org.apache.nutch.indexer

Class IndexingJob

java.lang.Object

org.apache.hadoop.conf.Configured

org.apache.nutch.indexer.IndexingJob

All Implemented Interfaces:

org.apache.hadoop.conf.Configurable, org.apache.hadoop.util.Tool

public class IndexingJob
extends org.apache.hadoop.conf.Configured
implements org.apache.hadoop.util.Tool

Generic indexer which relies on the plugins implementing IndexWriter

Field Summary

Fields

Modifier and Type	Field and Description
static org.slf4j.Logger	LOG

Constructor Summary

Constructors

Constructor and Description
IndexingJob()
IndexingJob(org.apache.hadoop.conf.Configuration conf)

Method Summary

Methods

Modifier and Type	Method and Description
void	index(org.apache.hadoop.fs.Path crawlDb, org.apache.hadoop.fs.Path linkDb, List<org.apache.hadoop.fs.Path> segments, boolean noCommit)
void	index(org.apache.hadoop.fs.Path crawlDb, org.apache.hadoop.fs.Path linkDb, List<org.apache.hadoop.fs.Path> segments, boolean noCommit, boolean deleteGone)
void	index(org.apache.hadoop.fs.Path crawlDb, org.apache.hadoop.fs.Path linkDb, List<org.apache.hadoop.fs.Path> segments, boolean noCommit, boolean deleteGone, String params)
void	index(org.apache.hadoop.fs.Path crawlDb, org.apache.hadoop.fs.Path linkDb, List<org.apache.hadoop.fs.Path> segments, boolean noCommit, boolean deleteGone, String params, boolean filter, boolean normalize)
static void	main(String[] args)
int	run(String[] args)

Methods inherited from class org.apache.hadoop.conf.Configured

getConf, setConf

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.hadoop.conf.Configurable

getConf, setConf

Field Detail

LOG

public static org.slf4j.Logger LOG

Constructor Detail

IndexingJob

public IndexingJob()

IndexingJob

public IndexingJob(org.apache.hadoop.conf.Configuration conf)

Method Detail

index

public void index(org.apache.hadoop.fs.Path crawlDb,
         org.apache.hadoop.fs.Path linkDb,
         List<org.apache.hadoop.fs.Path> segments,
         boolean noCommit)
           throws IOException

Throws:

IOException

index

public void index(org.apache.hadoop.fs.Path crawlDb,
         org.apache.hadoop.fs.Path linkDb,
         List<org.apache.hadoop.fs.Path> segments,
         boolean noCommit,
         boolean deleteGone)
           throws IOException

Throws:

IOException

index

public void index(org.apache.hadoop.fs.Path crawlDb,
         org.apache.hadoop.fs.Path linkDb,
         List<org.apache.hadoop.fs.Path> segments,
         boolean noCommit,
         boolean deleteGone,
         String params)
           throws IOException

Throws:

IOException

index

public void index(org.apache.hadoop.fs.Path crawlDb,
         org.apache.hadoop.fs.Path linkDb,
         List<org.apache.hadoop.fs.Path> segments,
         boolean noCommit,
         boolean deleteGone,
         String params,
         boolean filter,
         boolean normalize)
           throws IOException

Throws:

IOException

run

public int run(String[] args)
        throws Exception

Specified by:

run in interface org.apache.hadoop.util.Tool

Throws:

Exception

main

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

Throws:

Exception