blob: 681411d6f75bab47884ccfbcc87bd46c5ae2c403 [file] [log] [blame]
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<!-- NewPage -->
<html lang="en">
<head>
<!-- Generated by javadoc (1.8.0_221) on Tue Jan 19 12:27:57 PST 2021 -->
<title>SegmentMerger (apache-nutch 1.18 API)</title>
<meta name="date" content="2021-01-19">
<link rel="stylesheet" type="text/css" href="../../../../stylesheet.css" title="Style">
<script type="text/javascript" src="../../../../script.js"></script>
</head>
<body>
<script type="text/javascript"><!--
try {
if (location.href.indexOf('is-external=true') == -1) {
parent.document.title="SegmentMerger (apache-nutch 1.18 API)";
}
}
catch(err) {
}
//-->
var methods = {"i0":9,"i1":10,"i2":10,"i3":10};
var tabs = {65535:["t0","All Methods"],1:["t1","Static Methods"],2:["t2","Instance Methods"],8:["t4","Concrete Methods"]};
var altColor = "altColor";
var rowColor = "rowColor";
var tableTab = "tableTab";
var activeTableTab = "activeTableTab";
</script>
<noscript>
<div>JavaScript is disabled on your browser.</div>
</noscript>
<!-- ========= START OF TOP NAVBAR ======= -->
<div class="topNav"><a name="navbar.top">
<!-- -->
</a>
<div class="skipNav"><a href="#skip.navbar.top" title="Skip navigation links">Skip navigation links</a></div>
<a name="navbar.top.firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="class-use/SegmentMerger.html">Use</a></li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../index-all.html">Index</a></li>
<li><a href="../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../org/apache/nutch/segment/SegmentMergeFilters.html" title="class in org.apache.nutch.segment"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../org/apache/nutch/segment/SegmentMerger.ObjectInputFormat.html" title="class in org.apache.nutch.segment"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../index.html?org/apache/nutch/segment/SegmentMerger.html" target="_top">Frames</a></li>
<li><a href="SegmentMerger.html" target="_top">No&nbsp;Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_top">
<li><a href="../../../../allclasses-noframe.html">All&nbsp;Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_top");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li><a href="#nested.class.summary">Nested</a>&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor.summary">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method.summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor.detail">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method.detail">Method</a></li>
</ul>
</div>
<a name="skip.navbar.top">
<!-- -->
</a></div>
<!-- ========= END OF TOP NAVBAR ========= -->
<!-- ======== START OF CLASS DATA ======== -->
<div class="header">
<div class="subTitle">org.apache.nutch.segment</div>
<h2 title="Class SegmentMerger" class="title">Class SegmentMerger</h2>
</div>
<div class="contentContainer">
<ul class="inheritance">
<li><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true" title="class or interface in java.lang">java.lang.Object</a></li>
<li>
<ul class="inheritance">
<li><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true" title="class or interface in org.apache.hadoop.conf">org.apache.hadoop.conf.Configured</a></li>
<li>
<ul class="inheritance">
<li>org.apache.nutch.segment.SegmentMerger</li>
</ul>
</li>
</ul>
</li>
</ul>
<div class="description">
<ul class="blockList">
<li class="blockList">
<dl>
<dt>All Implemented Interfaces:</dt>
<dd><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configurable.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configurable</a>, <a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/util/Tool.html?is-external=true" title="class or interface in org.apache.hadoop.util">Tool</a></dd>
</dl>
<hr>
<br>
<pre>public class <span class="typeNameLabel">SegmentMerger</span>
extends <a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configured</a>
implements <a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/util/Tool.html?is-external=true" title="class or interface in org.apache.hadoop.util">Tool</a></pre>
<div class="block">This tool takes several segments and merges their data together. Only the
latest versions of data is retained.
Optionally, you can apply current URLFilters to remove prohibited URL-s.
<p>
Also, it's possible to slice the resulting segment into chunks of fixed size.
</p>
<h3>Important Notes</h3> <h4>Which parts are merged?</h4>
<p>
It doesn't make sense to merge data from segments, which are at different
stages of processing (e.g. one unfetched segment, one fetched but not parsed,
and one fetched and parsed). Therefore, prior to merging, the tool will
determine the lowest common set of input data, and only this data will be
merged. This may have some unintended consequences: e.g. if majority of input
segments are fetched and parsed, but one of them is unfetched, the tool will
fall back to just merging fetchlists, and it will skip all other data from
all segments.
</p>
<h4>Merging fetchlists</h4>
<p>
Merging segments, which contain just fetchlists (i.e. prior to fetching) is
not recommended, because this tool (unlike the
<a href="../../../../org/apache/nutch/crawl/Generator.html" title="class in org.apache.nutch.crawl"><code>Generator</code></a> doesn't ensure that fetchlist parts
for each map task are disjoint.
</p>
<p>
<h4>Duplicate content</h4>
Merging segments removes older content whenever possible (see below).
However, this is NOT the same as de-duplication, which in addition removes
identical content found at different URL-s. In other words, running
DeleteDuplicates is still necessary.
<p>
For some types of data (especially ParseText) it's not possible to determine
which version is really older. Therefore the tool always uses segment names
as timestamps, for all types of input data. Segment names are compared in
forward lexicographic order (0-9a-zA-Z), and data from segments with "higher"
names will prevail. It follows then that it is extremely important that
segments be named in an increasing lexicographic order as their creation time
increases.
</p>
<p>
<h4>Merging and indexes</h4>
Merged segment gets a different name. Since Indexer embeds segment names in
indexes, any indexes originally created for the input segments will NOT work
with the merged segment. Newly created merged segment(s) need to be indexed
afresh. This tool doesn't use existing indexes in any way, so if you plan to
merge segments you don't have to index them prior to merging.</div>
<dl>
<dt><span class="simpleTagLabel">Author:</span></dt>
<dd>Andrzej Bialecki</dd>
</dl>
</li>
</ul>
</div>
<div class="summary">
<ul class="blockList">
<li class="blockList">
<!-- ======== NESTED CLASS SUMMARY ======== -->
<ul class="blockList">
<li class="blockList"><a name="nested.class.summary">
<!-- -->
</a>
<h3>Nested Class Summary</h3>
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Nested Class Summary table, listing nested classes, and an explanation">
<caption><span>Nested Classes</span><span class="tabEnd">&nbsp;</span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Class and Description</th>
</tr>
<tr class="altColor">
<td class="colFirst"><code>static class&nbsp;</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.ObjectInputFormat.html" title="class in org.apache.nutch.segment">SegmentMerger.ObjectInputFormat</a></span></code>
<div class="block">Wraps inputs in an <a href="../../../../org/apache/nutch/metadata/MetaWrapper.html" title="class in org.apache.nutch.metadata"><code>MetaWrapper</code></a>, to permit merging different types
in reduce and use additional metadata.</div>
</td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>static class&nbsp;</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.SegmentMergerMapper.html" title="class in org.apache.nutch.segment">SegmentMerger.SegmentMergerMapper</a></span></code>&nbsp;</td>
</tr>
<tr class="altColor">
<td class="colFirst"><code>static class&nbsp;</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.SegmentMergerReducer.html" title="class in org.apache.nutch.segment">SegmentMerger.SegmentMergerReducer</a></span></code>
<div class="block">NOTE: in selecting the latest version we rely exclusively on the segment
name (not all segment data contain time information).</div>
</td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>static class&nbsp;</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.SegmentOutputFormat.html" title="class in org.apache.nutch.segment">SegmentMerger.SegmentOutputFormat</a></span></code>&nbsp;</td>
</tr>
</table>
</li>
</ul>
<!-- ======== CONSTRUCTOR SUMMARY ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor.summary">
<!-- -->
</a>
<h3>Constructor Summary</h3>
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Constructor Summary table, listing constructors, and an explanation">
<caption><span>Constructors</span><span class="tabEnd">&nbsp;</span></caption>
<tr>
<th class="colOne" scope="col">Constructor and Description</th>
</tr>
<tr class="altColor">
<td class="colOne"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#SegmentMerger--">SegmentMerger</a></span>()</code>&nbsp;</td>
</tr>
<tr class="rowColor">
<td class="colOne"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#SegmentMerger-org.apache.hadoop.conf.Configuration-">SegmentMerger</a></span>(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configuration.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configuration</a>&nbsp;conf)</code>&nbsp;</td>
</tr>
</table>
</li>
</ul>
<!-- ========== METHOD SUMMARY =========== -->
<ul class="blockList">
<li class="blockList"><a name="method.summary">
<!-- -->
</a>
<h3>Method Summary</h3>
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Method Summary table, listing methods, and an explanation">
<caption><span id="t0" class="activeTableTab"><span>All Methods</span><span class="tabEnd">&nbsp;</span></span><span id="t1" class="tableTab"><span><a href="javascript:show(1);">Static Methods</a></span><span class="tabEnd">&nbsp;</span></span><span id="t2" class="tableTab"><span><a href="javascript:show(2);">Instance Methods</a></span><span class="tabEnd">&nbsp;</span></span><span id="t4" class="tableTab"><span><a href="javascript:show(8);">Concrete Methods</a></span><span class="tabEnd">&nbsp;</span></span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Method and Description</th>
</tr>
<tr id="i0" class="altColor">
<td class="colFirst"><code>static void</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#main-java.lang.String:A-">main</a></span>(<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a>[]&nbsp;args)</code>&nbsp;</td>
</tr>
<tr id="i1" class="rowColor">
<td class="colFirst"><code>void</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#merge-org.apache.hadoop.fs.Path-org.apache.hadoop.fs.Path:A-boolean-boolean-long-">merge</a></span>(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/fs/Path.html?is-external=true" title="class or interface in org.apache.hadoop.fs">Path</a>&nbsp;out,
<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/fs/Path.html?is-external=true" title="class or interface in org.apache.hadoop.fs">Path</a>[]&nbsp;segs,
boolean&nbsp;filter,
boolean&nbsp;normalize,
long&nbsp;slice)</code>&nbsp;</td>
</tr>
<tr id="i2" class="altColor">
<td class="colFirst"><code>int</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#run-java.lang.String:A-">run</a></span>(<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a>[]&nbsp;args)</code>&nbsp;</td>
</tr>
<tr id="i3" class="rowColor">
<td class="colFirst"><code>void</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/segment/SegmentMerger.html#setConf-org.apache.hadoop.conf.Configuration-">setConf</a></span>(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configuration.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configuration</a>&nbsp;conf)</code>&nbsp;</td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.org.apache.hadoop.conf.Configured">
<!-- -->
</a>
<h3>Methods inherited from class&nbsp;org.apache.hadoop.conf.<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configured</a></h3>
<code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true#getConf--" title="class or interface in org.apache.hadoop.conf">getConf</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.java.lang.Object">
<!-- -->
</a>
<h3>Methods inherited from class&nbsp;java.lang.<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true" title="class or interface in java.lang">Object</a></h3>
<code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#clone--" title="class or interface in java.lang">clone</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#equals-java.lang.Object-" title="class or interface in java.lang">equals</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#finalize--" title="class or interface in java.lang">finalize</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#getClass--" title="class or interface in java.lang">getClass</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#hashCode--" title="class or interface in java.lang">hashCode</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#notify--" title="class or interface in java.lang">notify</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#notifyAll--" title="class or interface in java.lang">notifyAll</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#toString--" title="class or interface in java.lang">toString</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait--" title="class or interface in java.lang">wait</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait-long-" title="class or interface in java.lang">wait</a>, <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Object.html?is-external=true#wait-long-int-" title="class or interface in java.lang">wait</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.org.apache.hadoop.conf.Configurable">
<!-- -->
</a>
<h3>Methods inherited from interface&nbsp;org.apache.hadoop.conf.<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configurable.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configurable</a></h3>
<code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configurable.html?is-external=true#getConf--" title="class or interface in org.apache.hadoop.conf">getConf</a></code></li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
<div class="details">
<ul class="blockList">
<li class="blockList">
<!-- ========= CONSTRUCTOR DETAIL ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor.detail">
<!-- -->
</a>
<h3>Constructor Detail</h3>
<a name="SegmentMerger--">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>SegmentMerger</h4>
<pre>public&nbsp;SegmentMerger()</pre>
</li>
</ul>
<a name="SegmentMerger-org.apache.hadoop.conf.Configuration-">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>SegmentMerger</h4>
<pre>public&nbsp;SegmentMerger(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configuration.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configuration</a>&nbsp;conf)</pre>
</li>
</ul>
</li>
</ul>
<!-- ============ METHOD DETAIL ========== -->
<ul class="blockList">
<li class="blockList"><a name="method.detail">
<!-- -->
</a>
<h3>Method Detail</h3>
<a name="setConf-org.apache.hadoop.conf.Configuration-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>setConf</h4>
<pre>public&nbsp;void&nbsp;setConf(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configuration.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configuration</a>&nbsp;conf)</pre>
<dl>
<dt><span class="overrideSpecifyLabel">Specified by:</span></dt>
<dd><code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configurable.html?is-external=true#setConf-org.apache.hadoop.conf.Configuration-" title="class or interface in org.apache.hadoop.conf">setConf</a></code>&nbsp;in interface&nbsp;<code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configurable.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configurable</a></code></dd>
<dt><span class="overrideSpecifyLabel">Overrides:</span></dt>
<dd><code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true#setConf-org.apache.hadoop.conf.Configuration-" title="class or interface in org.apache.hadoop.conf">setConf</a></code>&nbsp;in class&nbsp;<code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/conf/Configured.html?is-external=true" title="class or interface in org.apache.hadoop.conf">Configured</a></code></dd>
</dl>
</li>
</ul>
<a name="merge-org.apache.hadoop.fs.Path-org.apache.hadoop.fs.Path:A-boolean-boolean-long-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>merge</h4>
<pre>public&nbsp;void&nbsp;merge(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/fs/Path.html?is-external=true" title="class or interface in org.apache.hadoop.fs">Path</a>&nbsp;out,
<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/fs/Path.html?is-external=true" title="class or interface in org.apache.hadoop.fs">Path</a>[]&nbsp;segs,
boolean&nbsp;filter,
boolean&nbsp;normalize,
long&nbsp;slice)
throws <a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a>,
<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/ClassNotFoundException.html?is-external=true" title="class or interface in java.lang">ClassNotFoundException</a>,
<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/InterruptedException.html?is-external=true" title="class or interface in java.lang">InterruptedException</a></pre>
<dl>
<dt><span class="throwsLabel">Throws:</span></dt>
<dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/io/IOException.html?is-external=true" title="class or interface in java.io">IOException</a></code></dd>
<dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/ClassNotFoundException.html?is-external=true" title="class or interface in java.lang">ClassNotFoundException</a></code></dd>
<dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/InterruptedException.html?is-external=true" title="class or interface in java.lang">InterruptedException</a></code></dd>
</dl>
</li>
</ul>
<a name="run-java.lang.String:A-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>run</h4>
<pre>public&nbsp;int&nbsp;run(<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a>[]&nbsp;args)
throws <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Exception.html?is-external=true" title="class or interface in java.lang">Exception</a></pre>
<dl>
<dt><span class="overrideSpecifyLabel">Specified by:</span></dt>
<dd><code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/util/Tool.html?is-external=true#run-java.lang.String:A-" title="class or interface in org.apache.hadoop.util">run</a></code>&nbsp;in interface&nbsp;<code><a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/util/Tool.html?is-external=true" title="class or interface in org.apache.hadoop.util">Tool</a></code></dd>
<dt><span class="paramLabel">Parameters:</span></dt>
<dd><code>args</code> - </dd>
<dt><span class="throwsLabel">Throws:</span></dt>
<dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Exception.html?is-external=true" title="class or interface in java.lang">Exception</a></code></dd>
</dl>
</li>
</ul>
<a name="main-java.lang.String:A-">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>main</h4>
<pre>public static&nbsp;void&nbsp;main(<a href="https://docs.oracle.com/javase/8/docs/api/java/lang/String.html?is-external=true" title="class or interface in java.lang">String</a>[]&nbsp;args)
throws <a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Exception.html?is-external=true" title="class or interface in java.lang">Exception</a></pre>
<dl>
<dt><span class="throwsLabel">Throws:</span></dt>
<dd><code><a href="https://docs.oracle.com/javase/8/docs/api/java/lang/Exception.html?is-external=true" title="class or interface in java.lang">Exception</a></code></dd>
</dl>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</div>
<!-- ========= END OF CLASS DATA ========= -->
<!-- ======= START OF BOTTOM NAVBAR ====== -->
<div class="bottomNav"><a name="navbar.bottom">
<!-- -->
</a>
<div class="skipNav"><a href="#skip.navbar.bottom" title="Skip navigation links">Skip navigation links</a></div>
<a name="navbar.bottom.firstrow">
<!-- -->
</a>
<ul class="navList" title="Navigation">
<li><a href="../../../../overview-summary.html">Overview</a></li>
<li><a href="package-summary.html">Package</a></li>
<li class="navBarCell1Rev">Class</li>
<li><a href="class-use/SegmentMerger.html">Use</a></li>
<li><a href="package-tree.html">Tree</a></li>
<li><a href="../../../../deprecated-list.html">Deprecated</a></li>
<li><a href="../../../../index-all.html">Index</a></li>
<li><a href="../../../../help-doc.html">Help</a></li>
</ul>
</div>
<div class="subNav">
<ul class="navList">
<li><a href="../../../../org/apache/nutch/segment/SegmentMergeFilters.html" title="class in org.apache.nutch.segment"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../org/apache/nutch/segment/SegmentMerger.ObjectInputFormat.html" title="class in org.apache.nutch.segment"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../index.html?org/apache/nutch/segment/SegmentMerger.html" target="_top">Frames</a></li>
<li><a href="SegmentMerger.html" target="_top">No&nbsp;Frames</a></li>
</ul>
<ul class="navList" id="allclasses_navbar_bottom">
<li><a href="../../../../allclasses-noframe.html">All&nbsp;Classes</a></li>
</ul>
<div>
<script type="text/javascript"><!--
allClassesLink = document.getElementById("allclasses_navbar_bottom");
if(window==top) {
allClassesLink.style.display = "block";
}
else {
allClassesLink.style.display = "none";
}
//-->
</script>
</div>
<div>
<ul class="subNavList">
<li>Summary:&nbsp;</li>
<li><a href="#nested.class.summary">Nested</a>&nbsp;|&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor.summary">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method.summary">Method</a></li>
</ul>
<ul class="subNavList">
<li>Detail:&nbsp;</li>
<li>Field&nbsp;|&nbsp;</li>
<li><a href="#constructor.detail">Constr</a>&nbsp;|&nbsp;</li>
<li><a href="#method.detail">Method</a></li>
</ul>
</div>
<a name="skip.navbar.bottom">
<!-- -->
</a></div>
<!-- ======== END OF BOTTOM NAVBAR ======= -->
<p class="legalCopy"><small>Copyright &copy; 2021 The Apache Software Foundation</small></p>
</body>
</html>