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
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
/*++
/* NAME
/* header_token 3
/* SUMMARY
/* mail header parser
/* SYNOPSIS
/* #include <header_token.h>
/*
/* typedef struct {
/* .in +4
/* int type;
/* const char *u.value;
/* /* ... */
/* .in
/* } HEADER_TOKEN;
/*
/* ssize_t header_token(token, token_len, token_buffer, ptr,
/* specials, terminator)
/* HEADER_TOKEN *token;
/* ssize_t token_len;
/* VSTRING *token_buffer;
/* const char **ptr;
/* const char *specials;
/* int terminator;
/* DESCRIPTION
/* This module parses a mail header value (text after field-name:)
/* into tokens. The parser understands RFC 822 linear white space,
/* quoted-string, comment, control characters, and a set of
/* user-specified special characters.
/*
/* A result token type is one of the following:
/* .IP HEADER_TOK_QSTRING
/* Quoted string as per RFC 822.
/* .IP HEADER_TOK_TOKEN
/* Token as per RFC 822, and the special characters supplied by the
/* caller.
/* .IP other
/* The value of a control character or special character.
/* .PP
/* header_token() tokenizes the input and stops after a user-specified
/* terminator (ignoring all tokens that exceed the capacity of
/* the result storage), or when it runs out of space for the result.
/* The terminator is not stored. The result value is the number of
/* tokens stored, or -1 when the input was exhausted before any tokens
/* were found.
/*
/* Arguments:
/* .IP token
/* Result array of HEADER_TOKEN structures. Token string values
/* are pointers to null-terminated substrings in the token_buffer.
/* .IP token_len
/* Length of the array of HEADER_TOKEN structures.
/* .IP token_buffer
/* Storage for result token string values.
/* .IP ptr
/* Input/output read position. The input is a null-terminated string.
/* .IP specials
/* Special characters according to the relevant RFC, or a
/* null pointer (default to the RFC 822 special characters).
/* This must include the optional terminator if one is specified.
/* .IP terminator
/* The special character to stop after, or zero.
/* BUGS
/* Eight-bit characters are not given special treatment.
/* SEE ALSO
/* RFC 822 (ARPA Internet Text Messages)
/* DIAGNOSTICS
/* Fatal errors: memory allocation problem.
/* LICENSE
/* .ad
/* .fi
/* The Secure Mailer license must be distributed with this software.
/* AUTHOR(S)
/* Wietse Venema
/* IBM T.J. Watson Research
/* P.O. Box 704
/* Yorktown Heights, NY 10598, USA
/*--*/
/* System library. */
#include <sys_defs.h>
#include <string.h>
#include <ctype.h>
/* Utility library. */
#include <msg.h>
#include <vstring.h>
/* Global library. */
#include <lex_822.h>
#include <header_token.h>
/* Application-specific. */
/*
* Silly little macros.
*/
#define STR(x) vstring_str(x)
#define LEN(x) VSTRING_LEN(x)
#define CU_CHAR_PTR(x) ((const unsigned char *) (x))
/* header_token - parse out the next item in a message header */
ssize_t header_token(HEADER_TOKEN *token, ssize_t token_len,
VSTRING *token_buffer, const char **ptr,
const char *user_specials, int user_terminator)
{
ssize_t comment_level;
const unsigned char *cp;
ssize_t len;
int ch;
ssize_t tok_count;
ssize_t n;
/*
* Initialize.
*/
VSTRING_RESET(token_buffer);
cp = CU_CHAR_PTR(*ptr);
tok_count = 0;
if (user_specials == 0)
user_specials = LEX_822_SPECIALS;
/*
* Main parsing loop.
*
* XXX What was the reason to continue parsing when user_terminator is
* specified? Perhaps this was needed at some intermediate stage of
* development?
*/
while ((ch = *cp) != 0 && (user_terminator != 0 || tok_count < token_len)) {
cp++;
/*
* Skip RFC 822 linear white space.
*/
if (IS_SPACE_TAB_CR_LF(ch))
continue;
/*
* Terminator.
*/
if (ch == user_terminator)
break;
/*
* Skip RFC 822 comment.
*/
if (ch == '(') {
comment_level = 1;
while ((ch = *cp) != 0) {
cp++;
if (ch == '(') { /* comments can nest! */
comment_level++;
} else if (ch == ')') {
if (--comment_level == 0)
break;
} else if (ch == '\\') {
if ((ch = *cp) == 0)
break;
cp++;
}
}
continue;
}
/*
* Copy quoted text according to RFC 822.
*/
if (ch == '"') {
if (tok_count < token_len) {
token[tok_count].u.offset = LEN(token_buffer);
token[tok_count].type = HEADER_TOK_QSTRING;
}
while ((ch = *cp) != 0) {
cp++;
if (ch == '"')
break;
if (ch == '\n') { /* unfold */
if (tok_count < token_len) {
len = LEN(token_buffer);
while (len > 0
&& IS_SPACE_TAB_CR_LF(STR(token_buffer)[len - 1]))
len--;
if (len < LEN(token_buffer))
vstring_truncate(token_buffer, len);
}
continue;
}
if (ch == '\\') {
if ((ch = *cp) == 0)
break;
cp++;
}
if (tok_count < token_len)
VSTRING_ADDCH(token_buffer, ch);
}
if (tok_count < token_len) {
VSTRING_ADDCH(token_buffer, 0);
tok_count++;
}
continue;
}
/*
* Control, or special.
*/
if (strchr(user_specials, ch) || ISCNTRL(ch)) {
if (tok_count < token_len) {
token[tok_count].u.offset = LEN(token_buffer);
token[tok_count].type = ch;
VSTRING_ADDCH(token_buffer, ch);
VSTRING_ADDCH(token_buffer, 0);
tok_count++;
}
continue;
}
/*
* Token.
*/
else {
if (tok_count < token_len) {
token[tok_count].u.offset = LEN(token_buffer);
token[tok_count].type = HEADER_TOK_TOKEN;
VSTRING_ADDCH(token_buffer, ch);
}
while ((ch = *cp) != 0 && !IS_SPACE_TAB_CR_LF(ch)
&& !ISCNTRL(ch) && !strchr(user_specials, ch)) {
cp++;
if (tok_count < token_len)
VSTRING_ADDCH(token_buffer, ch);
}
if (tok_count < token_len) {
VSTRING_ADDCH(token_buffer, 0);
tok_count++;
}
continue;
}
}
/*
* Ignore a zero-length item after the last terminator.
*/
if (tok_count == 0 && ch == 0)
return (-1);
/*
* Finalize. Fill in the string pointer array, now that the token buffer
* is no longer dynamically reallocated as it grows.
*/
*ptr = (const char *) cp;
for (n = 0; n < tok_count; n++)
token[n].u.value = STR(token_buffer) + token[n].u.offset;
if (msg_verbose)
msg_info("header_token: %s %s %s",
tok_count > 0 ? token[0].u.value : "",
tok_count > 1 ? token[1].u.value : "",
tok_count > 2 ? token[2].u.value : "");
return (tok_count);
}
|
