断点续传原理

(一)断点续传的原理
其实断点续传的原理很简单，就是在http的请求上和一般的下载有所不同而已。
打个比方，浏览器请求服务器上的一个文时，所发出的请求如下：
假设服务器域名为wwww.sjtu.edu.cn，文件名为down.zip。
get /down.zip http/1.1
accept: image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/vnd.ms-
excel, application/msword, application/vnd.ms-powerpoint, */*
accept-language: zh-cn
accept-encoding: gzip, deflate
user-agent: mozilla/4.0 (compatible; msie 5.01; windows nt 5.0)
connection: keep-alive


服务器收到请求后，按要求寻找请求的文件，提取文件的信息，然后返回给浏览器，返回信息如下：


200
content-length=106786028
accept-ranges=bytes
date=mon, 30 apr 2001 12:56:11 gmt
etag=w/"02ca57e173c11:95b"
content-type=application/octet-stream
server=microsoft-iis/5.0
last-modified=mon, 30 apr 2001 12:56:11 gmt


所谓断点续传，也就是要从文件已经下载的地方开始继续下载。所以在客户端浏览器传给
web服务器的时候要多加一条信息--从哪里开始。
下面是用自己编的一个"浏览器"来传递请求信息给web服务器，要求从2000070字节开始。
get /down.zip http/1.0
user-agent: netfox
range: bytes=2000070-
accept: text/html, image/gif, image/jpeg, *; q=.2, */*; q=.2


仔细看一下就会发现多了一行range: bytes=2000070-
这一行的意思就是告诉服务器down.zip这个文件从2000070字节开始传，前面的字节不用传了。
服务器收到这个请求以后，返回的信息如下：
206
content-length=106786028
content-range=bytes 2000070-106786027/106786028
date=mon, 30 apr 2001 12:55:20 gmt
etag=w/"02ca57e173c11:95b"
content-type=application/octet-stream
server=microsoft-iis/5.0
last-modified=mon, 30 apr 2001 12:55:20 gmt


和前面服务器返回的信息比较一下，就会发现增加了一行：
content-range=bytes 2000070-106786027/106786028
返回的代码也改为206了，而不再是200了。


知道了以上原理，就可以进行断点续传的编程了。


(二)java实现断点续传的关键几点


(1)用什么方法实现提交range: bytes=2000070-。
当然用最原始的socket是肯定能完成的，不过那样太费事了，其实java的net包中提供了这种功能。代码如下：
url url = new url("http://www.sjtu.edu.cn/down.zip");
httpurlconnection httpconnection = (httpurlconnection)url.openconnection


();
//设置user-agent
httpconnection.setrequestproperty("user-agent","netfox");
//设置断点续传的开始位置
httpconnection.setrequestproperty("range","bytes=2000070");
//获得输入流
inputstream input = httpconnection.getinputstream();


从输入流中取出的字节流就是down.zip文件从2000070开始的字节流。
大家看，其实断点续传用java实现起来还是很简单的吧。
接下来要做的事就是怎么保存获得的流到文件中去了。


保存文件采用的方法。
我采用的是io包中的randaccessfile类。
操作相当简单，假设从2000070处开始保存文件，代码如下：
randomaccess osavedfile = new randomaccessfile("down.zip","rw");
long npos = 2000070;
//定位文件指针到npos位置
osavedfile.seek(npos);
byte[] b = new byte[1024];
int nread;
//从输入流中读入字节流，然后写到文件中
while((nread=input.read(b,0,1024)) > 0)
{
osavedfile.write(b,0,nread);
}

怎么样，也很简单吧。
接下来要做的就是整合成一个完整的程序了。包括一系列的线程控制等等。



(三)断点续传内核的实现
主要用了6个类，包括一个测试类。
sitefilefetch.java负责整个文件的抓取，控制内部线程(filesplitterfetch类)。
filesplitterfetch.java负责部分文件的抓取。
fileaccess.java负责文件的存储。
siteinfobean.java要抓取的文件的信息，如文件保存的目录，名字，抓取文件的url等。
utility.java工具类，放一些简单的方法。
testmethod.java测试类。


下面是源程序：
/*
**sitefilefetch.java
*/
package netfox;
import java.io.*;
import java.net.*;


public class sitefilefetch extends thread {


siteinfobean siteinfobean = null; //文件信息bean
long[] nstartpos; //开始位置
long[] nendpos; //结束位置
filesplitterfetch[] filesplitterfetch; //子线程对象
long nfilelength; //文件长度
boolean bfirst = true; //是否第一次取文件
boolean bstop = false; //停止标志
file tmpfile; //文件下载的临时信息
dataoutputstream output; //输出到文件的输出流


public sitefilefetch(siteinfobean bean) throws ioexception
{
siteinfobean = bean;
//tmpfile = file.createtempfile ("zhong","1111",new file(bean.getsfilepath()));
tmpfile = new file(bean.getsfilepath()+file.separator + bean.getsfilename()+".info");
if(tmpfile.exists ())
{
bfirst = false;
read_npos();
}
else
{
nstartpos = new long[bean.getnsplitter()];
nendpos = new long[bean.getnsplitter()];
}



}


public void run()
{
//获得文件长度
//分割文件
//实例filesplitterfetch
//启动filesplitterfetch线程
//等待子线程返回
try{
if(bfirst)
{
nfilelength = getfilesize();
if(nfilelength == -1)
{
system.err.println("file length is not known!");
}
else if(nfilelength == -2)
{
system.err.println("file is not access!");
}
else
{
for(int i=0;i<nstartpos.length;i++)
{
nstartpos= (long)(i*(nfilelength/nstartpos.length));
}
for(int i=0;i<nendpos.length-1;i++)
{
nendpos = nstartpos[i+1];
}
nendpos[nendpos.length-1] = nfilelength;
}
}
//启动子线程
filesplitterfetch = new filesplitterfetch[nstartpos.length];
for(int i=0;i<nstartpos.length;i++)
{
filesplitterfetch = new filesplitterfetch(siteinfobean.getssiteurl(),
siteinfobean.getsfilepath() + file.separator + siteinfobean.getsfilename(),
nstartpos,nendpos,i);
utility.log("thread " + i + " , nstartpos = " + nstartpos + ", nendpos = " + nendpos);
filesplitterfetch.start();
}
// filesplitterfetch[npos.length-1] = new filesplitterfetch(siteinfobean.getssiteurl(),
siteinfobean.getsfilepath() + file.separator + siteinfobean.getsfilename(),npos[npos.length-1],nfilelength,npos.length-1);
// utility.log("thread " + (npos.length-1) + " , nstartpos = " + npos[npos.length-1] + ",
nendpos = " + nfilelength);
// filesplitterfetch[npos.length-1].start();


//等待子线程结束
//int count = 0;
//是否结束while循环
boolean breakwhile = false;


while(!bstop)
{
write_npos();
utility.sleep(500);
breakwhile = true;


for(int i=0;i<nstartpos.length;i++)
{
if(!filesplitterfetch.bdownover)
{
breakwhile = false;
break;
}
}
if(breakwhile)
break;


//count++;
//if(count>4)
// sitestop();
}


system.err.println("文件下载结束！");
}
catch(exception e){e.printstacktrace ();}
}


//获得文件长度
public long getfilesize()
{
int nfilelength = -1;
try{
url url = new url(siteinfobean.getssiteurl());
httpurlconnection httpconnection = (httpurlconnection)url.openconnection ();
httpconnection.setrequestproperty("user-agent","netfox");


int responsecode=httpconnection.getresponsecode();
if(responsecode>=400)
{
processerrorcode(responsecode);
return -2; //-2 represent access is error
}


string sheader;


for(int i=1;;i++)
{
//datainputstream in = new datainputstream(httpconnection.getinputstream ());
//utility.log(in.readline());
sheader=httpconnection.getheaderfieldkey(i);
if(sheader!=null)
{
if(sheader.equals("content-length"))
{
nfilelength = integer.parseint(httpconnection.getheaderfield(sheader));
break;
}
}
else
break;
}
}
catch(ioexception e){e.printstacktrace ();}
catch(exception e){e.printstacktrace ();}


utility.log(nfilelength);


return nfilelength;
}


//保存下载信息（文件指针位置）
private void write_npos()
{
try{
output = new dataoutputstream(new fileoutputstream(tmpfile));
output.writeint(nstartpos.length);
for(int i=0;i<nstartpos.length;i++)
{
// output.writelong(npos);
output.writelong(filesplitterfetch.nstartpos);
output.writelong(filesplitterfetch.nendpos);
}
output.close();
}
catch(ioexception e){e.printstacktrace ();}
catch(exception e){e.printstacktrace ();}
}


//读取保存的下载信息（文件指针位置）
private void read_npos()
{
try{
datainputstream input = new datainputstream(new fileinputstream(tmpfile));
int ncount = input.readint();
nstartpos = new long[ncount];
nendpos = new long[ncount];
for(int i=0;i<nstartpos.length;i++)
{
nstartpos = input.readlong();
nendpos = input.readlong();
}
input.close();
}
catch(ioexception e){e.printstacktrace ();}
catch(exception e){e.printstacktrace ();}
}


private void processerrorcode(int nerrorcode)
{
system.err.println("error code : " + nerrorcode);
}


//停止文件下载
public void sitestop()
{
bstop = true;
for(int i=0;i<nstartpos.length;i++)
filesplitterfetch.splitterstop();


}
}
/*
**filesplitterfetch.java
*/
package netfox;


import java.io.*;
import java.net.*;


public class filesplitterfetch extends thread {


string surl; //file url
long nstartpos; //file snippet start position
long nendpos; //file snippet end position
int nthreadid; //threads id
boolean bdownover = false; //downing is over
boolean bstop = false; //stop identical
fileaccessi fileaccessi = null; //file access interface


public filesplitterfetch(string surl,string sname,long nstart,long nend,int id) throws ioexception
{
this.surl = surl;
this.nstartpos = nstart;
this.nendpos = nend;
nthreadid = id;
fileaccessi = new fileaccessi(sname,nstartpos);
}


public void run()
{
while(nstartpos < nendpos && !bstop)
{


try{
url url = new url(surl);
httpurlconnection httpconnection = (httpurlconnection)url.openconnection ();
httpconnection.setrequestproperty("user-agent","netfox");
string sproperty = "bytes="+nstartpos+"-";
httpconnection.setrequestproperty("range",sproperty);
utility.log(sproperty);


inputstream input = httpconnection.getinputstream();
//logresponsehead(httpconnection);


byte[] b = new byte[1024];
int nread;
while((nread=input.read(b,0,1024)) > 0 && nstartpos < nendpos && !bstop)
{
nstartpos += fileaccessi.write(b,0,nread);
//if(nthreadid == 1)
// utility.log("nstartpos = " + nstartpos + ", nendpos = " + nendpos);
}


utility.log("thread " + nthreadid + " is over!");
bdownover = true;
//npos = fileaccessi.write (b,0,nread);
}
catch(exception e){e.printstacktrace ();}
}
}


//打印回应的头信息
public void logresponsehead(httpurlconnection con)
{
for(int i=1;;i++)
{
string header=con.getheaderfieldkey(i);
if(header!=null)
//responseheaders.put(header,httpconnection.getheaderfield(header));
utility.log(header+" : "+con.getheaderfield(header));
else
break;
}
}


public void splitterstop()
{
bstop = true;
}


}


/*
**fileaccess.java
*/
package netfox;
import java.io.*;


public class fileaccessi implements serializable{


randomaccessfile osavedfile;
long npos;


public fileaccessi() throws ioexception
{
this("",0);
}


public fileaccessi(string sname,long npos) throws ioexception
{
osavedfile = new randomaccessfile(sname,"rw");
this.npos = npos;
osavedfile.seek(npos);
}


public synchronized int write(byte[] b,int nstart,int nlen)
{
int n = -1;
try{
osavedfile.write(b,nstart,nlen);
n = nlen;
}
catch(ioexception e)
{
e.printstacktrace ();
}


return n;
}


}


/*
**siteinfobean.java
*/
package netfox;


public class siteinfobean {


private string ssiteurl; //sites url
private string sfilepath; //saved files path
private string sfilename; //saved files name
private int nsplitter; //count of splited downloading file


public siteinfobean()
{
//default value of nsplitter is 5
this("","","",5);
}


public siteinfobean(string surl,string spath,string sname,int nspiltter)
{
ssiteurl= surl;
sfilepath = spath;
sfilename = sname;
this.nsplitter = nspiltter;


}


public string getssiteurl()
{
return ssiteurl;
}


public void setssiteurl(string value)
{
ssiteurl = value;
}


public string getsfilepath()
{
return sfilepath;
}


public void setsfilepath(string value)
{
sfilepath = value;
}


public string getsfilename()
{
return sfilename;
}


public void setsfilename(string value)
{
sfilename = value;
}


public int getnsplitter()
{
return nsplitter;
}


public void setnsplitter(int ncount)
{
nsplitter = ncount;
}
}


/*
**utility.java
*/
package netfox;


public class utility {


public utility()
{


}


public static void sleep(int nsecond)
{
try{
thread.sleep(nsecond);
}
catch(exception e)
{
e.printstacktrace ();
}
}


public static void log(string smsg)
{
system.err.println(smsg);
}


public static void log(int smsg)
{
system.err.println(smsg);
}
}


/*
**testmethod.java
*/
package netfox;


public class testmethod {


public testmethod()
{ ///xx/weblogic60b2_win.exe
try{
siteinfobean bean = new siteinfobean("http://localhost/xx/weblogic60b2_win.exe","l:\\temp","weblogic60b2_win.exe",5);
//siteinfobean bean = new siteinfobean("http://localhost:8080/down.zip","l:\\temp","weblogic60b2_win.exe",5);
sitefilefetch filefetch = new sitefilefetch(bean);
filefetch.start();
}
catch(exception e){e.printstacktrace ();}


}


public static void main(string[] args)
{
new testmethod();
}
}