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
200
201
202
203
204
205
206
207
208
209
|
/***********************************************************************
Copyright (c) 2008 Innobase Oy. All rights reserved.
Copyright (c) 2008 Oracle. All rights reserved.
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 <ctype.h>
#ifdef HAVE_STRINGS_H
#include <strings.h>
#endif
#include "univ.i"
#include "ut0mem.h"
#include "api0ucode.h"
/**********************************************************************//**
@file api/api0ucode.c
Determines the connection character set.
@return connection character set */
UNIV_INTERN
const charset_t*
ib_ucode_get_connection_charset(void)
/*========-========================*/
{
return(NULL);
}
/**********************************************************************//**
Determines the character set based on id.
FIXME: If the id can't be found then what do we do, return some default ?
@return character set or NULL */
UNIV_INTERN
const charset_t*
ib_ucode_get_charset(
/*=================*/
ulint id) /*!< in: Charset-collation code */
{
return(NULL);
}
/******************************************************************//**
Get the variable length bounds of the given (multibyte) character set. */
UNIV_INTERN
void
ib_ucode_get_charset_width(
/*=======================*/
const charset_t*cs, /*!< in: Charset */
ulint* mbminlen, /*!< out: min len of a char (in bytes) */
ulint* mbmaxlen) /*!< out: max len of a char (in bytes) */
{
*mbminlen = *mbmaxlen = 0;
if (cs) {
//FIXME
//*mbminlen = charset_get_minlen(cs);
//*mbmaxlen = charset_get_maxlen(cs);
}
}
/******************************************************************//**
Compare two strings ignoring case.
@return 0 if equal */
int
ib_utf8_strcasecmp(
/*================*/
const char* p1, /*!< in: string to compare */
const char* p2) /*!< in: string to compare */
{
/* FIXME: Call the UTF-8 comparison function. */
/* FIXME: This should take cs as the parameter. */
return(strcasecmp(p1, p2));
}
/******************************************************************//**
Compare two strings ignoring case.
@return 0 if equal */
int
ib_utf8_strncasecmp(
/*=================*/
const char* p1, /*!< in: string to compare */
const char* p2, /*!< in: string to compare */
ulint len) /*!< in: length of string */
{
/* FIXME: Call the UTF-8 comparison function. */
/* FIXME: This should take cs as the parameter. */
/* FIXME: Which function? Note that this is locale-dependent.
For example, there is a capital dotted i and a lower-case
dotless I (U+0130 and U+0131, respectively). In many other
locales, I=i but not in Turkish. */
return(strncasecmp(p1, p2, len));
}
/******************************************************************//**
Makes all characters in a NUL-terminated UTF-8 string lower case. */
UNIV_INTERN
void
ib_utf8_casedown(
/*=============*/
char* a) /*!< in/out: str to put in lower case */
{
/* FIXME: Call the UTF-8 tolower() equivalent. */
/* FIXME: Is this function really needed? The proper
implementation is locale-dependent. In Turkish, the
lower-case counterpart of the upper-case I (U+0049, one byte)
is the dotless i (U+0131, two bytes in UTF-8). That cannot
even be converted in place. */
while (*a) {
*a = tolower(*a);
++a;
}
}
/******************************************************************//**
Converts an identifier to a table name. */
UNIV_INTERN
void
ib_utf8_convert_from_table_id(
/*==========================*/
const charset_t*cs, /*!< in: the 'from' character set */
char* to, /*!< out: converted identifier */
const char* from, /*!< in: identifier to convert */
ulint len) /*!< in: length of 'to', in bytes;
should be at least
5 * strlen(to) + 1 */
{
/* FIXME: why 5*strlen(to)+1? That is a relic from the MySQL
5.1 filename safe encoding that encodes some chars in
four-digit hexadecimal notation, such as @0023. Do we even
need this function? Could the files be named by table id or
something? */
/* FIXME: Call the UTF-8 equivalent */
strncpy(to, from, len);
}
/******************************************************************//**
Converts an identifier to UTF-8. */
UNIV_INTERN
void
ib_utf8_convert_from_id(
/*=====================*/
const charset_t*cs, /*!< in: the 'from' character set */
char* to, /*!< out: converted identifier */
const char* from, /*!< in: identifier to convert */
ulint len) /*!< in: length of 'to', in bytes;
should be at least
3 * strlen(to) + 1 */
{
/* FIXME: why 3*strlen(to)+1? I suppose that it comes from
MySQL, where the connection charset can be 8-bit, such as
the "latin1" (really Windows Code Page 1252). Converting
that to UTF-8 can take 1..3 characters per byte. */
/* FIXME: Do we even need this function? Can't we just assume
that the connection character encoding always is UTF-8? (We
may still want to support different collations for UTF-8.) */
/* FIXME: Call the UTF-8 equivalent */
strncpy(to, from, len);
}
/**********************************************************************//**
Test whether a UTF-8 character is a space or not.
@return TRUE if isspace(c) */
UNIV_INTERN
int
ib_utf8_isspace(
/*============*/
const charset_t*cs, /*!< in: charset */
char c) /*!< in: character to test */
{
/* FIXME: Call the equivalent UTF-8 function. */
/* FIXME: Do we really need this function? This is needed by
the InnoDB foreign key parser in MySQL, because U+00A0 is a
space in the MySQL connection charset latin1 but not in
utf8. */
return(isspace(c));
}
/******************************************************************//**
This function is used to find the storage length in bytes of the
characters that will fit into prefix_len bytes.
@return number of bytes required to copy the characters that will fit into prefix_len bytes. */
UNIV_INTERN
ulint
ib_ucode_get_storage_size(
/*======================*/
const charset_t*cs, /*!< in: character set */
ulint prefix_len, /*!< in: prefix length in bytes */
ulint str_len, /*!< in: length of the string in bytes */
const char* str) /*!< in: character string */
{
/* FIXME: Do we really need this function? Can't we assume
that all strings are UTF-8? (We still may want to support
different collations.) */
return(ut_min(prefix_len, str_len));
}
|
