org.apache.nutch.crawl

Class CrawlDbReader

java.lang.Object

org.apache.nutch.crawl.CrawlDbReader

All Implemented Interfaces:

Closeable, AutoCloseable

public class CrawlDbReader
extends Object
implements Closeable

Read utility for the CrawlDB.

Author:

Andrzej Bialecki

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CrawlDbReader.CrawlDatumCsvOutputFormat
static class	CrawlDbReader.CrawlDbDumpMapper
static class	CrawlDbReader.CrawlDbStatCombiner
static class	CrawlDbReader.CrawlDbStatMapper
static class	CrawlDbReader.CrawlDbStatReducer
static class	CrawlDbReader.CrawlDbTopNMapper
static class	CrawlDbReader.CrawlDbTopNReducer

Field Summary

Fields

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

Constructor Summary

Constructors

Constructor and Description
CrawlDbReader()

Method Summary

Methods

Modifier and Type	Method and Description
void	close()
CrawlDatum	get(String crawlDb, String url, org.apache.hadoop.conf.Configuration config)
static void	main(String[] args)
void	processDumpJob(String crawlDb, String output, org.apache.hadoop.conf.Configuration config, String format, String regex, String status, Integer retry)
void	processStatJob(String crawlDb, org.apache.hadoop.conf.Configuration config, boolean sort)
void	processTopNJob(String crawlDb, long topN, float min, String output, org.apache.hadoop.conf.Configuration config)
void	readUrl(String crawlDb, String url, org.apache.hadoop.conf.Configuration config)

Methods inherited from class java.lang.Object

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

Field Detail

LOG

public static final org.slf4j.Logger LOG

Constructor Detail

CrawlDbReader

public CrawlDbReader()

Method Detail

close

public void close()

Specified by:

close in interface Closeable

Specified by:

close in interface AutoCloseable

processStatJob

public void processStatJob(String crawlDb,
                  org.apache.hadoop.conf.Configuration config,
                  boolean sort)
                    throws IOException

Throws:

IOException

get

public CrawlDatum get(String crawlDb,
             String url,
             org.apache.hadoop.conf.Configuration config)
               throws IOException

Throws:

IOException

readUrl

public void readUrl(String crawlDb,
           String url,
           org.apache.hadoop.conf.Configuration config)
             throws IOException

Throws:

IOException

processDumpJob

public void processDumpJob(String crawlDb,
                  String output,
                  org.apache.hadoop.conf.Configuration config,
                  String format,
                  String regex,
                  String status,
                  Integer retry)
                    throws IOException

Throws:

IOException

processTopNJob

public void processTopNJob(String crawlDb,
                  long topN,
                  float min,
                  String output,
                  org.apache.hadoop.conf.Configuration config)
                    throws IOException

Throws:

IOException

main

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

Throws:

IOException