ObjFW  Diff

Differences From Artifact [208c62cea3]:

To Artifact [0efe0688a9]:

  • File src/OFString.h — part of check-in [545b6f740e] at 2013-01-13 13:07:52 on branch trunk — Add of_char{16,32}_t.

    For ObjC++, these are defined to char{16,32}_t if C++11 is used. This
    means passing e.g. a C++11 UTF-16 string to -[initWithUTF16String:]
    works without a warning.

    For C11, this is not necessary, as char{16,32}_t are just typedef'd to
    uint_least{16,32}_t in <uchar.h> and thus compatible to the definition
    of of_char{16,32}_t. The reason for not defining of_char{16,32}_t to
    char{16,32}_t when using C11 is that <uchar.h> might be missing and that
    char{16,32}_t are not required to be UTF-{16,32}, whereas in C++, they
    are required to be UTF-{16,32}. (user: js, size: 32041) [annotate] [blame] [check-ins using]


26
27
28
29
30
31
32







33
34
35
36
37
38
39
40

#import "OFObject.h"
#import "OFSerialization.h"
#import "OFJSONRepresentation.h"

@class OFConstantString;








typedef uint32_t of_unichar_t;

/*!
 * @brief The encoding of a string.
 */
typedef enum of_string_encoding_t {
	OF_STRING_ENCODING_UTF_8,
	OF_STRING_ENCODING_ASCII,







>
>
>
>
>
>
>
|







26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47

#import "OFObject.h"
#import "OFSerialization.h"
#import "OFJSONRepresentation.h"

@class OFConstantString;

#if defined(__cplusplus) && __cplusplus >= 201103L
typedef char16_t of_char16_t;
typedef char32_t of_char32_t;
#else
typedef uint_least16_t of_char16_t;
typedef uint_least32_t of_char32_t;
#endif
typedef of_char32_t of_unichar_t;

/*!
 * @brief The encoding of a string.
 */
typedef enum of_string_encoding_t {
	OF_STRING_ENCODING_UTF_8,
	OF_STRING_ENCODING_ASCII,
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

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string.
 *
 * @param string The UTF-16 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const uint16_t*)string;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string with the
 *	  specified length.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const uint16_t*)string
			       length: (size_t)length;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string, assuming the
 *	  specified byte order if no BOM is found.
 *
 * @param string The UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const uint16_t*)string
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string with the
 *	  specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const uint16_t*)string
			       length: (size_t)length
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string.
 *
 * @param string The UTF-32 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const uint32_t*)string;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string with the
 *	  specified length.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const uint32_t*)string
			       length: (size_t)length;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string, assuming the
 *	  specified byte order if no BOM is found.
 *
 * @param string The UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const uint32_t*)string
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string with the
 *	  specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const uint32_t*)string
			       length: (size_t)length
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a format string.
 *
 * See printf for the format syntax. As an addition, %@ is available as format







|









|










|












|









|









|










|












|







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

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string.
 *
 * @param string The UTF-16 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const of_char16_t*)string;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string with the
 *	  specified length.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const of_char16_t*)string
			       length: (size_t)length;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string, assuming the
 *	  specified byte order if no BOM is found.
 *
 * @param string The UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const of_char16_t*)string
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-16 encoded string with the
 *	  specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF16String: (const of_char16_t*)string
			       length: (size_t)length
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string.
 *
 * @param string The UTF-32 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const of_char32_t*)string;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string with the
 *	  specified length.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const of_char32_t*)string
			       length: (size_t)length;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string, assuming the
 *	  specified byte order if no BOM is found.
 *
 * @param string The UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const of_char32_t*)string
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a UTF-32 encoded string with the
 *	  specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return A new autoreleased OFString
 */
+ (instancetype)stringWithUTF32String: (const of_char32_t*)string
			       length: (size_t)length
			    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Creates a new OFString from a format string.
 *
 * See printf for the format syntax. As an addition, %@ is available as format
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string.
 *
 * @param string The UTF-16 string
 * @return An initialized OFString
 */
- initWithUTF16String: (const uint16_t*)string;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string with
 *	  the specified length.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @return An initialized OFString
 */
- initWithUTF16String: (const uint16_t*)string
	       length: (size_t)length;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string,
 *	  assuming the specified byte order if no BOM is found.
 *
 * @param string The UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF16String: (const uint16_t*)string
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string with
 *	  the specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF16String: (const uint16_t*)string
	       length: (size_t)length
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string.
 *
 * @param string The UTF-32 string
 * @return An initialized OFString
 */
- initWithUTF32String: (const uint32_t*)string;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string with
 *	  the specified length
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @return An initialized OFString
 */
- initWithUTF32String: (const uint32_t*)string
	       length: (size_t)length;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string,
 *	  assuming the specified byte order if no BOM is found.
 *
 * @param string The UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF32String: (const uint32_t*)string
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string with
 *	  the specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF32String: (const uint32_t*)string
	       length: (size_t)length
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a format string.
 *
 * See printf for the format syntax. As an addition, %@ is available as format







|









|










|












|









|









|










|












|







386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string.
 *
 * @param string The UTF-16 string
 * @return An initialized OFString
 */
- initWithUTF16String: (const of_char16_t*)string;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string with
 *	  the specified length.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @return An initialized OFString
 */
- initWithUTF16String: (const of_char16_t*)string
	       length: (size_t)length;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string,
 *	  assuming the specified byte order if no BOM is found.
 *
 * @param string The UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF16String: (const of_char16_t*)string
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-16 string with
 *	  the specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-16 string
 * @param length The length of the UTF-16 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF16String: (const of_char16_t*)string
	       length: (size_t)length
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string.
 *
 * @param string The UTF-32 string
 * @return An initialized OFString
 */
- initWithUTF32String: (const of_char32_t*)string;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string with
 *	  the specified length
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @return An initialized OFString
 */
- initWithUTF32String: (const of_char32_t*)string
	       length: (size_t)length;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string,
 *	  assuming the specified byte order if no BOM is found.
 *
 * @param string The UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF32String: (const of_char32_t*)string
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a UTF-32 string with
 *	  the specified length, assuming the specified byte order if no BOM is
 *	  found.
 *
 * @param string The UTF-32 string
 * @param length The length of the UTF-32 string
 * @param byteOrder The byte order to assume if there is no BOM
 * @return An initialized OFString
 */
- initWithUTF32String: (const of_char32_t*)string
	       length: (size_t)length
	    byteOrder: (of_byte_order_t)byteOrder;

/*!
 * @brief Initializes an already allocated OFString with a format string.
 *
 * See printf for the format syntax. As an addition, %@ is available as format
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @return The string in UTF-16 encoding with native byte order
 */
- (const uint16_t*)UTF16String OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the string in UTF-16 encoding with the specified byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @param byteOrder The byte order for the UTF-16 encoding
 * @return The string in UTF-16 encoding with the specified byte order
 */
- (const uint16_t*)UTF16StringWithByteOrder: (of_byte_order_t)byteOrder
    OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the length of the string in UTF-16 characters.
 *
 * @return The length of string in UTF-16 characters
 */
- (size_t)UTF16StringLength;

/*!
 * @brief Returns the string in UTF-32 encoding with native byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @return The string in UTF-32 encoding with native byte order
 */
- (const of_unichar_t*)UTF32String OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the string in UTF-32 encoding with the specified byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @param byteOrder The byte order for the UTF-32 encoding
 * @return The string in UTF-32 encoding with the specified byte order
 */
- (const of_unichar_t*)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder
    OF_RETURNS_INNER_POINTER;

/*!
 * @brief Writes the string into the specified file using UTF-8 encoding.
 *
 * @param path The path of the file to write to
 */







|











|


















|











|







952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @return The string in UTF-16 encoding with native byte order
 */
- (const of_char16_t*)UTF16String OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the string in UTF-16 encoding with the specified byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @param byteOrder The byte order for the UTF-16 encoding
 * @return The string in UTF-16 encoding with the specified byte order
 */
- (const of_char16_t*)UTF16StringWithByteOrder: (of_byte_order_t)byteOrder
    OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the length of the string in UTF-16 characters.
 *
 * @return The length of string in UTF-16 characters
 */
- (size_t)UTF16StringLength;

/*!
 * @brief Returns the string in UTF-32 encoding with native byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @return The string in UTF-32 encoding with native byte order
 */
- (const of_char32_t*)UTF32String OF_RETURNS_INNER_POINTER;

/*!
 * @brief Returns the string in UTF-32 encoding with the specified byte order.
 *
 * The result is valid until the autorelease pool is released. If you want to
 * use the result outside the scope of the current autorelease pool, you have to
 * copy it.
 *
 * @param byteOrder The byte order for the UTF-32 encoding
 * @return The string in UTF-32 encoding with the specified byte order
 */
- (const of_char32_t*)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder
    OF_RETURNS_INNER_POINTER;

/*!
 * @brief Writes the string into the specified file using UTF-8 encoding.
 *
 * @param path The path of the file to write to
 */
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
#endif

#ifdef __cplusplus
extern "C" {
#endif
extern size_t of_string_utf8_encode(of_unichar_t, char*);
extern size_t of_string_utf8_decode(const char*, size_t, of_unichar_t*);
extern size_t of_string_utf16_length(const uint16_t*);
extern size_t of_string_utf32_length(const uint32_t*);
#ifdef __cplusplus
}
#endif







|
|



1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
#endif

#ifdef __cplusplus
extern "C" {
#endif
extern size_t of_string_utf8_encode(of_unichar_t, char*);
extern size_t of_string_utf8_decode(const char*, size_t, of_unichar_t*);
extern size_t of_string_utf16_length(const of_char16_t*);
extern size_t of_string_utf32_length(const of_char32_t*);
#ifdef __cplusplus
}
#endif