org.apache.lucene.benchmark.utils

Class ExtractWikipedia

java.lang.Object

org.apache.lucene.benchmark.utils.ExtractWikipedia

public class ExtractWikipedia
extends java.lang.Object

Extract the downloaded Wikipedia dump into separate files for indexing.

Field Summary

Fields

Modifier and Type	Field and Description
static int	count
protected DocMaker	docMaker

Constructor Summary

Constructors

Constructor and Description
ExtractWikipedia(DocMaker docMaker, java.nio.file.Path outputDir)

Method Summary

Modifier and Type	Method and Description
void	create(java.lang.String id, java.lang.String title, java.lang.String time, java.lang.String body)
java.nio.file.Path	directory(int count, java.nio.file.Path directory)
void	extract()
static void	main(java.lang.String[] args)

Methods inherited from class java.lang.Object

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

Field Detail

count

public static int count

docMaker

protected DocMaker docMaker

Constructor Detail

ExtractWikipedia

public ExtractWikipedia(DocMaker docMaker,
                        java.nio.file.Path outputDir)
                 throws java.io.IOException

Throws:

java.io.IOException

Method Detail

directory

public java.nio.file.Path directory(int count,
                                    java.nio.file.Path directory)

create

public void create(java.lang.String id,
                   java.lang.String title,
                   java.lang.String time,
                   java.lang.String body)
            throws java.io.IOException

Throws:

java.io.IOException

extract

public void extract()
             throws java.lang.Exception

Throws:

java.lang.Exception

main

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

Throws:

java.lang.Exception