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
|
/*
* Copyright 2018, University Corporation for Atmospheric Research
* See netcdf/COPYRIGHT file for copying and redistribution conditions.
*/
#include "config.h"
#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef HAVE_STRING_H
#include <string.h>
#endif
#include "netcdf.h"
#include "ncutf8.h"
#include "utf8proc.h"
/* Provide a wrapper around whatever utf8 library we use. */
/*
* Check validity of a UTF8 encoded null-terminated byte string.
* Return codes:
* NC_NOERR -- string is valid utf8
* NC_ENOMEM -- out of memory
* NC_EINVAL -- invalid argument or internal error
* NC_EBADNAME-- not valid utf8
*/
int nc_utf8_validate(const unsigned char* name)
{
int ncstat = NC_NOERR;
const nc_utf8proc_uint8_t *str;
nc_utf8proc_ssize_t nchars = -1;
nc_utf8proc_int32_t codepoint;
nc_utf8proc_ssize_t count;
str = (const nc_utf8proc_uint8_t*)name;
while(*str) {
count = nc_utf8proc_iterate(str,nchars,&codepoint);
if(count < 0) {
switch (count) {
case UTF8PROC_ERROR_NOMEM:
case UTF8PROC_ERROR_OVERFLOW:
ncstat = NC_ENOMEM;
break;
case UTF8PROC_ERROR_INVALIDOPTS:
ncstat = NC_EINVAL;
break;
case UTF8PROC_ERROR_INVALIDUTF8:
case UTF8PROC_ERROR_NOTASSIGNED:
default:
ncstat = NC_EBADNAME;
break;
}
goto done;
} else { /* move to next char */
str += count;
}
}
done:
return ncstat;
}
/*
* Returns a pointer to newly allocated memory of a
* normalized version of the null-terminated string 'str'.
* Normalized string is returned in normalp argument;
* caller must free.
* Return codes:
* NC_NOERR -- success
* NC_ENOMEM -- out of memory
* NC_EINVAL -- illegal argument or internal error
* NC_EBADNAME -- other failure
*/
int
nc_utf8_normalize(const unsigned char* utf8, unsigned char** normalp)
{
int ncstat = NC_NOERR;
const nc_utf8proc_uint8_t* str = (const nc_utf8proc_uint8_t*)utf8;
nc_utf8proc_uint8_t* retval = NULL;
nc_utf8proc_ssize_t count;
count = nc_utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | UTF8PROC_COMPOSE);
if(count < 0) {/* error */
switch (count) {
case UTF8PROC_ERROR_NOMEM:
case UTF8PROC_ERROR_OVERFLOW:
ncstat = NC_ENOMEM;
break;
case UTF8PROC_ERROR_INVALIDOPTS:
ncstat = NC_EINVAL;
break;
case UTF8PROC_ERROR_INVALIDUTF8:
case UTF8PROC_ERROR_NOTASSIGNED:
default:
ncstat = NC_EBADNAME;
break;
}
goto done;
} else
if(normalp) *normalp = (unsigned char*)retval;
done:
return ncstat;
}
/*
* Convert a normalized utf8 string to utf16. This is approximate
* because it just does the truncation version of conversion for
* each 32-bit codepoint to get the corresponding utf16.
* Return codes:
* NC_NOERR -- success
* NC_ENOMEM -- out of memory
* NC_EINVAL -- invalid argument or internal error
* NC_EBADNAME-- not valid utf16
*/
int nc_utf8_to_utf16(const unsigned char* s8, unsigned short** utf16p, size_t* len16p)
{
int ncstat = NC_NOERR;
const nc_utf8proc_uint8_t *str;
nc_utf8proc_ssize_t nchars = -1;
nc_utf8proc_int32_t codepoint;
nc_utf8proc_ssize_t count;
size_t len8, len16;
unsigned short* utf16;
unsigned short* p16;
len8 = strlen((char*)s8);
utf16 = (unsigned short*)malloc(sizeof(unsigned short)*(len8+1));
if(utf16 == NULL) {
ncstat = NC_ENOMEM;
goto done;
}
str = (const nc_utf8proc_uint8_t*)s8;
/* Walk the string and convert each codepoint */
p16 = utf16;
len16 = 0;
while(*str) {
count = nc_utf8proc_iterate(str,nchars,&codepoint);
if(count < 0) {
switch (count) {
case UTF8PROC_ERROR_NOMEM:
case UTF8PROC_ERROR_OVERFLOW:
ncstat = NC_ENOMEM;
break;
case UTF8PROC_ERROR_INVALIDOPTS:
ncstat = NC_EINVAL;
break;
case UTF8PROC_ERROR_INVALIDUTF8:
case UTF8PROC_ERROR_NOTASSIGNED:
default:
ncstat = NC_EBADNAME;
break;
}
goto done;
} else { /* move to next char */
/* Complain if top 16 bits not zero */
if((codepoint & 0xFFFF0000) != 0) {
ncstat = NC_EBADNAME;
goto done;
}
/* Truncate codepoint to 16 bits and store */
*p16++ = (unsigned short)(codepoint & 0x0000FFFF);
str += count;
len16++;
}
}
*p16++ = (unsigned short)0;
if(utf16p)
*utf16p = utf16;
else
free(utf16);
if(len16p) *len16p = len16;
done:
if(ncstat) free(utf16);
return ncstat;
}
|
