untested utf32_is_word_boundary() and associated table changes
[disorder] / lib / unidata.h
1 /* Automatically generated file, see scripts/make-unidata */
2 #ifndef UNIDATA_H
3 #define UNIDATA_H
4 enum unicode_gc_cat {
5 unicode_gc_Cc,
6 unicode_gc_Cf,
7 unicode_gc_Cn,
8 unicode_gc_Co,
9 unicode_gc_Cs,
10 unicode_gc_Ll,
11 unicode_gc_Lm,
12 unicode_gc_Lo,
13 unicode_gc_Lt,
14 unicode_gc_Lu,
15 unicode_gc_Mc,
16 unicode_gc_Me,
17 unicode_gc_Mn,
18 unicode_gc_Nd,
19 unicode_gc_Nl,
20 unicode_gc_No,
21 unicode_gc_Pc,
22 unicode_gc_Pd,
23 unicode_gc_Pe,
24 unicode_gc_Pf,
25 unicode_gc_Pi,
26 unicode_gc_Po,
27 unicode_gc_Ps,
28 unicode_gc_Sc,
29 unicode_gc_Sk,
30 unicode_gc_Sm,
31 unicode_gc_So,
32 unicode_gc_Zl,
33 unicode_gc_Zp,
34 unicode_gc_Zs
35 };
36 enum unicode_Word_Break {
37 unicode_Word_Break_ALetter,
38 unicode_Word_Break_Extend,
39 unicode_Word_Break_ExtendNumLet,
40 unicode_Word_Break_Format,
41 unicode_Word_Break_Katakana,
42 unicode_Word_Break_MidLetter,
43 unicode_Word_Break_MidNum,
44 unicode_Word_Break_Numeric,
45 unicode_Word_Break_Other
46 };
47 enum unicode_flags {
48 unicode_normalize_before_casefold = 1
49 };
50
51 struct unidata {
52 const uint32_t *compat;
53 const uint32_t *canon;
54 const uint32_t *casefold;
55 int16_t upper_offset;
56 int16_t lower_offset;
57 unsigned char ccc;
58 char gc;
59 uint8_t flags;
60 char word_break;
61 };
62 extern const struct unidata *const unidata[];
63 #define UNICODE_NCHARS 195200
64 #define UNICODE_MODULUS 128
65 #endif