Mercurial > dovecot > core-2.2
annotate src/lib-mail/message-parser.h @ 1322:97f8c00b8d4c HEAD
Better handling for multiline headers. Before we skipped headers larger than
input buffer size (8k with read (default), 256k with mmap). The skipping was
also a bit buggy.
Now we parse the lines one at a time. There's also a way to read the header
fully into memory before parsing it, if really needed.
author | Timo Sirainen <tss@iki.fi> |
---|---|
date | Wed, 26 Mar 2003 19:29:01 +0200 |
parents | 60646878858e |
children | 676995d7c0ca |
rev | line source |
---|---|
0 | 1 #ifndef __MESSAGE_PARSER_H |
2 #define __MESSAGE_PARSER_H | |
3 | |
988
8028c4dcf38f
mail-storage.h interface changes, affects pretty much everything.
Timo Sirainen <tss@iki.fi>
parents:
953
diff
changeset
|
4 #include "message-size.h" |
8028c4dcf38f
mail-storage.h interface changes, affects pretty much everything.
Timo Sirainen <tss@iki.fi>
parents:
953
diff
changeset
|
5 |
896
21ffcce83c70
Rewrote rfc822-tokenize.c to work one token at a time so it won't uselessly
Timo Sirainen <tss@iki.fi>
parents:
764
diff
changeset
|
6 #define IS_LWSP(c) \ |
21ffcce83c70
Rewrote rfc822-tokenize.c to work one token at a time so it won't uselessly
Timo Sirainen <tss@iki.fi>
parents:
764
diff
changeset
|
7 ((c) == ' ' || (c) == '\t') |
21ffcce83c70
Rewrote rfc822-tokenize.c to work one token at a time so it won't uselessly
Timo Sirainen <tss@iki.fi>
parents:
764
diff
changeset
|
8 |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
9 enum message_part_flags { |
106
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
10 MESSAGE_PART_FLAG_MULTIPART = 0x01, |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
11 MESSAGE_PART_FLAG_MULTIPART_DIGEST = 0x02, |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
12 MESSAGE_PART_FLAG_MESSAGE_RFC822 = 0x04, |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
13 |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
14 /* content-type: text/... */ |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
15 MESSAGE_PART_FLAG_TEXT = 0x08, |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
16 |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
17 /* content-transfer-encoding: binary */ |
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
18 MESSAGE_PART_FLAG_BINARY = 0x10 |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
19 }; |
106
5fe3e04ca8d9
Added support for caching of MessagePart data. This is useful for fetching
Timo Sirainen <tss@iki.fi>
parents:
105
diff
changeset
|
20 |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
21 struct message_part { |
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
22 struct message_part *parent; |
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
23 struct message_part *next; |
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
24 struct message_part *children; |
0 | 25 |
105
31034993473c
there was no need for MessagePart->pos.virtual_pos, so removed it.
Timo Sirainen <tss@iki.fi>
parents:
50
diff
changeset
|
26 uoff_t physical_pos; /* absolute position from beginning of message */ |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
27 struct message_size header_size; |
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
28 struct message_size body_size; |
0 | 29 |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
30 enum message_part_flags flags; |
10
82b7de533f98
s/user_data/context/ and some s/Data/Context/
Timo Sirainen <tss@iki.fi>
parents:
9
diff
changeset
|
31 void *context; |
0 | 32 }; |
33 | |
1322
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
34 struct message_header_parser_ctx; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
35 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
36 struct message_header_line { |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
37 const char *name; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
38 size_t name_len; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
39 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
40 const unsigned char *value; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
41 size_t value_len; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
42 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
43 const unsigned char *full_value; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
44 size_t full_value_len; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
45 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
46 unsigned int continues:1; /* multiline header, continues in next line */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
47 unsigned int continued:1; /* multiline header, continues */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
48 unsigned int eoh:1; /* "end of headers" line */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
49 unsigned int no_newline:1; /* no \n after this line */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
50 unsigned int use_full_value:1; /* set if you want full_value */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
51 }; |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
52 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
53 /* called once with hdr = NULL at end of headers */ |
1038
60646878858e
Function typedefs now define them as functions, not function pointers.
Timo Sirainen <tss@iki.fi>
parents:
988
diff
changeset
|
54 typedef void message_header_callback_t(struct message_part *part, |
1322
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
55 struct message_header_line *hdr, |
1038
60646878858e
Function typedefs now define them as functions, not function pointers.
Timo Sirainen <tss@iki.fi>
parents:
988
diff
changeset
|
56 void *context); |
0 | 57 |
953
411006be3c66
Naming change for function typedefs.
Timo Sirainen <tss@iki.fi>
parents:
903
diff
changeset
|
58 /* callback is called for each field in message header. */ |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
59 struct message_part *message_parse(pool_t pool, struct istream *input, |
1038
60646878858e
Function typedefs now define them as functions, not function pointers.
Timo Sirainen <tss@iki.fi>
parents:
988
diff
changeset
|
60 message_header_callback_t *callback, |
953
411006be3c66
Naming change for function typedefs.
Timo Sirainen <tss@iki.fi>
parents:
903
diff
changeset
|
61 void *context); |
903
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
62 void message_parse_header(struct message_part *part, struct istream *input, |
fd8888f6f037
Naming style changes, finally got tired of most of the typedefs. Also the
Timo Sirainen <tss@iki.fi>
parents:
898
diff
changeset
|
63 struct message_size *hdr_size, |
1038
60646878858e
Function typedefs now define them as functions, not function pointers.
Timo Sirainen <tss@iki.fi>
parents:
988
diff
changeset
|
64 message_header_callback_t *callback, void *context); |
0 | 65 |
1322
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
66 struct message_header_parser_ctx * |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
67 message_parse_header_init(struct istream *input, struct message_size *hdr_size); |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
68 void message_parse_header_deinit(struct message_header_parser_ctx *ctx); |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
69 |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
70 /* Read and return next header line. */ |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
71 struct message_header_line * |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
72 message_parse_header_next(struct message_header_parser_ctx *ctx); |
97f8c00b8d4c
Better handling for multiline headers. Before we skipped headers larger than
Timo Sirainen <tss@iki.fi>
parents:
1038
diff
changeset
|
73 |
0 | 74 #endif |