一般来说,对于一个请求,服务器都会对其进行解析,以确定请求的合法性以及行进的路径。于是本节将讲解如何获取请求的数据。(转载请指明出于breaksoftware的csdn博客)
我们使用《服务器架设笔记——编译Apache及其插件》一文中的方法创建一个Handler工程——get_request。该工程中,我们可以操作的入口函数是
static int get_request_handler(request_rec *r)
{
r->content_type = "text/html";
通过该入口函数,我们可以直接得到的数据就是request_rec结构体对象指针r。通过查阅源码,我们得到其定义
/**
* @brief A structure that represents the current request
*/
struct request_rec {
/** The pool associated with the request */
apr_pool_t *pool;
/** The connection to the client */
conn_rec *connection;
/** The virtual host for this request */
server_rec *server;
/** Pointer to the redirected request if this is an external redirect */
request_rec *next;
/** Pointer to the previous request if this is an internal redirect */
request_rec *prev;
/** Pointer to the main request if this is a sub-request
* (see http_request.h) */
request_rec *main;
/* Info about the request itself... we begin with stuff that only
* protocol.c should ever touch...
*/
/** First line of request */
char *the_request;
/** HTTP/0.9, "simple" request (e.g. GET /foo\n w/no headers) */
int assbackwards;
/** A proxy request (calculated during post_read_request/translate_name)
* possible values PROXYREQ_NONE, PROXYREQ_PROXY, PROXYREQ_REVERSE,
* PROXYREQ_RESPONSE
*/
int proxyreq;
/** HEAD request, as opposed to GET */
int header_only;
/** Protocol version number of protocol; 1.1 = 1001 */
int proto_num;
/** Protocol string, as given to us, or HTTP/0.9 */
char *protocol;
/** Host, as set by full URI or Host: */
const char *hostname;
/** Time when the request started */
apr_time_t request_time;
/** Status line, if set by script */
const char *status_line;
/** Status line */
int status;
/* Request method, two ways; also, protocol, etc.. Outside of protocol.c,
* look, but don't touch.
*/
/** M_GET, M_POST, etc. */
int method_number;
/** Request method (eg. GET, HEAD, POST, etc.) */
const char *method;
/**
* 'allowed' is a bitvector of the allowed methods.
*
* A handler must ensure that the request method is one that
* it is capable of handling. Generally modules should DECLINE
* any request methods they do not handle. Prior to aborting the
* handler like this the handler should set r->allowed to the list
* of methods that it is willing to handle. This bitvector is used
* to construct the "Allow:" header required for OPTIONS requests,
* and HTTP_METHOD_NOT_ALLOWED and HTTP_NOT_IMPLEMENTED status codes.
*
* Since the default_handler deals with OPTIONS, all modules can
* usually decline to deal with OPTIONS. TRACE is always allowed,
* modules don't need to set it explicitly.
*
* Since the default_handler will always handle a GET, a
* module which does *not* implement GET should probably return
* HTTP_METHOD_NOT_ALLOWED. Unfortunately this means that a Script GET
* handler can't be installed by mod_actions.
*/
apr_int64_t allowed;
/** Array of extension methods */
apr_array_header_t *allowed_xmethods;
/** List of allowed methods */
ap_method_list_t *allowed_methods;
/** byte count in stream is for body */
apr_off_t sent_bodyct;
/** body byte count, for easy access */
apr_off_t bytes_sent;
/** Last modified time of the requested resource */
apr_time_t mtime;
/* HTTP/1.1 connection-level features */
/** The Range: header */
const char *range;
/** The "real" content length */
apr_off_t clength;
/** sending chunked transfer-coding */
int chunked;
/** Method for reading the request body
* (eg. REQUEST_CHUNKED_ERROR, REQUEST_NO_BODY,
* REQUEST_CHUNKED_DECHUNK, etc...) */
int read_body;
/** reading chunked transfer-coding */
int read_chunked;
/** is client waiting for a 100 response? */
unsigned expecting_100;
/** The optional kept body of the request. */
apr_bucket_brigade *kept_body;
/** For ap_body_to_table(): parsed body */
/* XXX: ap_body_to_table has been removed. Remove body_table too or
* XXX: keep it to reintroduce ap_body_to_table without major bump? */
apr_table_t *body_table;
/** Remaining bytes left to read from the request body */
apr_off_t remaining;
/** Number of bytes that have been read from the request body */
apr_off_t read_length;
/* MIME header environments, in and out. Also, an array containing
* environment variables to be passed to subprocesses, so people can
* write modules to add to that environment.
*
* The difference between headers_out and err_headers_out is that the
* latter are printed even on error, and persist across internal redirects
* (so the headers printed for ErrorDocument handlers will have them).
*
* The 'notes' apr_table_t is for notes from one module to another, with no
* other set purpose in mind...
*/
/** MIME header environment from the request */
apr_table_t *headers_in;
/** MIME header environment for the response */
apr_table_t *headers_out;
/** MIME header environment for the response, printed even on errors and
* persist across internal redirects */
apr_table_t *err_headers_out;
/** Array of environment variables to be used for sub processes */
apr_table_t *subprocess_env;
/** Notes from one module to another */
apr_table_t *notes;
/* content_type, handler, content_encoding, and all content_languages
* MUST be lowercased strings. They may be pointers to static strings;
* they should not be modified in place.
*/
/** The content-type for the current request */
const char *content_type; /* Break these out --- we dispatch on 'em */
/** The handler string that we use to call a handler function */
const char *handler; /* What we *really* dispatch on */
/** How to encode the data */
const char *content_encoding;
/** Array of strings representing the content languages */
apr_array_header_t *content_languages;
/** variant list validator (if negotiated) */
char *vlist_validator;
/** If an authentication check was made, this gets set to the user name. */
char *user;
/** If an authentication check was made, this gets set to the auth type. */
char *ap_auth_type;
/* What object is being requested (either directly, or via include
* or content-negotiation mapping).
*/
/** The URI without any parsing performed */
char *unparsed_uri;
/** The path portion of the URI, or "/" if no path provided */
char *uri;
/** The filename on disk corresponding to this response */
char *filename;
/* XXX: What does this mean? Please define "canonicalize" -aaron */
/** The true filename, we canonicalize r->filename if these don't match */
char *canonical_filename;
/** The PATH_INFO extracted from this request */
char *path_info;
/** The QUERY_ARGS extracted from this request */
char *args;
/**
* Flag for the handler to accept or reject path_info on
* the current request. All modules should respect the
* AP_REQ_ACCEPT_PATH_INFO and AP_REQ_REJECT_PATH_INFO
* values, while AP_REQ_DEFAULT_PATH_INFO indicates they
* may follow existing conventions. This is set to the
* user's preference upon HOOK_VERY_FIRST of the fixups.
*/
int used_path_info;
/** A flag to determine if the eos bucket has been sent yet */
int eos_sent;
/* Various other config info which may change with .htaccess files
* These are config vectors, with one void* pointer for each module
* (the thing pointed to being the module's business).
*/
/** Options set in config files, etc. */
struct ap_conf_vector_t *per_dir_config;
/** Notes on *this* request */
struct ap_conf_vector_t *request_config;
/** Optional request log level configuration. Will usually point
* to a server or per_dir config, i.e. must be copied before
* modifying */
const struct ap_logconf *log;
/** Id to identify request in access and error log. Set when the first
* error log entry for this request is generated.
*/
const char *log_id;
/**
* A linked list of the .htaccess configuration directives
* accessed by this request.
* N.B. always add to the head of the list, _never_ to the end.
* that way, a sub request's list can (temporarily) point to a parent's list
*/
const struct htaccess_result *htaccess;
/** A list of output filters to be used for this request */
struct ap_filter_t *output_filters;
/** A list of input filters to be used for this request */
struct ap_filter_t *input_filters;
/** A list of protocol level output filters to be used for this
* request */
struct ap_filter_t *proto_output_filters;
/** A list of protocol level input filters to be used for this
* request */
struct ap_filter_t *proto_input_filters;
/** This response can not be cached */
int no_cache;
/** There is no local copy of this response */
int no_local_copy;
/** Mutex protect callbacks registered with ap_mpm_register_timed_callback
* from being run before the original handler finishes running
*/
apr_thread_mutex_t *invoke_mtx;
/** A struct containing the components of URI */
apr_uri_t parsed_uri;
/** finfo.protection (st_mode) set to zero if no such file */
apr_finfo_t finfo;
/** remote address information from conn_rec, can be overridden if
* necessary by a module.
* This is the address that originated the request.
*/
apr_sockaddr_t *useragent_addr;
char *useragent_ip;
/** MIME trailer environment from the request */
apr_table_t *trailers_in;
/** MIME trailer environment from the response */
apr_table_t *trailers_out;
};
这是个非常大的结构体,可谓是包罗万象。对于初学者来说,想完全弄明白各项是什么还是比较困难的。而我们的需求很简单,我们就列出我们可能需要关心的数据
/** First line of request */
char *the_request;
请求的第一行数据
/** Protocol version number of protocol; 1.1 = 1001 */
int proto_num;
/** Protocol string, as given to us, or HTTP/0.9 */
char *protocol;
/** Host, as set by full URI or Host: */
const char *hostname;
协议的版本和请求的类型
/** Time when the request started */
apr_time_t request_time;
请求的时间
/** The URI without any parsing performed */
char *unparsed_uri;
/** The path portion of the URI, or "/" if no path provided */
char *uri;
/** The filename on disk corresponding to this response */
char *filename;
未进行urldecode的URI、经过urldecode的URI和处理该请求的文件路径
/** The PATH_INFO extracted from this request */
char *path_info;
/** The QUERY_ARGS extracted from this request */
char *args;
请求中的路径和参数
/** A struct containing the components of URI */
apr_uri_t parsed_uri;
请求解析的详细结果
char *useragent_ip;
请求来源的IP
/** MIME header environment from the request */
apr_table_t *headers_in;
以table形式保存的http头信息
对于基础数据类型我们很容易编写出例程
if (r->the_request) {
ap_rprintf(r, "the request : %s\n", r->the_request);
}
else {
ap_rprintf(r, "the request is NULL\n");
}
if (r->protocol) {
ap_rprintf(r, "protocol : %s\n", r->protocol);
}
else {
ap_rprintf(r, "protocol is NULL\n");
}
ap_rprintf(r, "proto_num is %d\n", r->proto_num);
而对于请求时间apr_time_t类型,我们可以参考《服务器架设笔记——Apache模块开发基础知识》中对模块的介绍。我们查看源码,可以编写出如下例程
static void print_time(request_rec* r) {
if (!r) {
ap_rprintf(r, "request_rec pointer is NULL\n");
return;
}
char data_str[128] = {0};
apr_status_t status = apr_ctime(data_str, r->request_time);
if (APR_SUCCESS != status) {
ap_rprintf(r, "apr_ctime error\n");
}
else {
ap_rprintf(r, "ctime\t:\t%s\n", data_str);
}
apr_time_exp_t exp_t;
memset(&exp_t, 0, sizeof(exp_t));
status = apr_time_exp_gmt(&exp_t, r->request_time);
if (APR_SUCCESS != status) {
ap_rprintf(r, "apr_time_exp_gmt error\n");
}
else {
ap_rprintf(r, "exp time\t:\n");
ap_rprintf(r, "\ttm_usec\t:\t%d\n", exp_t.tm_usec);
ap_rprintf(r, "\ttm_sec\t:\t%d\n", exp_t.tm_sec);
ap_rprintf(r, "\ttm_min\t:\t%d\n", exp_t.tm_min);
ap_rprintf(r, "\ttm_hour\t:\t%d\n", exp_t.tm_hour);
ap_rprintf(r, "\ttm_mday\t:\t%d\n", exp_t.tm_mday);
ap_rprintf(r, "\ttm_mon\t:\t%d\n", exp_t.tm_mon);
ap_rprintf(r, "\ttm_year\t:\t%d\n", exp_t.tm_year);
ap_rprintf(r, "\ttm_wday\t:\t%d\n", exp_t.tm_wday);
ap_rprintf(r, "\ttm_yday\t:\t%d\n", exp_t.tm_yday);
ap_rprintf(r, "\ttm_isdst\t:\t%d\n", exp_t.tm_isdst);
ap_rprintf(r, "\ttm_gmtoff\t:\t%d\n", exp_t.tm_gmtoff);
}
}
其中apr_time_exp_t的定义在《apr_time.h》中。
/**
* a structure similar to ANSI struct tm with the following differences:
* - tm_usec isn't an ANSI field
* - tm_gmtoff isn't an ANSI field (it's a BSDism)
*/
struct apr_time_exp_t {
/** microseconds past tm_sec */
apr_int32_t tm_usec;
/** (0-61) seconds past tm_min */
apr_int32_t tm_sec;
/** (0-59) minutes past tm_hour */
apr_int32_t tm_min;
/** (0-23) hours past midnight */
apr_int32_t tm_hour;
/** (1-31) day of the month */
apr_int32_t tm_mday;
/** (0-11) month of the year */
apr_int32_t tm_mon;
/** year since 1900 */
apr_int32_t tm_year;
/** (0-6) days since Sunday */
apr_int32_t tm_wday;
/** (0-365) days since January 1 */
apr_int32_t tm_yday;
/** daylight saving time */
apr_int32_t tm_isdst;
/** seconds east of UTC */
apr_int32_t tm_gmtoff;
};
对于已分析过了的请求结构体apr_uri_t的例程也非常简单,我就不再列出来,只是把其结构体定义贴一下。大家一看就明白
/**
* A structure to encompass all of the fields in a uri
*/
struct apr_uri_t {
/** scheme ("http"/"ftp"/...) */
char *scheme;
/** combined [user[:password]\@]host[:port] */
char *hostinfo;
/** user name, as in http://user:passwd\@host:port/ */
char *user;
/** password, as in http://user:passwd\@host:port/ */
char *password;
/** hostname from URI (or from Host: header) */
char *hostname;
/** port string (integer representation is in "port") */
char *port_str;
/** the request path (or NULL if only scheme://host was given) */
char *path;
/** Everything after a '?' in the path, if present */
char *query;
/** Trailing "#fragment" string, if present */
char *fragment;
/** structure returned from gethostbyname() */
struct hostent *hostent;
/** The port number, numeric, valid only if port_str != NULL */
apr_port_t port;
/** has the structure been initialized */
unsigned is_initialized:1;
/** has the DNS been looked up yet */
unsigned dns_looked_up:1;
/** has the dns been resolved yet */
unsigned dns_resolved:1;
};
这些例程中麻烦的是对apr_table_t的解析。因为网上很难找到对该table的遍历代码,于是我只能参考apr_table_clone中代码得出如下
static void print_table(request_rec *r, const apr_table_t* t) {
const apr_array_header_t* array = apr_table_elts(t);
apr_table_entry_t* elts = (apr_table_entry_t*)array->elts;
for (int i = 0; i < array->nelts; i++) {
ap_rprintf(r, "\t%s : %s\n", elts[i].key, elts[i].val);
}
}
我们请求一个URL:http://192.168.191.129/AP%26AC%3aHE?a=b#c
其返回如下
headers_in start
Host : 192.168.191.129
Connection : keep-alive
Cache-Control : max-age=0
Accept : text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
User-Agent : Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.72 Safari/537.36
Accept-Encoding : gzip,deflate,sdch
Accept-Language : zh-CN,zh;q=0.8
headers_in end
headers_out start
headers_out end
the request : GET /AP%26AC%3aHE?a=b HTTP/1.1
protocol : HTTP/1.1
proto_num is 1001
method : GET
host name : 192.168.191.129
unparsed uri : /AP%26AC%3aHE?a=b
uri : /AP&AC:HE
filename : /usr/local/apache2/htdocs/AP&AC:HE
path info :
args : a=b
user is NULL
log id is NULL
useragent ip : 192.168.191.1
ctime : Mon Feb 16 18:20:39 2015
exp time :
tm_usec : 200039
tm_sec : 39
tm_min : 20
tm_hour : 10
tm_mday : 16
tm_mon : 1
tm_year : 115
tm_wday : 1
tm_yday : 46
tm_isdst : 0
tm_gmtoff : 0
scheme is NULL
hostinfo is NULL
user is NULL
password is NULL
hostname is NULL
port_str is NULL
path : /AP&AC:HE
query : a=b
fragment is NULL
The sample page from mod_get_request.c