searcher.java

基于lucene的 全文检索程序。可以对office等文件pdf文件进行检索

package org.tatan.framework;
import java.io.StringReader;

import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
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.analysis.Token;
import org.apache.lucene.analysis.TokenStream;

import org.apache.lucene.analysis.cjk.CJKAnalyzer;


public class Searcher {
     public static void main(String[] args) throws Exception {
        
         Directory fsDir = FSDirectory.getDirectory("D:\\testdoc\\index", false);
            IndexSearcher is = new IndexSearcher(fsDir);
            
            Token[] tokens = AnalyzerUtils.tokensFromAnalysis(new CJKAnalyzer(), "大家好");
            for (int i = 0; i < tokens.length; i++) {
            	System.out.println(tokens[i].termText());
            	QueryParser qp = new QueryParser("body", new CJKAnalyzer());
            	Query query = qp.parse(tokens[i].termText());
           //Query query = QueryParser.parse(tokens[i].termText(), "body", new CJKAnalyzer());
            	// Highlighter highlighter = new Highlighter(new QueryScorer(query));
                // TokenStream tokenStream = new CJKAnalyzer().tokenStream("contents",
                //         new StringReader("body"));
                // System.out.println(highlighter.getBestFragment(tokenStream, "body"));
            Hits hits = is.search(query);
            SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'><B>","</B></font>");   
            Highlighter highlighter = new Highlighter(simpleHTMLFormatter,new QueryScorer(query));      
            highlighter.setTextFragmenter(new SimpleFragmenter(200));
            
            for (int j = 0; j < hits.length(); j++) {
                Document doc = hits.doc(j);
                System.out.println(doc.get("filename"));
                TokenStream tokenStream =new CJKAnalyzer().tokenStream("body", new StringReader(doc.get("body")));
                System.out.println(highlighter.getBestFragment(tokenStream,doc.get("body")));

              }
           
            
            }
     }
}