Lucene开发环境搭建-Maven

##1 pom文件中导入具体jar包
具体pom文件如下：

<dependencies>
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-core</artifactId>
            <version>7.2.0</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>7.2.0</version>
        </dependency>
        <!--中文分词器-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-analyzers-smartcn</artifactId>
            <version>7.2.0</version>
        </dependency>

        <!--对分词索引查询解析-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-queryparser</artifactId>
            <version>7.2.0</version>
        </dependency>
        <!--检索关键字高亮显示-->
        <dependency>
            <groupId>org.apache.lucene</groupId>
            <artifactId>lucene-highlighter</artifactId>
            <version>7.2.0</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/com.janeluo/ikanalyzer -->
        <dependency>
            <groupId>com.janeluo</groupId>
            <artifactId>ikanalyzer</artifactId>
            <version>2012_u6</version>
        </dependency>

    </dependencies>

##2 引入IK分词器
在工程的resource目录下，新建IK配置文件IKAnalyzer.cfg.xml,配置如下：

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">  
<properties>  
	<comment>IK Analyzer 扩展配置</comment>
	<!--用户可以在这里配置自己的扩展字典--> 
	<entry key="ext_dict">ext.dic;</entry> 
	<!--用户可以在这里配置自己的扩展停止词字典-->
	<entry key="ext_stopwords">stopword.dic;ext_stopword.dic</entry> 	
</properties>

resource目录下,新建配置文件中的ext.dic、stopword.dic、ext_stopword.dic
##3 IK分词器使用
Lucene使用IK分词器需要修改IKAnalyzer和IKTokenizer。
新建类IKAnalyzer6x继承自IKAnalyzer，代码如下：

package com.fulb.lucene.ik;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;

/**
 * @author fulibao
 * @version 1.0
 * @created 2018/2/18 下午10:25
 **/
public class IKAnalyzer6x extends Analyzer {
    private boolean useSmart;

    public boolean useSmart() {
        return useSmart;
    }

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

    // IK分词器Lucene Analyzer接口实现类;默认细粒度切分算法
    public IKAnalyzer6x() {
        this(false);
    }

    // IK分词器Lucene Analyzer接口实现类;当为true时，分词器进行智能切分
    public IKAnalyzer6x(boolean useSmart) {
        super();
        this.useSmart = useSmart;
    }

    // 重写最新版本的createComponents;重载Analyzer接口，构造分词组件
    @Override
    protected TokenStreamComponents createComponents(String fieldName) {
        Tokenizer _IKTokenizer = new IKTokenizer6x(this.useSmart());
        return new TokenStreamComponents(_IKTokenizer);
    }
}

新建类IKTokenizer6x继承自IKTokenizer，代码示例如下：

package com.fulb.lucene.ik;

import java.io.IOException;
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;

/**
 * @author fulibao
 * @version 1.0
 * @created 2018/2/18 下午6:25
 **/
public class IKTokenizer6x 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;

    // Lucene 6.x Tokenizer适配器类构造函数;实现最新的Tokenizer接口
    public IKTokenizer6x(boolean useSmart) {
        super();
        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.getLexemeText());
            // 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;
    }

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

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

##4 分词器使用代码示例
一段使用Lucene进行分词的代码示例

package com.fulb.lucene.analyzer;

import java.io.IOException;
import java.io.StringReader;
import java.nio.file.Paths;

import com.fulb.lucene.ik.IKAnalyzer6x;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

/**
 * @author fulibao
 * @version 1.0
 * @created 2018/2/18 下午5:47
 **/
public class VariousAnalyzers {
    private static String str ="中华人民共和国简称中国,  是一个有13亿人口的国家";
    public static void main(String[] args) throws IOException {
        Analyzer analyzer = null;

        analyzer = new StandardAnalyzer();// 标准分词
        System.out.println("标准分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new WhitespaceAnalyzer(); // 空格分词
        System.out.println("空格分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new SimpleAnalyzer(); // 简单分词
        System.out.println("简单分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new CJKAnalyzer(); // 二分法分词
        System.out.println("二分法分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new KeywordAnalyzer(); // 关键字分词
        System.out.println("关键字分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

//        analyzer = new StopAnalyzer(Paths.get(VariousAnalyzers.class.getClassLoader().getResource("stopword.dic").getPath()));
        analyzer = new StopAnalyzer();

        // 停用词分词
        System.out.println("停用词分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new SmartChineseAnalyzer(); // 中文智能分词
        System.out.println("中文智能分词:" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new IKAnalyzer6x(); // IK分词(细粒度切分算法)
        System.out.println("IK分词(细粒度切分算法):" + analyzer.getClass());
        printAnalyzer(analyzer);

        analyzer = new IKAnalyzer6x(true); // IK分词(智能切分算法)
        System.out.println("IK分词(智能切分算法):" + analyzer.getClass());
        printAnalyzer(analyzer);
    }

    public static void printAnalyzer(Analyzer analyzer) throws IOException {
        StringReader reader = new StringReader(str);
        TokenStream toStream = analyzer.tokenStream(str, reader);
        toStream.reset();// 清空流
        CharTermAttribute teAttribute = toStream.getAttribute(CharTermAttribute.class);
        while (toStream.incrementToken()) {
            System.out.print(teAttribute.toString() + "|");
        }
        System.out.println("\n");
        analyzer.close();
    }
}