| <!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 12:27:56 PST 2021 --> |
| <title>IndexerMapReduce (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="IndexerMapReduce (apache-nutch 1.18 API)"; |
| } |
| } |
| catch(err) { |
| } |
| //--> |
| var methods = {"i0":9}; |
| var tabs = {65535:["t0","All Methods"],1:["t1","Static 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/IndexerMapReduce.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/indexer/CleaningJob.DeleterReducer.html" title="class in org.apache.nutch.indexer"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.IndexerMapper.html" title="class in org.apache.nutch.indexer"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../index.html?org/apache/nutch/indexer/IndexerMapReduce.html" target="_top">Frames</a></li> |
| <li><a href="IndexerMapReduce.html" target="_top">No Frames</a></li> |
| </ul> |
| <ul class="navList" id="allclasses_navbar_top"> |
| <li><a href="../../../../allclasses-noframe.html">All 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: </li> |
| <li><a href="#nested.class.summary">Nested</a> | </li> |
| <li><a href="#field.summary">Field</a> | </li> |
| <li><a href="#constructor.summary">Constr</a> | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li><a href="#field.detail">Field</a> | </li> |
| <li><a href="#constructor.detail">Constr</a> | </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.indexer</div> |
| <h2 title="Class IndexerMapReduce" class="title">Class IndexerMapReduce</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.indexer.IndexerMapReduce</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></dd> |
| </dl> |
| <hr> |
| <br> |
| <pre>public class <span class="typeNameLabel">IndexerMapReduce</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></pre> |
| <div class="block"><p> |
| This class is typically invoked from within |
| <a href="../../../../org/apache/nutch/indexer/IndexingJob.html" title="class in org.apache.nutch.indexer"><code>IndexingJob</code></a> and handles all MapReduce |
| functionality required when undertaking indexing. |
| </p> |
| <p> |
| This is a consequence of one or more indexing plugins being invoked which |
| extend <a href="../../../../org/apache/nutch/indexer/IndexWriter.html" title="interface in org.apache.nutch.indexer"><code>IndexWriter</code></a>. |
| </p> |
| <p> |
| See |
| <code>org.apache.nutch.indexer.IndexerMapReduce#initMRJob(Path, Path, Collection, JobConf, boolean)</code> |
| for details on the specific data structures and parameters required for |
| indexing. |
| </p></div> |
| </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"> </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 </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.IndexerMapper.html" title="class in org.apache.nutch.indexer">IndexerMapReduce.IndexerMapper</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static class </code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.IndexerReducer.html" title="class in org.apache.nutch.indexer">IndexerMapReduce.IndexerReducer</a></span></code> </td> |
| </tr> |
| </table> |
| </li> |
| </ul> |
| <!-- =========== 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"> </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>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_BINARY_AS_BASE64">INDEXER_BINARY_AS_BASE64</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_DELETE">INDEXER_DELETE</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_DELETE_ROBOTS_NOINDEX">INDEXER_DELETE_ROBOTS_NOINDEX</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_DELETE_SKIPPED">INDEXER_DELETE_SKIPPED</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_NO_COMMIT">INDEXER_NO_COMMIT</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_PARAMS">INDEXER_PARAMS</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#INDEXER_SKIP_NOTMODIFIED">INDEXER_SKIP_NOTMODIFIED</a></span></code> </td> |
| </tr> |
| <tr class="rowColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#URL_FILTERING">URL_FILTERING</a></span></code> </td> |
| </tr> |
| <tr class="altColor"> |
| <td class="colFirst"><code>static <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></code></td> |
| <td class="colLast"><code><span class="memberNameLink"><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.html#URL_NORMALIZING">URL_NORMALIZING</a></span></code> </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"> </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/indexer/IndexerMapReduce.html#IndexerMapReduce--">IndexerMapReduce</a></span>()</code> </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"> </span></span><span id="t1" class="tableTab"><span><a href="javascript:show(1);">Static Methods</a></span><span class="tabEnd"> </span></span><span id="t4" class="tableTab"><span><a href="javascript:show(8);">Concrete Methods</a></span><span class="tabEnd"> </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/indexer/IndexerMapReduce.html#initMRJob-org.apache.hadoop.fs.Path-org.apache.hadoop.fs.Path-java.util.Collection-org.apache.hadoop.mapreduce.Job-boolean-">initMRJob</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> crawlDb, |
| <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> linkDb, |
| <a href="https://docs.oracle.com/javase/8/docs/api/java/util/Collection.html?is-external=true" title="class or interface in java.util">Collection</a><<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>> segments, |
| <a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/mapreduce/Job.html?is-external=true" title="class or interface in org.apache.hadoop.mapreduce">Job</a> job, |
| boolean addBinaryContent)</code> </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 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>, <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></li> |
| </ul> |
| <ul class="blockList"> |
| <li class="blockList"><a name="methods.inherited.from.class.java.lang.Object"> |
| <!-- --> |
| </a> |
| <h3>Methods inherited from class 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> |
| </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="INDEXER_PARAMS"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_PARAMS</h4> |
| <pre>public static final <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> INDEXER_PARAMS</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_PARAMS">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_DELETE"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_DELETE</h4> |
| <pre>public static final <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> INDEXER_DELETE</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_DELETE">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_NO_COMMIT"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_NO_COMMIT</h4> |
| <pre>public static final <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> INDEXER_NO_COMMIT</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_NO_COMMIT">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_DELETE_ROBOTS_NOINDEX"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_DELETE_ROBOTS_NOINDEX</h4> |
| <pre>public static final <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> INDEXER_DELETE_ROBOTS_NOINDEX</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_DELETE_ROBOTS_NOINDEX">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_DELETE_SKIPPED"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_DELETE_SKIPPED</h4> |
| <pre>public static final <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> INDEXER_DELETE_SKIPPED</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_DELETE_SKIPPED">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_SKIP_NOTMODIFIED"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>INDEXER_SKIP_NOTMODIFIED</h4> |
| <pre>public static final <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> INDEXER_SKIP_NOTMODIFIED</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_SKIP_NOTMODIFIED">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="URL_FILTERING"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>URL_FILTERING</h4> |
| <pre>public static final <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> URL_FILTERING</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.URL_FILTERING">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="URL_NORMALIZING"> |
| <!-- --> |
| </a> |
| <ul class="blockList"> |
| <li class="blockList"> |
| <h4>URL_NORMALIZING</h4> |
| <pre>public static final <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> URL_NORMALIZING</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.URL_NORMALIZING">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| <a name="INDEXER_BINARY_AS_BASE64"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>INDEXER_BINARY_AS_BASE64</h4> |
| <pre>public static final <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> INDEXER_BINARY_AS_BASE64</pre> |
| <dl> |
| <dt><span class="seeLabel">See Also:</span></dt> |
| <dd><a href="../../../../constant-values.html#org.apache.nutch.indexer.IndexerMapReduce.INDEXER_BINARY_AS_BASE64">Constant Field Values</a></dd> |
| </dl> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ========= CONSTRUCTOR DETAIL ======== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="constructor.detail"> |
| <!-- --> |
| </a> |
| <h3>Constructor Detail</h3> |
| <a name="IndexerMapReduce--"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>IndexerMapReduce</h4> |
| <pre>public IndexerMapReduce()</pre> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| <!-- ============ METHOD DETAIL ========== --> |
| <ul class="blockList"> |
| <li class="blockList"><a name="method.detail"> |
| <!-- --> |
| </a> |
| <h3>Method Detail</h3> |
| <a name="initMRJob-org.apache.hadoop.fs.Path-org.apache.hadoop.fs.Path-java.util.Collection-org.apache.hadoop.mapreduce.Job-boolean-"> |
| <!-- --> |
| </a> |
| <ul class="blockListLast"> |
| <li class="blockList"> |
| <h4>initMRJob</h4> |
| <pre>public static void initMRJob(<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> crawlDb, |
| <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> linkDb, |
| <a href="https://docs.oracle.com/javase/8/docs/api/java/util/Collection.html?is-external=true" title="class or interface in java.util">Collection</a><<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>> segments, |
| <a href="https://hadoop.apache.org/docs/r3.1.3/api/org/apache/hadoop/mapreduce/Job.html?is-external=true" title="class or interface in org.apache.hadoop.mapreduce">Job</a> job, |
| boolean addBinaryContent) |
| 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></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> |
| </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/IndexerMapReduce.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/indexer/CleaningJob.DeleterReducer.html" title="class in org.apache.nutch.indexer"><span class="typeNameLink">Prev Class</span></a></li> |
| <li><a href="../../../../org/apache/nutch/indexer/IndexerMapReduce.IndexerMapper.html" title="class in org.apache.nutch.indexer"><span class="typeNameLink">Next Class</span></a></li> |
| </ul> |
| <ul class="navList"> |
| <li><a href="../../../../index.html?org/apache/nutch/indexer/IndexerMapReduce.html" target="_top">Frames</a></li> |
| <li><a href="IndexerMapReduce.html" target="_top">No Frames</a></li> |
| </ul> |
| <ul class="navList" id="allclasses_navbar_bottom"> |
| <li><a href="../../../../allclasses-noframe.html">All 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: </li> |
| <li><a href="#nested.class.summary">Nested</a> | </li> |
| <li><a href="#field.summary">Field</a> | </li> |
| <li><a href="#constructor.summary">Constr</a> | </li> |
| <li><a href="#method.summary">Method</a></li> |
| </ul> |
| <ul class="subNavList"> |
| <li>Detail: </li> |
| <li><a href="#field.detail">Field</a> | </li> |
| <li><a href="#constructor.detail">Constr</a> | </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 © 2021 The Apache Software Foundation</small></p> |
| </body> |
| </html> |