blob: 55fbe41bc9c33fabff6eaeeeb730f9f807e19c5d [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 12:27:55 PST 2021 -->
<title>AdaptiveFetchSchedule (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="AdaptiveFetchSchedule (apache-nutch 1.18 API)";
}
}
catch(err) {
}
//-->
var methods = {"i0":9,"i1":10,"i2":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/AdaptiveFetchSchedule.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/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../index.html?org/apache/nutch/crawl/AdaptiveFetchSchedule.html" target="_top">Frames</a></li>
<li><a href="AdaptiveFetchSchedule.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>Nested&nbsp;|&nbsp;</li>
<li><a href="#field.summary">Field</a>&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><a href="#field.detail">Field</a>&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.crawl</div>
<h2 title="Class AdaptiveFetchSchedule" class="title">Class AdaptiveFetchSchedule</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><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">org.apache.nutch.crawl.AbstractFetchSchedule</a></li>
<li>
<ul class="inheritance">
<li>org.apache.nutch.crawl.AdaptiveFetchSchedule</li>
</ul>
</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="../../../../org/apache/nutch/crawl/FetchSchedule.html" title="interface in org.apache.nutch.crawl">FetchSchedule</a></dd>
</dl>
<dl>
<dt>Direct Known Subclasses:</dt>
<dd><a href="../../../../org/apache/nutch/crawl/MimeAdaptiveFetchSchedule.html" title="class in org.apache.nutch.crawl">MimeAdaptiveFetchSchedule</a></dd>
</dl>
<hr>
<br>
<pre>public class <span class="typeNameLabel">AdaptiveFetchSchedule</span>
extends <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">AbstractFetchSchedule</a></pre>
<div class="block">This class implements an adaptive re-fetch algorithm. This works as follows:
<ul>
<li>for pages that has changed since the last fetchTime, decrease their
fetchInterval by a factor of DEC_FACTOR (default value is 0.2f).</li>
<li>for pages that haven't changed since the last fetchTime, increase their
fetchInterval by a factor of INC_FACTOR (default value is 0.2f).<br>
If SYNC_DELTA property is true, then:
<ul>
<li>calculate a <code>delta = fetchTime - modifiedTime</code></li>
<li>try to synchronize with the time of change, by shifting the next
fetchTime by a fraction of the difference between the last modification time
and the last fetch time. I.e. the next fetch time will be set to
<code>fetchTime + fetchInterval - delta * SYNC_DELTA_RATE</code></li>
<li>if the adjusted fetch interval is bigger than the delta, then
<code>fetchInterval = delta</code>.</li>
</ul>
</li>
<li>the minimum value of fetchInterval may not be smaller than MIN_INTERVAL
(default is 1 minute).</li>
<li>the maximum value of fetchInterval may not be bigger than MAX_INTERVAL
(default is 365 days).</li>
</ul>
<p>
NOTE: values of DEC_FACTOR and INC_FACTOR higher than 0.4f may destabilize
the algorithm, so that the fetch interval either increases or decreases
infinitely, with little relevance to the page changes. Please use
<a href="../../../../org/apache/nutch/crawl/AdaptiveFetchSchedule.html#main-java.lang.String:A-"><code>main(String[])</code></a> method to test the values before applying them in a
production system.
</p></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">
<!-- =========== FIELD SUMMARY =========== -->
<ul class="blockList">
<li class="blockList"><a name="field.summary">
<!-- -->
</a>
<h3>Field Summary</h3>
<table class="memberSummary" border="0" cellpadding="3" cellspacing="0" summary="Field Summary table, listing fields, and an explanation">
<caption><span>Fields</span><span class="tabEnd">&nbsp;</span></caption>
<tr>
<th class="colFirst" scope="col">Modifier and Type</th>
<th class="colLast" scope="col">Field and Description</th>
</tr>
<tr class="altColor">
<td class="colFirst"><code>protected float</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/crawl/AdaptiveFetchSchedule.html#DEC_RATE">DEC_RATE</a></span></code>&nbsp;</td>
</tr>
<tr class="rowColor">
<td class="colFirst"><code>protected float</code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/crawl/AdaptiveFetchSchedule.html#INC_RATE">INC_RATE</a></span></code>&nbsp;</td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="fields.inherited.from.class.org.apache.nutch.crawl.AbstractFetchSchedule">
<!-- -->
</a>
<h3>Fields inherited from class&nbsp;org.apache.nutch.crawl.<a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">AbstractFetchSchedule</a></h3>
<code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#defaultInterval">defaultInterval</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#maxInterval">maxInterval</a></code></li>
</ul>
<ul class="blockList">
<li class="blockList"><a name="fields.inherited.from.class.org.apache.nutch.crawl.FetchSchedule">
<!-- -->
</a>
<h3>Fields inherited from interface&nbsp;org.apache.nutch.crawl.<a href="../../../../org/apache/nutch/crawl/FetchSchedule.html" title="interface in org.apache.nutch.crawl">FetchSchedule</a></h3>
<code><a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#SECONDS_PER_DAY">SECONDS_PER_DAY</a>, <a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_MODIFIED">STATUS_MODIFIED</a>, <a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_NOTMODIFIED">STATUS_NOTMODIFIED</a>, <a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_UNKNOWN">STATUS_UNKNOWN</a></code></li>
</ul>
</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/crawl/AdaptiveFetchSchedule.html#AdaptiveFetchSchedule--">AdaptiveFetchSchedule</a></span>()</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/crawl/AdaptiveFetchSchedule.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/crawl/AdaptiveFetchSchedule.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>
<tr id="i2" class="altColor">
<td class="colFirst"><code><a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl">CrawlDatum</a></code></td>
<td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/crawl/AdaptiveFetchSchedule.html#setFetchSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-long-int-">setFetchSchedule</a></span>(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/io/Text.html?is-external=true" title="class or interface in org.apache.hadoop.io">Text</a>&nbsp;url,
<a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl">CrawlDatum</a>&nbsp;datum,
long&nbsp;prevFetchTime,
long&nbsp;prevModifiedTime,
long&nbsp;fetchTime,
long&nbsp;modifiedTime,
int&nbsp;state)</code>
<div class="block">Sets the <code>fetchInterval</code> and <code>fetchTime</code> on a
successfully fetched page.</div>
</td>
</tr>
</table>
<ul class="blockList">
<li class="blockList"><a name="methods.inherited.from.class.org.apache.nutch.crawl.AbstractFetchSchedule">
<!-- -->
</a>
<h3>Methods inherited from class&nbsp;org.apache.nutch.crawl.<a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">AbstractFetchSchedule</a></h3>
<code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#calculateLastFetchTime-org.apache.nutch.crawl.CrawlDatum-">calculateLastFetchTime</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#forceRefetch-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-boolean-">forceRefetch</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#initializeSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-">initializeSchedule</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#setPageGoneSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-">setPageGoneSchedule</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#setPageRetrySchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-">setPageRetrySchedule</a>, <a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#shouldFetch-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-">shouldFetch</a></code></li>
</ul>
<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">
<!-- ============ FIELD DETAIL =========== -->
<ul class="blockList">
<li class="blockList"><a name="field.detail">
<!-- -->
</a>
<h3>Field Detail</h3>
<a name="INC_RATE">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>INC_RATE</h4>
<pre>protected&nbsp;float INC_RATE</pre>
</li>
</ul>
<a name="DEC_RATE">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>DEC_RATE</h4>
<pre>protected&nbsp;float DEC_RATE</pre>
</li>
</ul>
</li>
</ul>
<!-- ========= CONSTRUCTOR DETAIL ======== -->
<ul class="blockList">
<li class="blockList"><a name="constructor.detail">
<!-- -->
</a>
<h3>Constructor Detail</h3>
<a name="AdaptiveFetchSchedule--">
<!-- -->
</a>
<ul class="blockListLast">
<li class="blockList">
<h4>AdaptiveFetchSchedule</h4>
<pre>public&nbsp;AdaptiveFetchSchedule()</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="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#setConf-org.apache.hadoop.conf.Configuration-">setConf</a></code>&nbsp;in class&nbsp;<code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">AbstractFetchSchedule</a></code></dd>
</dl>
</li>
</ul>
<a name="setFetchSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-long-int-">
<!-- -->
</a>
<ul class="blockList">
<li class="blockList">
<h4>setFetchSchedule</h4>
<pre>public&nbsp;<a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl">CrawlDatum</a>&nbsp;setFetchSchedule(<a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/io/Text.html?is-external=true" title="class or interface in org.apache.hadoop.io">Text</a>&nbsp;url,
<a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl">CrawlDatum</a>&nbsp;datum,
long&nbsp;prevFetchTime,
long&nbsp;prevModifiedTime,
long&nbsp;fetchTime,
long&nbsp;modifiedTime,
int&nbsp;state)</pre>
<div class="block"><span class="descfrmTypeLabel">Description copied from class:&nbsp;<code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#setFetchSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-long-int-">AbstractFetchSchedule</a></code></span></div>
<div class="block">Sets the <code>fetchInterval</code> and <code>fetchTime</code> on a
successfully fetched page. NOTE: this implementation resets the retry
counter - extending classes should call super.setFetchSchedule() to
preserve this behavior.</div>
<dl>
<dt><span class="overrideSpecifyLabel">Specified by:</span></dt>
<dd><code><a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#setFetchSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-long-int-">setFetchSchedule</a></code>&nbsp;in interface&nbsp;<code><a href="../../../../org/apache/nutch/crawl/FetchSchedule.html" title="interface in org.apache.nutch.crawl">FetchSchedule</a></code></dd>
<dt><span class="overrideSpecifyLabel">Overrides:</span></dt>
<dd><code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html#setFetchSchedule-org.apache.hadoop.io.Text-org.apache.nutch.crawl.CrawlDatum-long-long-long-long-int-">setFetchSchedule</a></code>&nbsp;in class&nbsp;<code><a href="../../../../org/apache/nutch/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl">AbstractFetchSchedule</a></code></dd>
<dt><span class="paramLabel">Parameters:</span></dt>
<dd><code>url</code> - url of the page</dd>
<dd><code>datum</code> - page description to be adjusted. NOTE: this instance, passed by
reference, may be modified inside the method.</dd>
<dd><code>prevFetchTime</code> - previous value of fetch time, or 0 if not available.</dd>
<dd><code>prevModifiedTime</code> - previous value of modifiedTime, or 0 if not available.</dd>
<dd><code>fetchTime</code> - the latest time, when the page was recently re-fetched. Most
FetchSchedule implementations should update the value in @see
CrawlDatum to something greater than this value.</dd>
<dd><code>modifiedTime</code> - last time the content was modified. This information comes from
the protocol implementations, or is set to &lt; 0 if not available.
Most FetchSchedule implementations should update the value in @see
CrawlDatum to this value.</dd>
<dd><code>state</code> - if <a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_MODIFIED"><code>FetchSchedule.STATUS_MODIFIED</code></a>, then the content is considered to be
"changed" before the <code>fetchTime</code>, if
<a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_NOTMODIFIED"><code>FetchSchedule.STATUS_NOTMODIFIED</code></a> then the content is known to be
unchanged. This information may be obtained by comparing page
signatures before and after fetching. If this is set to
<a href="../../../../org/apache/nutch/crawl/FetchSchedule.html#STATUS_UNKNOWN"><code>FetchSchedule.STATUS_UNKNOWN</code></a>, then it is unknown whether the page was
changed; implementations are free to follow a sensible default
behavior.</dd>
<dt><span class="returnLabel">Returns:</span></dt>
<dd>adjusted page information, including all original information.
NOTE: this may be a different instance than @see CrawlDatum, but
implementations should make sure that it contains at least all
information from @see CrawlDatum}.</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/AdaptiveFetchSchedule.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/crawl/AbstractFetchSchedule.html" title="class in org.apache.nutch.crawl"><span class="typeNameLink">Prev&nbsp;Class</span></a></li>
<li><a href="../../../../org/apache/nutch/crawl/CrawlDatum.html" title="class in org.apache.nutch.crawl"><span class="typeNameLink">Next&nbsp;Class</span></a></li>
</ul>
<ul class="navList">
<li><a href="../../../../index.html?org/apache/nutch/crawl/AdaptiveFetchSchedule.html" target="_top">Frames</a></li>
<li><a href="AdaptiveFetchSchedule.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>Nested&nbsp;|&nbsp;</li>
<li><a href="#field.summary">Field</a>&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><a href="#field.detail">Field</a>&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>