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
|
/* Copyright (C) 2000 MySQL AB
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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */
#include "m_string.h"
#include "m_ctype.h"
/*
This files implements routines which parse XML based
character set and collation description files.
Unicode collations are encoded according to
Unicode Technical Standard #35
Locale Data Markup Language (LDML)
http://www.unicode.org/reports/tr35/
and converted into ICU string according to
Collation Customization
http://oss.software.ibm.com/icu/userguide/Collate_Customization.html
*/
struct my_cs_file_section_st
{
int state;
const char *str;
};
#define MY_CS_CSDESCR_SIZE 64
#define MY_CS_TAILORING_SIZE 1024
typedef struct my_cs_file_info
{
char csname[MY_CS_NAME_SIZE];
char name[MY_CS_NAME_SIZE];
unsigned char ctype[MY_CS_CTYPE_TABLE_SIZE];
unsigned char to_lower[MY_CS_TO_LOWER_TABLE_SIZE];
unsigned char to_upper[MY_CS_TO_UPPER_TABLE_SIZE];
unsigned char sort_order[MY_CS_SORT_ORDER_TABLE_SIZE];
uint16_t tab_to_uni[MY_CS_TO_UNI_TABLE_SIZE];
char comment[MY_CS_CSDESCR_SIZE];
char tailoring[MY_CS_TAILORING_SIZE];
size_t tailoring_length;
CHARSET_INFO cs;
int (*add_collation)(CHARSET_INFO *cs);
} MY_CHARSET_LOADER;
/*
Check repertoire: detect pure ascii strings
*/
uint
my_string_repertoire(const CHARSET_INFO * const cs, const char *str, ulong length)
{
const char *strend= str + length;
if (cs->mbminlen == 1)
{
for ( ; str < strend; str++)
{
if (((unsigned char) *str) > 0x7F)
return MY_REPERTOIRE_UNICODE30;
}
}
else
{
my_wc_t wc;
int chlen;
for (; (chlen= cs->cset->mb_wc(cs, &wc, (unsigned char *)str, (unsigned char *)strend)) > 0; str+= chlen)
{
if (wc > 0x7F)
return MY_REPERTOIRE_UNICODE30;
}
}
return MY_REPERTOIRE_ASCII;
}
/*
Detect whether a character set is ASCII compatible.
Returns true for:
- all 8bit character sets whose Unicode mapping of 0x7B is '{'
(ignores swe7 which maps 0x7B to "LATIN LETTER A WITH DIAERESIS")
- all multi-byte character sets having mbminlen == 1
(ignores ucs2 whose mbminlen is 2)
TODO:
When merging to 5.2, this function should be changed
to check a new flag MY_CS_NONASCII,
return (cs->flag & MY_CS_NONASCII) ? 0 : 1;
This flag was previously added into 5.2 under terms
of WL#3759 "Optimize identifier conversion in client-server protocol"
especially to mark character sets not compatible with ASCII.
We won't backport this flag to 5.0 or 5.1.
This function is Ok for 5.0 and 5.1, because we're not going
to introduce new tricky character sets between 5.0 and 5.2.
*/
bool
my_charset_is_ascii_based(const CHARSET_INFO * const cs)
{
return
(cs->mbmaxlen == 1 && cs->tab_to_uni && cs->tab_to_uni['{'] == '{') ||
(cs->mbminlen == 1 && cs->mbmaxlen > 1);
}
/*
Detect if a character set is 8bit,
and it is pure ascii, i.e. doesn't have
characters outside U+0000..U+007F
This functions is shared between "conf_to_src"
and dynamic charsets loader in "mysqld".
*/
bool
my_charset_is_8bit_pure_ascii(const CHARSET_INFO * const cs)
{
size_t code;
if (!cs->tab_to_uni)
return 0;
for (code= 0; code < 256; code++)
{
if (cs->tab_to_uni[code] > 0x7F)
return 0;
}
return 1;
}
/*
Shared function between conf_to_src and mysys.
Check if a 8bit character set is compatible with
ascii on the range 0x00..0x7F.
*/
bool
my_charset_is_ascii_compatible(const CHARSET_INFO * const cs)
{
uint32_t i;
if (!cs->tab_to_uni)
return 1;
for (i= 0; i < 128; i++)
{
if (cs->tab_to_uni[i] != i)
return 0;
}
return 1;
}
|