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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
|
/* This is part of the netCDF package.
Copyright 2006 University Corporation for Atmospheric Research/Unidata.
See COPYRIGHT file for conditions of use.
This is a very simple example which writes a netCDF file with
Unicode names encoded with UTF-8. It is the NETCDF3 equivalent
of tst_unicode.c
Russ Rew, Ed Hartnett
*/
#include <config.h>
#include <stdlib.h>
#include <nc_tests.h>
#include "err_macros.h"
#include <netcdf.h>
#include <string.h>
/* The data file we will create. */
#define FILE_NAME "tst_utf8.nc"
#define NDIMS 1
#define NX 18
#define ENUM_VALUE 2
#define BORING_NAME "boring"
/* (unnormalized) UTF-8 encoding for Unicode 8-character "Hello" in Greek */
char name_utf8[] = "\xCE\x9A\xCE\xB1\xCE\xBB\xCE\xB7\xCE\xBC\xE1\xBD\xB3\xCF\x81\xCE\xB1";
/* NFC normalized UTF-8 for Unicode 8-character "Hello" in Greek */
char norm_utf8[] = "\xCE\x9A\xCE\xB1\xCE\xBB\xCE\xB7\xCE\xBC\xCE\xAD\xCF\x81\xCE\xB1";
/* This is the struct for the compound type. */
struct comp {
int i;
};
/* Given an ncid, check the file to make sure it has all the objects I
* expect. */
int
check_nc4_file(int ncid)
{
int varid, dimid, attnum, grpid, grpid2, grpid3, numgrps;
int numtypes, enum_typeid, comp_typeid;
int class_in;
size_t att_len, size_in, num_mem, nfields_in;
nc_type att_type, base_type_in;
char name_in[NC_MAX_NAME + 1], strings_in[NC_MAX_NAME + 1], value;
/* Check the group. */
if (nc_inq_grps(ncid, &numgrps, &grpid)) ERR;
if (numgrps != 1) ERR;
name_in[0] = 0;
if (nc_inq_grpname(grpid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
/* Check the variable. */
if (nc_inq_varid(grpid, name_utf8, &varid)) ERR;
if (nc_inq_varname(grpid, varid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_inq_varid(grpid, norm_utf8, &varid)) ERR;
name_in[0] = 0;
if (nc_inq_varname(grpid, varid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_get_var(grpid, varid, strings_in)) ERR;
if (strncmp(name_utf8, strings_in, sizeof(name_utf8))) ERR;
strings_in[0] = '\0'; /* Reset my string buffer. */
/* Check the dimension. */
if (nc_inq_dimid(grpid, name_utf8, &dimid)) ERR;
if (nc_inq_dimname(grpid, dimid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_inq_dimid(grpid, norm_utf8, &dimid)) ERR;
if (nc_inq_dimname(grpid, dimid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
/* Check the attribute. We don't normalize data or attribute
* values, so get exactly what was put for the value, but
* normalized values for names. */
if (nc_inq_attid(grpid, varid, norm_utf8, &attnum)) ERR;
if (attnum) ERR;
attnum = 99; /* Reset. */
if (nc_inq_attid(grpid, varid, name_utf8, &attnum)) ERR;
if (attnum) ERR;
if (nc_inq_att(grpid, varid, norm_utf8, &att_type, &att_len)) ERR;
if (att_type != NC_CHAR || att_len != sizeof(name_utf8)) ERR;
if (nc_get_att_text(grpid, varid, norm_utf8, strings_in)) ERR;
if (strncmp(name_utf8, strings_in, sizeof(name_utf8))) ERR;
/* Check the enum type. */
if (nc_inq_grps(grpid, &numgrps, &grpid2)) ERR;
if (numgrps != 1) ERR;
if (nc_inq_typeids(grpid2, &numtypes, &enum_typeid)) ERR;
if (numtypes != 1) ERR;
if (nc_inq_user_type(grpid2, enum_typeid, name_in, &size_in, &base_type_in,
&nfields_in, &class_in)) ERR;
if (strncmp(norm_utf8, name_in, strlen(norm_utf8)) || size_in != 1 ||
base_type_in != NC_BYTE || nfields_in != 1 || class_in != NC_ENUM) ERR;
name_in[0] = size_in = base_type_in = 0;
if (nc_inq_enum(grpid2, enum_typeid, name_in, &base_type_in, &size_in, &num_mem)) ERR;
if (strncmp(norm_utf8, name_in, strlen(norm_utf8)) || size_in != 1 ||
base_type_in != NC_BYTE || num_mem != 1) ERR;
if (nc_inq_enum_member(grpid2, enum_typeid, 0, name_in, &value)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8)) || value != ENUM_VALUE) ERR;
/* Check the compound type. */
if (nc_inq_grps(grpid2, &numgrps, &grpid3)) ERR;
if (numgrps != 1) ERR;
if (nc_inq_typeids(grpid3, &numtypes, &comp_typeid)) ERR;
if (numtypes != 1) ERR;
name_in[0] = 0;
if (nc_inq_user_type(grpid3, comp_typeid, name_in, &size_in, &base_type_in,
&nfields_in, &class_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8)) || size_in != sizeof(struct comp) ||
base_type_in != NC_NAT || nfields_in != 1 || class_in != NC_COMPOUND) ERR;
size_in = nfields_in = 999;
if (nc_inq_compound(grpid3, comp_typeid, name_in, &size_in, &nfields_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8)) || size_in != sizeof(struct comp) ||
nfields_in != 1) ERR;
name_in[0] = 0;
if (nc_inq_compound_fieldname(grpid3, comp_typeid, 0, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
return NC_NOERR;
}
/* Given an ncid, check the file to make sure it has all the objects I
* expect. */
int
check_classic_file(int ncid)
{
int varid, dimid, attnum;
size_t att_len;
nc_type att_type;
char name_in[sizeof(name_utf8) + 1], strings_in[sizeof(name_utf8) + 1];
/* Check the variable. */
if (nc_inq_varid(ncid, name_utf8, &varid)) ERR;
if (nc_inq_varname(ncid, varid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_inq_varid(ncid, norm_utf8, &varid)) ERR;
name_in[0] = 0;
if (nc_inq_varname(ncid, varid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_get_var_text(ncid, varid, strings_in)) ERR;
if (strncmp(name_utf8, strings_in, sizeof(name_utf8))) ERR;
strings_in[0] = '\0'; /* Reset my string buffer. */
/* Check the dimension. */
if (nc_inq_dimid(ncid, name_utf8, &dimid)) ERR;
if (nc_inq_dimname(ncid, dimid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
if (nc_inq_dimid(ncid, norm_utf8, &dimid)) ERR;
if (nc_inq_dimname(ncid, dimid, name_in)) ERR;
if (strncmp(norm_utf8, name_in, sizeof(norm_utf8))) ERR;
/* Check the attribute. We don't normalize data or attribute
* values, so get exactly what was put for the value, but
* normalized values for names. */
if (nc_inq_attid(ncid, varid, norm_utf8, &attnum)) ERR;
if (attnum) ERR;
attnum = 99; /* Reset. */
if (nc_inq_attid(ncid, varid, name_utf8, &attnum)) ERR;
if (attnum) ERR;
if (nc_inq_att(ncid, varid, norm_utf8, &att_type, &att_len)) ERR;
if (att_type != NC_CHAR || att_len != sizeof(name_utf8)) ERR;
if (nc_get_att_text(ncid, varid, norm_utf8, strings_in)) ERR;
if (strncmp(name_utf8, strings_in, sizeof(name_utf8))) ERR;
return NC_NOERR;
}
int
main(int argc, char **argv)
{
printf("\n*** Testing UTF-8 names.\n");
printf("*** creating UTF-8 names in classic model netcdf files...");
{
int ncid, varid, dimids[NDIMS];
int f;
for (f = NC_FORMAT_CLASSIC; f < NC_FORMAT_NETCDF4_CLASSIC; f++)
{
if (nc_set_default_format(f, NULL)) ERR;
if (nc_create(FILE_NAME, NC_CLOBBER, &ncid)) ERR;
/* Define various netcdf objects with a Unicode UTF-8 encoded name
* that must be normalized. Where possible, also use the utf8
* string as the value. The name will be normalized, but not the
* value. */
if (nc_def_dim(ncid, name_utf8, NX, &dimids[0])) ERR;
if (nc_def_var(ncid, name_utf8, NC_CHAR, NDIMS, dimids, &varid)) ERR;
if (nc_put_att_text(ncid, varid, name_utf8, sizeof(name_utf8), name_utf8)) ERR;
if (nc_enddef(ncid)) ERR;
/* Write var data. */
if (nc_put_var_text(ncid, varid, name_utf8)) ERR;
/* Check the file. */
check_classic_file(ncid);
if (nc_close(ncid)) ERR;
/* Reopen the file and check again. */
if (nc_open(FILE_NAME, NC_NOWRITE, &ncid)) ERR;
check_classic_file(ncid);
if (nc_close(ncid)) ERR;
} /* next format */
}
SUMMARIZE_ERR;
#define DIM1_NAME "d1"
#define VAR1_NAME "v1"
#define ATT1_NAME "a1"
printf("*** renaming to UTF-8 names in classic model netcdf files...");
{
int ncid, varid, dimids[NDIMS];
int f;
for (f = NC_FORMAT_CLASSIC; f < NC_FORMAT_NETCDF4_CLASSIC; f++)
{
if (nc_set_default_format(f, NULL)) ERR;
if (nc_create(FILE_NAME, NC_CLOBBER, &ncid)) ERR;
/* Create objects. */
if (nc_def_dim(ncid, DIM1_NAME, NX, &dimids[0])) ERR;
if (nc_rename_dim(ncid, 0, name_utf8)) ERR;
if (nc_def_var(ncid, name_utf8, NC_CHAR, NDIMS, dimids, &varid)) ERR;
if (nc_put_att_text(ncid, varid, ATT1_NAME, sizeof(name_utf8), name_utf8)) ERR;
if (nc_rename_att(ncid, 0, ATT1_NAME, name_utf8)) ERR;
if (nc_enddef(ncid)) ERR;
/* Write var data. */
if (nc_put_var_text(ncid, varid, name_utf8)) ERR;
/* Check the file. */
check_classic_file(ncid);
if (nc_close(ncid)) ERR;
/* Reopen the file and check again. */
if (nc_open(FILE_NAME, NC_NOWRITE, &ncid)) ERR;
check_classic_file(ncid);
if (nc_close(ncid)) ERR;
} /* next format */
}
SUMMARIZE_ERR;
printf("*** creating UTF-8 names in netcdf-4 file...");
{
int ncid, varid, grpid, comp_typeid, enum_typeid, grpid2, grpid3;
int dimids[NDIMS];
char my_int = ENUM_VALUE;
if (nc_create(FILE_NAME, NC_NETCDF4 | NC_CLOBBER, &ncid)) ERR;
/* Define various netcdf objects with a Unicode UTF-8 encoded name
* that must be normalized. Where possible, also use the utf8
* string as the value. The name will be normalized, but not the
* value. */
if (nc_def_grp(ncid, name_utf8, &grpid)) ERR;
if (nc_def_dim(grpid, name_utf8, NX, &dimids[0])) ERR;
if (nc_def_var(grpid, name_utf8, NC_CHAR, NDIMS, dimids, &varid)) ERR;
if (nc_put_att_text(grpid, varid, name_utf8, sizeof(name_utf8), name_utf8)) ERR;
if (nc_def_grp(grpid, "tmp", &grpid2)) ERR;
if (nc_def_enum(grpid2, NC_BYTE, name_utf8, &enum_typeid)) ERR;
if (nc_insert_enum(grpid2, enum_typeid, name_utf8, &my_int)) ERR;
if (nc_def_grp(grpid2, "tmp", &grpid3)) ERR;
if (nc_def_compound(grpid3, sizeof(struct comp), name_utf8, &comp_typeid)) ERR;
if (nc_insert_compound(grpid3, comp_typeid, name_utf8, offsetof(struct comp, i), NC_INT)) ERR;
/* Write var data. */
if (nc_put_var_text(grpid, varid, name_utf8)) ERR;
/* Check the file. */
check_nc4_file(ncid);
if (nc_close(ncid)) ERR;
/* Reopen the file and check again. */
if (nc_open(FILE_NAME, NC_NOWRITE, &ncid)) ERR;
check_nc4_file(ncid);
if (nc_close(ncid)) ERR;
}
SUMMARIZE_ERR;
printf("*** ensuring UTF-8 normaization is applied in rename...");
{
int ncid, varid;
char name_in[NC_MAX_NAME + 1];
if (nc_create(FILE_NAME, NC_NETCDF4 | NC_CLOBBER, &ncid)) ERR;
if (nc_def_var(ncid, BORING_NAME, NC_CHAR, 0, NULL, &varid)) ERR;
if (nc_rename_var(ncid, varid, name_utf8)) ERR;
if (nc_inq_varname(ncid, 0, name_in)) ERR;
if (!strcmp(name_in, norm_utf8)) ERR;
if (nc_close(ncid)) ERR;
/* Reopen the file and check again. */
if (nc_open(FILE_NAME, NC_NOWRITE, &ncid)) ERR;
if (nc_inq_varname(ncid, 0, name_in)) ERR;
if (!strcmp(name_in, norm_utf8)) ERR;
if (nc_close(ncid)) ERR;
}
SUMMARIZE_ERR;
FINAL_RESULTS;
}
|
