Lucene + mmseg4j 中文分词记要

http://javadoc.org.cn/home.php?mod=space&uid=2&do=blog&id=19

package test;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;

import com.tuyard.groupen.SpiderImpl;

public class GoodsSearch {

 @Test
 public void testQuery() {
  try {

   Directory indexDirectory = FSDirectory.open(SpiderImpl.indexDateDir);
   IndexSearcher searcher = new IndexSearcher(indexDirectory, true);

   BooleanQuery query = new BooleanQuery();
   Query termQuery = new TermQuery(new Term("city", String.valueOf(3))); // 基本／精确
                                      // 查询
   query.add(termQuery, Occur.MUST);// 根据索引中的document生成时的设置，可以实现精确记录
   QueryParser qp = new QueryParser(Version.LUCENE_29, "content", SpiderImpl.Analyzer);
   Query qcontent = qp.parse("东北");
   query.add(qcontent, Occur.MUST);
   //
   TopDocs tds = searcher.search(query, 10);
   // request.setAttribute("paging", Paging.getPagingString(tds.totalHits,
   // pageSize, cpage, "/q.htm?p=$&q=" + URLEncoder.encode(str, "utf-8") +
   // ".htm"));
   StringBuffer sb = new StringBuffer();
   for (ScoreDoc sd : tds.scoreDocs) {
    System.out.println(sd.score);
    sb.append(searcher.doc(sd.doc).get("id")).append(",");
    System.out.println(searcher.doc(sd.doc).get("id"));
   }
   System.out.println("==" + sb.toString());
   // String sql = "select * from TB_Goods where id in(" + sb + ")";
   // request.setAttribute("list", objs[2]);
  } catch (Exception e) {
   e.printStackTrace();
  }
 }

 @Test
 public void testBuilder() {
  try {
   String txt = "京华时报1月23日报道 昨天，受一股来自中西伯利亚的强冷空气影响，本市出现大风降温天气，白天最高气温只有零下7摄氏度，同时伴有6到7级的偏北风。";
   IndexWriter iwriter = new IndexWriter(Search.goodsIndex, Search.Analyzer, true,
     IndexWriter.MaxFieldLength.LIMITED);

   Document doc = new Document();
   doc.add(new Field("txt", txt, Field.Store.YES, Field.Index.ANALYZED));
   iwriter.addDocument(doc);
   iwriter.commit();
   iwriter.optimize();
   iwriter.close();

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

 @Test
 public void testSearch() {
  try {
   IndexSearcher searcher = new IndexSearcher(Search.goodsIndex, true);
   QueryParser qp = new QueryParser(Version.LUCENE_29, "txt", Search.Analyzer);
   Query q = qp.parse("西伯利亚");
   System.out.println(q);
   TopDocs tds = searcher.search(q, 10);
   System.out.println("======size:" + tds.totalHits + "========");
   for (ScoreDoc sd : tds.scoreDocs) {
    System.out.println(sd.score);
    System.out.println(searcher.doc(sd.doc).get("txt"));
   }
  } catch (Exception e) {
   e.printStackTrace();
  }

 }
}

 

相关的jar文件: http://www.apache.org/dist/lucene/java/lucene-2.9.3.zip


http://code.google.com/p/mmseg4j/