追寻人生

学习之园地,创意之源泉

  博客园 :: 首页 :: 博问 :: 闪存 :: 新随笔 :: 联系 :: 订阅 订阅 :: 管理 ::
http://www.matrix.org.cn/thread.shtml?topicId=753ba0a5-125e-11dc-b33a-df989147150e&forumId=32

Lucene是可以做到的,利用lucene的Filter,具体可以查看lucene的api中的org.apache.lucene.search.CachingWrapperFilter,它可以缓存上次的搜索结果,从而实现在结果中的搜索。

测试实例:
package com.wsjava;
import java.io.IOException;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.CachingWrapperFilter;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.QueryFilter;

public class IndexTest {

        /**
         * @param args
         * @throws ParseException
         * @throws IOException
         */
        public static void main(String[] args) throws IOException, ParseException {
                index();
                search("day"); //简单搜索
                searchInResult("day", "you"); //在结果集中搜索
        }
        
        public static void index() throws IOException {
                IndexWriter writer = new IndexWriter("d:/tesindex",new SimpleAnalyzer(), true);
                writer.setMaxMergeDocs(1000);
                writer.setMergeFactor(100);
                for (int i = 0; i < 10; i++) {
                        Document doc = new Document();
                        String content = "How do you do?";
                        if (i >= 5) {
                                content = "What's a good day. ";
                        }
                        if (i >= 7) {
                                content = "Nice day. Thanks you!";
                        }
                        doc.add(new Field("content", content, Field.Store.YES,Field.Index.TOKENIZED));
                        writer.addDocument(doc);
                }

        }
        
        //简单实现对qw的搜索.
        public static void search(String qw) throws IOException, ParseException {
                QueryParser queryParser = new QueryParser("content",new SimpleAnalyzer());
                Query query = queryParser.parse(qw.trim());
                QueryFilter filter = new QueryFilter(query);
                
                search(query, filter);
        }
        
        //在搜索oldqw的结果集中搜索qw.
        public static void searchInResult(String qw, String oldqw) throws ParseException, IOException {                
                QueryParser queryParser = new QueryParser("content",new SimpleAnalyzer());
                Query query = queryParser.parse(qw.trim());
                Query oldQuery = queryParser.parse(oldqw.trim());
                QueryFilter oldFilter = new QueryFilter(oldQuery);
                CachingWrapperFilter filter = new CachingWrapperFilter(oldFilter);
                
                search(query, filter);
        }
        
        private static void search(Query query, Filter filter) throws IOException, ParseException {
                IndexSearcher ins = new IndexSearcher("d:/tesindex");
                Hits hits = ins.search(query, filter);
                for (int i = 0; i < hits.length(); i++) {
                        Document doc = hits.doc(i);
                        System.out.println(doc.get("content"));
                }
                System.out.println();
        }
}

上面是简单的测试程序。当然在实际应用中可以做得比较复杂。
posted on 2007-07-06 15:26  追梦华仔  阅读(3136)  评论(4编辑  收藏  举报