/src/dovecot/src/lib/unicode-data.h
Line | Count | Source |
1 | | #ifndef UNICODE_DATA_H |
2 | | #define UNICODE_DATA_H |
3 | | |
4 | | #include "unicode-data-tables.h" |
5 | | |
6 | | static inline bool |
7 | | unicode_general_category_is_group(enum unicode_general_category gencat) |
8 | 0 | { |
9 | 0 | return ((gencat & 0x0f) == 0x00); |
10 | 0 | } Unexecuted instantiation: unichar.c:unicode_general_category_is_group Unexecuted instantiation: unicode-transform.c:unicode_general_category_is_group |
11 | | |
12 | | static inline const struct unicode_code_point_data * |
13 | | unicode_code_point_get_data(uint32_t cp) |
14 | 0 | { |
15 | 0 | unsigned int idx8 = cp >> 24; |
16 | 0 | unsigned int blk16 = unicode_code_points_index8[idx8]; |
17 | 0 | unsigned int idx16 = (blk16 << 8) + ((cp >> 16) & 0xFF); |
18 | 0 | unsigned int blk24 = unicode_code_points_index16[idx16]; |
19 | 0 | unsigned int idx24 = (blk24 << 8) + ((cp >> 8) & 0xFF); |
20 | 0 | unsigned int blk32 = unicode_code_points_index24[idx24]; |
21 | 0 | unsigned int idx32 = (blk32 << 8) + (cp & 0xFF); |
22 | 0 | unsigned int idxcp = unicode_code_points_index32[idx32]; |
23 | |
|
24 | 0 | return &unicode_code_points[idxcp]; |
25 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_get_data Unexecuted instantiation: unicode-transform.c:unicode_code_point_get_data |
26 | | |
27 | | static inline size_t |
28 | | unicode_code_point_data_get_first_decomposition( |
29 | | const struct unicode_code_point_data *cp_data, |
30 | | uint8_t *type_r, const uint32_t **decomp_r) |
31 | 0 | { |
32 | 0 | uint32_t offset; |
33 | 0 |
|
34 | 0 | if (type_r != NULL) |
35 | 0 | *type_r = cp_data->decomposition_type; |
36 | 0 | offset = cp_data->decomposition_first_offset; |
37 | 0 | *decomp_r = &unicode_decompositions[offset]; |
38 | 0 | return cp_data->decomposition_first_length; |
39 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_get_first_decomposition Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_get_first_decomposition |
40 | | |
41 | | static inline size_t |
42 | | unicode_code_point_data_get_full_decomposition( |
43 | | const struct unicode_code_point_data *cp_data, bool canonical, |
44 | | const uint32_t **decomp_r) |
45 | 0 | { |
46 | 0 | uint32_t offset; |
47 | |
|
48 | 0 | if (canonical) { |
49 | 0 | offset = cp_data->decomposition_full_offset; |
50 | 0 | *decomp_r = &unicode_decompositions[offset]; |
51 | 0 | return cp_data->decomposition_full_length; |
52 | 0 | } |
53 | 0 | offset = cp_data->decomposition_full_k_offset; |
54 | 0 | *decomp_r = &unicode_decompositions[offset]; |
55 | 0 | return cp_data->decomposition_full_k_length; |
56 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_get_full_decomposition Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_get_full_decomposition |
57 | | |
58 | | static inline uint32_t |
59 | | unicode_code_point_data_find_composition( |
60 | | const struct unicode_code_point_data *cp_data, uint32_t second) |
61 | 0 | { |
62 | 0 | const uint32_t *compositions = |
63 | 0 | &unicode_compositions[cp_data->composition_offset]; |
64 | 0 | size_t left_idx, right_idx; |
65 | |
|
66 | 0 | left_idx = 0; right_idx = cp_data->composition_count; |
67 | 0 | while (left_idx < right_idx) { |
68 | 0 | unsigned int idx = (left_idx + right_idx) / 2; |
69 | |
|
70 | 0 | if (second > compositions[idx]) |
71 | 0 | left_idx = idx + 1; |
72 | 0 | else if (second < compositions[idx]) |
73 | 0 | right_idx = idx; |
74 | 0 | else { |
75 | 0 | return unicode_composition_primaries[ |
76 | 0 | cp_data->composition_offset + idx]; |
77 | 0 | } |
78 | 0 | } |
79 | | |
80 | 0 | return 0x0000; |
81 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_find_composition Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_find_composition |
82 | | |
83 | | static inline size_t |
84 | | unicode_code_point_get_full_decomposition(uint32_t cp, bool canonical, |
85 | | const uint32_t **decomp_r) |
86 | 0 | { |
87 | 0 | const struct unicode_code_point_data *cp_data = |
88 | 0 | unicode_code_point_get_data(cp); |
89 | |
|
90 | 0 | return unicode_code_point_data_get_full_decomposition( |
91 | 0 | cp_data, canonical, decomp_r); |
92 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_get_full_decomposition Unexecuted instantiation: unicode-transform.c:unicode_code_point_get_full_decomposition |
93 | | |
94 | | static inline size_t |
95 | | unicode_code_point_data_get_uppercase_mapping( |
96 | | const struct unicode_code_point_data *cp_data, |
97 | | const uint32_t **map_r) |
98 | 0 | { |
99 | 0 | uint32_t offset; |
100 | |
|
101 | 0 | offset = cp_data->uppercase_mapping_offset; |
102 | 0 | *map_r = &unicode_case_mappings[offset]; |
103 | 0 | return cp_data->uppercase_mapping_length; |
104 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_get_uppercase_mapping Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_get_uppercase_mapping |
105 | | |
106 | | static inline size_t |
107 | | unicode_code_point_data_get_lowercase_mapping( |
108 | | const struct unicode_code_point_data *cp_data, |
109 | | const uint32_t **map_r) |
110 | 0 | { |
111 | 0 | uint32_t offset; |
112 | |
|
113 | 0 | offset = cp_data->lowercase_mapping_offset; |
114 | 0 | *map_r = &unicode_case_mappings[offset]; |
115 | 0 | return cp_data->lowercase_mapping_length; |
116 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_get_lowercase_mapping Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_get_lowercase_mapping |
117 | | |
118 | | static inline size_t |
119 | | unicode_code_point_data_get_casefold_mapping( |
120 | | const struct unicode_code_point_data *cp_data, |
121 | | const uint32_t **map_r) |
122 | 0 | { |
123 | 0 | uint32_t offset; |
124 | |
|
125 | 0 | offset = cp_data->casefold_mapping_offset; |
126 | 0 | *map_r = &unicode_case_mappings[offset]; |
127 | 0 | return cp_data->casefold_mapping_length; |
128 | 0 | } Unexecuted instantiation: unichar.c:unicode_code_point_data_get_casefold_mapping Unexecuted instantiation: unicode-transform.c:unicode_code_point_data_get_casefold_mapping |
129 | | |
130 | | uint8_t unicode_general_category_from_string(const char *str); |
131 | | |
132 | | #endif |