<%@ page contentType="text/html; charset=gb2312"%>
<%@ page import="java.io.*"%>
<%@ page import="java.util.*" %>
全文搜索
全文搜索
<%!
//filestring = filterweb(filestring,'<','>'); //过滤网页中的HTML语句
String filterweb(String str, char c1, char c2)
{
int pos1=str.indexOf(c1);
int pos2=str.indexOf(c2);
while((pos1!=-1)&&(pos2!=-1))
{
str=str.substring(0,pos1)+str.substring(pos2+1,str.length());
pos1=str.indexOf(c1);
pos2=str.indexOf(c2);
}
return str;
}
%>
<%
String[] FileArray = new String[1000]; int pFileArray=0;
String[] DirectoryQueue = new String[1000]; int pDirectoryQueue=0;
String findstr="";
String realPath="";
String element="";
String tmps="";
Iterator iter=null;
Collection set;
set=application.getResourcePaths("/");
iter = set.iterator();
while (iter.hasNext())
{
element = iter.next();
realPath=application.getRealPath("/");
realPath=realPath+element.substring(1,element.length());
tmps=realPath.substring(realPath.length()-1,realPath.length());
if(tmps.equals("/")) //如果为目录
{
realPath=realPath.replace('/','\\');
realPath=realPath.substring(0,realPath.length()-1); //删除目录种最后的字符“\”
DirectoryQueue[pDirectoryQueue++]=realPath; //入队列
} else
{
FileArray[pFileArray++]=realPath;
}
} //end while (iter.hasNext())
while(pDirectoryQueue!=0) //如果队列不为空
{
pDirectoryQueue--;
String CurPath=DirectoryQueue[pDirectoryQueue];
String relativePath =application.getRealPath("/"); //"D:\tomcat6\webapps\ROOT\"
relativePath ="\\"+CurPath.replace(relativePath ,""); //获取相对路径
set=application.getResourcePaths(relativePath );
iter = set.iterator();
while(iter.hasNext())
{
element = iter.next();
realPath=application.getRealPath("/"); //"D:\tomcat6\webapps\ROOT\"
realPath=realPath+element.substring(1,element.length()); //构造绝对路径
tmps=realPath.substring(realPath.length()-1,realPath.length());
if(tmps.equals("/")) //如果为目录
{
realPath=realPath.replace('/','\\');
realPath=realPath.substring(0,realPath.length()-1); //删除目录种最后的字符“\”
DirectoryQueue[pDirectoryQueue++]=realPath; //入队列
} else
{
realPath=realPath.replace('/','\\');
//if(realPath.lastIndexOf(".htm")!=-1)
{
FileArray[pFileArray++]=realPath;
//out.println(realPath+" --------> "+realPath.lastIndexOf(".htm")+"
");
}
// else if(realPath.lastIndexOf(".html")!=-1) FileArray[pFileArray++]=realPath;
// else if(realPath.lastIndexOf(".jsp")!=-1) FileArray[pFileArray++]=realPath;
}
} //end while (iter.hasNext())
}//end while(pDirectoryQueue!=0)
//----------------- 依次检索站内的每个网页 -----------------------------
//out.println("站内一共 "+pFileArray+" 个文件
");
//if(1==1) return;
int curFileNo=0;
int htmcount=0;
for(curFileNo=0;curFileNo");
//if(1==1) continue;
//if(realPath.equals("D:\\tomcat6\\webapps\\ROOT\\ch6\\testsearch.htm")) return;
FileInputStream fis = null;
fis = new FileInputStream(realPath);
BufferedReader br = new BufferedReader(new InputStreamReader(fis));
String filestring="";
String tempstring="";
while((tempstring=br.readLine())!=null) //把网页文件读入字符串
{
filestring = filestring + tempstring ;
}
//------------------- 开始处理 -------------------------------
filestring = filestring.replace(" ",""); //过滤字符串
int loc1 = filestring.indexOf("");
int loc2 = filestring.indexOf("");
String title = "" ;
if ( loc1 != -1 && loc2 != -1 )
{
title = filestring.substring(loc1+7,loc2); //读取网页中的title项
}
int pos1=filestring.indexOf("");
filestring=filestring.substring(pos1,pos2); //取 之间的部分
filestring = filterweb(filestring,'<','>'); //过滤网页中的HTML语句
filestring = filestring.replace(" ",""); //过滤特殊字符
filestring = filestring.replace(" ",""); //过滤特殊字符
filestring = filestring.replace(" ",""); //过滤空格
findstr="和平使命";
String ShowStr="";
int start=-1;
boolean FindOK = false ;
if((start=filestring.indexOf(findstr))!=-1) //找正文
{
pos1=start-80;
pos2=start+80;
if(pos1<0) pos1=0;
if(pos2>filestring.length()) pos2=filestring.length();
ShowStr=filestring.substring(pos1,pos2);
ShowStr=ShowStr.replace(findstr,""+findstr+"")+"...";
FindOK=true;
}
if(!FindOK) //如果在正文中找不到，则找标题
{
if(title.indexOf(findstr)!=-1)
{
ShowStr=title.replace(findstr,""+findstr+"");
FindOK=true;
}
}
if(FindOK)
{
// out.println("
------------------------------------------------------------------------------
");
String ROOTPath=application.getRealPath("/");
String relpath=realPath.replace(ROOTPath,""); //取相对路径
String httpstr="http://"+request.getServerName()+":"+request.getServerPort()+"/"+relpath;
httpstr=httpstr.replace("\\","/");
%>
<%
}
//else out.println("没有找到！
");
//if((start=filestring.indexOf(findstr))!=-1)
//if(1==1) return;
// if(1==1) return;
}//end for(curFileNo=0;curFileNo
");
%>
ssssssssssssssssss22