tcpip数据包编码解析(chunk and gzip)
做tcpip协议栈数据包重组时遇到一些编码问题,主要是chunk和gzip编码。
先看chunk:
RFC2616中对Chunked的定义:
Chunked-Body = *chunk
last-chunk
trailer
CRLF
chunk = chunk-size [ chunk-extension ] CRLF
chunk-data CRLF
chunk-size = 1*HEX
last-chunk = 1*("0") [ chunk-extension ] CRLF
chunk-extension= *( ";" chunk-ext-name [ "=" chunk-ext-val ] )
chunk-ext-name = token
chunk-ext-val = token | quoted-string
chunk-data = chunk-size(OCTET)
trailer = *(entity-header CRLF)
以下是解码过程的伪代码:
length := 0//用来记录解码后的数据体长度
read chunk-size, chunk-extension (if any) and CRLF//第一次读取块大小
while (chunk-size > 0) {//一直循环,直到读取的块大小为0
read chunk-data and CRLF//读取块数据体,以回车结束
append chunk-data to entity-body//添加块数据体到解码后实体数据
length := length + chunk-size//更新解码后的实体长度
read chunk-size and CRLF//读取新的块大小
}
read entity-header//以下代码读取全部的头标记
while (entity-header not empty) {
append entity-header to existing header fields
read entity-header
}
Content-Length := length//头标记中添加内容长度
Remove "chunked" from Transfer-Encoding//头标记中移除Transfer-Encoding
Chunked-Body = *chunk
last-chunk
trailer
CRLF
chunk = chunk-size [ chunk-extension ] CRLF
chunk-data CRLF
chunk-size = 1*HEX
last-chunk = 1*("0") [ chunk-extension ] CRLF
chunk-extension= *( ";" chunk-ext-name [ "=" chunk-ext-val ] )
chunk-ext-name = token
chunk-ext-val = token | quoted-string
chunk-data = chunk-size(OCTET)
trailer = *(entity-header CRLF)
以下是解码过程的伪代码:
length := 0//用来记录解码后的数据体长度
read chunk-size, chunk-extension (if any) and CRLF//第一次读取块大小
while (chunk-size > 0) {//一直循环,直到读取的块大小为0
read chunk-data and CRLF//读取块数据体,以回车结束
append chunk-data to entity-body//添加块数据体到解码后实体数据
length := length + chunk-size//更新解码后的实体长度
read chunk-size and CRLF//读取新的块大小
}
read entity-header//以下代码读取全部的头标记
while (entity-header not empty) {
append entity-header to existing header fields
read entity-header
}
Content-Length := length//头标记中添加内容长度
Remove "chunked" from Transfer-Encoding//头标记中移除Transfer-Encoding
伪码的逻辑有点混乱,研究了下,自己写了C语言的解码代码:
//////////////////////////////////////
char * unchunk (char *filename)
{
char cmdbuf[1024];
/*if (strstr (filename, ".trunk") == 0)
{
strcat (filename, ".trunk");
memset (cmdbuf, 0x0, sizeof (tmpfile));
&n
{
char cmdbuf[1024];
/*if (strstr (filename, ".trunk") == 0)
{
strcat (filename, ".trunk");
memset (cmdbuf, 0x0, sizeof (tmpfile));
&n