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
|
/* Copyright (c) 2002-2018 Dovecot authors, see the included COPYING file */
#include "lib.h"
#include "buffer.h"
#include "istream.h"
#include "str.h"
#include "str-find.h"
#include "rfc822-parser.h"
#include "message-decoder.h"
#include "message-parser.h"
#include "message-search.h"
struct message_search_context {
enum message_search_flags flags;
normalizer_func_t *normalizer;
struct str_find_context *str_find_ctx;
struct message_part *prev_part;
struct message_decoder_context *decoder;
bool content_type_text:1; /* text/any or message/any */
};
struct message_search_context *
message_search_init(const char *normalized_key_utf8,
normalizer_func_t *normalizer,
enum message_search_flags flags)
{
struct message_search_context *ctx;
i_assert(*normalized_key_utf8 != '\0');
ctx = i_new(struct message_search_context, 1);
ctx->flags = flags;
ctx->decoder = message_decoder_init(normalizer, 0);
ctx->str_find_ctx = str_find_init(default_pool, normalized_key_utf8);
return ctx;
}
void message_search_deinit(struct message_search_context **_ctx)
{
struct message_search_context *ctx = *_ctx;
*_ctx = NULL;
str_find_deinit(&ctx->str_find_ctx);
message_decoder_deinit(&ctx->decoder);
i_free(ctx);
}
static void parse_content_type(struct message_search_context *ctx,
struct message_header_line *hdr)
{
struct rfc822_parser_context parser;
string_t *content_type;
rfc822_parser_init(&parser, hdr->full_value, hdr->full_value_len, NULL);
rfc822_skip_lwsp(&parser);
content_type = t_str_new(64);
(void)rfc822_parse_content_type(&parser, content_type);
ctx->content_type_text =
strncasecmp(str_c(content_type), "text/", 5) == 0 ||
strncasecmp(str_c(content_type), "message/", 8) == 0;
rfc822_parser_deinit(&parser);
}
static void handle_header(struct message_search_context *ctx,
struct message_header_line *hdr)
{
if (hdr->name_len == 12 &&
strcasecmp(hdr->name, "Content-Type") == 0) {
if (hdr->continues) {
hdr->use_full_value = TRUE;
return;
}
T_BEGIN {
parse_content_type(ctx, hdr);
} T_END;
}
}
static bool search_header(struct message_search_context *ctx,
const struct message_header_line *hdr)
{
static const unsigned char crlf[2] = { '\r', '\n' };
return str_find_more(ctx->str_find_ctx,
(const unsigned char *)hdr->name, hdr->name_len) ||
str_find_more(ctx->str_find_ctx,
hdr->middle, hdr->middle_len) ||
str_find_more(ctx->str_find_ctx, hdr->full_value,
hdr->full_value_len) ||
(!hdr->no_newline &&
str_find_more(ctx->str_find_ctx, crlf, 2));
}
static bool message_search_more_decoded2(struct message_search_context *ctx,
struct message_block *block)
{
if (block->hdr != NULL) {
if (search_header(ctx, block->hdr))
return TRUE;
} else {
if (str_find_more(ctx->str_find_ctx, block->data, block->size))
return TRUE;
}
return FALSE;
}
bool message_search_more(struct message_search_context *ctx,
struct message_block *raw_block)
{
struct message_block decoded_block;
return message_search_more_get_decoded(ctx, raw_block, &decoded_block);
}
bool message_search_more_get_decoded(struct message_search_context *ctx,
struct message_block *raw_block,
struct message_block *decoded_block_r)
{
struct message_header_line *hdr = raw_block->hdr;
struct message_block decoded_block;
i_zero(decoded_block_r);
decoded_block_r->part = raw_block->part;
if (raw_block->part != ctx->prev_part) {
/* part changes. we must change this before looking at
content type */
message_search_reset(ctx);
ctx->prev_part = raw_block->part;
if (hdr == NULL) {
/* we're returning to a multipart message. */
ctx->content_type_text = FALSE;
}
}
if (hdr != NULL) {
handle_header(ctx, hdr);
if ((ctx->flags & MESSAGE_SEARCH_FLAG_SKIP_HEADERS) != 0) {
/* we want to search only message bodies, but
but decoder needs some headers so that it can
decode the body properly. */
if (hdr->name_len != 12 && hdr->name_len != 25)
return FALSE;
if (strcasecmp(hdr->name, "Content-Type") != 0 &&
strcasecmp(hdr->name,
"Content-Transfer-Encoding") != 0)
return FALSE;
}
} else {
/* body */
if (!ctx->content_type_text)
return FALSE;
}
if (!message_decoder_decode_next_block(ctx->decoder, raw_block,
&decoded_block))
return FALSE;
if (decoded_block.hdr != NULL &&
(ctx->flags & MESSAGE_SEARCH_FLAG_SKIP_HEADERS) != 0) {
/* Content-* header */
return FALSE;
}
*decoded_block_r = decoded_block;
return message_search_more_decoded2(ctx, &decoded_block);
}
bool message_search_more_decoded(struct message_search_context *ctx,
struct message_block *block)
{
if (block->part != ctx->prev_part) {
/* part changes */
message_search_reset(ctx);
ctx->prev_part = block->part;
}
return message_search_more_decoded2(ctx, block);
}
void message_search_reset(struct message_search_context *ctx)
{
/* Content-Type defaults to text/plain */
ctx->content_type_text = TRUE;
ctx->prev_part = NULL;
str_find_reset(ctx->str_find_ctx);
message_decoder_decode_reset(ctx->decoder);
}
static int
message_search_msg_real(struct message_search_context *ctx,
struct istream *input, struct message_part *parts,
const char **error_r)
{
const struct message_parser_settings parser_set = {
.hdr_flags = MESSAGE_HEADER_PARSER_FLAG_CLEAN_ONELINE,
};
struct message_parser_ctx *parser_ctx;
struct message_block raw_block;
struct message_part *new_parts;
int ret;
message_search_reset(ctx);
if (parts != NULL) {
parser_ctx = message_parser_init_from_parts(parts,
input, &parser_set);
} else {
parser_ctx = message_parser_init(pool_datastack_create(),
input, &parser_set);
}
while ((ret = message_parser_parse_next_block(parser_ctx,
&raw_block)) > 0) {
if (message_search_more(ctx, &raw_block)) {
ret = 1;
break;
}
}
i_assert(ret != 0);
if (ret < 0 && input->stream_errno == 0) {
/* normal exit */
ret = 0;
}
if (message_parser_deinit_from_parts(&parser_ctx, &new_parts, error_r) < 0) {
/* broken parts */
ret = -1;
}
return ret;
}
int message_search_msg(struct message_search_context *ctx,
struct istream *input, struct message_part *parts,
const char **error_r)
{
int ret;
T_BEGIN {
ret = message_search_msg_real(ctx, input, parts, error_r);
} T_END_PASS_STR_IF(ret < 0, error_r);
return ret;
}
|
