应用层协议实现系列——HTTP服务器之http协议解析
Posted 心砚thu
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了应用层协议实现系列——HTTP服务器之http协议解析相关的知识，希望对你有一定的参考价值。
上一篇文章《仿nginx Http服务器的设计与实现（一）——多进程和多路IO的实现》中实现了一个仿照nginx的支持高并发的服务器，但只是实现了端口监听和数据接收，并没有实现对http协议的解析，下面就对如何解析http协议进行说明。
我们可以通过浏览器访问之前所搭建的http服务器，可以看到终端输出如下：
GET / HTTP/1.1
Host: 127.0.0.1:8080
Connection: keep-alive
Cache-Control: max-age=0
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.131 Safari/537.36
Accept-Encoding: gzip,deflate,sdch
Accept-Language: zh-CN,zh;q=0.8参考一些网上的资料可以知道，http协议主要有三部分组成，即请求行、若干请求字段、请求体。请求行主要包括所使用的http方法，访问的路径以及http的版本。请求字段主要包括若干个详细说明本次http请求的字段，每个字段由字段名+冒号+空格+字段值组成。请求体主要包括发送到客户端的数据。其中请求行和请求字段之间是连续的，而请求字段与请求体之间会有两个空白行（\\r\\n）分隔。
在明确了这些内容之后，我们就可以开始对接收到的http请求进行解析了。本文将使用两个类，CHttpRequest和CHttpResponse来实现这一功能。下面首先修改上一篇文章中的
handleRequest方法：
//处理http请求
bool handleRequest(int connFd)
if (connFd<=0) return false;
//读取缓存
char buff[4096];
//读取http header
int len = (int)recv(connFd, buff, sizeof(buff), 0);
if (len<=0)
return false;
buff[len] = '\\0';
std::cout<<buff<<std::endl;
CHttpRequest *httpRequest = new CHttpRequest();
httpRequest->handleRequest(buff);
CHttpResponse *httpResponse = new CHttpResponse(httpRequest);
bool result = httpResponse->response(connFd);
//返回是否需要中断连接
std::string transformConnection(httpRequest->connection);
std::transform(transformConnection.begin(), transformConnection.end(), transformConnection.begin(), ::tolower);
return transformConnection == "Keep-Alive" && result;
该代码中采用了一个长度为4096的缓冲区接收http头，接收完成之后，调用CHttpRequest进行解析。下面来看看CHttpRequest的代码：
#include "CHttpRequest.h"
#include "define.h"
using namespace std;
CHttpRequest::CHttpRequest()
connection = "Close";
modifiedTime = "";
fileStart = 0;
fileEnd = 0;
fieldMap[TS_HTTP_HEADER_CONNECTION] = &CHttpRequest::handleConnection;
fieldMap[TS_HTTP_HEADER_AUTHORIZATION] = &CHttpRequest::handleAuthorization;
fieldMap[TS_HTTP_HEADER_RANGE] = &CHttpRequest::handleRange;
fieldMap[TS_HTTP_HEADER_IF_MOD_SINCE] = &CHttpRequest::handleIfModSince;
void CHttpRequest::handleRequest(char *header)
stringstream stream;
stream<<header;
int count = 0;
while (1)
if (stream.eof())
break;
char line[1024];
stream.getline(line, sizeof(line));
if (strcmp(line, "")==0)
continue;
stringstream lineStream;
lineStream<<line;
//first line
if (count == 0)
lineStream>>method;
lineStream>>path;
lineStream>>version;
else
string fieldName;
lineStream>>fieldName;
//remove \\r
line[strlen(line)-1] = '\\0';
void(CHttpRequest::*func)(char*) = fieldMap[fieldName];
if (func!=NULL)
(this->*func)(line+fieldName.length()+1);
count++;
void CHttpRequest::handleConnection(char *field)
if (ENABLE_KEEP_ALIVE)
connection = string(field);
void CHttpRequest::handleAuthorization(char *field)
char authName[10], authInfo[256];
sscanf(field, "%s %s", authName, authInfo);
authorize = string(authInfo);
void CHttpRequest::handleRange(char *field)
if (strstr(field, "bytes=")==field)
char *start = strtok(field+strlen("bytes="), "-");
fileStart = start==NULL?0:atol(start);
char *end = strtok(NULL, "-");
fileEnd = end==NULL?0:atol(end);
void CHttpRequest::handleIfModSince(char *field)
modifiedTime = string(field);
为了保证http解析的效率，本文采用了与nginx中类似的做法，将字段名与解析函数放到了map中（nginx中使用的是hash表，在这里简化为map）。在解析完成之后，调用CHttpResponse构造响应。CHttpResponse代码如下：
#include "CHttpResponse.h"
#include "CHttpRequest.h"
#include <sys/socket.h>
#include "define.h"
#include <string.h>
#define HTTP_RESPONSE_404 "<html><head><title>404 Not Found</title></head><body><h1>Not Found</h1><p>The requested URL was not found on this server.</p></body></html>"
std::string getStringFromTime(time_t time)
char timeBuff[64];
struct tm tm = *gmtime(&time);
strftime(timeBuff, sizeof timeBuff, "%a, %d %b %Y %H:%M:%S %Z", &tm);
return std::string(timeBuff);
CHttpResponse::CHttpResponse(CHttpRequest *request)
m_request = request;
if (m_request->method.compare(TS_HTTP_METHOD_GET_S)==0 || m_request->method.compare(TS_HTTP_METHOD_HEAD_S)==0)
std::string path = ROOT_PATH;
if (m_request->path.compare("/")==0)
path += ROOT_HTML;
else
path += m_request->path;
m_statusCode = 0;
//if file exist
if (isFileExist(path.c_str()))
//if receive modified time
if (!m_request->modifiedTime.empty())
time_t time = fileModifiedTime(path.c_str());
if (getStringFromTime(time) == m_request->modifiedTime)
m_statusCode = TS_HTTP_STATUS_NOT_MODIFIED;
m_statusMsg = TS_HTTP_STATUS_NOT_MODIFIED_S;
//if file modified
if (m_statusCode == 0)
if (m_request->fileStart || m_request->fileEnd)
long long fileSize = getFileSize(path.c_str());
//if request range satisfied
if (m_request->fileStart<fileSize && m_request->fileEnd<fileSize)
m_statusCode = TS_HTTP_STATUS_PARTIAL_CONTENT;
m_statusMsg = TS_HTTP_STATUS_PARTIAL_CONTENT_S;
m_sendFilePath = path;
else
m_statusCode = TS_HTTP_STATUS_REQUEST_RANGE_NOT_SATISFIABLE;
m_statusMsg = TS_HTTP_STATUS_REQUEST_RANGE_NOT_SATISFIABLE_S;
else
m_statusCode = TS_HTTP_STATUS_OK;
m_statusMsg = TS_HTTP_STATUS_OK_S;
m_sendFilePath = path;
else
m_statusCode = TS_HTTP_STATUS_NOT_FOUND;
m_statusMsg = TS_HTTP_STATUS_NOT_FOUND_S;
m_sendStr = HTTP_RESPONSE_404;
bool CHttpResponse::response(int connFd)
bool result = true;
std::stringstream responseStream;
responseStream<<m_request->version<<" "<<m_statusMsg<<"\\r\\n";
//time
responseStream<<"Date: "<<getStringFromTime(time(0))<<"\\r\\n";
//server name
responseStream<<"Server: "<<SERVER_NAME<<"\\r\\n";
//keep alive
responseStream<<"Connection: "<<m_request->connection<<"\\r\\n";
//content length
long long contentLength = 0;
//if file exist
if (!m_sendFilePath.empty())
//if define file end
if (m_request->fileEnd)
contentLength = m_request->fileEnd - m_request->fileStart + 1;
//if define file start
else if (m_request->fileStart)
contentLength = getFileSize(m_sendFilePath.c_str()) - m_request->fileStart + 1;
//if undefine start or end
else
contentLength = getFileSize(m_sendFilePath.c_str());
else if (!m_sendStr.empty())
contentLength = m_sendStr.length();
if (contentLength)
responseStream<<"Content-Length: "<<contentLength<<"\\r\\n";
//last modified
if (!m_sendFilePath.empty())
responseStream<<"Last-Modified: "<<getStringFromTime(fileModifiedTime(m_sendFilePath.c_str()))<<"\\r\\n";
responseStream<<"Accept-Ranges: "<<"bytes"<<"\\r\\n";
//content type
if (!m_sendFilePath.empty())
char path[256];
strcpy(path, m_sendFilePath.c_str());
char *ext = strtok(path, ".");
char *lastExt = ext;
while (ext!=NULL)
ext = strtok(NULL, ".");
if (ext) lastExt = ext;
for (int i=0; i<38; i++)
if (strcmp(mmt[i].ext, lastExt)==0)
responseStream<<"Content-Type: "<<mmt[i].type<<"\\r\\n";
break;
//other
switch (m_statusCode)
case TS_HTTP_STATUS_UNAUTHORIZED:
responseStream<<"WWW-Authenticate: Basic realm=\\"zhaoxy.com\\"\\r\\n";
break;
case TS_HTTP_STATUS_FOUND:
responseStream<<"Location: /index.html\\r\\n";
break;
case TS_HTTP_STATUS_PARTIAL_CONTENT:
responseStream<<"Content-Range: "<<"bytes "<<m_request->fileStart<<"-"<<(m_request->fileEnd==0?contentLength:m_request->fileEnd)<<"/"<<getFileSize(m_sendFilePath.c_str())<<"\\r\\n";
break;
default:
break;
//seperator
responseStream<<"\\r\\n";
//send response header
std::string responseStr = responseStream.str();
std::cout<<responseStr<<std::endl;
send(connFd, responseStr.c_str(), responseStr.length(), 0);
//content
//if not head method
if (m_request->method.compare(TS_HTTP_METHOD_HEAD_S)!=0)
if (!m_sendFilePath.empty())
std::ifstream file(m_sendFilePath);
file.seekg(m_request->fileStart, std::ifstream::beg);
while(file.tellg() != -1)
char *p = new char[1024];
bzero(p, 1024);
file.read(p, 1024);
int n = (int)send(connFd, p, 1024, 0);
if (n < 0)
std::cout<<"ERROR writing to socket"<<std::endl;
result = false;
break;
delete p;
file.close();
else
send(connFd, m_sendStr.c_str(), m_sendStr.length(), 0);
return result;
该代码支持断点续传、last modified和authorization字段。具体的逻辑不作详细说明，有疑问的可以留言。
该Http服务器的代码已经上传到GitHub上，大家可以直接下载。
以上是关于应用层协议实现系列——HTTP服务器之http协议解析的主要内容，如果未能解决你的问题，请参考以下文章