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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
|
/* __ _
* ____ / /_ ____ ___ __ ___________ _(_)
* / __ \/ __ \/ __ `__ \/ / / / ___/ __ `/ /
* / /_/ / / / / / / / / / /_/ / /__/ /_/ / /
* \____/_/ /_/_/ /_/ /_/\__, /\___/\__, /_/
* /____/ /____/
*
* 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"
#include <string.h>
static inline char * handle_colon(char ** start, char ** end, char ** search) {
// HTTP headers and content are separated by an empty line (which is two
// newlines), but before that there are pairs of names and values, separated
// by a colon, e.g. Content-Type: text/html and this function is called, when
// *end reaches a colon.
*end[0] = '\0'; // remember header 'names' and search for the value
(*end)++; // jump over the colon
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
}
return *start; // remember, where name starts, will be important in the newline case
}
static inline char * handle_semicolon(char ** start, char ** end, char ** search) {
// 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(0 < strcasecmp(*start, s_multipart_form_data))
{
*end = *end + sizeof(s_multipart_form_data) + 1;
*end += strspn(*end, "-");
*start = *end;
*end += strcspn(*end, "\r\n ");
*end[0] = '\0';
DEBUG("> Boundary found: %s\n", *start);
}
*search = "\r\n"; // do not search further semicolons
return *start;
}
void parse_http(size_t new_socket, char * request, size_t request_length) {
// this http parser modifies the input buffer and replaces single characters
// with \0-chars to terminate them, but it does not copy strings, because
// that would require tedious length checks and would also allow the user
// to submit forms with unreasonable long strings in strange places or to
// make it shorter: it would make boundary checks necessary for every single
// heaer name, value, sub-value and content. This implementation is more
// generic and only requires content length bounary checks.
char * start = request;
char * end = "\0";
char * search = "\r\n";
Http_Header http_header = {0};
request[request_length] = '\0';
// {{{ Parse the request line (e.g. "POST / HTTP/1.1")
http_header.method = start;
start += strcspn(start, " ");
start[0] = '\0';
http_header.url = ++start;
start += strcspn(start, " ");
start[0] = '\0';
http_header.protocol = ++start;
start += strcspn(start, "\r\n");
http_header.newline_length = strspn(start, "\r\n");
start[0] = '\0';
start += http_header.newline_length;
DEBUG("%% Request line: method='%s' url='%s' protocol='%s' newline_length=%ld\n",
http_header.method, http_header.url, http_header.protocol, http_header.newline_length);
// }}}
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 ':':
name = handle_colon(&start, &end, &search);
break;
case ';':
http_header.boundary = handle_semicolon(&start, &end, &search);
http_header.boundary_size = end - start;
break;
case '\r': // fallthrough
case '\n':
end[0] = '\0';
search = ":"; // we will continue to search for headers
// {{{ NAME AND VALUE OF A HEADER FIELD KNOWN
if(NULL != name) {
DEBUG("\033[32m[%ld]> '% 20s' = '%s'\033[0m\n", matchlen, name, start);
if (0 == strcasecmp("Content-Disposition", name))
{ http_header.content_disposition = start; }
} // }}}
// {{{ END OF A HTTP HEADER (two newlines)
if(matchlen > http_header.newline_length) {
end += matchlen; // go behind the double line break...
DEBUG("%% END HEADERS, because there were %d newlines; boundary='%s'[%ld]\n",
matchlen / http_header.newline_length,
http_header.boundary,
http_header.boundary_size
);
start = end;
for(; ; )
{
size_t size_remaining = (size_t) request_length - (end - request) - 1;
DEBUG("%ld remaining.\n", size_remaining);
matchlen = strspn(end, "-");
if(0 == strncmp(end + matchlen, http_header.boundary, http_header.boundary_size)) {
size_t file_size = end - http_header.newline_length - start;
DEBUG("> Content ends here, size of the last file is %ld\n", file_size);
start[file_size + 1] = '\0';
next_part(&http_header, start, file_size);
end += http_header.boundary_size + matchlen;
matchlen = http_header.newline_length;
DEBUG("> end is at %p, matchlen is %ld\n", end, matchlen);
search = ":";
break;
} else {
if(!http_header.boundary
|| size_remaining <= 0
|| NULL == (end = memchr((void*) end, '-', size_remaining))) {
DEBUG("EOF reached or no further '-' found\n");
break;
}
// end++;
}
}
} // }}} if condition after a header
break;
default:
DEBUG("Unknown char found: '%c'\n ", end[0]);
break;
} // switch
if(NULL == end)
break;
else
start = end + matchlen;
}
// failed to find URL? Use a default to avoid NULL pointer exceptions later
if(!http_header.url || http_header.url[0] == '\0' || http_header.url[1] == '\0') {
http_header.url = "/index.html";
DEBUG("Warning: Request had no URL and is probably invalid: %d", http_header.url[0]);
}
DEBUG("> sending answer...\n");
FILE * f = fdopen((size_t) new_socket, "w");
send_answer(&http_header, f);
fflush(f);
fclose(f);
DEBUG("> answer sent.\n");
}
// modeline for vim: shiftwidth=2 tabstop=2 number foldmethod=marker
|
