索引源代码:
package lucene;
/**
* <p>title: </p>
* <p>description: </p>
* <p>copyright: copyright (c) 2003</p>
* <p>company: </p>
* @author shirley
* @version 1.0
*/
import org.apache.lucene.index.*;
import org.apache.lucene.analysis.*;
import java.io.*;
import org.apache.lucene.document.*;
public class indexfiles {
//使用方法:: indexfiles [索引输出目录] [索引的文件列表] …
public static void main(string[] arg) throws exception {
string[] args = new string[2];
//索引后存放索引信息的路径
args[0] = system.getproperty("java.io.tmpdir", "tmp") + system.getproperty("file.separator") + "index-1";
//待索引文件
args[1] = "e:\\appwork\\lucene\\rfc2047.txt";
args[2] = "e:\\appwork\\cyberoffice\\co\\sheldon java mail.htm";
args[3] = "e:\\appwork\\lucene\\englishtest.doc";
args[4] = "e:\\appwork\\cyberoffice\\co\\xls1.xls";
args[5] = "e:\\appwork\\cyberoffice\\co\\ppt1.ppt";
string indexpath = args[0];
indexwriter writer;
//用指定的语言分析器构造一个新的写索引器(第3个参数表示是否为追加索引)
writer = new indexwriter(indexpath, new simpleanalyzer(), false);
for (int i=1; i<args.length; i++) {
system.out.println("indexing file " + args[i]);
inputstream is = new fileinputstream(args[i]);
//构造包含2个字段field的document对象
//一个是路径path字段,不索引,只存储
//一个是内容body字段,进行全文索引,并存储
document doc = new document();
doc.add(field.unindexed("path", args[i]));
doc.add(field.text("body", (reader) new inputstreamreader(is)));
//将文档写入索引
writer.adddocument(doc);
is.close();
};
//关闭写索引器
writer.close();
}
}
搜索源代码:
package lucene;
/**
* <p>title: </p>
* <p>description: </p>
* <p>copyright: copyright (c) 2003</p>
* <p>company: </p>
* @author shirley
* @version 1.0
*/
import org.apache.lucene.search.*;
import org.apache.lucene.queryparser.*;
import org.apache.lucene.analysis.*;
public class search {
public static void main(string[] arg) throws exception {
string[] args = new string[2];
//索引后存放索引信息的路径
args[0] = system.getproperty("java.io.tmpdir", "tmp") + system.getproperty("file.separator") + "index-1";
//搜索關鍵字
args[1] = "sending";
string indexpath = args[0];
string querystring = args[1];
//指向索引目录的搜索器
searcher searcher = new indexsearcher(indexpath);
//查询解析器:使用和索引同样的语言分析器
query query = queryparser.parse(querystring, "body", new simpleanalyzer());
//搜索结果使用hits存储
hits hits = searcher.search(query);
//通过hits可以访问到相应字段的数据和查询的匹配度
for (int i=0; i<hits.length(); i++) {
system.out.println(hits.doc(i).get("path") + "; score: " + hits.score(i));
};
}
}
注:目前程序只支持英文索引,可以过滤文件类型为.txt .doc .htm .xls .ppt
中文索引及其它类型文件的索引正在研究中……
