Lucene 6.0下使用IK分词器
Lucene 6.0使用IK分词器需要修改修改IKAnalyzer和IKTokenizer.
使用时先新建一个MyIKTokenizer类,一个MyIkAnalyzer类:
MyIKTokenizer.java
import java.io.IOException;
import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;
public class MyIKTokenizer extends Tokenizer {
// IK分词器实现
private IKSegmenter _IKImplement;
// 词元文本属性
private final CharTermAttribute termAtt;
// 词元位移属性
private final OffsetAttribute offsetAtt;
// 词元分类属性(该属性分类参考org.wltea.analyzer.core.Lexeme中的分类常量)
private final TypeAttribute typeAtt;
// 记录最后一个词元的结束位置
private int endPosition;
public MyIKTokenizer(Reader in) {
this(in, false);
}
public MyIKTokenizer(Reader in, boolean useSmart) {
offsetAtt = addAttribute(OffsetAttribute.class);
termAtt = addAttribute(CharTermAttribute.class);
typeAtt = addAttribute(TypeAttribute.class);
_IKImplement = new IKSegmenter(input, useSmart);
}
@Override
public boolean incrementToken() throws IOException {
// 清除所有的词元属性
clearAttributes();
Lexeme nextLexeme = _IKImplement.next();
if (nextLexeme != null) {
// 将Lexeme转成Attributes
// 设置词元文本
termAtt.append(nextLexeme.getLexemeText());
// 设置词元长度
termAtt.setLength(nextLexeme.getLength());
// 设置词元位移
offsetAtt.setOffset(nextLexeme.getBeginPosition(),
nextLexeme.getEndPosition());
// 记录分词的最后位置
endPosition = nextLexeme.getEndPosition();
// 记录词元分类
typeAtt.setType(nextLexeme.getLexemeTypeString());
// 返会true告知还有下个词元
return true;
}
// 返会false告知词元输出完毕
return false;
}
public void reset() throws IOException {
super.reset();
_IKImplement.reset(input);
}
@Override
public final void end() {
// set final offset
int finalOffset = correctOffset(this.endPosition);
offsetAtt.setOffset(finalOffset, finalOffset);
}
}
MyIkAnalyzer.java
package cn.ucas.lucene.ik;
import java.io.Reader;
import java.io.StringReader;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.util.IOUtils;
public class MyIkAnalyzer extends Analyzer {
@Override
protected TokenStreamComponents createComponents(String arg0) {
Reader reader=null;
try{
reader=new StringReader(arg0);
MyIKTokenizer it = new MyIKTokenizer(reader);
return new Analyzer.TokenStreamComponents(it);
}finally {
IOUtils.closeWhileHandlingException(reader);
}
}
}
在Lucene中使用IK分词器:
Analyzer myIkAnalyzer=new MyIkAnalyzer();