Module org.apache.lucene.analysis.nori

Package org.apache.lucene.analysis.ko.util

Class TokenInfoDictionaryBuilder

java.lang.Object

org.apache.lucene.analysis.ko.util.TokenInfoDictionaryBuilder

class TokenInfoDictionaryBuilder
extends Object

Field Summary

Fields

Modifier and Type	Field	Description
private String	encoding
private Normalizer.Form	normalForm
private int	offset	Internal word id - incrementally assigned as entries are read and added.

Constructor Summary

Constructors

Constructor	Description
TokenInfoDictionaryBuilder(String encoding, boolean normalizeEntries)

Method Summary

Modifier and Type	Method	Description
TokenInfoDictionaryWriter	build(Path dir)
private TokenInfoDictionaryWriter	buildDictionary(List<Path> csvFiles)

Methods inherited from class java.lang.Object

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

Field Details

offset

private int offset

Internal word id - incrementally assigned as entries are read and added. This will be byte offset of dictionary file

encoding

private String encoding

normalForm

private Normalizer.Form normalForm

Constructor Details

TokenInfoDictionaryBuilder

TokenInfoDictionaryBuilder(String encoding,
 boolean normalizeEntries)

Method Details

build

public TokenInfoDictionaryWriter build(Path dir)
                                throws IOException

Throws:

IOException

buildDictionary

private TokenInfoDictionaryWriter buildDictionary(List<Path> csvFiles)
                                           throws IOException

Throws:

IOException