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
|
#include "ts_locale.h"
#include "utils/builtins.h"
#include "utils/pg_locale.h"
#include "mb/pg_wchar.h"
#ifdef TS_USE_WIDE
#ifdef WIN32
size_t
wchar2char(char *to, const wchar_t *from, size_t len)
{
if (GetDatabaseEncoding() == PG_UTF8)
{
int r;
if (len == 0)
return 0;
r = WideCharToMultiByte(CP_UTF8, 0, from, -1, to, len,
NULL, NULL);
if (r == 0)
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("UTF-16 to UTF-8 translation failed: %lu",
GetLastError())));
Assert(r <= len);
return r;
}
return wcstombs(to, from, len);
}
size_t
char2wchar(wchar_t *to, const char *from, size_t len)
{
if (GetDatabaseEncoding() == PG_UTF8)
{
int r;
if (len == 0)
return 0;
r = MultiByteToWideChar(CP_UTF8, 0, from, len, to, len);
if (!r)
{
pg_verifymbstr(from, strlen(from), false);
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("invalid multibyte character for locale"),
errhint("The server's LC_CTYPE locale is probably incompatible with the database encoding.")));
}
Assert(r <= len);
return r;
}
return mbstowcs(to, from, len);
}
#endif /* WIN32 */
int
_t_isalpha(const char *ptr)
{
wchar_t character;
char2wchar(&character, ptr, 1);
return iswalpha((wint_t) character);
}
int
_t_isprint(const char *ptr)
{
wchar_t character;
char2wchar(&character, ptr, 1);
return iswprint((wint_t) character);
}
#endif /* TS_USE_WIDE */
char *
lowerstr(char *str)
{
char *ptr = str;
char *out;
int len = strlen(str);
if ( len == 0 )
return pstrdup("");
#ifdef TS_USE_WIDE
/*
* Use wide char code only when max encoding length > 1 and ctype != C.
* Some operating systems fail with multi-byte encodings and a C locale.
* Also, for a C locale there is no need to process as multibyte. From
* backend/utils/adt/oracle_compat.c Teodor
*/
if (pg_database_encoding_max_length() > 1 && !lc_ctype_is_c())
{
wchar_t *wstr,
*wptr;
int wlen;
/*
*alloc number of wchar_t for worst case, len contains
* number of bytes <= number of characters and
* alloc 1 wchar_t for 0, because wchar2char(wcstombs in really)
* wants zero-terminated string
*/
wptr = wstr = (wchar_t *) palloc(sizeof(wchar_t) * (len+1));
/*
* str SHOULD be cstring, so wlen contains number
* of converted character
*/
wlen = char2wchar(wstr, str, len);
if ( wlen < 0 )
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("transalation failed from server encoding to wchar_t")));
Assert(wlen<=len);
wstr[wlen] = 0;
while (*wptr)
{
*wptr = towlower((wint_t) *wptr);
wptr++;
}
/*
* Alloc result string for worst case + '\0'
*/
len = sizeof(char)*pg_database_encoding_max_length()*(wlen+1);
out = (char*)palloc(len);
/*
* wlen now is number of bytes which is always >= number of characters
*/
wlen = wchar2char(out, wstr, len);
pfree(wstr);
if ( wlen < 0 )
ereport(ERROR,
(errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE),
errmsg("transalation failed from wchar_t to server encoding %d", errno)));
Assert(wlen<=len);
out[wlen]='\0';
}
else
#endif
{
char *outptr;
outptr = out = (char*)palloc( sizeof(char) * (len+1) );
while (*ptr)
{
*outptr++ = tolower(*(unsigned char *) ptr);
ptr++;
}
*outptr = '\0';
}
return out;
}
|
