maven部署lucence4.6版本demo中文分词搜索引擎代码

以前写过一个lucence3.5版本的案例。但是现在要用maven， 并且要用新版本。 研究了下。 稍微跟老版本有所不同。 记录下来初期的一段代码供大家参考。  能完成一般的， 建立索引，修改索引，中文分词，删除索引，关键字查询， 高亮显示关键字查询结果。   

原创地址：https://blog.csdn.net/yjflinchong/article/details/109601765

数据对象

import java.util.List;

public class LucenceVo {
   
   public static final String ID = "id";
   public static final String TITLE = "title";
   public static final String TYPE = "type";
   public static final String DESCRIPTION = "description";
   
   private String id;
   private String type;
   private String title;
   private String description;
   public String getId() {
      return id;
   }
   public void setId(String id) {
      this.id = id;
   }
   public String getType() {
      return type;
   }
   public void setType(String type) {
      this.type = type;
   }
   public String getTitle() {
      return title;
   }
   public void setTitle(String title) {
      this.title = title;
   }
   public String getDescription() {
      return description;
   }
   public void setDescription(String description) {
      this.description = description;
   }

}

工具类，lucence建立 索引，修改索引，删除索引，查询，高亮查询。 中文分词器。

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

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.*;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.*;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;


public class MyLuceneUtil {

    private static File indexDir;
    private static boolean havapath;
    private static Analyzer analyzer;
    private static QueryParser parser;
   private int textmaxlength = 200;
   private static String prefixHTML = "<font color='red'>";
   private static String suffixHTML = "</font>";
    private static MyLuceneUtil lucence = null;

    /** 初始化工具 **/
    private MyLuceneUtil(){
            System.out.println("lucence初始化开始....");
//            analyzer = new StandardAnalyzer(Version.LUCENE_46);
         analyzer = new IKAnalyzer();
            indexDir = new File(this.getClass().getClassLoader().getResource("lucence_index").getFile());
            havapath = (indexDir.list().length >= 0);
            parser = new QueryParser(Version.LUCENE_46, LucenceVo.DESCRIPTION,
                    analyzer);
    }

    /** 返回一个单例 **/
    public static MyLuceneUtil instance(){
        if(lucence==null) {
            lucence = new MyLuceneUtil();
        }
        return lucence;
    }

   public List<LucenceVo> searchList(String querystr, int start, int size) throws IOException {
//    Query q = null;
//    try {
//       StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
//       q = new QueryParser(Version.LUCENE_46,"title", analyzer).parse(querystr);
//    } catch (Exception e) {
//       e.printStackTrace();
//    }
      // search
      int hitsPerPage = (size+start);
      Directory index = FSDirectory.open(indexDir);

      IndexReader reader = DirectoryReader.open(index);
      IndexSearcher searcher = new IndexSearcher(reader);
      TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
        try {
//       StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
         searcher.search(parser.parse(querystr), collector);
      } catch (Exception e) {
         e.printStackTrace();
      }

      ScoreDoc[] hits = collector.topDocs().scoreDocs;
      int end = (size+start)<hits.length?(size+start):hits.length;
      // display results
//    System.out.println("Found " + hits.length + " hits.");
      List<LucenceVo> volist = new ArrayList<LucenceVo>();
      for (int i = start; i < end; ++i) {
         int docId = hits[i].doc;
         Document d = searcher.doc(docId);
            LucenceVo info = new LucenceVo();
//       System.out.println((i + 1) + ". " + d.get("id") + "\t" + d.get("title") + "\t" + d.get(info.DESCRIPTION));
            info.setId(d.get(info.ID));
            info.setTitle(d.get(info.TITLE));
            info.setType(d.get(info.TYPE));
            info.setDescription(d.get(info.DESCRIPTION));
            volist.add(info);
      }
      reader.close();
      return volist;
   }

   public static void cutWordsDemo(String text) throws IOException {
//    SimpleAnalyzer analyzer = new SimpleAnalyzer(Version.LUCENE_46);
      TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(text));
      CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
      try {
         tokenStream.reset();
         while (tokenStream.incrementToken()) {
            System.out.println(charTermAttribute.toString());
         }
         tokenStream.end();
      } finally {
         tokenStream.close();
//       analyzer.close();
      }
   }




   /**
    * 添加单个到索引库中
    * @
    * @param vo
    * @throws IOException
    */
   public void addIndex(LucenceVo vo) throws IOException {
      IndexWriter writer = openIndexWriter();
      try {
         Document document = builderDocument(vo);
         writer.addDocument(document);
      } finally {
         writer.close();
      }
   }

    /**
     * 修改单个到索引库中
     * @
     * @param vo
     * @throws IOException
     */
    public void updateIndex(LucenceVo vo) throws IOException {
        IndexWriter writer = openIndexWriter();
        try {
            Document document = builderDocument(vo);
            writer.updateDocument(new Term(vo.ID, vo.getId()),document);
        } finally {
            writer.close();
        }
    }

   /**
    * 修改单个到索引库中
    * @
    * @param vo
    * @throws IOException
    */
   public void deleteIndex(LucenceVo vo) throws IOException {
      IndexWriter writer = openIndexWriter();
      try {
         writer.deleteDocuments(new Term(vo.ID, vo.getId()));
      } finally {
         writer.close();
      }
   }



   /**
    * 删除所有索引文件
    * @
    */
   public void deleteAllFile(){
      File[] files = indexDir.listFiles();
      for (int i = 0; i < files.length; i++) {
         if(!files[i].getAbsolutePath().endsWith(".java") && !files[i].getAbsolutePath().endsWith(".class"))
            files[i].delete();
      }
   }

   private IndexWriter openIndexWriter() throws IOException {
        IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_46, analyzer);
      //索引 设置为追加或者覆盖
        indexWriterConfig.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);
      return new IndexWriter(FSDirectory.open(indexDir), indexWriterConfig);
   }

   @SuppressWarnings("static-access")
   private Document builderDocument(LucenceVo lucenceVo) {
      Document document = new Document();
        document.add(new StringField(lucenceVo.ID, lucenceVo.getId(), Field.Store.YES));
        document.add(new TextField(lucenceVo.TITLE, lucenceVo.getTitle(), Field.Store.YES));
        document.add(new TextField(lucenceVo.DESCRIPTION, lucenceVo.getDescription(), Field.Store.YES));
        document.add(new TextField(lucenceVo.TYPE, lucenceVo.getType(), Field.Store.YES));
      return document;
   }

   /**
    * 索引库中查询-高亮
    * @param keyword
    * @return
    * @
    */
   public List<LucenceVo> searchIndexHighlighter(String keyword,int start,int size)  {
      IndexSearcher searcher = null;
      List<LucenceVo> list = new ArrayList<LucenceVo>();
      if(!havapath){
         return list;
      }
      try {
         IndexReader reader = IndexReader.open(FSDirectory.open(indexDir));
         searcher = new IndexSearcher(reader);
         Query query =parser.parse(keyword);
         TopDocs topDocs = searcher.search(query, (size+start));
         ScoreDoc[] scoreDocs = topDocs.scoreDocs;
         int end = (size+start)<topDocs.totalHits?(size+start):topDocs.totalHits;
         for (int i = start; i < end; i++) {
            Document doc = searcher.doc(scoreDocs[i].doc);
            LucenceVo info = new LucenceVo();
            //关键词加亮
            SimpleHTMLFormatter simpleHTMLFormatter = new  SimpleHTMLFormatter(prefixHTML, suffixHTML);
            Highlighter highlighter = new  Highlighter(simpleHTMLFormatter, new QueryScorer(query));
            highlighter.setTextFragmenter(new SimpleFragmenter(textmaxlength));
//          String DESCRIPTION = highlighter.getBestFragment(analyzer,LucenceVo.DESCRIPTION,doc.get(LucenceVo.DESCRIPTION));
            String TITLE = highlighter.getBestFragment(analyzer,LucenceVo.TITLE,doc.get(LucenceVo.TITLE));
                info.setDescription(doc.get(LucenceVo.DESCRIPTION));
            if(TITLE==null)
            {
                    TITLE = doc.get(LucenceVo.TITLE);
            }
            //取消重复加亮节点
            TITLE = TITLE.replaceAll(suffixHTML+prefixHTML, "");
//          DESCRIPTION = info.getDescription().replaceAll(suffixHTML+prefixHTML, "");
            //实体赋值
            info.setId(doc.get(LucenceVo.ID));
            info.setTitle(TITLE);
            list.add(info);
         }
      }catch (Exception e) {
         e.printStackTrace();
      }

      return list;
   }


   public void testwirte(){
      for (int i = 0; i < 10; i++) {
         LucenceVo vo = new LucenceVo();
         vo.setId("myid"+i);
         vo.setTitle("中国今天新闻"+i);
         vo.setDescription("中国今天新闻"+i+"。新闻关键字备注"+i);
         vo.setType("新闻");
         try{
            this.updateIndex(vo);

         }catch (Exception e){
            e.printStackTrace();
         }
      }
   }

   public static void main(String[] args) {
      MyLuceneUtil lu =  MyLuceneUtil.instance();
      try{
//        lu.testwirte();
         List<LucenceVo> list =  lu.searchList("中国3 关键字",0,5);
//           List<LucenceVo> list =  lu.searchIndexHighlighter("关键字",0,5);
           for (int i=0;i<list.size();i++){
               System.out.println(list.get(i).getTitle()+"==="+list.get(i).getId());
           }
      }catch (Exception e){
         e.printStackTrace();
      }
   }

}

 

maven 配置文件

<!-- lucence搜索引擎 -->
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-core</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-analyzers-common</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-queryparser</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-codecs</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-highlighter</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>org.apache.lucene</groupId>
   <artifactId>lucene-memory</artifactId>
   <version>4.6.1</version>
</dependency>
<dependency>
   <groupId>com.janeluo</groupId>
   <artifactId>ikanalyzer</artifactId>
   <version>2012_u6</version>
</dependency>