http请求是典型的请求-响应类型的的网络协议,而http是文件协议,所以我们在分析请求行与请求头,以及输出响应行与响应头,往往是一行一行的进行处理。如果我们自己来写一个http服务器,通常在一个连接建立好后,客户端会发送请求过来。然后我们读取一行数据,分析出请求行中包含的method、uri、http_version信息。然后再一行一行处理请求头,并根据请求method与请求头的信息来决定是否有请求体以及请求体的长度,然后再去读取请求体。得到请求后,我们处理请求产生需要输出的数据,然后再生成响应行,响应头以及响应体。在将响应发送给客户端之后,一个完整的请求就处理完了。当然这是最简单的webserver的处理方式,其实nginx也是这样做的,只是有一些小小的区别,比如,当请求头读取完成后,就开始进行请求的处理了。nginx通过ngx_http_request_t来保存解析请求与输出响应相关的数据。
struct ngx_http_request_s {
uint32_t signature ; /* "HTTP" */
/*
与连接有关的内容
*/
ngx_connection_t * connection ;
/*
以下四个保存的是模块所对应的上下文结构体的指针。
其中ctx对应于自定义的上下文结构体指针
main_conf对应于main的上下文结构体指针
loc_conf对应于loc的上下文结构体指针
src_conf对应于srv的上下文结构体指针
*/
void ** ctx ;
void ** main_conf ;
void ** srv_conf ;
void ** loc_conf ;
/*读写事件的函数指针*/
ngx_http_event_handler_pt read_event_handler ;
ngx_http_event_handler_pt write_event_handler ;
#if (NGX_HTTP_CACHE)
ngx_http_cache_t * cache ;
#endif
/*
与upstream模块相关的结构体
*/
ngx_http_upstream_t * upstream ;/*用于upstream模块*/
ngx_array_t * upstream_states ;/*与upstream模块相关*/
/* of ngx_http_upstream_state_t */
ngx_pool_t * pool ;/*内存池*/
ngx_buf_t * header_in ; // 会保存一些消息体的内容
ngx_http_headers_in_t headers_in ;//代表请求头部 // 请求的header结构体
ngx_http_headers_out_t headers_out ;//代表响应头部
ngx_http_request_body_t * request_body;//代表请求头部 .r-> request_body-> bufs中存放的请求体中的数据
time_t lingering_time ; /*unkown*/
time_t start_sec ;/*unkown*/
ngx_msec_t start_msec ; /*unkown*/
/*
从method到http_protocol都是请求行中信息
*/
ngx_uint_t method ;
ngx_uint_t http_version ;//http版本
ngx_str_t request_line ;//请求行
ngx_str_t uri ;
ngx_str_t args ;
ngx_str_t exten ;
ngx_str_t unparsed_uri ;
ngx_str_t method_name ;
ngx_str_t http_protocol ;
ngx_chain_t * out ; /*unkown*//*这里要注意ngx_http_request_t中有一个out的chain,这个chain保存的是上一次还没有被发完的buf,这样每次我们接收到新的chain的话,就需要将新的chain连接到老的out chain上,然后再发出去*/
/*接下来从main到posted_requests都是与主请求和子请求有关的内容/
ngx_http_request_t * main ; //这个表示主的request,也就是当前的request链中最上面的那个request,通过这个域我们就能判断当前的request是不是subrequest。
ngx_http_request_t * parent ; //这个表示当前的request的父request。
//subrequest就是子请求,也就是在当前的一个请求中nginx再生成一个请求。
ngx_http_postponed_request_t * postponed ;// 先来看postponed,这个域用来缓存父request的数据(也就是将要发送数据的request)
ngx_http_post_subrequest_t * post_subrequest ;// 这个域保存了子请求的post request,它也就是保存了需要被发送的request.
ngx_http_posted_request_t * posted_requests ;// 这个保存了所有的需要处理的request链表,也就是说它即包含子请求也包含父请求
/* virtual hosts based on the address:port
r->virtual_names = addr_conf->virtual_names
*/
ngx_http_virtual_names_t * virtual_names ;
ngx_int_t phase_handler ; /*应该是在请求处理的多个阶段中,利用phase_handler依次执行多个阶段*/
ngx_http_handler_pt content_handler ; /*生成内容的处理函数 比如ngx_http_proxy_handler等*/
ngx_uint_t access_code ;/*unkown*/
ngx_http_variable_value_t * variables ;//variables 包含了所有的变量
#if (NGX_PCRE)
ngx_uint_t ncaptures ;
int * captures ;
u_char * captures_data ;
#endif
size_t limit_rate ;/*unkown*/
/*
r->limit_rate,这个表示当前的request的发送限制速率,这个也是在nginx.conf中配置的,而一般就是通过这个值来设置c->write->delayed的。也就是说如果发送速率大于这个limit了的话,就设置delayed,然后这边的request就会延迟发送
*/
/* used to learn the Apache compatible response length without a header */
size_t header_size ;/*unkown*/
off_t request_length ;/*unkown*/
ngx_uint_t err_status ;/*unkown*/
ngx_http_connection_t * http_connection ;/*unkown*/
ngx_http_log_handler_pt log_handler ; /*unkown*/
ngx_http_cleanup_t * cleanup ;
unsigned subrequests :8;
unsigned count :8;
unsigned blocked :8;
unsigned aio :1;
unsigned http_state :4;
/* URI with "/." and on Win32 with "//" */
unsigned complex_uri :1;
/* URI with "%" */
unsigned quoted_uri :1;
/* URI with "+" */
unsigned plus_in_uri :1;
/* URI with " " */
unsigned space_in_uri :1;
unsigned invalid_header :1; // 一个标示位,标示header是否有效,不正常的结束视为无效
unsigned add_uri_to_alias :1;
unsigned valid_location :1;
unsigned valid_unparsed_uri :1;
unsigned uri_changed :1;
unsigned uri_changes :4;
/ *
下面这两个参数就会设定为每个body都存放到临时文件里,并且这个临时文件在请求结束后不会被删除:
r->request_body_in_persistent_file = 1; r->request_body_in_file_only = 1; */
unsigned request_body_in_single_buf :1;
unsigned request_body_in_file_only :1;
unsigned request_body_in_persistent_file :1;
unsigned request_body_in_clean_file :1;
unsigned request_body_file_group_access :1;
unsigned request_body_file_log_level :3;
unsigned subrequest_in_memory :1;
unsigned waited :1;
#if (NGX_HTTP_CACHE)
unsigned cached :1;
#endif
#if (NGX_HTTP_GZIP)
unsigned gzip_tested :1;
unsigned gzip_ok :1;
unsigned gzip_vary :1;
#endif
unsigned proxy :1;
unsigned bypass_cache :1;
unsigned no_cache :1;
/*
* instead of using the request context data in
* ngx_http_limit_conn_module and ngx_http_limit_req_module
* we use the single bits in the request structure
*/
unsigned limit_conn_set :1;
unsigned limit_req_set :1;
#if 0
unsigned cacheable:1;
#endif
unsigned pipeline :1;
unsigned plain_http :1;
unsigned chunked :1;
unsigned header_only :1; /*当请求方法为HEAD时,r->header_only=1 ,在ngx_http_header_filter函数中*/
unsigned keepalive :1;
unsigned lingering_close :1;
unsigned discard_body :1;
unsigned internal :1;
unsigned error_page :1;
unsigned ignore_content_encoding :1;
unsigned filter_finalize :1;
unsigned post_action :1;
unsigned request_complete :1;
unsigned request_output :1;
unsigned header_sent :1;
unsigned expect_tested :1;
unsigned root_tested :1;
unsigned done :1;
unsigned logged :1;
unsigned buffered :4;
unsigned main_filter_need_in_memory :1;
unsigned filter_need_in_memory :1;
unsigned filter_need_temporary :1;
unsigned allow_ranges :1;
#if (NGX_STAT_STUB)
unsigned stat_reading :1;
unsigned stat_writing :1;
#endif
/* used to parse HTTP headers */
/*
通过打印,不能获得header_name_start内容
通过打印,可以获得header_start内容:为cookie内容+空行,也就是header_start内容包含cookie,但不仅仅包含cookie。
*/
ngx_uint_t state ;
ngx_uint_t header_hash ;
ngx_uint_t lowcase_index ;
u_char lowcase_header [NGX_HTTP_LC_HEADER_LEN];
u_char * header_name_start ;
u_char * header_name_end ;
u_char * header_start ;
u_char * header_end ;
/*
* a memory that can be reused after parsing a request line
* via ngx_http_ephemeral_t
*/
/* used to parse HTTP 请求行的消息
** 通过打印,可以知道接下来这部分内容都是关于HTTP请求行的,通过这些指针可以方便找到所需的请求行中的内容,比如 r-> method_end+1,r-> http_protocol .data-1 之间就是URI。
*/
u_char * uri_start ;
u_char * uri_end ;
u_char * uri_ext ;
u_char * args_start ;
u_char * request_start ;
u_char * request_end ;
u_char * method_end ;
u_char * schema_start ;
u_char * schema_end ;
u_char * host_start ;
u_char * host_end ;
u_char * port_start ;
u_char * port_end ;
unsigned http_minor :16;
unsigned http_major :16;
};
|
测试中所添加函数内容:
#if 1
printf ( "***ngx_http_upload_handler server :%s\t length is %d\n" ,out_headers_in. server . data ,out_headers_in. server . len );
yk_print_ngx_str_t ( "server is " ,r-> headers_in . server . data ,r-> headers_in . server . len );
yk_print_ngx_str_t ( "request_line is " ,r-> request_line . data ,r-> request_line . len );
yk_print_ngx_str_t ( " uri is " ,r-> uri . data ,r-> uri . len );
yk_print_ngx_str_t ( " args is " ,r-> args . data ,r-> args . len );
yk_print_ngx_str_t ( "method_name is " ,r-> method_name . data ,r-> method_name . len );
yk_print_ngx_str_t ( "unparsed_uri is " ,r-> unparsed_uri . data ,r-> unparsed_uri . len );
yk_print_start2end( "r->uri_start" ,r-> uri_start ,r-> uri_end );
yk_print_start2end( "r->request_start" ,r-> request_start ,r-> request_end );
yk_print_start2end( "r->schema_start" ,r-> schema_start ,r-> schema_start );
yk_print_start2end( "r->host_start" ,r-> host_start ,r-> host_start );
// printf("uri_ext is %s \t method_end is %s \t ",r->uri_ext,r->method_end);
yk_print_start2end( "uri is" ,r-> method_end +1,r-> http_protocol . data -1); /*这句话可以将 uri完整无错的打印出来*/
yk_print_start2end( "method_name start-end is" ,r-> method_name . data ,r-> method_end +1); /*这句话可以将method完整无错的打印出来*/
//yk_print_start2end("header_name_start is",r->header_name_start,r->header_name_end);
yk_print_start2end( "header_start is" ,r-> header_start ,r-> header_end );
#endif
|
ngx_http_request_t 中header_in作用:
会保存一些消息体的内容,在用户名密码登陆的时候
|
typedef struct {
ngx_temp_file_t * temp_file ;
ngx_chain_t * bufs ;/*消息体都保存在这个chain里面*/
ngx_buf_t * buf ; /*用作临时存储的buf,在ngx_http_read_client_request_body和ngx_http_do_read_client_request_body中用得到 */
off_t rest ;
ngx_chain_t * to_write ;
ngx_http_client_body_handler_pt post_handler ;
} ngx_http_request_body_t ;
|
通过下面的语句可以打印bufs中内容。
/*below is edited by yankai*/
yankai_cl = r->request_body->bufs;
yankai_sum_rb_bufs = 0;
for (; yankai_cl; yankai_cl = yankai_cl->next){
yankai_sum_rb_bufs += (size_t)ngx_buf_size(yankai_cl->buf);
}
printf( "###yankai_sum_rb_bufs in ngx_http_upload_body_handler mm is %d\n" ,yankai_sum_rb_bufs);
|
下面这段话来自于http://tengine.taobao.org/book/chapter_12.html
ngx_http_headers_in_t结构的headers字段为一个链表结构,它被用来保存所有请求头,初始为它分配了20个节点,每个节点的类型为ngx_table_elt_t,保存请求头的name/value值对,还可以看到ngx_http_headers_in_t结构有很多类型为ngx_table_elt_t*的指针成员,而且从它们的命名可以看出是一些常见的请求头名字,nginx对这些常用的请求头在ngx_http_headers_in_t结构里面保存了一份引用,后续需要使用的话,可以直接通过这些成员得到,另外也事先为cookie头分配了2个元素的数组空间,做完这些内存准备工作之后,该请求对应的读事件结构的处理函数被设置为ngx_http_process_request_headers,并随后马上调用了该函数。
typedef struct {
ngx_list_t headers ;
/*从host到keep_alive 均为常见的http头部字段*/
ngx_table_elt_t * host ;
ngx_table_elt_t * connection ;
ngx_table_elt_t * if_modified_since ;
ngx_table_elt_t * if_unmodified_since ;
ngx_table_elt_t * user_agent ;
ngx_table_elt_t * referer ;
ngx_table_elt_t * content_length ;
ngx_table_elt_t * content_type ;
ngx_table_elt_t * range ;
ngx_table_elt_t * if_range ;
ngx_table_elt_t * transfer_encoding ;
ngx_table_elt_t * expect ;
#if (NGX_HTTP_GZIP)
ngx_table_elt_t * accept_encoding ;
ngx_table_elt_t * via ;
#endif
ngx_table_elt_t * authorization ;
ngx_table_elt_t * keep_alive ;
#if (NGX_HTTP_X_FORWARDED_FOR)
ngx_table_elt_t * x_forwarded_for ;
#endif
#if (NGX_HTTP_REALIP)
ngx_table_elt_t *x_real_ip;
#endif
#if (NGX_HTTP_HEADERS)
ngx_table_elt_t *accept;
ngx_table_elt_t *accept_language;
#endif
#if (NGX_HTTP_DAV)
ngx_table_elt_t *depth;
ngx_table_elt_t *destination;
ngx_table_elt_t *overwrite;
ngx_table_elt_t *date;
#endif
ngx_str_t user ;/*unkown*/
ngx_str_t passwd ;/*unkown*/
ngx_array_t cookies ;
ngx_str_t server ;
off_t content_length_n ;/*unkown*/
time_t keep_alive_n ;/*unkown*/
unsigned connection_type :2;
unsigned msie :1;
unsigned msie6 :1;
unsigned opera :1;
unsigned gecko :1;
unsigned chrome :1;
unsigned safari :1;
unsigned konqueror :1;
} ngx_http_headers_in_t ;
|
|
说明:ngx_http_headers_in_t是包含请求头中所有内容, 1)ngx_table_elt_t 都是RFC2616中提到的请求头域的内容 2)user、passwd未知 3)cookie里面保存的是cookie的内容,可以通过下面的代码打印出来
|
/*
*函数功能:知道字符串的其实地址和中止地址,输出该字符串
*/
void yk_print_start2end( char * description, u_char * start, u_char *end)
{
printf ( "%s\t" ,description);
u_char * ptemp;
for (ptemp = start; ptemp != end; ptemp++)
printf ( "%c" ,*ptemp);
printf ( "\n" );
}
/*
*函数功能:知道字符串的其实地址和中止地址,输出该字符串
*/
void yk_print_ngx_str_t( char * description, u_char * data, int len)
{
printf ( "%s\t" ,description);
u_char * ptemp;
for (ptemp = data; ptemp != (data + len); ptemp++)
printf ( "%c" ,*ptemp);
printf ( "\n" );
}
打印cookie内容
#if 0
/*six line code source :http://lijinxing17.blog.163.com/blog/static/34977708201062710583500/*/
ngx_table_elt_t ** cookies = NULL;
ngx_uint_t i;
printf( "Cookie count: %d\n" , r->headers_in.cookies.nelts);
cookies = r->headers_in.cookies.elts;
for ( i = 0 ; i < r->headers_in.cookies.nelts; i++) {
printf( "Cookie line %d: %s\n" , i, cookies[i]->value.data);
}
#endif
|
ngx_http_headers_in_t结构体中user passwd headers ngx_connection_t *connection ngx_http_connection_t *http_connection |