http message parsin wip but really better

This commit is contained in:
hugogogo
2022-08-11 00:28:01 +02:00
parent 11f71ea74f
commit 1d67e6988d
8 changed files with 112 additions and 81 deletions

View File

@@ -30,7 +30,6 @@ SRCS = main.cpp \
utils.cpp \
cgi_script.cpp \
Client.cpp \
parsing_message_http.cpp \
OBJS_D = builds
OBJS = $(SRCS:%.cpp=$(OBJS_D)/%.o)

View File

@@ -77,22 +77,26 @@ Client & Client::operator=( Client const & rhs )
// https://www.tutorialspoint.com/http/http_requests.htm
void Client::parse_request(std::vector<ServerConfig> &servers)
{
std::map<std::string, std::string> headers;
std::string body;
// std::map<std::string, std::string> headers;
// std::string body;
std::string copy_request;
// DEBUG
// std::cout << "\nREQUEST ____________\n" << raw_request << "\n_____________\n";
clear_request(); // not mandatory
_parse_request_line();
_parse_request_line(copy_request);
if (status)
return;
_parse_request_headers(copy_request);
if (status)
return;
_parse_request_headers();
assigned_server = ::_determine_process_server(this, servers);
assigned_location = ::_determine_location(*assigned_server, _request.abs_path);
_check_request_errors();
if (status)
return;
// use getter for headers because it works case insensitive
_parse_port_hostname(this->get_rq_headers("Host"));
/* dont clear raw_request, we need it for future reparsing of body
@@ -203,7 +207,7 @@ void Client::_parse_request_line()
std::string raw_line;
int ret;
raw_line = extract_line();
raw_line = ::get_line(raw_request, 0, CRLF);
line = ::split_trim(raw_line, " ", ' ');
if (line.size() != 3)
{
@@ -233,8 +237,22 @@ void Client::_parse_request_uri( std::string uri )
void Client::_parse_request_headers()
{
// TODO: check error and adjust status
_request.headers = ::parse_http_headers(raw_request);
std::string headers;
size_t pos;
int ret;
headers = raw_request;
// extract header part
::extract_line(headers, 0, CRLF);
pos = headers.find(CRLF);
::extract_line(headers, pos); // delete from pos to the end
// copy result of parser into headers
ret = ::parse_http_headers(raw_request, _request.headers);
if (ret > 0)
{
std::cerr << "err _parse_request_headers(): " << ret << " field are bad formated\n";
status = 400; // "bad request"
}
}
void Client::_parse_port_hostname(std::string host)

View File

@@ -11,7 +11,6 @@
# include <arpa/inet.h> // htonl, htons, ntohl, ntohs, inet_addr, inet_ntoa
# include "utils.hpp"
# include "ServerConfig.hpp"
# include "parsing_message_http.hpp"
struct Script
{

View File

@@ -9,6 +9,14 @@ void throw_test()
throw std::bad_alloc();
}
// notice : the use of getline make it such as
// it doesn't identify multiple delim as one :
// " something \n else " -> 1 - something
// 2 - else
// is not the same as :
// " something \n\n else " -> 1 - something
// 2 -
// 3 - else
std::vector<std::string> split(std::string input, char delimiter)
{
std::vector<std::string> answer;
@@ -176,29 +184,91 @@ std::string str_tolower(std::string str)
// identify a line in a string, by delim (ex. '\n')
// delete this line from the string
// and return the deleted line
std::string extract_line(std::string * str, size_t pos, std::string delim)
// if delim is empty, the extraction begin exactly at pos, and end at npos
std::string
extract_line(std::string & str, size_t pos = 0, std::string delim = "")
{
std::string del_str;
size_t begin;
size_t end;
begin = (*str).rfind(delim, pos);
begin = str.rfind(delim, pos);
if (begin == std::string::npos)
begin = 0;
else
begin += delim.size();
end = (*str).find(delim, pos);
if (end == std::string::npos)
end = 0;
else
end = str.find(delim, pos);
if (end != std::string::npos)
end += delim.size();
if (delim.empty())
end = std::string::npos;
del_str = (*str).substr(begin, end - begin);
(*str).erase(begin, end - begin);
del_str = str.substr(begin, end - begin);
str.erase(begin, end - begin);
return del_str;
}
// get a line in a string, by delim
// same as extract, except it doesn't delete it
std::string get_line(std::string str, size_t pos = 0, std::string delim = "")
{
std::string ret_str;
size_t begin;
size_t end;
begin = str.rfind(delim, pos);
if (begin == std::string::npos)
begin = 0;
else
begin += delim.size();
end = str.find(delim, pos);
if (end != std::string::npos)
end += delim.size();
if (delim.empty())
end = std::string::npos;
ret_str = str.substr(begin, end - begin);
return ret_str;
}
std::map<std::string, std::string>
parse_http_headers (
std::string headers,
std::map<std::string, std::string> fields )
{
std::vector<std::string> list;
std::vector<std::string>::iterator it;
std::vector<std::string>::iterator it_end;
size_t err = 0;
size_t pos;
list = ::split_trim(sub, CRLF, ' ');
it_end = list.end();
for (it = list.begin(); it != it_end; it++)
{
pos = (*it).find(':');
if (pos == std::string::npos)
{
err++;
continue;
}
key = (*it).substr(0, pos);
if ( key.find(' ') != std::string::npos )
{
err++;
continue;
}
key = ::str_tolower(key); // to make "key" case_insensitive
val = (*it).substr(pos + 1);
val = ::trim(val, ' ');
fields.insert( std::pair<std::string, std::string>(key, val) );
}
return err;
}
bool operator==(const listen_socket& lhs, int fd)
{ return lhs.fd == fd; }

View File

@@ -45,7 +45,10 @@ std::string http_methods_to_str(unsigned int methods);
int path_is_valid(std::string path);
void replace_all_substr(std::string &str, const std::string &ori_substr, const std::string &new_substr);
std::string str_tolower(std::string str);
std::string extract_line(std::string * str, size_t pos, std::string delim);
std::string extract_line(std::string & s, size_t p, std::string d);
std::string get_line(std::string str, size_t pos, std::string del);
std::map<std::string, std::string>
parse_http_headers (std::string headers, std::map<std::string, std::string> fields );
void throw_test();
#endif

View File

@@ -152,7 +152,7 @@ void Webserv::_check_script_status(Client *client, std::string output)
{
status_pos = pos + std::string("Status:").size();
client->status = atoi(output.c_str() + status_pos);
::del_line_in_str(&output, pos, CRLF);
::extract_line(output, pos, CRLF);
}
else
client->status = 200;
@@ -176,7 +176,7 @@ void Webserv::_check_script_fields(Client *client, std::string output)
if (it_srv->first == it_scr->first)
{
pos = client->response.find(it_srv->first);
::del_line_in_str(&client->response, pos, CRLF);
::extract_line(client->response, pos, CRLF);
}
}
}

View File

@@ -1,48 +1,6 @@
#include "parsing_message_http.hpp"
/*
- parse_http_first_line() :
- copy first line into a vector of 3 strings
/ copy line into a vector of 3 strings
- parse_http_headers(std::string message)
-
- parse_http_body(std::string message)
*/
std::map<std::string, std::string>
parse_http_headers(std::string message)
{
std::map<std::string, std::string> headers;
std::vector<std::string> list;
std::vector<std::string>::iterator it;
std::string sub;
std::string key;
std::string val;
size_t pos;
pos = (message).find(CRLF CRLF);
sub = (message).substr(0, pos);
list = ::split(sub, '\n');
if ( maybe_http_first_line( *list.begin() ) )
list.erase(list.begin());
for (it = list.begin(); it != list.end(); it++)
{
// TODO: if pattern is not "NAME: value" return error
pos = (*it).find(':');
key = (*it).substr( 0, pos );
key = ::trim(key, ' ');
key = ::trim(key, '\r');
key = ::str_tolower(key);
val = (*it).substr( pos + 1 );
val = ::trim(val, ' ');
val = ::trim(val, '\r');
headers.insert( std::pair<std::string, std::string>(key, val) );
}
return headers;
}
std::string
parse_http_body(std::string message)
{
@@ -57,18 +15,3 @@ std::string
return body;
}
bool maybe_http_first_line(std::string str)
{
// method SP target SP version https://www.rfc-editor.org/rfc/rfc7230.html#section-3.1.1
// version SP status SP reason https://www.rfc-editor.org/rfc/rfc7230.html#section-3.1.2
std::vector<std::string> sline;
sline = ::split(str, ' ');
if (sline.size() != 3)
return false;
if (sline[0].find(':') != std::string::npos)
return false;
return true;
}

View File

@@ -9,14 +9,13 @@
# include "utils.hpp"
std::map<std::string, std::string>
parse_http_headers(std::string message);
parse_http_headers (
std::string headers,
std::map<std::string, std::string> fields )
std::string
parse_http_body(std::string message);
bool
maybe_http_first_line(std::string);
// http message structure :
//
// start-line