.Final.jar
+  * commons-lang-2.5.jar
+  * commons-configuration-1.6.jar
+  * slf4j-api-1.7.5.jar
+  * slf4j-log4j12-1.7.5.jar
+  * commons-cli-1.2.jar
+  * commons-io-2.1.jar"
+
+
+FAQ
+===========================================
+
+java.nio.channels.UnresolvedAddressException
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+When retriving the final result, Tajo JDBC Driver tries to access HDFS data nodes.
+So, the network access between JDBC client and HDFS data nodes must be available.
+In many cases, a HDFS cluster is built in a private network which use private hostnames.
+So, the host names must be shared with the JDBC client side.
+

Added: tajo/site/docs/current/_sources/partitioning/column_partitioning.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/partitioning/column_partitioning.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/partitioning/column_partitioning.txt (added)
+++ tajo/site/docs/current/_sources/partitioning/column_partitioning.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,5 @@
+*********************************
+Column Partitioning
+*********************************
+
+.. todo::
\ No newline at end of file

Added: tajo/site/docs/current/_sources/partitioning/hash_partitioning.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/partitioning/hash_partitioning.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/partitioning/hash_partitioning.txt (added)
+++ tajo/site/docs/current/_sources/partitioning/hash_partitioning.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,5 @@
+********************************
+Hash Partitioning
+********************************
+
+.. todo::
\ No newline at end of file

Added: tajo/site/docs/current/_sources/partitioning/intro_to_partitioning.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/partitioning/intro_to_partitioning.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/partitioning/intro_to_partitioning.txt (added)
+++ tajo/site/docs/current/_sources/partitioning/intro_to_partitioning.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,16 @@
+**************************************
+Introduction to Partitioning
+**************************************
+
+======================
+Partition Key
+======================
+
+=========================
+Partitioning Methods
+=========================
+
+Tajo provides the following partitioning methods:
+ * Column Partitioning
+ * Range Partitioning (TODO)
+ * Hash Partitioning (TODO)
\ No newline at end of file

Added: tajo/site/docs/current/_sources/partitioning/range_partitioning.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/partitioning/range_partitioning.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/partitioning/range_partitioning.txt (added)
+++ tajo/site/docs/current/_sources/partitioning/range_partitioning.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,5 @@
+***************************
+Range Partitioning
+***************************
+
+.. todo::
\ No newline at end of file

Added: tajo/site/docs/current/_sources/sql_language.txt
URL: http://svn.apache.org/viewvc/tajo/site/docs/current/_sources/sql_language.txt?rev=1583596&view=auto
==============================================================================
--- tajo/site/docs/current/_sources/sql_language.txt (added)
+++ tajo/site/docs/current/_sources/sql_language.txt Tue Apr  1 10:22:23 2014
@@ -0,0 +1,13 @@
+************
+SQL Language
+************
+
+.. toctree::
+    :maxdepth: 1
+
+    sql_language/data_model
+    sql_language/ddl
+    sql_language/insert
+    sql_language/queries    
+    sql_language/sql_expression
+    sql_language/predicates
\ No newline at end of file



Mime
View raw message