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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
#ifndef CTYPE_UNIDATA_H_INCLUDED
#define CTYPE_UNIDATA_H_INCLUDED
/*
Copyright (c) 2018, 2023 MariaDB Corporation
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; version 2 of the License.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
extern const uint16 weight_general_ci_page00[256];
extern const uint16 *weight_general_ci_index[256];
extern const uint16 weight_general_mysql500_ci_page00[256];
extern const uint16 *weight_general_mysql500_ci_index[256];
extern const MY_CASEFOLD_CHARACTER u300_casefold_page00[256];
static inline my_wc_t my_u300_tolower_7bit(uchar ch)
{
return u300_casefold_page00[ch].tolower;
}
static inline my_wc_t my_u300_toupper_7bit(uchar ch)
{
return u300_casefold_page00[ch].toupper;
}
static inline my_wc_t my_general_ci_bmp_char_to_weight(my_wc_t wc)
{
const uint16 *page;
DBUG_ASSERT((wc >> 8) < array_elements(weight_general_ci_index));
page= weight_general_ci_index[wc >> 8];
return page ? page[wc & 0xFF] : wc;
}
static inline my_wc_t my_general_ci_char_to_weight(my_wc_t wc)
{
if ((wc >> 8) < array_elements(weight_general_ci_index))
return my_general_ci_bmp_char_to_weight(wc);
return MY_CS_REPLACEMENT_CHARACTER;
}
static inline my_wc_t my_general_mysql500_ci_bmp_char_to_weight(my_wc_t wc)
{
const uint16 *page;
DBUG_ASSERT((wc >> 8) < array_elements(weight_general_mysql500_ci_index));
page= weight_general_mysql500_ci_index[wc >> 8];
return page ? page[wc & 0xFF] : wc;
}
static inline void my_tosort_unicode_bmp(MY_CASEFOLD_INFO *uni_plane,
my_wc_t *wc)
{
const uint16 *page;
DBUG_ASSERT(*wc <= uni_plane->maxchar);
if ((page= uni_plane->simple_weight[*wc >> 8]))
*wc= page[*wc & 0xFF];
}
static inline void my_tosort_unicode(MY_CASEFOLD_INFO *uni_plane,
my_wc_t *wc)
{
if (*wc <= uni_plane->maxchar)
{
const uint16 *page;
if ((page= uni_plane->simple_weight[*wc >> 8]))
*wc= page[*wc & 0xFF];
}
else
{
*wc= MY_CS_REPLACEMENT_CHARACTER;
}
}
static inline void
my_tolower_unicode_bmp(MY_CASEFOLD_INFO *uni_plane, my_wc_t *wc)
{
const MY_CASEFOLD_CHARACTER *page;
DBUG_ASSERT(*wc <= uni_plane->maxchar);
if ((page= uni_plane->page[*wc >> 8]))
*wc= page[*wc & 0xFF].tolower;
}
static inline void
my_toupper_unicode_bmp(MY_CASEFOLD_INFO *uni_plane, my_wc_t *wc)
{
const MY_CASEFOLD_CHARACTER *page;
DBUG_ASSERT(*wc <= uni_plane->maxchar);
if ((page= uni_plane->page[*wc >> 8]))
*wc= page[*wc & 0xFF].toupper;
}
static inline void
my_tolower_unicode(MY_CASEFOLD_INFO *uni_plane, my_wc_t *wc)
{
if (*wc <= uni_plane->maxchar)
{
const MY_CASEFOLD_CHARACTER *page;
if ((page= uni_plane->page[(*wc >> 8)]))
*wc= page[*wc & 0xFF].tolower;
}
}
static inline void
my_toupper_unicode(MY_CASEFOLD_INFO *uni_plane, my_wc_t *wc)
{
if (*wc <= uni_plane->maxchar)
{
const MY_CASEFOLD_CHARACTER *page;
if ((page= uni_plane->page[(*wc >> 8)]))
*wc= page[*wc & 0xFF].toupper;
}
}
/*
Compare two characters for equality, according to the collation.
For simple Unicode AI CI collations, e.g. utf8mb4_general_ci.
@return TRUE if the two characters are equal
@return FALSE otherwise
*/
static inline my_bool
my_casefold_char_eq_general_ci(MY_CASEFOLD_INFO *casefold,
my_wc_t wc1, my_wc_t wc2)
{
DBUG_ASSERT(casefold->simple_weight);
my_tosort_unicode(casefold, &wc1);
my_tosort_unicode(casefold, &wc2);
return wc1 == wc2;
}
/*
Compare two characters for equality, according to the collation.
For simple Uncode AS CI collations, e.g. utf8mb4_general1400_as_ci.
@return TRUE if the two characters are equal
@return FALSE otherwise
*/
static inline my_bool
my_casefold_char_eq_general_as_ci(MY_CASEFOLD_INFO *casefold,
my_wc_t wc1, my_wc_t wc2)
{
my_toupper_unicode(casefold, &wc1);
my_toupper_unicode(casefold, &wc2);
return wc1 == wc2;
}
extern MY_CASEFOLD_INFO my_casefold_default;
extern MY_CASEFOLD_INFO my_casefold_turkish;
extern MY_CASEFOLD_INFO my_casefold_mysql500;
extern MY_CASEFOLD_INFO my_casefold_unicode520;
extern MY_CASEFOLD_INFO my_casefold_unicode1400;
extern MY_CASEFOLD_INFO my_casefold_unicode1400tr;
my_strnxfrm_pad_ret_t
my_strxfrm_pad_nweights_unicode_be2(uchar *str, uchar *strend,
size_t nweights);
size_t my_strxfrm_pad_unicode_be2(uchar *str, uchar *strend);
my_strnxfrm_pad_ret_t
my_strxfrm_pad_nweights_unicode_be3(uchar *str, uchar *strend,
size_t nweights);
size_t my_strxfrm_pad_unicode_be3(uchar *str, uchar *strend);
#define PUT_WC_BE2_HAVE_1BYTE(dst, de, wc) \
do { *dst++= (uchar) (wc >> 8); if (dst < de) *dst++= (uchar) (wc & 0xFF); } while(0)
#define PUT_WC_BE3_HAVE_1BYTE(dst, de, wc) \
do { *dst++= (uchar) (wc >> 16); \
if (dst < de) *dst++= (uchar) ((wc >> 8) & 0xFF);\
if (dst < de) *dst++= (uchar) (wc & 0xFF);\
} while(0)
#endif /* CTYPE_UNIDATA_H_INCLUDED */
|
