summaryrefslogtreecommitdiff
path: root/http_parser.c
blob: 05cd0943a2473f7163382e51a0bafa14390be4ee (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
/*          __                               _
*    ____  / /_  ____ ___  __  ___________ _(_)
*   / __ \/ __ \/ __ `__ \/ / / / ___/ __ `/ /
*  / /_/ / / / / / / / / / /_/ / /__/ /_/ / /
*  \____/_/ /_/_/ /_/ /_/\__, /\___/\__, /_/
*                       /____/     /____/
*
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 2021, Max Christian Pohle <max@coderonline.de>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
*    notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
*    notice, this list of conditions and the following disclaimer in the
*    documentation and/or other materials provided with the distribution.
*
* {{{ DISCLAIMER
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
* }}}
*/

#include "main.h"

void parse_http(size_t new_socket, char * request, size_t request_length) {
	char * start = request;
	char * end = NULL;
	char * search = "\r\n";

	Http_Header http_header = {0};

	char * name = NULL;
	while(NULL != (end = strpbrk(start, search))) { // TODO: try harder to break things (are SEGFAULTs possible?)

		size_t matchlen = strspn(end, search);
		switch(end[0]) {
			case ':':
				end[0] = '\0'; // {{{ remember header 'names' and search for the value
				end++;         // jump over the colon

				name = start;  // remember, where name starts, will be important in the newline case

				if (0 == strcasecmp("Content-Type", start)) {
					search = "\r\n;"; // (more unlikely) also search for a semicolon in Content-Type: [...]; boundary=[...]
				} else {
					search = "\r\n";  // (likely) search for some kind of newline
				} // }}}
				break;
			case ';':
				// {{{ find the form-data boundary in the main header
				start += strspn(start, "; "); // remove spaces and semicolons (boundary check implicit; also stops at '\0')

				const char s_multipart_form_data[] = "boundary=";
				if(NULL == http_header.boundary && 0 < strcasecmp(start, s_multipart_form_data))
				{
					http_header.boundary = end + sizeof(s_multipart_form_data) + 1;
					http_header.boundary += strspn(http_header.boundary, "-");
					DEBUG("> Boundary found, now looking where it ends...\n");
					search = "\r\n";
					continue;
				} /// }}}
				break;
			case '\r': // fallthrough
			case '\n':
				// {{{ newlines are special: sometimes content parts follow and sometimes headers, guess what...
				end[0] = '\0';
				search = ":"; // we will continue to search for headers
				if(NULL == name) {
					if(NULL == http_header.method) {
						DEBUG("[%ld]> HTTP REQUEST LINE :: %s \n", matchlen, start);
						end[0] = '\0';

						while(NULL != (start = memchr(start, ' ', end - start))) {
							if(NULL == http_header.url)
								http_header.url = ++start;
							else
								start[0] = '\0';
						}
						http_header.method = start;
						http_header.newline_length = matchlen;
					} else {
						DEBUG("[...]\n"); // if we want to intentially skip something, we land here by setting name = NUL;
						break;
					}
				} else { // we know that name is not NULL and can work with it
					if (0 == strcasecmp("Content-Disposition", name))
					{ http_header.content_disposition = start; }
				} // }}}
				DEBUG("\033[32m[%ld]> '% 20s' = '%s'\033[0m\n", matchlen, name, start);
				// {{{ check if a http header ended (e.g. two newlines)
				if(matchlen > http_header.newline_length) {
					DEBUG("> END HEADERS, because there were %d newlines; boundary='%s'[%ld]\n", matchlen / http_header.newline_length, http_header.boundary, http_header.boundary_size);
					end += matchlen;

					// if it was the first header, we calculate the boundary size and expect more headers to come after a boundary
					if(http_header.boundary && http_header.boundary_size == 0) {
						DEBUG("================================================================================\n");
						http_header.boundary_size = strlen(http_header.boundary);
						// skip the first header and boundary...
						start = end;
						start += strspn(start, "-");
						start += http_header.boundary_size;
						start += http_header.newline_length;
						continue;
					} else {
						char * content_start = end;
						while(1)
						{
							size_t size_remaining = (size_t)  request_length - (end - request) - 1;
							DEBUG("%ld remaining.\n", size_remaining);

							if(size_remaining <= 0) {
								DEBUG("> not even the boundary would fit in that what is left.\n");
								break;
							}

							if(NULL == (end = memchr((void*) end, '-', size_remaining))) {
								DEBUG("no further '-' found\n");
								break;
							}

							char * content_end = end - http_header.newline_length;

							end += strspn(end, "-");
							if(0 == strncmp(end, http_header.boundary, http_header.boundary_size)) {
								size_t file_size = content_end - content_start;
								DEBUG("> Content ends here, size of the last file is %ld\n", file_size);

								content_start[file_size + 1] = '\0';
								next_part(&http_header, content_start, file_size);

								end += http_header.boundary_size;
								matchlen = strspn(end, "\r\n");
								DEBUG("> end is at %p, matchlen is %ld\n", end, matchlen);

								search = ":";
								break;
							} else {
								end = end + 1;
							}
						}
					}
					break;
				} // }}} if condition after a header
		} // switch

		if(NULL == end)
			break;
		else
			start = end + matchlen;
	}

	DEBUG("> sending answer...\n");
	send_answer(&http_header, new_socket);
	DEBUG("> answer sent.\n");
}

// modeline for vim: shiftwidth=2 tabstop=2 number foldmethod=marker
..