用Lucene建立索引及查询示例
首先去 apache 网站下载 lucene 的开发包,并配置好环境变量
http://jakarta.apache.org/lucene/docs/index.html
建立索引程序:
/*
* Created on 2004-4-26
*/
import org.apache.lucene.index.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.document.*;
import java.io.*;
/**
* @author bell.wang
*/
public class IndexFiles {
public static void main(String[] args) {
try{
IndexWriter writer = new IndexWriter("myindex", new StandardAnalyzer(), true);
File files = new File("mydoc");
String[] Fnamelist = files.list();
for (int i = 0; i < Fnamelist.length; i++){
File file = new File(files,Fnamelist[i]);
Document doc = new Document();
Field fld = Field.Text("path", file.getPath());
doc.add(fld);
fld = Field.Keyword("modified", DateField.timeToString(file.lastModified()));
doc.add(fld);
FileInputStream in = new FileInputStream(file);
Reader reader = new BufferedReader(new InputStreamReader(in));
fld = Field.Text("contents", reader);
doc.add(fld);
writer.addDocument(doc);
System.out.println("Added : " + doc.get("path"));
}
writer.optimize();
writer.close();
System.out.println("Has Added Total: " + Fnamelist.length);
}catch(Exception e){
System.out.println(e);
}
}
}
程序对当前路径下mydoc目录下所有文件建立索引,其中索引有三个字段: 文件路径,
最后修改时间,文件内容. 建立的索引文件在当前路径下的myindex目录
检索程序:
/*
* Created on 2004-4-26
*
*/
import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.search.*;
import org.apache.lucene.queryParser.*;
import org.apache.lucene.document.*;
//import com.augmentum.hrms.*;
import java.util.Date;
/**
* @author bell.wang
*
*/
public class SearchFile {
public static void main(String[] args) {
//XMap a = new XMap("");
Analyzer anlzr = new StandardAnalyzer();
try{
Query q = QueryParser.parse("数据库", "contents", anlzr);
System.out.println("Searching for : " + q.toString("contents"));
Searcher serch = new IndexSearcher("myindex");
Hits hts = serch.search(q);
for(int i=0; i<hts.length(); i++){
Document doc = hts.doc(i);
String path = doc.get("path");
System.out.println("Find: " +i+": "+ path);
System.out.println("Find: " + doc.get("modified"));
System.out.println("Find: " + doc.get("path"));
}
System.out.println("Find Total: " + hts.length());
}catch(Exception e){
System.out.println(e);
}
}
}
程序对索引的contents字段用“数据库“关键字进行查询,返回
的是所有包含有关键字的文档集合,分别打印出各个字段.
上面的程序我用纯文本文件测试通过,.txt,.jsp,.html 都可以,
word,pdf 等文件需要经过转化才能对其进行索引。