You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@orc.apache.org by om...@apache.org on 2015/06/22 23:07:28 UTC
[4/8] orc git commit: Publish first version of site.
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/hive-ddl.html
----------------------------------------------------------------------
diff --git a/docs/hive-ddl.html b/docs/hive-ddl.html
new file mode 100644
index 0000000..310bbfb
--- /dev/null
+++ b/docs/hive-ddl.html
@@ -0,0 +1,998 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Hive DDL</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Hive DDL</h1>
+ <p>ORC is well integrated into Hive, so storing your istari table as ORC
+is done by adding “STORED AS ORC”.</p>
+
+<p><code>CREATE TABLE istari (
+ name STRING,
+ color STRING
+) STORED AS ORC;
+</code></p>
+
+<p>To modify a table so that new partitions of the istari table are
+stored as ORC files:</p>
+
+<p><code>ALTER TABLE istari SET FILEFORMAT ORC;
+</code></p>
+
+<p>As of Hive 0.14, users can request an efficient merge of small ORC files
+together by issuing a CONCATENATE command on their table or partition. The
+files will be merged at the stripe level without reserializatoin.</p>
+
+<p><code>ALTER TABLE istari [PARTITION partition_spec] CONCATENATE;
+</code></p>
+
+<p>To get information about an ORC file, use the orcfiledump command.</p>
+
+<p><code>% hive --orcfiledump <path_to_file>
+</code></p>
+
+<p>As of Hive 1.1, to display the data in the ORC file, use:</p>
+
+<p><code>% hive --orcfiledump -d <path_to_file>
+</code></p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+
+
+ <a href="/docs/acid.html" class="prev">Back</a>
+
+ </div>
+ <div class="right align-left">
+
+
+
+ <a href="/docs/hive-config.html" class="next">Next</a>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/index.html
----------------------------------------------------------------------
diff --git a/docs/index.html b/docs/index.html
new file mode 100644
index 0000000..8eae9af
--- /dev/null
+++ b/docs/index.html
@@ -0,0 +1,984 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Background</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Background</h1>
+ <p>Back in January 2013, we created ORC files as part of the initiative
+to massively speed up Apache Hive and improve the storage efficiency
+of data stored in Apache Hadoop. The focus was on enabling high speed
+processing and reducing file sizes.</p>
+
+<p>ORC is a self-describing type-aware columnar file format designed for
+Hadoop workloads. It is optimized for large streaming reads, but with
+integrated support for finding required rows quickly. Storing data in
+a columnar format lets the reader read, decompress, and process only
+the values that are required for the current query. Because ORC files
+are type-aware, the writer chooses the most appropriate encoding for
+the type and builds an internal index as the file is written.</p>
+
+<p>Predicate pushdown uses those indexes to determine which stripes in a
+file need to be read for a particular query and the row indexes can
+narrow the search to a particular set of 10,000 rows. ORC supports the
+complete set of types in Hive, including the complex types: structs,
+lists, maps, and unions.</p>
+
+<p>Many large Hadoop users have adopted ORC. For instance, Facebook uses
+ORC to <a href="http://s.apache.org/fb-scaling-300-pb">save tens of petabytes</a>
+in their data warehouse and demonstrated that ORC is <a href="http://s.apache.org/presto-orc">significantly
+faster</a> than RC File or Parquet. Yahoo
+uses ORC to store their production data and has released some of their
+<a href="http://s.apache.org/yahoo-orc">benchmark results</a>.</p>
+
+<p>ORC files are divided in to <em>stripes</em> that are roughly 64MB by
+default. The stripes in a file are independent of each other and form
+the natural unit of distributed work. Within each stripe, the columns
+are separated from each other so the reader can read just the columns
+that are required.</p>
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+ <span class="prev disabled">Back</span>
+
+ </div>
+ <div class="right align-left">
+
+
+
+ <a href="/docs/types.html" class="next">Next</a>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/indexes.html
----------------------------------------------------------------------
diff --git a/docs/indexes.html b/docs/indexes.html
new file mode 100644
index 0000000..9ae634a
--- /dev/null
+++ b/docs/indexes.html
@@ -0,0 +1,989 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Indexes</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Indexes</h1>
+ <p>ORC provides three level of indexes within each file:</p>
+
+<ul>
+ <li>file level - statistics about the values in each column across the entire
+file</li>
+ <li>stripe level - statistics about the values in each column for each stripe</li>
+ <li>row level - statistics about the values in each column for each set of
+10,000 rows within a stripe</li>
+</ul>
+
+<p>The file and stripe level column statistics are in the file footer so
+that they are easy to access to determine if the rest of the file
+needs to be read at all. Row level indexes include both the column
+statistics for each row group and the position for seeking to the
+start of the row group.</p>
+
+<p>Column statistics always contain the count of values and whether there
+are null values present. Most other primitive types include the
+minimum and maximum values and for numeric types the sum. As of Hive
+1.2, the indexes can include bloom filters, which provide a much more
+selective filter.</p>
+
+<p>The indexes at all levels are used by the reader using Search
+ARGuments or SARGs, which are simplified expressions that restrict the
+rows that are of interest. For example, if a query was looking for
+people older than 100 years old, the SARG would be “age > 100” and
+only files, stripes, or row groups that had people over 100 years old
+would be read.</p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+
+
+ <a href="/docs/types.html" class="prev">Back</a>
+
+ </div>
+ <div class="right align-left">
+
+
+
+ <a href="/docs/acid.html" class="next">Next</a>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/run-length.html
----------------------------------------------------------------------
diff --git a/docs/run-length.html b/docs/run-length.html
new file mode 100644
index 0000000..4821888
--- /dev/null
+++ b/docs/run-length.html
@@ -0,0 +1,1377 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Run Length Encoding</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Run Length Encoding</h1>
+ <h1 id="base-128-varint">Base 128 Varint</h1>
+
+<p>Variable width integer encodings take advantage of the fact that most
+numbers are small and that having smaller encodings for small numbers
+shrinks the overall size of the data. ORC uses the varint format from
+Protocol Buffers, which writes data in little endian format using the
+low 7 bits of each byte. The high bit in each byte is set if the
+number continues into the next byte.</p>
+
+<table>
+ <thead>
+ <tr>
+ <th style="text-align: left">Unsigned Original</th>
+ <th style="text-align: left">Serialized</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td style="text-align: left">0</td>
+ <td style="text-align: left">0x00</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">1</td>
+ <td style="text-align: left">0x01</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">127</td>
+ <td style="text-align: left">0x7f</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">128</td>
+ <td style="text-align: left">0x80, 0x01</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">129</td>
+ <td style="text-align: left">0x81, 0x01</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">16,383</td>
+ <td style="text-align: left">0xff, 0x7f</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">16,384</td>
+ <td style="text-align: left">0x80, 0x80, 0x01</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">16,385</td>
+ <td style="text-align: left">0x81, 0x80, 0x01</td>
+ </tr>
+ </tbody>
+</table>
+
+<p>For signed integer types, the number is converted into an unsigned
+number using a zigzag encoding. Zigzag encoding moves the sign bit to
+the least significant bit using the expression (val « 1) ^ (val »
+63) and derives its name from the fact that positive and negative
+numbers alternate once encoded. The unsigned number is then serialized
+as above.</p>
+
+<table>
+ <thead>
+ <tr>
+ <th style="text-align: left">Signed Original</th>
+ <th style="text-align: left">Unsigned</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td style="text-align: left">0</td>
+ <td style="text-align: left">0</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">-1</td>
+ <td style="text-align: left">1</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">1</td>
+ <td style="text-align: left">2</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">-2</td>
+ <td style="text-align: left">3</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">2</td>
+ <td style="text-align: left">4</td>
+ </tr>
+ </tbody>
+</table>
+
+<h1 id="byte-run-length-encoding">Byte Run Length Encoding</h1>
+
+<p>For byte streams, ORC uses a very light weight encoding of identical
+values.</p>
+
+<ul>
+ <li>Run - a sequence of at least 3 identical values</li>
+ <li>Literals - a sequence of non-identical values</li>
+</ul>
+
+<p>The first byte of each group of values is a header than determines
+whether it is a run (value between 0 to 127) or literal list (value
+between -128 to -1). For runs, the control byte is the length of the
+run minus the length of the minimal run (3) and the control byte for
+literal lists is the negative length of the list. For example, a
+hundred 0’s is encoded as [0x61, 0x00] and the sequence 0x44, 0x45
+would be encoded as [0xfe, 0x44, 0x45]. The next group can choose
+either of the encodings.</p>
+
+<h1 id="boolean-run-length-encoding">Boolean Run Length Encoding</h1>
+
+<p>For encoding boolean types, the bits are put in the bytes from most
+significant to least significant. The bytes are encoded using byte run
+length encoding as described in the previous section. For example,
+the byte sequence [0xff, 0x80] would be one true followed by
+seven false values.</p>
+
+<h1 id="integer-run-length-encoding-version-1">Integer Run Length Encoding, version 1</h1>
+
+<p>In Hive 0.11 ORC files used Run Length Encoding version 1 (RLEv1),
+which provides a lightweight compression of signed or unsigned integer
+sequences. RLEv1 has two sub-encodings:</p>
+
+<ul>
+ <li>Run - a sequence of values that differ by a small fixed delta</li>
+ <li>Literals - a sequence of varint encoded values</li>
+</ul>
+
+<p>Runs start with an initial byte of 0x00 to 0x7f, which encodes the
+length of the run - 3. A second byte provides the fixed delta in the
+range of -128 to 127. Finally, the first value of the run is encoded
+as a base 128 varint.</p>
+
+<p>For example, if the sequence is 100 instances of 7 the encoding would
+start with 100 - 3, followed by a delta of 0, and a varint of 7 for
+an encoding of [0x61, 0x00, 0x07]. To encode the sequence of numbers
+running from 100 to 1, the first byte is 100 - 3, the delta is -1,
+and the varint is 100 for an encoding of [0x61, 0xff, 0x64].</p>
+
+<p>Literals start with an initial byte of 0x80 to 0xff, which corresponds
+to the negative of number of literals in the sequence. Following the
+header byte, the list of N varints is encoded. Thus, if there are
+no runs, the overhead is 1 byte for each 128 integers. The first 5
+prime numbers [2, 3, 4, 7, 11] would encoded as [0xfb, 0x02, 0x03,
+0x04, 0x07, 0xb].</p>
+
+<h1 id="integer-run-length-encoding-version-2">Integer Run Length Encoding, version 2</h1>
+
+<p>In Hive 0.12, ORC introduced Run Length Encoding version 2 (RLEv2),
+which has improved compression and fixed bit width encodings for
+faster expansion. RLEv2 uses four sub-encodings based on the data:</p>
+
+<ul>
+ <li>Short Repeat - used for short sequences with repeated values</li>
+ <li>Direct - used for random sequences with a fixed bit width</li>
+ <li>Patched Base - used for random sequences with a variable bit width</li>
+ <li>Delta - used for monotonically increasing or decreasing sequences</li>
+</ul>
+
+<h2 id="short-repeat">Short Repeat</h2>
+
+<p>The short repeat encoding is used for short repeating integer
+sequences with the goal of minimizing the overhead of the header. All
+of the bits listed in the header are from the first byte to the last
+and from most significant bit to least significant bit. If the type is
+signed, the value is zigzag encoded.</p>
+
+<ul>
+ <li>1 byte header
+ <ul>
+ <li>2 bits for encoding type (0)</li>
+ <li>3 bits for width (W) of repeating value (1 to 8 bytes)</li>
+ <li>3 bits for repeat count (3 to 10 values)</li>
+ </ul>
+ </li>
+ <li>W bytes in big endian format, which is zigzag encoded if they type
+is signed</li>
+</ul>
+
+<p>The unsigned sequence of [10000, 10000, 10000, 10000, 10000] would be
+serialized with short repeat encoding (0), a width of 2 bytes (1), and
+repeat count of 5 (2) as [0x0a, 0x27, 0x10].</p>
+
+<h2 id="direct">Direct</h2>
+
+<p>The direct encoding is used for integer sequences whose values have a
+relatively constant bit width. It encodes the values directly using a
+fixed width big endian encoding. The width of the values is encoded
+using the table below.</p>
+
+<p>The 5 bit width encoding table for RLEv2:</p>
+
+<table>
+ <thead>
+ <tr>
+ <th style="text-align: left">Width in Bits</th>
+ <th style="text-align: left">Encoded Value</th>
+ <th style="text-align: left">Notes</th>
+ </tr>
+ </thead>
+ <tbody>
+ <tr>
+ <td style="text-align: left">0</td>
+ <td style="text-align: left">0</td>
+ <td style="text-align: left">for delta encoding</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">1</td>
+ <td style="text-align: left">0</td>
+ <td style="text-align: left">for non-delta encoding</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">2</td>
+ <td style="text-align: left">1</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">4</td>
+ <td style="text-align: left">3</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">8</td>
+ <td style="text-align: left">7</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">16</td>
+ <td style="text-align: left">15</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">24</td>
+ <td style="text-align: left">23</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">32</td>
+ <td style="text-align: left">27</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">40</td>
+ <td style="text-align: left">28</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">48</td>
+ <td style="text-align: left">29</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">56</td>
+ <td style="text-align: left">30</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">64</td>
+ <td style="text-align: left">31</td>
+ <td style="text-align: left"> </td>
+ </tr>
+ <tr>
+ <td style="text-align: left">3</td>
+ <td style="text-align: left">2</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">5 <= x <= 7</td>
+ <td style="text-align: left">x - 1</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">9 <= x <= 15</td>
+ <td style="text-align: left">x - 1</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">17 <= x <= 21</td>
+ <td style="text-align: left">x - 1</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">26</td>
+ <td style="text-align: left">24</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">28</td>
+ <td style="text-align: left">25</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ <tr>
+ <td style="text-align: left">30</td>
+ <td style="text-align: left">26</td>
+ <td style="text-align: left">deprecated</td>
+ </tr>
+ </tbody>
+</table>
+
+<ul>
+ <li>2 bytes header
+ <ul>
+ <li>2 bits for encoding type (1)</li>
+ <li>5 bits for encoded width (W) of values (1 to 64 bits) using the 5 bit
+width encoding table</li>
+ <li>9 bits for length (L) (1 to 512 values)</li>
+ </ul>
+ </li>
+ <li>W * L bits (padded to the next byte) encoded in big endian format, which is
+zigzag encoding if the type is signed</li>
+</ul>
+
+<p>The unsigned sequence of [23713, 43806, 57005, 48879] would be
+serialized with direct encoding (1), a width of 16 bits (15), and
+length of 4 (3) as [0x5e, 0x03, 0x5c, 0xa1, 0xab, 0x1e, 0xde, 0xad,
+0xbe, 0xef].</p>
+
+<h2 id="patched-base">Patched Base</h2>
+
+<p>The patched base encoding is used for integer sequences whose bit
+widths varies a lot. The minimum signed value of the sequence is found
+and subtracted from the other values. The bit width of those adjusted
+values is analyzed and the 90 percentile of the bit width is chosen
+as W. The 10\% of values larger than W use patches from a patch list
+to set the additional bits. Patches are encoded as a list of gaps in
+the index values and the additional value bits.</p>
+
+<ul>
+ <li>4 bytes header
+ <ul>
+ <li>2 bits for encoding type (2)</li>
+ <li>5 bits for encoded width (W) of values (1 to 64 bits) using the 5 bit
+ width encoding table</li>
+ <li>9 bits for length (L) (1 to 512 values)</li>
+ <li>3 bits for base value width (BW) (1 to 8 bytes)</li>
+ <li>5 bits for patch width (PW) (1 to 64 bits) using the 5 bit width
+encoding table</li>
+ <li>3 bits for patch gap width (PGW) (1 to 8 bits)</li>
+ <li>5 bits for patch list length (PLL) (0 to 31 patches)</li>
+ </ul>
+ </li>
+ <li>Base value (BW bytes) - The base value is stored as a big endian value
+with negative values marked by the most significant bit set. If it that
+bit is set, the entire value is negated.</li>
+ <li>Data values (W * L bits padded to the byte) - A sequence of W bit positive
+values that are added to the base value.</li>
+ <li>Data values (W * L bits padded to the byte) - A sequence of W bit positive
+values that are added to the base value.</li>
+ <li>Patch list (PLL * (PGW + PW) bytes) - A list of patches for values
+that didn’t fit within W bits. Each entry in the list consists of a
+gap, which is the number of elements skipped from the previous
+patch, and a patch value. Patches are applied by logically or’ing
+the data values with the relevant patch shifted W bits left. If a
+patch is 0, it was introduced to skip over more than 255 items. The
+combined length of each patch (PGW + PW) must be less or equal to
+64.</li>
+</ul>
+
+<p>The unsigned sequence of [2030, 2000, 2020, 1000000, 2040, 2050, 2060,
+2070, 2080, 2090] has a minimum of 2000, which makes the adjusted
+sequence [30, 0, 20, 998000, 40, 50, 60, 70, 80, 90]. It has an
+encoding of patched base (2), a bit width of 8 (7), a length of 10
+(9), a base value width of 2 bytes (1), a patch width of 12 bits (11),
+patch gap width of 2 bits (1), and a patch list length of 1 (1). The
+base value is 2000 and the combined result is [0x8e, 0x09, 0x2b, 0x21,
+0x07, 0xd0, 0x1e, 0x00, 0x14, 0x70, 0x28, 0x32, 0x3c, 0x46, 0x50,
+0x5a, 0xfc, 0xe8]</p>
+
+<h2 id="delta">Delta</h2>
+
+<p>The Delta encoding is used for monotonically increasing or decreasing
+sequences. The first two numbers in the sequence can not be identical,
+because the encoding is using the sign of the first delta to determine
+if the series is increasing or decreasing.</p>
+
+<ul>
+ <li>2 bytes header
+ <ul>
+ <li>2 bits for encoding type (3)</li>
+ <li>5 bits for encoded width (W) of deltas (0 to 64 bits) using the 5 bit
+width encoding table</li>
+ <li>9 bits for run length (L) (1 to 512 values)</li>
+ </ul>
+ </li>
+ <li>Base value - encoded as (signed or unsigned) varint</li>
+ <li>Delta base - encoded as signed varint</li>
+ <li>Delta values $W * (L - 2)$ bytes - encode each delta after the first
+one. If the delta base is positive, the sequence is increasing and if it is
+negative the sequence is decreasing.</li>
+</ul>
+
+<p>The unsigned sequence of [2, 3, 5, 7, 11, 13, 17, 19, 23, 29] would be
+serialized with delta encoding (3), a width of 4 bits (3), length of
+10 (9), a base of 2 (2), and first delta of 1 (2). The resulting
+sequence is [0xc6, 0x09, 0x02, 0x02, 0x22, 0x42, 0x42, 0x46].</p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+
+
+ <a href="/docs/compression.html" class="prev">Back</a>
+
+ </div>
+ <div class="right align-left">
+
+
+
+ <a href="/docs/stripes.html" class="next">Next</a>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/spec-index.html
----------------------------------------------------------------------
diff --git a/docs/spec-index.html b/docs/spec-index.html
new file mode 100644
index 0000000..0151fc2
--- /dev/null
+++ b/docs/spec-index.html
@@ -0,0 +1,1108 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Indexes</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Indexes</h1>
+ <h1 id="row-group-index">Row Group Index</h1>
+
+<p>The row group indexes consist of a ROW_INDEX stream for each primitive
+column that has an entry for each row group. Row groups are controlled
+by the writer and default to 10,000 rows. Each RowIndexEntry gives the
+position of each stream for the column and the statistics for that row
+group.</p>
+
+<p>The index streams are placed at the front of the stripe, because in
+the default case of streaming they do not need to be read. They are
+only loaded when either predicate push down is being used or the
+reader seeks to a particular row.</p>
+
+<p><code>message RowIndexEntry {
+ repeated uint64 positions = 1 [packed=true];
+ optional ColumnStatistics statistics = 2;
+}
+</code></p>
+
+<p><code>message RowIndex {
+ repeated RowIndexEntry entry = 1;
+}
+</code></p>
+
+<p>To record positions, each stream needs a sequence of numbers. For
+uncompressed streams, the position is the byte offset of the RLE run’s
+start location followed by the number of values that need to be
+consumed from the run. In compressed streams, the first number is the
+start of the compression chunk in the stream, followed by the number
+of decompressed bytes that need to be consumed, and finally the number
+of values consumed in the RLE.</p>
+
+<p>For columns with multiple streams, the sequences of positions in each
+stream are concatenated. That was an unfortunate decision on my part
+that we should fix at some point, because it makes code that uses the
+indexes error-prone.</p>
+
+<p>Because dictionaries are accessed randomly, there is not a position to
+record for the dictionary and the entire dictionary must be read even
+if only part of a stripe is being read.</p>
+
+<h1 id="bloom-filter-index">Bloom Filter Index</h1>
+
+<p>Bloom Filters are added to ORC indexes from Hive 1.2.0 onwards.
+Predicate pushdown can make use of bloom filters to better prune
+the row groups that do not satisfy the filter condition.
+The bloom filter indexes consist of a BLOOM_FILTER stream for each
+column specified through ‘orc.bloom.filter.columns’ table properties.
+A BLOOM_FILTER stream records a bloom filter entry for each row
+group (default to 10,000 rows) in a column. Only the row groups that
+satisfy min/max row index evaluation will be evaluated against the
+bloom filter index.</p>
+
+<p>Each BloomFilterEntry stores the number of hash functions (‘k’) used and
+the bitset backing the bloom filter. The bitset is serialized as repeated
+longs from which the number of bits (‘m’) for the bloom filter can be derived.
+m = bitset.length * 64.</p>
+
+<p><code>message BloomFilter {
+ optional uint32 numHashFunctions = 1;
+ repeated fixed64 bitset = 2;
+}
+</code></p>
+
+<p><code>message BloomFilterIndex {
+ repeated BloomFilter bloomFilter = 1;
+}
+</code></p>
+
+<p>Bloom filter internally uses two different hash functions to map a key
+to a position in the bit set. For tinyint, smallint, int, bigint, float
+and double types, Thomas Wang’s 64-bit integer hash function is used.
+Floats are converted to IEEE-754 32 bit representation
+(using Java’s Float.floatToIntBits(float)). Similary, Doubles are
+converted to IEEE-754 64 bit representation (using Java’s
+Double.doubleToLongBits(double)). All these primitive types
+are cast to long base type before being passed on to the hash function.
+For strings and binary types, Murmur3 64 bit hash algorithm is used.
+The 64 bit variant of Murmur3 considers only the most significant
+8 bytes of Murmur3 128-bit algorithm. The 64 bit hashcode generated
+from the above algorithms is used as a base to derive ‘k’ different
+hash functions. We use the idea mentioned in the paper “Less Hashing,
+Same Performance: Building a Better Bloom Filter” by Kirsch et. al. to
+quickly compute the k hashcodes.</p>
+
+<p>The algorithm for computing k hashcodes and setting the bit position
+in a bloom filter is as follows:</p>
+
+<ol>
+ <li>Get 64 bit base hash code from Murmur3 or Thomas Wang’s hash algorithm.</li>
+ <li>Split the above hashcode into two 32-bit hashcodes (say hash1 and hash2).</li>
+ <li>k’th hashcode is obtained by (where k > 0):
+ <ul>
+ <li>combinedHash = hash1 + (k * hash2)</li>
+ </ul>
+ </li>
+ <li>If combinedHash is negative flip all the bits:
+ <ul>
+ <li>combinedHash = ~combinedHash</li>
+ </ul>
+ </li>
+ <li>Bit set position is obtained by performing modulo with m:
+ <ul>
+ <li>position = combinedHash % m</li>
+ </ul>
+ </li>
+ <li>Set the position in bit set. The LSB 6 bits identifies the long index
+within bitset and bit position within the long uses little endian order.
+ <ul>
+ <li>bitset[position »> 6] |= (1L « position);</li>
+ </ul>
+ </li>
+</ol>
+
+<p>Bloom filter streams are interlaced with row group indexes. This placement
+makes it convenient to read the bloom filter stream and row index stream
+together in single read operation.</p>
+
+<p><img src="/img/BloomFilter.png" alt="bloom filter" /></p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+
+
+ <a href="/docs/encodings.html" class="prev">Back</a>
+
+ </div>
+ <div class="right align-left">
+
+ <span class="next disabled">Next</span>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>
http://git-wip-us.apache.org/repos/asf/orc/blob/6a400548/docs/spec-intro.html
----------------------------------------------------------------------
diff --git a/docs/spec-intro.html b/docs/spec-intro.html
new file mode 100644
index 0000000..5784360
--- /dev/null
+++ b/docs/spec-intro.html
@@ -0,0 +1,993 @@
+<!DOCTYPE HTML>
+<html lang="en-US">
+<head>
+ <meta charset="UTF-8">
+ <title>Introduction</title>
+ <meta name="viewport" content="width=device-width,initial-scale=1">
+ <meta name="generator" content="Jekyll v2.4.0">
+ <link rel="stylesheet" href="//fonts.googleapis.com/css?family=Lato:300,300italic,400,400italic,700,700italic,900">
+ <link rel="stylesheet" href="/css/screen.css">
+ <link rel="icon" type="image/x-icon" href="/favicon.ico">
+ <!--[if lt IE 9]>
+ <script src="/js/html5shiv.min.js"></script>
+ <script src="/js/respond.min.js"></script>
+ <![endif]-->
+</head>
+
+
+<body class="wrap">
+ <header role="banner">
+ <nav class="mobile-nav show-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ <div class="grid">
+ <div class="unit one-third center-on-mobiles">
+ <h1>
+ <a href="/">
+ <span class="sr-only">Apache ORC</span>
+ <img src="/img/logo.png" width="249" height="115" alt="ORC Logo">
+ </a>
+ </h1>
+ </div>
+ <nav class="main-nav unit two-thirds hide-on-mobiles">
+ <ul>
+ <li class="">
+ <a href="/">Home</a>
+ </li>
+ <li class="current">
+ <a href="/docs/">Documentation</a>
+ </li>
+ <li class="">
+ <a href="/talks/">Talks</a>
+ </li>
+ <li class="">
+ <a href="/news/">News</a>
+ </li>
+ <li class="">
+ <a href="/help/">Help</a>
+ </li>
+ <li class="">
+ <a href="/develop/">Develop</a>
+ </li>
+</ul>
+
+ </nav>
+ </div>
+</header>
+
+
+ <section class="docs">
+ <div class="grid">
+
+ <div class="docs-nav-mobile unit whole show-on-mobiles">
+ <select onchange="if (this.value) window.location.href=this.value">
+ <option value="">Navigate the docs…</option>
+
+ <optgroup label="Overview">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/index.html">Background</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/types.html">Types</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/indexes.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/acid.html">ACID support</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Hive Usage">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-ddl.html">Hive DDL</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/hive-config.html">Hive Configuration</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ <optgroup label="Format Specification">
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-intro.html">Introduction</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/file-tail.html">File Tail</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/compression.html">Compression</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/run-length.html">Run Length Encoding</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/stripes.html">Stripes</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/encodings.html">Column Encodings</option>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <option value="/docs/spec-index.html">Indexes</option>
+
+
+
+
+
+
+
+
+
+
+ </optgroup>
+
+ </select>
+</div>
+
+
+ <div class="unit four-fifths">
+ <article>
+ <h1>Introduction</h1>
+ <p>Hive’s RCFile was the standard format for storing tabular data in
+Hadoop for several years. However, RCFile has limitations because it
+treats each column as a binary blob without semantics. In Hive 0.11 we
+added a new file format named Optimized Row Columnar (ORC) file that
+uses and retains the type information from the table definition. ORC
+uses type specific readers and writers that provide light weight
+compression techniques such as dictionary encoding, bit packing, delta
+encoding, and run length encoding – resulting in dramatically smaller
+files. Additionally, ORC can apply generic compression using zlib, or
+Snappy on top of the lightweight compression for even smaller
+files. However, storage savings are only part of the gain. ORC
+supports projection, which selects subsets of the columns for reading,
+so that queries reading only one column read only the required
+bytes. Furthermore, ORC files include light weight indexes that
+include the minimum and maximum values for each column in each set of
+10,000 rows and the entire file. Using pushdown filters from Hive, the
+file reader can skip entire sets of rows that aren’t important for
+this query.</p>
+
+<p><img src="/img/OrcFileLayout.png" alt="ORC file structure" /></p>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <div class="section-nav">
+ <div class="left align-right">
+
+
+
+ <a href="/docs/hive-config.html" class="prev">Back</a>
+
+ </div>
+ <div class="right align-left">
+
+
+
+ <a href="/docs/file-tail.html" class="next">Next</a>
+
+ </div>
+ </div>
+ <div class="clear"></div>
+
+
+ </article>
+ </div>
+
+ <div class="unit one-fifth hide-on-mobiles">
+ <aside>
+
+ <h4>Overview</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/index.html">Background</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/types.html">Types</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/indexes.html">Indexes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/acid.html">ACID support</a></li>
+
+
+
+</ul>
+
+
+ <h4>Hive Usage</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-ddl.html">Hive DDL</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/hive-config.html">Hive Configuration</a></li>
+
+
+
+</ul>
+
+
+ <h4>Format Specification</h4>
+
+
+<ul>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class="current"><a href="/docs/spec-intro.html">Introduction</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/file-tail.html">File Tail</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/compression.html">Compression</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/run-length.html">Run Length Encoding</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/stripes.html">Stripes</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/encodings.html">Column Encodings</a></li>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ <li class=""><a href="/docs/spec-index.html">Indexes</a></li>
+
+
+
+</ul>
+
+
+ </aside>
+</div>
+
+
+ <div class="clear"></div>
+
+ </div>
+ </section>
+
+
+ <footer role="contentinfo">
+ <p>The contents of this website are © 2015
+ <a href="https://www.apache.org/">Apache Software Foundation</a>
+ under the terms of the <a
+ href="https://www.apache.org/licenses/LICENSE-2.0.html">
+ Apache License v2</a>. Apache ORC and its logo are trademarks
+ of the Apache Software Foundation.</p>
+</footer>
+
+ <script>
+ var anchorForId = function (id) {
+ var anchor = document.createElement("a");
+ anchor.className = "header-link";
+ anchor.href = "#" + id;
+ anchor.innerHTML = "<span class=\"sr-only\">Permalink</span><i class=\"fa fa-link\"></i>";
+ anchor.title = "Permalink";
+ return anchor;
+ };
+
+ var linkifyAnchors = function (level, containingElement) {
+ var headers = containingElement.getElementsByTagName("h" + level);
+ for (var h = 0; h < headers.length; h++) {
+ var header = headers[h];
+
+ if (typeof header.id !== "undefined" && header.id !== "") {
+ header.appendChild(anchorForId(header.id));
+ }
+ }
+ };
+
+ document.onreadystatechange = function () {
+ if (this.readyState === "complete") {
+ var contentBlock = document.getElementsByClassName("docs")[0] || document.getElementsByClassName("news")[0];
+ if (!contentBlock) {
+ return;
+ }
+ for (var level = 1; level <= 6; level++) {
+ linkifyAnchors(level, contentBlock);
+ }
+ }
+ };
+</script>
+
+
+</body>
+</html>