org.archive.access.nutch
Class NutchwaxIndexer

java.lang.Object
  org.apache.hadoop.util.ToolBase
      org.apache.nutch.indexer.Indexer
          org.archive.access.nutch.NutchwaxIndexer

All Implemented Interfaces:

org.apache.hadoop.conf.Configurable, org.apache.hadoop.io.Closeable, org.apache.hadoop.mapred.JobConfigurable, org.apache.hadoop.mapred.Mapper, org.apache.hadoop.mapred.Reducer, org.apache.hadoop.util.Tool

public class NutchwaxIndexer
extends org.apache.nutch.indexer.Indexer

Subclass of nutch Indexer that handles keys that are not just URLs.

Author:

stack

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.nutch.indexer.Indexer

org.apache.nutch.indexer.Indexer.OutputFormat

Field Summary

org.apache.commons.logging.Log

LOG

Fields inherited from class org.apache.nutch.indexer.Indexer

DONE_NAME

Fields inherited from class org.apache.hadoop.util.ToolBase

conf

Constructor Summary

NutchwaxIndexer()

NutchwaxIndexer(org.apache.hadoop.conf.Configuration c)

Method Summary

void	index(org.apache.hadoop.fs.Path indexDir, org.apache.hadoop.fs.Path crawlDb, org.apache.hadoop.fs.Path linkDb, org.apache.hadoop.fs.Path[] segments)
static void	main(java.lang.String[] args)
void	reduce(org.apache.hadoop.io.WritableComparable key, java.util.Iterator values, org.apache.hadoop.mapred.OutputCollector output, org.apache.hadoop.mapred.Reporter reporter)

Methods inherited from class org.apache.nutch.indexer.Indexer

close, configure, map, run

Methods inherited from class org.apache.hadoop.util.ToolBase

doMain, getConf, setConf

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LOG

public final org.apache.commons.logging.Log LOG

Constructor Detail

NutchwaxIndexer

public NutchwaxIndexer()

NutchwaxIndexer

public NutchwaxIndexer(org.apache.hadoop.conf.Configuration c)

Method Detail

reduce

public void reduce(org.apache.hadoop.io.WritableComparable key,
                   java.util.Iterator values,
                   org.apache.hadoop.mapred.OutputCollector output,
                   org.apache.hadoop.mapred.Reporter reporter)
            throws java.io.IOException

Specified by:

reduce in interface org.apache.hadoop.mapred.Reducer

Overrides:

reduce in class org.apache.nutch.indexer.Indexer

Throws:

java.io.IOException

index

public void index(org.apache.hadoop.fs.Path indexDir,
                  org.apache.hadoop.fs.Path crawlDb,
                  org.apache.hadoop.fs.Path linkDb,
                  org.apache.hadoop.fs.Path[] segments)
           throws java.io.IOException

Overrides:

index in class org.apache.nutch.indexer.Indexer

Throws:

java.io.IOException

main

public static void main(java.lang.String[] args)
                 throws java.lang.Exception

Throws:

java.lang.Exception