Lucene 高亮 分词 搜索

首先运行
@Test
public void testSave(){
    Article article=new Article();
    article.setId(1); //模拟数据
    article.setTitle("双12");
    article.setContent("双12就要疯狂购");
    //创建索引  Lucene上下文  帮我去保存的
    articleDAO.save(article);
}
高亮
import entity.Article;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.wltea.analyzer.lucene.IKAnalyzer;
import util.AritcleDocumentUtils;
import util.Configuration;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.search.highlight.*;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;

import java.io.IOException;
import java.io.StringReader;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;

public class HighLighterTest {
    @Test
    public void search() throws IOException, ParseException, InvalidTokenOffsetsException {
        String  word="疯狂";
        IndexReader indexReader= DirectoryReader.open(Configuration.getDirectory());
        //1.6   索引搜索
        IndexSearcher indexSearcher=new IndexSearcher(indexReader);
        //1.7 针对一个字段进行查询。 入参列名 和 分词器
        QueryParser queryParser=new MultiFieldQueryParser(new String[]{"title","content"},Configuration.getAnalyzer());
        //1.8 类似  Query抽象类
        Query query=queryParser.parse(word);
        // 1.9  去索引目录中查询，返回的是TopDocs对象，里面存放的就是上面放的document文档对象
        TopDocs topDocs = indexSearcher.search(query, 100);
        //1.10 int totalHits -- 命中的查询的总数。
        int count= (int) topDocs.totalHits;//总结果数
        System.out.println(count+"总记录数");
        //1.11 ScoreDoc 里面有我们真正的文档对象
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;

        /**
         * 分割线==================================================高亮思路一
         */
        //一、创建并配置高亮器
        //指定摘要的大小
        //创建高亮器
        Formatter formatter=new SimpleHTMLFormatter("<font color='red'>","</font>");
        Scorer scorer=new QueryScorer(query,"content");
        Highlighter highlighter=new Highlighter(formatter,scorer);
        //摘要
        Fragmenter fragmenter=new SimpleFragmenter(20);
        highlighter.setTextFragmenter(fragmenter);

        //处理结果
        List<Article> list=new ArrayList<Article>();
        for (int i=0;i<scoreDocs.length;i++){
            int docid=scoreDocs[i].doc;
            //1.12  根据内部编号    取出真正的  Document数据
            Document doc=  indexSearcher.doc(docid);


            /**
             *
             *分割线二============================================
             *
             *
             */
            //二：做高亮操作  如果高亮字段中没有关键词，返回null
            String text=highlighter.getBestFragment(Configuration.getAnalyzer(),"content",doc.get("content"));
            ((Field) doc.getField("content")).setStringValue(text);
            //把Document转化成Article
            Article article= AritcleDocumentUtils.documentToArticle(doc);
            list.add(article);
        }
        for (Article arti:list){
            System.out.println(arti.getTitle());
            System.out.println(arti.getContent());
        }
    }
}
 

分词
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.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.*;
import org.apache.lucene.index.Term;
import org.apache.lucene.util.Version;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

import java.io.IOException;
import java.io.StringReader;

/**
 * Created by Happy on 2017-12-01.
 */
public class AnalyzerTest {

    @Test
    //分词器
    public void test() throws Exception {
        //String word="a good person,Happy Every Day";
        //String word="我为何不哭，因为我仅存的，就只有坚强了";
        String word="中华人民共和国，小星星，我们是";
        //Analyzer analyzer = new StandardAnalyzer();//一元分词
        // Analyzer analyzer=new CJKAnalyzer();  //二元分词
        // Analyzer analyzer=new SmartChineseAnalyzer();  //智能中文分词
        //IK分词
        Analyzer analyzer=new IKAnalyzer(true);
        testAnalyzer(analyzer,word);
    }

 
    //使用指定的分词器对指定的文本进行分词
    public  void testAnalyzer(Analyzer analyzer, String text) throws Exception {
        System.out.println("分词器：" + analyzer.getClass());
        StringReader reader= new StringReader(text);
        TokenStream tokenStream = analyzer.tokenStream("content",reader);
        tokenStream.reset();
        CharTermAttribute cta =tokenStream.addAttribute(CharTermAttribute.class);
        while (tokenStream.incrementToken()) {
            System.out.println(cta);
        }
        reader.close();
    }
}

搜索

import entity.Article;
import util.AritcleDocumentUtils;
import util.Configuration;
import util.LuceneUtil;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
import org.junit.Test;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/**
 * Created by Happy on 2017-12-04.
 */
public class QueryTest {
    @Test
    //关键词查询
    public void testPrimaryKey() throws ParseException, InvalidTokenOffsetsException, IOException {
        Query query= new TermQuery(new Term("content","疯狂"));
        search(query);
    }

    @Test
    //通配符查询  Struts2  WildCard  *_*
    public void testWildCard() throws ParseException, InvalidTokenOffsetsException, IOException {
        /**
         * ?:1个任意字符
         * *:0或者多个任意字符
         */
        Query query= new WildcardQuery(new Term("content","疯*"));
        search(query);
    }

    @Test
    //查询所有
    public void testAll() throws ParseException, InvalidTokenOffsetsException, IOException {
        Query query= new MatchAllDocsQuery();
        search(query);
    }

    @Test
    //模糊查询
    public void testLike() throws ParseException, InvalidTokenOffsetsException, IOException {
        //第二个参数指定最小相似度，表示有多少写对了就查出来
        Query query= new FuzzyQuery(new Term("title","pring"),2);
        search(query);
    }



    public void search(Query query) throws IOException, ParseException, InvalidTokenOffsetsException {
       /* String  word="content:疯狂";*/
        IndexReader indexReader= DirectoryReader.open(Configuration.getDirectory());
        //1.6   索引搜索
        IndexSearcher indexSearcher=new IndexSearcher(indexReader);
       /* //1.7 针对一个字段进行查询。 入参列名 和 分词器
        QueryParser queryParser=new MultiFieldQueryParser(new String[]{"title","content"},Configuration.getAnalyzer());
        //1.8 类似  Query抽象类
        Query query=queryParser.parse(word);*/
      // Query query= new TermQuery(new Term("content","疯狂"));
        // 1.9  去索引目录中查询，返回的是TopDocs对象，里面存放的就是上面放的document文档对象
        TopDocs topDocs = indexSearcher.search(query,100);
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;

        //处理结果
        List<Article> list=new ArrayList<Article>();
        for (int i=0;i<scoreDocs.length;i++){
            ScoreDoc scoreDoc=scoreDocs[i];
            System.out.println("得分"+scoreDoc.score);
            int docid=scoreDocs[i].doc;
            //1.12  根据内部编号    取出真正的  Document数据
            Document doc=  indexSearcher.doc(docid);
            //把Document转化成Article
            Article article= AritcleDocumentUtils.documentToArticle(doc);
            list.add(article);
        }
        for (Article arti:list){
            System.out.println("id===="+arti.getId());
            System.out.println(arti.getTitle());
            System.out.println(arti.getContent());
        }
    }
}