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
|
/* Copyright (c) 2002-2018 Dovecot authors, see the included COPYING file */
#include "lib.h"
#include "base64.h"
#include "buffer.h"
#include "unichar.h"
#include "charset-utf8.h"
#include "quoted-printable.h"
#include "message-header-decode.h"
static size_t
message_header_decode_encoded(const unsigned char *data, size_t size,
buffer_t *decodebuf, size_t *charsetlen_r)
{
#define QCOUNT 3
unsigned int num = 0;
size_t i, start_pos[QCOUNT] = {0, 0, 0};
/* data should contain "charset?encoding?text?=" */
for (i = 0; i < size; i++) {
if (data[i] == '?') {
start_pos[num++] = i;
if (num == QCOUNT)
break;
}
}
if (i+1 >= size || data[i+1] != '=') {
/* invalid block */
return 0;
}
i_assert(num == QCOUNT);
buffer_append(decodebuf, data, start_pos[0]);
buffer_append_c(decodebuf, '\0');
*charsetlen_r = decodebuf->used;
switch (data[start_pos[0]+1]) {
case 'q':
case 'Q':
if (quoted_printable_q_decode(data + start_pos[1] + 1,
start_pos[2] - start_pos[1] - 1,
decodebuf) < 0) {
/* we skipped over some invalid data */
}
break;
case 'b':
case 'B':
if (base64_decode(data + start_pos[1] + 1,
start_pos[2] - start_pos[1] - 1,
NULL, decodebuf) < 0) {
/* contains invalid data. show what we got so far. */
}
break;
default:
/* unknown encoding */
return 0;
}
return start_pos[2] + 2;
}
static bool is_only_lwsp(const unsigned char *data, size_t size)
{
size_t i;
for (i = 0; i < size; i++) {
if (!(data[i] == ' ' || data[i] == '\t' ||
data[i] == '\r' || data[i] == '\n'))
return FALSE;
}
return TRUE;
}
void message_header_decode(const unsigned char *data, size_t size,
message_header_decode_callback_t *callback,
void *context)
{
buffer_t *decodebuf = NULL;
size_t charsetlen = 0;
size_t pos, start_pos, ret;
/* =?charset?Q|B?text?= */
start_pos = 0;
for (pos = 0; pos + 1 < size; ) {
if (data[pos] != '=' || data[pos+1] != '?') {
pos++;
continue;
}
/* encoded string beginning */
if (pos != start_pos &&
!is_only_lwsp(data+start_pos, pos-start_pos)) {
/* send the unencoded data so far */
if (!callback(data + start_pos, pos - start_pos,
NULL, context)) {
start_pos = size;
break;
}
}
if (decodebuf == NULL) {
decodebuf = buffer_create_dynamic(default_pool,
size - pos);
} else {
buffer_set_used_size(decodebuf, 0);
}
pos += 2;
ret = message_header_decode_encoded(data + pos, size - pos,
decodebuf, &charsetlen);
if (ret == 0) {
start_pos = pos-2;
continue;
}
pos += ret;
if (decodebuf->used > charsetlen) {
/* decodebuf contains <charset> NUL <text> */
if (!callback(CONST_PTR_OFFSET(decodebuf->data,
charsetlen),
decodebuf->used - charsetlen,
decodebuf->data, context)) {
start_pos = size;
break;
}
}
start_pos = pos;
}
if (size != start_pos) {
i_assert(size > start_pos);
(void)callback(data + start_pos, size - start_pos,
NULL, context);
}
buffer_free(&decodebuf);
}
struct decode_utf8_context {
buffer_t *dest;
normalizer_func_t *normalizer;
bool changed:1;
};
static bool
decode_utf8_callback(const unsigned char *data, size_t size,
const char *charset, void *context)
{
struct decode_utf8_context *ctx = context;
struct charset_translation *t;
if (charset == NULL || charset_is_utf8(charset)) {
/* ASCII / UTF-8 */
if (ctx->normalizer != NULL) {
(void)ctx->normalizer(data, size, ctx->dest);
} else {
if (uni_utf8_get_valid_data(data, size, ctx->dest))
buffer_append(ctx->dest, data, size);
}
return TRUE;
}
if (charset_to_utf8_begin(charset, ctx->normalizer, &t) < 0) {
/* data probably still contains some valid ASCII characters.
append them. */
if (uni_utf8_get_valid_data(data, size, ctx->dest))
buffer_append(ctx->dest, data, size);
return TRUE;
}
/* ignore any errors */
(void)charset_to_utf8(t, data, &size, ctx->dest);
charset_to_utf8_end(&t);
return TRUE;
}
void message_header_decode_utf8(const unsigned char *data, size_t size,
buffer_t *dest, normalizer_func_t *normalizer)
{
struct decode_utf8_context ctx;
i_zero(&ctx);
ctx.dest = dest;
ctx.normalizer = normalizer;
message_header_decode(data, size, decode_utf8_callback, &ctx);
}
|
