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
|
/* URL check functions */
#ifndef URL_H
#define URL_H
#include "config.h"
#include "mem_pool.h"
#include "fstring.h"
struct rspamd_task;
struct mime_text_part;
enum rspamd_url_flags {
RSPAMD_URL_FLAG_PHISHED = 1 << 0,
RSPAMD_URL_FLAG_NUMERIC = 1 << 1,
RSPAMD_URL_FLAG_OBSCURED = 1 << 2,
};
struct rspamd_url {
gchar *string;
gint protocol;
guint port;
gchar *user;
gchar *host;
gchar *data;
gchar *query;
gchar *fragment;
gchar *surbl;
gchar *tld;
struct rspamd_url *phished_url;
guint protocollen;
guint userlen;
guint hostlen;
guint datalen;
guint querylen;
guint fragmentlen;
guint surbllen;
guint tldlen;
guint urllen;
enum rspamd_url_flags flags;
};
enum uri_errno {
URI_ERRNO_OK = 0, /* Parsing went well */
URI_ERRNO_EMPTY, /* The URI string was empty */
URI_ERRNO_INVALID_PROTOCOL, /* No protocol was found */
URI_ERRNO_INVALID_PORT, /* Port number is bad */
URI_ERRNO_BAD_ENCODING, /* Bad characters encoding */
URI_ERRNO_BAD_FORMAT
};
enum rspamd_url_protocol {
PROTOCOL_FILE = 0,
PROTOCOL_FTP,
PROTOCOL_HTTP,
PROTOCOL_HTTPS,
PROTOCOL_MAILTO,
PROTOCOL_UNKNOWN
};
/**
* Initialize url library
* @param cfg
*/
void rspamd_url_init (const gchar *tld_file);
/*
* Parse urls inside text
* @param pool memory pool
* @param task task object
* @param part current text part
* @param is_html turn on html euristic
*/
void rspamd_url_text_extract (rspamd_mempool_t *pool,
struct rspamd_task *task,
struct mime_text_part *part,
gboolean is_html);
/*
* Parse a single url into an uri structure
* @param pool memory pool
* @param uristring text form of url
* @param uri url object, must be pre allocated
*/
enum uri_errno rspamd_url_parse (struct rspamd_url *uri,
gchar *uristring,
gsize len,
rspamd_mempool_t *pool);
/*
* Try to extract url from a text
* @param pool memory pool
* @param begin begin of text
* @param len length of text
* @param start storage for start position of url found (or NULL)
* @param end storage for end position of url found (or NULL)
* @param url_str storage for url string(or NULL)
* @return TRUE if url is found in specified text
*/
gboolean rspamd_url_find (rspamd_mempool_t *pool,
const gchar *begin,
gsize len,
const gchar **start,
const gchar **end,
gchar **url_str,
gboolean is_html,
gint *statep);
/*
* Return text representation of url parsing error
*/
const gchar * rspamd_url_strerror (enum uri_errno err);
/**
* Convenience routine to extract urls from an arbitrarty text
* @param pool
* @param start
* @param pos
* @return url or NULL
*/
struct rspamd_url *
rspamd_url_get_next (rspamd_mempool_t *pool,
const gchar *start, gchar const **pos, gint *statep);
/**
* Find TLD for a specified host string
* @param in input host
* @param inlen length of input
* @param out output rspamd_ftok_t with tld position
* @return TRUE if tld has been found
*/
gboolean rspamd_url_find_tld (const gchar *in, gsize inlen, rspamd_ftok_t *out);
#endif
|
