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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
|
/*-------------------------------------------------------------------------
*
* ts_locale.c
* locale compatiblility layer for tsearch
*
* Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/tsearch/ts_locale.c,v 1.1 2007/08/21 01:11:18 tgl Exp $
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "tsearch/ts_locale.h"
#include "tsearch/ts_public.h"
#ifdef TS_USE_WIDE
#ifdef WIN32
size_t
wchar2char(char *to, const wchar_t *from, size_t len)
{
if (len == 0)
return 0;
if (GetDatabaseEncoding() == PG_UTF8)
{
int r;
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);
}
#endif /* WIN32 */
size_t
char2wchar(wchar_t *to, const char *from, size_t len)
{
if (len == 0)
return 0;
#ifdef WIN32
if (GetDatabaseEncoding() == PG_UTF8)
{
int r;
r = MultiByteToWideChar(CP_UTF8, 0, from, len, to, len);
if (!r)
{
pg_verifymbstr(from, len, 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;
}
else
#endif /* WIN32 */
if (lc_ctype_is_c())
{
/*
* pg_mb2wchar_with_len always adds trailing '\0', so 'to' should be
* allocated with sufficient space
*/
return pg_mb2wchar_with_len(from, (pg_wchar *) to, len);
}
else
{
/*
* mbstowcs require ending '\0'
*/
char *str = pnstrdup(from, len);
size_t tolen;
tolen = mbstowcs(to, str, len);
pfree(str);
return tolen;
}
}
int
_t_isalpha(const char *ptr)
{
wchar_t character[2];
if (lc_ctype_is_c())
return isalpha(TOUCHAR(ptr));
char2wchar(character, ptr, 1);
return iswalpha((wint_t) *character);
}
int
_t_isprint(const char *ptr)
{
wchar_t character[2];
if (lc_ctype_is_c())
return isprint(TOUCHAR(ptr));
char2wchar(character, ptr, 1);
return iswprint((wint_t) *character);
}
#endif /* TS_USE_WIDE */
/*
* Convert C-string from UTF8 to server encoding and
* lower it
*/
char *
recode_and_lowerstr(char *str)
{
char *recoded;
char *ret;
recoded = (char *) pg_do_encoding_conversion((unsigned char *) str, strlen(str),
PG_UTF8, GetDatabaseEncoding());
if (recoded == NULL)
elog(ERROR, "encoding conversion failed");
ret = lowerstr(recoded);
if (recoded != str)
pfree(recoded);
return ret;
}
char *
lowerstr(char *str)
{
return lowerstr_with_len(str, strlen(str));
}
char *
lowerstr_with_len(char *str, int len)
{
char *ptr = str;
char *out;
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("translation 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("translation 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 && ptr - str < len)
{
*outptr++ = tolower(*(unsigned char *) ptr);
ptr++;
}
*outptr = '\0';
}
return out;
}
|
