自己动手写http服务器——处理http连接（二）

关于http报文格式请看这篇文章

//http_conn.h
#ifndef HTTPCONNECTION_H
#define HTTPCONNECTION_H

#include <unistd.h>
#include <signal.h>
#include <sys/types.h>
#include <sys/epoll.h>
#include <fcntl.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <assert.h>
#include <sys/stat.h>
#include <string.h>
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <stdarg.h>
#include <errno.h>
#include "locker.h"

class http_conn
{
public:
    static const int FILENAME_LEN = 200;        

    static const int READ_BUFFER_SIZE = 2048;

    static const int WRITE_BUFFER_SIZE = 1024;

    enum METHOD { GET = 0, POST, HEAD, PUT, DELETE, TRACE, OPTIONS, CONNECT, PATCH }; //http请求的格式，只支持get

    enum CHECK_STATE { CHECK_STATE_REQUESTLINE = 0, CHECK_STATE_HEADER, CHECK_STATE_CONTENT };//主状态机的状态，检查请求行，检查请求头部，检查内容实体

    enum HTTP_CODE { NO_REQUEST, GET_REQUEST, BAD_REQUEST, NO_RESOURCE, FORBIDDEN_REQUEST, FILE_REQUEST, INTERNAL_ERROR, CLOSED_CONNECTION }; //http响应报文的状态码

    enum LINE_STATUS { LINE_OK = 0, LINE_BAD, LINE_OPEN };  //请求行的状态

public:
    http_conn(){}
    ~http_conn(){}

public:
    void init( int sockfd, const sockaddr_in& addr );
    void close_conn( bool real_close = true );
    void process();
    bool read();
    bool write();

private:
    void init();
    HTTP_CODE process_read();
    bool process_write( HTTP_CODE ret );

    HTTP_CODE parse_request_line( char* text );
    HTTP_CODE parse_headers( char* text );
    HTTP_CODE parse_content( char* text );
    HTTP_CODE do_request();
    char* get_line() { return m_read_buf + m_start_line; }
    LINE_STATUS parse_line();

    void unmap();
    bool add_response( const char* format, ... ); //添加响应
    bool add_content( const char* content ); //添加响应内容
    bool add_status_line( int status, const char* title ); //添加响应状态行
    bool add_headers( int content_length );    //添加http响应报文的头部字段
    bool add_content_length( int content_length ); //添加内容实体的长度
    bool add_linger();//添加响应报文的Connection字段，指定是否保持连接
    bool add_blank_line(); //添加\r\n

public:
    static int m_epollfd;         //epoll文件句柄
    static int m_user_count;

private:
    int m_sockfd;       //当前连接的client sockdfd
    sockaddr_in m_address;

    char m_read_buf[ READ_BUFFER_SIZE ]; //读缓冲区
    int m_read_idx;  //标示读缓冲区已经读入的客户数据的最后一个字节的下一个位置
    int m_checked_idx; //当前正在分析的字符在读缓冲区的位置
    int m_start_line;//当前正在解析的行的起始位置
    char m_write_buf[ WRITE_BUFFER_SIZE ];
    int m_write_idx; //写缓冲区中待发送的字节数。

    CHECK_STATE m_check_state; //主状态机的状态
    METHOD m_method;

    char m_real_file[ FILENAME_LEN ];//客户请求文件的完整路径。
    char* m_url;
    char* m_version; //http版本信息，我们只支持1.1
    char* m_host;
    int m_content_length;//http请求的消息体的长度
    bool m_linger; //http请求是否要保持链接

    char* m_file_address; //客户请求的目标文件被映射到内存中位置
    struct stat m_file_stat; //目标文件的状态
    struct iovec m_iv[2];
    int m_iv_count;
};

#endif

//http_conn.cpp
#include "http_conn.h"
//http响应报文的状态，以及原因短语
const char* ok_200_title = "OK";
const char* error_400_title = "Bad Request";
const char* error_400_form = "Your request has bad syntax or is inherently impossible to satisfy.\n";
const char* error_403_title = "Forbidden";
const char* error_403_form = "You do not have permission to get file from this server.\n";
const char* error_404_title = "Not Found";
const char* error_404_form = "The requested file was not found on this server.\n";
const char* error_500_title = "Internal Error";
const char* error_500_form = "There was an unusual problem serving the requested file.\n";
const char* doc_root = "/var/www/html";
//将文件IO操作设置为非阻塞
int setnonblocking( int fd )
{
   int old_option = fcntl( fd, F_GETFL );
   int new_option = old_option | O_NONBLOCK;
   fcntl( fd, F_SETFL, new_option );
   return old_option;
}

//向epoll中加入要监听的文件描述符
void addfd( int epollfd, int fd, bool one_shot )
{
    epoll_event event;
    event.data.fd = fd;
    event.events = EPOLLIN | EPOLLET | EPOLLRDHUP;
    if( one_shot )
    {
        event.events |= EPOLLONESHOT;
    }
    epoll_ctl( epollfd, EPOLL_CTL_ADD, fd, &event );
    setnonblocking( fd );
}

//在epoll删除文件描述符
void removefd( int epollfd, int fd )
{
    epoll_ctl( epollfd, EPOLL_CTL_DEL, fd, 0 );
    close( fd );
}

//修该文件描述符的监听事件
void modfd( int epollfd, int fd, int ev )
{
    epoll_event event;
    event.data.fd = fd;
    event.events = ev | EPOLLET | EPOLLONESHOT | EPOLLRDHUP;
    epoll_ctl( epollfd, EPOLL_CTL_MOD, fd, &event );
}

int http_conn::m_user_count = 0;
int http_conn::m_epollfd = -1;

void http_conn::close_conn( bool real_close )
{
    if( real_close && ( m_sockfd != -1 ) )
    {
        //modfd( m_epollfd, m_sockfd, EPOLLIN );
        removefd( m_epollfd, m_sockfd );
        m_sockfd = -1;
        m_user_count--;
    }
}

void http_conn::init( int sockfd, const sockaddr_in& addr )
{
    m_sockfd = sockfd;
    m_address = addr;
    int error = 0;
    socklen_t len = sizeof( error );
    getsockopt( m_sockfd, SOL_SOCKET, SO_ERROR, &error, &len );
    int reuse = 1;
    setsockopt( m_sockfd, SOL_SOCKET, SO_REUSEADDR, &reuse, sizeof( reuse ) );
    addfd( m_epollfd, sockfd, true );
    m_user_count++;

    init();
}

void http_conn::init()
{
    m_check_state = CHECK_STATE_REQUESTLINE;
    m_linger = false;

    m_method = GET;
    m_url = 0;
    m_version = 0;
    m_content_length = 0;
    m_host = 0;
    m_start_line = 0;
    m_checked_idx = 0;
    m_read_idx = 0;
    m_write_idx = 0;
    memset( m_read_buf, '\0', READ_BUFFER_SIZE );
    memset( m_write_buf, '\0', WRITE_BUFFER_SIZE );
    memset( m_real_file, '\0', FILENAME_LEN );
}
//截取http请求行
http_conn::LINE_STATUS http_conn::parse_line()
{
    char temp;
    for ( ; m_checked_idx < m_read_idx; ++m_checked_idx )
    {
        temp = m_read_buf[ m_checked_idx ];
        if ( temp == '\r' )
        {
            if ( ( m_checked_idx + 1 ) == m_read_idx )
            {
                return LINE_OPEN;
            }
            else if ( m_read_buf[ m_checked_idx + 1 ] == '\n' )
            {
                m_read_buf[ m_checked_idx++ ] = '\0';
                m_read_buf[ m_checked_idx++ ] = '\0';
                return LINE_OK;
            }

            return LINE_BAD;
        }
        else if( temp == '\n' )
        {
            if( ( m_checked_idx > 1 ) && ( m_read_buf[ m_checked_idx - 1 ] == '\r' ) )
            {
                m_read_buf[ m_checked_idx-1 ] = '\0';
                m_read_buf[ m_checked_idx++ ] = '\0';
                return LINE_OK;
            }
            return LINE_BAD;
        }
    }

    return LINE_OPEN;
}
//将请求报文读到读缓冲区中
bool http_conn::read()
{
    if( m_read_idx >= READ_BUFFER_SIZE )
    {
        return false;
    }

    int bytes_read = 0;
    while( true )
    {
        bytes_read = recv( m_sockfd, m_read_buf + m_read_idx, READ_BUFFER_SIZE - m_read_idx, 0 );
        if ( bytes_read == -1 )
        {
            if( errno == EAGAIN || errno == EWOULDBLOCK )
            {
                break;
            }
            return false;
        }
        else if ( bytes_read == 0 )
        {
            return false;
        }

        m_read_idx += bytes_read;
    }
    return true;
}
//获取http请求行中的请求方式，URL，version
http_conn::HTTP_CODE http_conn::parse_request_line( char* text )
{
    m_url = strpbrk( text, " \t" );
    if ( ! m_url )
    {
        return BAD_REQUEST;
    }
    *m_url++ = '\0';

    char* method = text;
    if ( strcasecmp( method, "GET" ) == 0 )
    {
        m_method = GET;
    }
    else
    {
        return BAD_REQUEST;
    }

    m_url += strspn( m_url, " \t" );
    m_version = strpbrk( m_url, " \t" );
    if ( ! m_version )
    {
        return BAD_REQUEST;
    }
    *m_version++ = '\0';
    m_version += strspn( m_version, " \t" );
    if ( strcasecmp( m_version, "HTTP/1.1" ) != 0 )
    {
        return BAD_REQUEST;
    }

    if ( strncasecmp( m_url, "http://", 7 ) == 0 )
    {
        m_url += 7;
        m_url = strchr( m_url, '/' );
    }

    if ( ! m_url || m_url[ 0 ] != '/' )
    {
        return BAD_REQUEST;
    }

    m_check_state = CHECK_STATE_HEADER;
    return NO_REQUEST;
}
//分析请求报文的首部字段
http_conn::HTTP_CODE http_conn::parse_headers( char* text )
{
    if( text[ 0 ] == '\0' )
    {
        if ( m_method == HEAD )
        {
            return GET_REQUEST;
        }

        if ( m_content_length != 0 )
        {
            m_check_state = CHECK_STATE_CONTENT;
            return NO_REQUEST;
        }

        return GET_REQUEST;
    }
    else if ( strncasecmp( text, "Connection:", 11 ) == 0 )
    {
        text += 11;
        text += strspn( text, " \t" );
        if ( strcasecmp( text, "keep-alive" ) == 0 )
        {
            m_linger = true;
        }
    }
    else if ( strncasecmp( text, "Content-Length:", 15 ) == 0 )
    {
        text += 15;
        text += strspn( text, " \t" );
        m_content_length = atol( text );
    }
    else if ( strncasecmp( text, "Host:", 5 ) == 0 )
    {
        text += 5;
        text += strspn( text, " \t" );
        m_host = text;
    }
    else
    {
        printf( "oop! unknow header %s\n", text );
    }

    return NO_REQUEST;

}
//分析请求保卫的内容实体
http_conn::HTTP_CODE http_conn::parse_content( char* text )
{
    if ( m_read_idx >= ( m_content_length + m_checked_idx ) )
    {
        text[ m_content_length ] = '\0';
        return GET_REQUEST;
    }

    return NO_REQUEST;
}

//处理读请求
http_conn::HTTP_CODE http_conn::process_read()
{
    LINE_STATUS line_status = LINE_OK;
    HTTP_CODE ret = NO_REQUEST;
    char* text = 0;

    while ( ( ( m_check_state == CHECK_STATE_CONTENT ) && ( line_status == LINE_OK  ) )
                || ( ( line_status = parse_line() ) == LINE_OK ) )
    {
        text = get_line();
        m_start_line = m_checked_idx;
        printf( "got 1 http line: %s\n", text );

        switch ( m_check_state )
        {
            case CHECK_STATE_REQUESTLINE:
            {
                ret = parse_request_line( text );
                if ( ret == BAD_REQUEST )
                {
                    return BAD_REQUEST;
                }
                break;
            }
            case CHECK_STATE_HEADER:
            {
                ret = parse_headers( text );
                if ( ret == BAD_REQUEST )
                {
                    return BAD_REQUEST;
                }
                else if ( ret == GET_REQUEST )
                {
                    return do_request();
                }
                break;
            }
            case CHECK_STATE_CONTENT:
            {
                ret = parse_content( text );
                if ( ret == GET_REQUEST )
                {
                    return do_request();
                }
                line_status = LINE_OPEN;
                break;
            }
            default:
            {
                return INTERNAL_ERROR;
            }
        }
    }

    return NO_REQUEST;
}

//对http请求发出响应
http_conn::HTTP_CODE http_conn::do_request()
{
    strcpy( m_real_file, doc_root );
    int len = strlen( doc_root );
    strncpy( m_real_file + len, m_url, FILENAME_LEN - len - 1 );
    if ( stat( m_real_file, &m_file_stat ) < 0 )
    {
        return NO_RESOURCE;
    }

    if ( ! ( m_file_stat.st_mode & S_IROTH ) )
    {
        return FORBIDDEN_REQUEST;
    }

    if ( S_ISDIR( m_file_stat.st_mode ) )
    {
        return BAD_REQUEST;
    }

    int fd = open( m_real_file, O_RDONLY );
    m_file_address = ( char* )mmap( 0, m_file_stat.st_size, PROT_READ, MAP_PRIVATE, fd, 0 );
    close( fd );
    return FILE_REQUEST;
}

//解除文件内存映射
void http_conn::unmap()
{
    if( m_file_address )
    {
        munmap( m_file_address, m_file_stat.st_size );
        m_file_address = 0;
    }
}
//发送数据
bool http_conn::write()
{
    int temp = 0;
    int bytes_have_send = 0;
    int bytes_to_send = m_write_idx;
    if ( bytes_to_send == 0 )
    {
        modfd( m_epollfd, m_sockfd, EPOLLIN );
        init();
        return true;
    }

    while( 1 )
    {
        temp = writev( m_sockfd, m_iv, m_iv_count );
        if ( temp <= -1 )
        {
            if( errno == EAGAIN )
            {
                modfd( m_epollfd, m_sockfd, EPOLLOUT );
                return true;
            }
            unmap();
            return false;
        }

        bytes_to_send -= temp;
        bytes_have_send += temp;
        if ( bytes_to_send <= bytes_have_send )
        {
            unmap();
            if( m_linger )
            {
                init();
                modfd( m_epollfd, m_sockfd, EPOLLIN );
                return true;
            }
            else
            {
                modfd( m_epollfd, m_sockfd, EPOLLIN );
                return false;
            }
        }
    }
}

bool http_conn::add_response( const char* format, ... )
{
    if( m_write_idx >= WRITE_BUFFER_SIZE )
    {
        return false;
    }
    va_list arg_list;
    va_start( arg_list, format );
    int len = vsnprintf( m_write_buf + m_write_idx, WRITE_BUFFER_SIZE - 1 - m_write_idx, format, arg_list );
    if( len >= ( WRITE_BUFFER_SIZE - 1 - m_write_idx ) )
    {
        return false;
    }
    m_write_idx += len;
    va_end( arg_list );
    return true;
}

bool http_conn::add_status_line( int status, const char* title )
{
    return add_response( "%s %d %s\r\n", "HTTP/1.1", status, title );
}

bool http_conn::add_headers( int content_len )
{
    add_content_length( content_len );
    add_linger();
    add_blank_line();
}

bool http_conn::add_content_length( int content_len )
{
    return add_response( "Content-Length: %d\r\n", content_len );
}

bool http_conn::add_linger()
{
    return add_response( "Connection: %s\r\n", ( m_linger == true ) ? "keep-alive" : "close" );
}

bool http_conn::add_blank_line()
{
    return add_response( "%s", "\r\n" );
}

bool http_conn::add_content( const char* content )
{
    return add_response( "%s", content );
}
//处理写请求
bool http_conn::process_write( HTTP_CODE ret )
{
    switch ( ret )
    {
        case INTERNAL_ERROR:
        {
            add_status_line( 500, error_500_title );
            add_headers( strlen( error_500_form ) );
            if ( ! add_content( error_500_form ) )
            {
                return false;
            }
            break;
        }
        case BAD_REQUEST:
        {
            add_status_line( 400, error_400_title );
            add_headers( strlen( error_400_form ) );
            if ( ! add_content( error_400_form ) )
            {
                return false;
            }
            break;
        }
        case NO_RESOURCE:
        {
            add_status_line( 404, error_404_title );
            add_headers( strlen( error_404_form ) );
            if ( ! add_content( error_404_form ) )
            {
                return false;
            }
            break;
        }
        case FORBIDDEN_REQUEST:
        {
            add_status_line( 403, error_403_title );
            add_headers( strlen( error_403_form ) );
            if ( ! add_content( error_403_form ) )
            {
                return false;
            }
            break;
        }
        case FILE_REQUEST:
        {
            add_status_line( 200, ok_200_title );
            if ( m_file_stat.st_size != 0 )
            {
                add_headers( m_file_stat.st_size );
                m_iv[ 0 ].iov_base = m_write_buf;
                m_iv[ 0 ].iov_len = m_write_idx;
                m_iv[ 1 ].iov_base = m_file_address;
                m_iv[ 1 ].iov_len = m_file_stat.st_size;
                m_iv_count = 2;
                return true;
            }
            else
            {
                const char* ok_string = "<html><body></body></html>";
                add_headers( strlen( ok_string ) );
                if ( ! add_content( ok_string ) )
                {
                    return false;
                }
            }
        }
        default:
        {
            return false;
        }
    }

    m_iv[ 0 ].iov_base = m_write_buf;
    m_iv[ 0 ].iov_len = m_write_idx;
    m_iv_count = 1;
    return true;
}
//处理http请求的线程调用的入口函数
void http_conn::process()
{
    HTTP_CODE read_ret = process_read();
    if ( read_ret == NO_REQUEST )
    {
        modfd( m_epollfd, m_sockfd, EPOLLIN );
        return;
    }

    bool write_ret = process_write( read_ret );
    if ( ! write_ret )
    {
        close_conn();
    }

    modfd( m_epollfd, m_sockfd, EPOLLOUT );
}