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
|
#ifndef FTS_TOKENIZER_GENERIC_PRIVATE_H
#define FTS_TOKENIZER_GENERIC_PRIVATE_H
extern const struct fts_tokenizer_vfuncs generic_tokenizer_vfuncs_simple;
extern const struct fts_tokenizer_vfuncs generic_tokenizer_vfuncs_tr29;
/* Word boundary letter type */
enum letter_type {
LETTER_TYPE_NONE = 0,
LETTER_TYPE_CR,
LETTER_TYPE_LF,
LETTER_TYPE_NEWLINE,
LETTER_TYPE_EXTEND,
LETTER_TYPE_REGIONAL_INDICATOR,
LETTER_TYPE_FORMAT,
LETTER_TYPE_KATAKANA,
LETTER_TYPE_HEBREW_LETTER,
LETTER_TYPE_ALETTER,
LETTER_TYPE_SINGLE_QUOTE,
LETTER_TYPE_DOUBLE_QUOTE,
LETTER_TYPE_MIDNUMLET,
LETTER_TYPE_MIDLETTER,
LETTER_TYPE_MIDNUM,
LETTER_TYPE_NUMERIC,
LETTER_TYPE_EXTENDNUMLET,
LETTER_TYPE_SOT,
LETTER_TYPE_EOT,
LETTER_TYPE_APOSTROPHE, /* Own modification to TR29 */
LETTER_TYPE_PREFIXSPLAT, /* Dovecot '*' for glob-like explicit prefix searching */
LETTER_TYPE_OTHER /* WB14 "any" */
};
enum boundary_algorithm {
BOUNDARY_ALGORITHM_NONE = 0,
BOUNDARY_ALGORITHM_SIMPLE,
#define ALGORITHM_SIMPLE_NAME "simple"
BOUNDARY_ALGORITHM_TR29
#define ALGORITHM_TR29_NAME "tr29"
};
struct generic_fts_tokenizer {
struct fts_tokenizer tokenizer;
unsigned int max_length;
bool prefixsplat; /* for search strings, accept a trailing '*' for explicit prefix */
bool wb5a; /* TR29 rule for prefix separation
in e.g. French or Italian. */
bool seen_wb5a;
unichar_t prev_letter;
unichar_t letter;
enum boundary_algorithm algorithm;
enum letter_type prev_type;
enum letter_type prev_prev_type;
size_t untruncated_length;
buffer_t *token;
};
#endif
|
