1 /*
2 * Unicode utilities
3 *
4 * Copyright (c) 2017-2018 Fabrice Bellard
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to deal
8 * in the Software without restriction, including without limitation the rights
9 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
10 * copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in
14 * all copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
19 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
22 * THE SOFTWARE.
23 */
24 #ifndef LIBUNICODE_H
25 #define LIBUNICODE_H
26
27 #include <inttypes.h>
28
29 #define LRE_BOOL int /* for documentation purposes */
30
31 /* define it to include all the unicode tables (40KB larger) */
32 #define CONFIG_ALL_UNICODE
33
34 #define LRE_CC_RES_LEN_MAX 3
35
36 typedef enum {
37 UNICODE_NFC,
38 UNICODE_NFD,
39 UNICODE_NFKC,
40 UNICODE_NFKD,
41 } UnicodeNormalizationEnum;
42
43 int lre_case_conv(uint32_t *res, uint32_t c, int conv_type);
44 LRE_BOOL lre_is_cased(uint32_t c);
45 LRE_BOOL lre_is_case_ignorable(uint32_t c);
46
47 /* char ranges */
48
49 typedef struct {
50 int len; /* in points, always even */
51 int size;
52 uint32_t *points; /* points sorted by increasing value */
53 void *mem_opaque;
54 void *(*realloc_func)(void *opaque, void *ptr, size_t size);
55 } CharRange;
56
57 typedef enum {
58 CR_OP_UNION,
59 CR_OP_INTER,
60 CR_OP_XOR,
61 } CharRangeOpEnum;
62
63 void cr_init(CharRange *cr, void *mem_opaque, void *(*realloc_func)(void *opaque, void *ptr, size_t size));
64 void cr_free(CharRange *cr);
65 int cr_realloc(CharRange *cr, int size);
66 int cr_copy(CharRange *cr, const CharRange *cr1);
67
cr_add_point(CharRange * cr,uint32_t v)68 static inline int cr_add_point(CharRange *cr, uint32_t v)
69 {
70 if (cr->len >= cr->size) {
71 if (cr_realloc(cr, cr->len + 1))
72 return -1;
73 }
74 cr->points[cr->len++] = v;
75 return 0;
76 }
77
cr_add_interval(CharRange * cr,uint32_t c1,uint32_t c2)78 static inline int cr_add_interval(CharRange *cr, uint32_t c1, uint32_t c2)
79 {
80 if ((cr->len + 2) > cr->size) {
81 if (cr_realloc(cr, cr->len + 2))
82 return -1;
83 }
84 cr->points[cr->len++] = c1;
85 cr->points[cr->len++] = c2;
86 return 0;
87 }
88
89 int cr_union1(CharRange *cr, const uint32_t *b_pt, int b_len);
90
cr_union_interval(CharRange * cr,uint32_t c1,uint32_t c2)91 static inline int cr_union_interval(CharRange *cr, uint32_t c1, uint32_t c2)
92 {
93 uint32_t b_pt[2];
94 b_pt[0] = c1;
95 b_pt[1] = c2 + 1;
96 return cr_union1(cr, b_pt, 2);
97 }
98
99 int cr_op(CharRange *cr, const uint32_t *a_pt, int a_len,
100 const uint32_t *b_pt, int b_len, int op);
101
102 int cr_invert(CharRange *cr);
103
104 #ifdef CONFIG_ALL_UNICODE
105
106 LRE_BOOL lre_is_id_start(uint32_t c);
107 LRE_BOOL lre_is_id_continue(uint32_t c);
108
109 int unicode_normalize(uint32_t **pdst, const uint32_t *src, int src_len,
110 UnicodeNormalizationEnum n_type,
111 void *opaque, void *(*realloc_func)(void *opaque, void *ptr, size_t size));
112
113 /* Unicode character range functions */
114
115 int unicode_script(CharRange *cr,
116 const char *script_name, LRE_BOOL is_ext);
117 int unicode_general_category(CharRange *cr, const char *gc_name);
118 int unicode_prop(CharRange *cr, const char *prop_name);
119
120 #endif /* CONFIG_ALL_UNICODE */
121
122 #undef LRE_BOOL
123
124 #endif /* LIBUNICODE_H */
125