lucene自定义分词器

感谢http://qindongliang1922.iteye.com/blog/1927605 

这篇文章让我豁然开朗~

建议研究lucene时一定要下载源码

 

下面代码中有个bug，，，一开始没弄没明白，在用这个分词器进行索引后发现搜不到东西。。是tokenStart和tokenEnd的错，这2个表示该词所在位置，，我这样说不知道对不对，但我感觉我的意思已经表达出来

 

package TEST;

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.util.AttributeFactory;

public class My extends Tokenizer {

	private final StringBuilder buffer = new StringBuilder();

	private int tokenStart = 0, tokenEnd = 0;
	private final static String PUNCTION = " -()/";
	private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
	private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
	//private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);

	public My(Reader reader) {
		super(reader);
	}

	public My(AttributeFactory factory, Reader input) {
		super(factory, input);
	}

	@Override
	public boolean incrementToken() throws IOException {
		clearAttributes();
		buffer.setLength(0);
		int ci;
		char ch;
		tokenStart = tokenEnd;
		
		ci = input.read();
		if(ci>64&&ci<91){
			ci=ci+32;
		}
		ch = (char) ci;
		while (true) {
			if (ci == -1){
				if (buffer.length() == 0)
					return false;
				else {
					termAtt.setEmpty().append(buffer);
					offsetAtt.setOffset(correctOffset(tokenStart),
							correctOffset(tokenEnd));
					return true;
				}
			}
			else if (PUNCTION.indexOf(ch) != -1) {
				//buffer.append(ch);
				tokenEnd++;
				if(buffer.length()>0){
					termAtt.setEmpty().append(buffer);
					offsetAtt.setOffset(correctOffset(tokenStart),
						correctOffset(tokenEnd));
					return true;
				}else
				{
					ci = input.read();
					if(ci>64&&ci<91){
						ci=ci+32;
					}
					ch = (char) ci;
				}
			} else {
				buffer.append(ch);
				tokenEnd++;
				ci = input.read();
				if(ci>64&&ci<91){
					ci=ci+32;
				}
				ch = (char) ci;
			}
		}
		
	}
	@Override
	public void reset() throws IOException {
		super.reset();
		tokenStart = tokenEnd = 0;
	}
	@Override
	public void end() throws IOException {
		super.end();
		final int finalOffset = correctOffset(tokenEnd);
		offsetAtt.setOffset(finalOffset, finalOffset);
	}

}

 然后开始写分词器

package TEST;

import java.io.Reader;

import org.apache.lucene.analysis.Analyzer;

public class MyAnalyzer extends Analyzer{

	@Override
	protected TokenStreamComponents createComponents(String fieldName,
			Reader reader) {
		return new TokenStreamComponents(new My(reader));
	}

}

 最后测试下

package TEST;

import java.io.StringReader;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

public class TestMy {
	public static void main(String[] args) throws Exception {
		MyAnalyzer ma = new MyAnalyzer();
		String str = "Norther 雪中悍刀行 河北邯郸   AC DF-II-SDFzd(asd)/小时";
		//MyChineseAnalyzer mc= new MyChineseAnalyzer();  这是三劫散仙的分词器
		TokenStream ts = ma.tokenStream("field", new StringReader(str));
		CharTermAttribute c = ts.addAttribute(CharTermAttribute.class);
		ts.reset();
		while (ts.incrementToken()) {
			System.out.println(c.toString());
		}

		ts.end();
		ts.close();

	}
}

 测试结果：