lucene IKAnalyzer中文分词器学习(1)

<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-core</artifactId>
    <version>5.3.1</version>
</dependency>
<!--一般分词器,适用于英文分词-->
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-analyzers-common</artifactId>
    <version>5.3.1</version>
</dependency>
<!--中文分词器-->
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-analyzers-smartcn</artifactId>
    <version>5.3.1</version>
</dependency>
<!--对分词索引查询解析-->
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-queryparser</artifactId>
    <version>5.3.1</version>
</dependency>
<!--检索关键字高亮显示-->
<dependency>
    <groupId>org.apache.lucene</groupId>
    <artifactId>lucene-highlighter</artifactId>
    <version>5.3.1</version>
</dependency>
<!--IK分词器-->
<dependency>
    <groupId>com.janeluo</groupId>
    <artifactId>ikanalyzer</artifactId>
    <version>2012_u6</version>
</dependency>

IKAnalyzer不支持5.x的lucene  添加下面两个类即可

import org.apache.lucene.analysis.Analyzer;

public class IKAnalyzer5x extends Analyzer {

    private boolean useSmart;

    public boolean useSmart() {
        return this.useSmart;
    }

    public void setUseSmart(boolean useSmart) {
        this.useSmart = useSmart;
    }

    public IKAnalyzer5x() {
        this(false);
    }

    public IKAnalyzer5x(boolean useSmart) {
        this.useSmart = useSmart;
    }

    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        IKTokenizer5x _IKTokenizer = new IKTokenizer5x(this.useSmart);
        return new TokenStreamComponents(_IKTokenizer);
    }
}
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.apache.lucene.util.AttributeFactory;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;

import java.io.IOException;


public class IKTokenizer5x extends Tokenizer {
    private IKSegmenter _IKImplement;
    private final CharTermAttribute termAtt = (CharTermAttribute)this.addAttribute(CharTermAttribute.class);
    private final OffsetAttribute offsetAtt = (OffsetAttribute)this.addAttribute(OffsetAttribute.class);
    private final TypeAttribute typeAtt = (TypeAttribute)this.addAttribute(TypeAttribute.class);
    private int endPosition;

    public IKTokenizer5x() {
        this._IKImplement = new IKSegmenter(this.input, true);
    }

    public IKTokenizer5x(boolean useSmart) {
        this._IKImplement = new IKSegmenter(this.input, useSmart);
    }

    public IKTokenizer5x(AttributeFactory factory) {
        super(factory);
        this._IKImplement = new IKSegmenter(this.input, true);
    }

    public boolean incrementToken() throws IOException {
        this.clearAttributes();
        Lexeme nextLexeme = this._IKImplement.next();
        if(nextLexeme != null) {
            this.termAtt.append(nextLexeme.getLexemeText());
            this.termAtt.setLength(nextLexeme.getLength());
            this.offsetAtt.setOffset(nextLexeme.getBeginPosition(), nextLexeme.getEndPosition());
            this.endPosition = nextLexeme.getEndPosition();
            this.typeAtt.setType(nextLexeme.getLexemeTypeString());
            return true;
        } else {
            return false;
        }
    }

    public void reset() throws IOException {
        super.reset();
        this._IKImplement.reset(this.input);
    }

    public final void end() {
        int finalOffset = this.correctOffset(this.endPosition);
        this.offsetAtt.setOffset(finalOffset, finalOffset);
    }
}

调用测试分词器

Analyzer analyzer = new IKAnalyzer5x(true);
TokenStream tokenStream = analyzer.tokenStream("test", "一个新款韩版长袖羊驼绒羊毛皮草外套女海宁皮草");
OffsetAttribute offsetAttribute = tokenStream.addAttribute(OffsetAttribute.class);
tokenStream.reset();
while (tokenStream.incrementToken()) {
    System.out.println(offsetAttribute.toString());
}

 

 

转载于:https://my.oschina.net/zhuqianli/blog/1583691

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值