ObjFW  Diff

Differences From Artifact [0d15ab4aab]:

To Artifact [18e27cfd00]:


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

#ifdef OF_HAVE_SYS_TYPES_H
# include <sys/types.h>
#endif

#import "OFUTF8String.h"
#import "OFUTF8String+Private.h"

#import "OFArray.h"
#import "OFData.h"
#import "OFMutableUTF8String.h"

#import "OFInitializationFailedException.h"
#import "OFInvalidArgumentException.h"
#import "OFInvalidEncodingException.h"
#import "OFInvalidFormatException.h"
#import "OFOutOfMemoryException.h"
#import "OFOutOfRangeException.h"

#import "of_asprintf.h"
#import "unicode.h"

extern const of_char16_t of_iso_8859_2_table[];
extern const size_t of_iso_8859_2_table_offset;
extern const of_char16_t of_iso_8859_3_table[];
extern const size_t of_iso_8859_3_table_offset;
extern const of_char16_t of_iso_8859_15_table[];
extern const size_t of_iso_8859_15_table_offset;
extern const of_char16_t of_windows_1251_table[];
extern const size_t of_windows_1251_table_offset;
extern const of_char16_t of_windows_1252_table[];
extern const size_t of_windows_1252_table_offset;
extern const of_char16_t of_codepage_437_table[];
extern const size_t of_codepage_437_table_offset;
extern const of_char16_t of_codepage_850_table[];
extern const size_t of_codepage_850_table_offset;
extern const of_char16_t of_codepage_858_table[];
extern const size_t of_codepage_858_table_offset;
extern const of_char16_t of_mac_roman_table[];
extern const size_t of_mac_roman_table_offset;
extern const of_char16_t of_koi8_r_table[];
extern const size_t of_koi8_r_table_offset;
extern const of_char16_t of_koi8_u_table[];
extern const size_t of_koi8_u_table_offset;

static inline int
memcasecmp(const char *first, const char *second, size_t length)
{
	for (size_t i = 0; i < length; i++) {
		unsigned char f = first[i];
		unsigned char s = second[i];

		f = of_ascii_toupper(f);
		s = of_ascii_toupper(s);

		if (f > s)
			return OF_ORDERED_DESCENDING;
		if (f < s)
			return OF_ORDERED_ASCENDING;
	}

	return OF_ORDERED_SAME;
}

int
of_string_utf8_check(const char *UTF8String, size_t UTF8Length, size_t *length)
{
	size_t tmpLength = UTF8Length;
	int isUTF8 = 0;

	for (size_t i = 0; i < UTF8Length; i++) {
		/* No sign of UTF-8 here */
		if OF_LIKELY (!(UTF8String[i] & 0x80))







>











<


|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|








|
|


|

|


|



|







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

#ifdef OF_HAVE_SYS_TYPES_H
# include <sys/types.h>
#endif

#import "OFUTF8String.h"
#import "OFUTF8String+Private.h"
#import "OFASPrintF.h"
#import "OFArray.h"
#import "OFData.h"
#import "OFMutableUTF8String.h"

#import "OFInitializationFailedException.h"
#import "OFInvalidArgumentException.h"
#import "OFInvalidEncodingException.h"
#import "OFInvalidFormatException.h"
#import "OFOutOfMemoryException.h"
#import "OFOutOfRangeException.h"


#import "unicode.h"

extern const OFChar16 OFISO8859_2Table[];
extern const size_t OFISO8859_2TableOffset;
extern const OFChar16 OFISO8859_3Table[];
extern const size_t OFISO8859_3TableOffset;
extern const OFChar16 OFISO8859_15Table[];
extern const size_t OFISO8859_15TableOffset;
extern const OFChar16 OFWindows1251Table[];
extern const size_t OFWindows1251TableOffset;
extern const OFChar16 OFWindows1252Table[];
extern const size_t OFWindows1252TableOffset;
extern const OFChar16 OFCodepage437Table[];
extern const size_t OFCodepage437TableOffset;
extern const OFChar16 OFCodepage850Table[];
extern const size_t OFCodepage850TableOffset;
extern const OFChar16 OFCodepage858Table[];
extern const size_t OFCodepage858TableOffset;
extern const OFChar16 OFMacRomanTable[];
extern const size_t OFMacRomanTableOffset;
extern const OFChar16 OFKOI8RTable[];
extern const size_t OFKOI8RTableOffset;
extern const OFChar16 OFKOI8UTable[];
extern const size_t OFKOI8UTableOffset;

static inline int
memcasecmp(const char *first, const char *second, size_t length)
{
	for (size_t i = 0; i < length; i++) {
		unsigned char f = first[i];
		unsigned char s = second[i];

		f = OFASCIIToUpper(f);
		s = OFASCIIToUpper(s);

		if (f > s)
			return OFOrderedDescending;
		if (f < s)
			return OFOrderedAscending;
	}

	return OFOrderedSame;
}

int
OFUTF8StringCheck(const char *UTF8String, size_t UTF8Length, size_t *length)
{
	size_t tmpLength = UTF8Length;
	int isUTF8 = 0;

	for (size_t i = 0; i < UTF8Length; i++) {
		/* No sign of UTF-8 here */
		if OF_LIKELY (!(UTF8String[i] & 0x80))
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
	if (length != NULL)
		*length = tmpLength;

	return isUTF8;
}

size_t
of_string_utf8_get_index(const char *string, size_t position)
{
	size_t idx = position;

	for (size_t i = 0; i < position; i++)
		if OF_UNLIKELY ((string[i] & 0xC0) == 0x80)
			idx--;

	return idx;
}

size_t
of_string_utf8_get_position(const char *string, size_t idx, size_t length)
{
	for (size_t i = 0; i <= idx; i++)
		if OF_UNLIKELY ((string[i] & 0xC0) == 0x80)
			if (++idx > length)
				@throw [OFInvalidFormatException exception];

	return idx;
}

@implementation OFUTF8String
- (instancetype)init
{
	self = [super init];

	@try {
		_s = &_storage;

		_s->cString = of_alloc_zeroed(1, 1);
		_s->freeWhenDone = true;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;







|











|

















|







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
	if (length != NULL)
		*length = tmpLength;

	return isUTF8;
}

size_t
positionToIndex(const char *string, size_t position)
{
	size_t idx = position;

	for (size_t i = 0; i < position; i++)
		if OF_UNLIKELY ((string[i] & 0xC0) == 0x80)
			idx--;

	return idx;
}

size_t
OFUTF8StringIndexToPosition(const char *string, size_t idx, size_t length)
{
	for (size_t i = 0; i <= idx; i++)
		if OF_UNLIKELY ((string[i] & 0xC0) == 0x80)
			if (++idx > length)
				@throw [OFInvalidFormatException exception];

	return idx;
}

@implementation OFUTF8String
- (instancetype)init
{
	self = [super init];

	@try {
		_s = &_storage;

		_s->cString = OFAllocZeroedMemory(1, 1);
		_s->freeWhenDone = true;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
		}

		_s = &_storage;

		_s->cString = storage;
		_s->cStringLength = UTF8StringLength;

		switch (of_string_utf8_check(UTF8String, UTF8StringLength,
		    &_s->length)) {
		case 1:
			_s->isUTF8 = true;
			break;
		case -1:
			@throw [OFInvalidEncodingException exception];
		}

		memcpy(_s->cString, UTF8String, UTF8StringLength);
		_s->cString[UTF8StringLength] = 0;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithCString: (const char *)cString
		       encoding: (of_string_encoding_t)encoding
			 length: (size_t)cStringLength
{
	self = [super init];

	@try {
		const of_char16_t *table;
		size_t tableOffset, j;

		if (encoding == OF_STRING_ENCODING_UTF_8 &&
		    cStringLength >= 3 &&
		    memcmp(cString, "\xEF\xBB\xBF", 3) == 0) {
			cString += 3;
			cStringLength -= 3;
		}

		_s = &_storage;

		_s->cString = of_alloc(cStringLength + 1, 1);
		_s->cStringLength = cStringLength;
		_s->freeWhenDone = true;

		if (encoding == OF_STRING_ENCODING_UTF_8 ||
		    encoding == OF_STRING_ENCODING_ASCII) {
			switch (of_string_utf8_check(cString, cStringLength,
			    &_s->length)) {
			case 1:
				if (encoding == OF_STRING_ENCODING_ASCII)
					@throw [OFInvalidEncodingException
					    exception];

				_s->isUTF8 = true;
				break;
			case -1:
				@throw [OFInvalidEncodingException exception];
			}

			memcpy(_s->cString, cString, cStringLength);
			_s->cString[cStringLength] = 0;

			return self;
		}

		/* All other encodings we support are single byte encodings */
		_s->length = cStringLength;

		if (encoding == OF_STRING_ENCODING_ISO_8859_1) {
			j = 0;
			for (size_t i = 0; i < cStringLength; i++) {
				char buffer[4];
				size_t bytes;

				if (!(cString[i] & 0x80)) {
					_s->cString[j++] = cString[i];
					continue;
				}

				_s->isUTF8 = true;
				bytes = of_string_utf8_encode(
				    (uint8_t)cString[i], buffer);

				if (bytes == 0)
					@throw [OFInvalidEncodingException
					    exception];

				_s->cStringLength += bytes - 1;
				_s->cString = of_realloc(_s->cString,
				    _s->cStringLength + 1, 1);

				memcpy(_s->cString + j, buffer, bytes);
				j += bytes;
			}

			_s->cString[_s->cStringLength] = 0;

			return self;
		}

		switch (encoding) {
#define CASE(encoding, var)				\
		case encoding:				\
			table = var;			\
			tableOffset = var##_offset;	\
			break;
#ifdef HAVE_ISO_8859_2
		CASE(OF_STRING_ENCODING_ISO_8859_2, of_iso_8859_2_table)
#endif
#ifdef HAVE_ISO_8859_3
		CASE(OF_STRING_ENCODING_ISO_8859_3, of_iso_8859_3_table)
#endif
#ifdef HAVE_ISO_8859_15
		CASE(OF_STRING_ENCODING_ISO_8859_15, of_iso_8859_15_table)
#endif
#ifdef HAVE_WINDOWS_1251
		CASE(OF_STRING_ENCODING_WINDOWS_1251, of_windows_1251_table)
#endif
#ifdef HAVE_WINDOWS_1252
		CASE(OF_STRING_ENCODING_WINDOWS_1252, of_windows_1252_table)
#endif
#ifdef HAVE_CODEPAGE_437
		CASE(OF_STRING_ENCODING_CODEPAGE_437, of_codepage_437_table)
#endif
#ifdef HAVE_CODEPAGE_850
		CASE(OF_STRING_ENCODING_CODEPAGE_850, of_codepage_850_table)
#endif
#ifdef HAVE_CODEPAGE_858
		CASE(OF_STRING_ENCODING_CODEPAGE_858, of_codepage_858_table)
#endif
#ifdef HAVE_MAC_ROMAN
		CASE(OF_STRING_ENCODING_MAC_ROMAN, of_mac_roman_table)
#endif
#ifdef HAVE_KOI8_R
		CASE(OF_STRING_ENCODING_KOI8_R, of_koi8_r_table)
#endif
#ifdef HAVE_KOI8_U
		CASE(OF_STRING_ENCODING_KOI8_U, of_koi8_u_table)
#endif
#undef CASE
		default:
			@throw [OFInvalidEncodingException exception];
		}

		j = 0;
		for (size_t i = 0; i < cStringLength; i++) {
			unsigned char character = (unsigned char)cString[i];
			of_unichar_t unichar;
			char buffer[4];
			size_t byteLength;

			if (character < tableOffset) {
				_s->cString[j++] = cString[i];
				continue;
			}

			unichar = table[character - tableOffset];

			if (unichar == 0xFFFF)
				@throw [OFInvalidEncodingException exception];

			_s->isUTF8 = true;
			byteLength = of_string_utf8_encode(unichar, buffer);

			if (byteLength == 0)
				@throw [OFInvalidEncodingException exception];

			_s->cStringLength += byteLength - 1;
			_s->cString = of_realloc(_s->cString,
			    _s->cStringLength + 1, 1);

			memcpy(_s->cString + j, buffer, byteLength);
			j += byteLength;
		}

		_s->cString[_s->cStringLength] = 0;







|



















|





|


|








|



|
|
|


|


















|











|







|















|


|


|


|


|


|


|


|


|


|


|


|









|














|





|







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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
		}

		_s = &_storage;

		_s->cString = storage;
		_s->cStringLength = UTF8StringLength;

		switch (OFUTF8StringCheck(UTF8String, UTF8StringLength,
		    &_s->length)) {
		case 1:
			_s->isUTF8 = true;
			break;
		case -1:
			@throw [OFInvalidEncodingException exception];
		}

		memcpy(_s->cString, UTF8String, UTF8StringLength);
		_s->cString[UTF8StringLength] = 0;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithCString: (const char *)cString
		       encoding: (OFStringEncoding)encoding
			 length: (size_t)cStringLength
{
	self = [super init];

	@try {
		const OFChar16 *table;
		size_t tableOffset, j;

		if (encoding == OFStringEncodingUTF8 &&
		    cStringLength >= 3 &&
		    memcmp(cString, "\xEF\xBB\xBF", 3) == 0) {
			cString += 3;
			cStringLength -= 3;
		}

		_s = &_storage;

		_s->cString = OFAllocMemory(cStringLength + 1, 1);
		_s->cStringLength = cStringLength;
		_s->freeWhenDone = true;

		if (encoding == OFStringEncodingUTF8 ||
		    encoding == OFStringEncodingASCII) {
			switch (OFUTF8StringCheck(cString, cStringLength,
			    &_s->length)) {
			case 1:
				if (encoding == OFStringEncodingASCII)
					@throw [OFInvalidEncodingException
					    exception];

				_s->isUTF8 = true;
				break;
			case -1:
				@throw [OFInvalidEncodingException exception];
			}

			memcpy(_s->cString, cString, cStringLength);
			_s->cString[cStringLength] = 0;

			return self;
		}

		/* All other encodings we support are single byte encodings */
		_s->length = cStringLength;

		if (encoding == OFStringEncodingISO8859_1) {
			j = 0;
			for (size_t i = 0; i < cStringLength; i++) {
				char buffer[4];
				size_t bytes;

				if (!(cString[i] & 0x80)) {
					_s->cString[j++] = cString[i];
					continue;
				}

				_s->isUTF8 = true;
				bytes = OFUTF8StringEncode(
				    (uint8_t)cString[i], buffer);

				if (bytes == 0)
					@throw [OFInvalidEncodingException
					    exception];

				_s->cStringLength += bytes - 1;
				_s->cString = OFResizeMemory(_s->cString,
				    _s->cStringLength + 1, 1);

				memcpy(_s->cString + j, buffer, bytes);
				j += bytes;
			}

			_s->cString[_s->cStringLength] = 0;

			return self;
		}

		switch (encoding) {
#define CASE(encoding, var)				\
		case encoding:				\
			table = var;			\
			tableOffset = var##Offset;	\
			break;
#ifdef HAVE_ISO_8859_2
		CASE(OFStringEncodingISO8859_2, OFISO8859_2Table)
#endif
#ifdef HAVE_ISO_8859_3
		CASE(OFStringEncodingISO8859_3, OFISO8859_3Table)
#endif
#ifdef HAVE_ISO_8859_15
		CASE(OFStringEncodingISO8859_15, OFISO8859_15Table)
#endif
#ifdef HAVE_WINDOWS_1251
		CASE(OFStringEncodingWindows1251, OFWindows1251Table)
#endif
#ifdef HAVE_WINDOWS_1252
		CASE(OFStringEncodingWindows1252, OFWindows1252Table)
#endif
#ifdef HAVE_CODEPAGE_437
		CASE(OFStringEncodingCodepage437, OFCodepage437Table)
#endif
#ifdef HAVE_CODEPAGE_850
		CASE(OFStringEncodingCodepage850, OFCodepage850Table)
#endif
#ifdef HAVE_CODEPAGE_858
		CASE(OFStringEncodingCodepage858, OFCodepage858Table)
#endif
#ifdef HAVE_MAC_ROMAN
		CASE(OFStringEncodingMacRoman, OFMacRomanTable)
#endif
#ifdef HAVE_KOI8_R
		CASE(OFStringEncodingKOI8R, OFKOI8RTable)
#endif
#ifdef HAVE_KOI8_U
		CASE(OFStringEncodingKOI8U, OFKOI8UTable)
#endif
#undef CASE
		default:
			@throw [OFInvalidEncodingException exception];
		}

		j = 0;
		for (size_t i = 0; i < cStringLength; i++) {
			unsigned char character = (unsigned char)cString[i];
			OFUnichar unichar;
			char buffer[4];
			size_t byteLength;

			if (character < tableOffset) {
				_s->cString[j++] = cString[i];
				continue;
			}

			unichar = table[character - tableOffset];

			if (unichar == 0xFFFF)
				@throw [OFInvalidEncodingException exception];

			_s->isUTF8 = true;
			byteLength = OFUTF8StringEncode(unichar, buffer);

			if (byteLength == 0)
				@throw [OFInvalidEncodingException exception];

			_s->cStringLength += byteLength - 1;
			_s->cString = OFResizeMemory(_s->cString,
			    _s->cStringLength + 1, 1);

			memcpy(_s->cString + j, buffer, byteLength);
			j += byteLength;
		}

		_s->cString[_s->cStringLength] = 0;
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423

		if (UTF8StringLength >= 3 &&
		    memcmp(UTF8String, "\xEF\xBB\xBF", 3) == 0) {
			UTF8String += 3;
			UTF8StringLength -= 3;
		}

		switch (of_string_utf8_check(UTF8String, UTF8StringLength,
		    &_s->length)) {
		case 1:
			_s->isUTF8 = true;
			break;
		case -1:
			@throw [OFInvalidEncodingException exception];
		}







|







409
410
411
412
413
414
415
416
417
418
419
420
421
422
423

		if (UTF8StringLength >= 3 &&
		    memcmp(UTF8String, "\xEF\xBB\xBF", 3) == 0) {
			UTF8String += 3;
			UTF8StringLength -= 3;
		}

		switch (OFUTF8StringCheck(UTF8String, UTF8StringLength,
		    &_s->length)) {
		case 1:
			_s->isUTF8 = true;
			break;
		case -1:
			@throw [OFInvalidEncodingException exception];
		}
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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622

623
624
625
626
627
628
629
630
		    [string isKindOfClass: [OFMutableUTF8String class]])
			_s->isUTF8 = ((OFUTF8String *)string)->_s->isUTF8;
		else
			_s->isUTF8 = true;

		_s->length = string.length;

		_s->cString = of_alloc(_s->cStringLength + 1, 1);
		memcpy(_s->cString, string.UTF8String, _s->cStringLength + 1);
		_s->freeWhenDone = true;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithCharacters: (const of_unichar_t *)characters
			    length: (size_t)length
{
	self = [super init];

	@try {
		size_t j;

		_s = &_storage;

		_s->cString = of_alloc((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			size_t len = of_string_utf8_encode(characters[i],
			    _s->cString + j);

			if (len == 0)
				@throw [OFInvalidEncodingException exception];

			if (len > 1)
				_s->isUTF8 = true;

			j += len;
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = of_realloc(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithUTF16String: (const of_char16_t *)string
			     length: (size_t)length
			  byteOrder: (of_byte_order_t)byteOrder
{
	self = [super init];

	@try {
		size_t j;
		bool swap = false;

		if (length > 0 && *string == 0xFEFF) {
			string++;
			length--;
		} else if (length > 0 && *string == 0xFFFE) {
			swap = true;
			string++;
			length--;
		} else if (byteOrder != OF_BYTE_ORDER_NATIVE)
			swap = true;

		_s = &_storage;

		_s->cString = of_alloc((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			of_unichar_t character =
			    (swap ? OF_BSWAP16(string[i]) : string[i]);
			size_t len;

			/* Missing high surrogate */
			if ((character & 0xFC00) == 0xDC00)
				@throw [OFInvalidEncodingException exception];

			if ((character & 0xFC00) == 0xD800) {
				of_char16_t nextCharacter;

				if (length <= i + 1)
					@throw [OFInvalidEncodingException
					    exception];

				nextCharacter = (swap
				    ? OF_BSWAP16(string[i + 1])
				    : string[i + 1]);

				if ((nextCharacter & 0xFC00) != 0xDC00)
					@throw [OFInvalidEncodingException
					    exception];

				character = (((character & 0x3FF) << 10) |
				    (nextCharacter & 0x3FF)) + 0x10000;

				i++;
				_s->length--;
			}

			len = of_string_utf8_encode(character, _s->cString + j);

			if (len == 0)
				@throw [OFInvalidEncodingException exception];

			if (len > 1)
				_s->isUTF8 = true;

			j += len;
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = of_realloc(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithUTF32String: (const of_char32_t *)characters
			     length: (size_t)length
			  byteOrder: (of_byte_order_t)byteOrder
{
	self = [super init];

	@try {
		size_t j;
		bool swap = false;

		if (length > 0 && *characters == 0xFEFF) {
			characters++;
			length--;
		} else if (length > 0 && *characters == 0xFFFE0000) {
			swap = true;
			characters++;
			length--;
		} else if (byteOrder != OF_BYTE_ORDER_NATIVE)
			swap = true;

		_s = &_storage;

		_s->cString = of_alloc((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			char buffer[4];
			size_t len = of_string_utf8_encode(

			    (swap ? OF_BSWAP32(characters[i]) : characters[i]),
			    buffer);

			switch (len) {
			case 1:
				_s->cString[j++] = buffer[0];
				break;
			case 2:







|










|









|





|















|











|

|














|




|





|
|







|






|













|














|











|

|














|




|






|
>
|







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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
		    [string isKindOfClass: [OFMutableUTF8String class]])
			_s->isUTF8 = ((OFUTF8String *)string)->_s->isUTF8;
		else
			_s->isUTF8 = true;

		_s->length = string.length;

		_s->cString = OFAllocMemory(_s->cStringLength + 1, 1);
		memcpy(_s->cString, string.UTF8String, _s->cStringLength + 1);
		_s->freeWhenDone = true;
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithCharacters: (const OFUnichar *)characters
			    length: (size_t)length
{
	self = [super init];

	@try {
		size_t j;

		_s = &_storage;

		_s->cString = OFAllocMemory((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			size_t len = OFUTF8StringEncode(characters[i],
			    _s->cString + j);

			if (len == 0)
				@throw [OFInvalidEncodingException exception];

			if (len > 1)
				_s->isUTF8 = true;

			j += len;
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = OFResizeMemory(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithUTF16String: (const OFChar16 *)string
			     length: (size_t)length
			  byteOrder: (OFByteOrder)byteOrder
{
	self = [super init];

	@try {
		size_t j;
		bool swap = false;

		if (length > 0 && *string == 0xFEFF) {
			string++;
			length--;
		} else if (length > 0 && *string == 0xFFFE) {
			swap = true;
			string++;
			length--;
		} else if (byteOrder != OFByteOrderNative)
			swap = true;

		_s = &_storage;

		_s->cString = OFAllocMemory((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			OFUnichar character =
			    (swap ? OFByteSwap16(string[i]) : string[i]);
			size_t len;

			/* Missing high surrogate */
			if ((character & 0xFC00) == 0xDC00)
				@throw [OFInvalidEncodingException exception];

			if ((character & 0xFC00) == 0xD800) {
				OFChar16 nextCharacter;

				if (length <= i + 1)
					@throw [OFInvalidEncodingException
					    exception];

				nextCharacter = (swap
				    ? OFByteSwap16(string[i + 1])
				    : string[i + 1]);

				if ((nextCharacter & 0xFC00) != 0xDC00)
					@throw [OFInvalidEncodingException
					    exception];

				character = (((character & 0x3FF) << 10) |
				    (nextCharacter & 0x3FF)) + 0x10000;

				i++;
				_s->length--;
			}

			len = OFUTF8StringEncode(character, _s->cString + j);

			if (len == 0)
				@throw [OFInvalidEncodingException exception];

			if (len > 1)
				_s->isUTF8 = true;

			j += len;
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = OFResizeMemory(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (instancetype)initWithUTF32String: (const OFChar32 *)characters
			     length: (size_t)length
			  byteOrder: (OFByteOrder)byteOrder
{
	self = [super init];

	@try {
		size_t j;
		bool swap = false;

		if (length > 0 && *characters == 0xFEFF) {
			characters++;
			length--;
		} else if (length > 0 && *characters == 0xFFFE0000) {
			swap = true;
			characters++;
			length--;
		} else if (byteOrder != OFByteOrderNative)
			swap = true;

		_s = &_storage;

		_s->cString = OFAllocMemory((length * 4) + 1, 1);
		_s->length = length;
		_s->freeWhenDone = true;

		j = 0;
		for (size_t i = 0; i < length; i++) {
			char buffer[4];
			size_t len = OFUTF8StringEncode((swap
			    ? OFByteSwap32(characters[i])
			    : characters[i]),
			    buffer);

			switch (len) {
			case 1:
				_s->cString[j++] = buffer[0];
				break;
			case 2:
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
			}
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = of_realloc(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}







|







642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
			}
		}

		_s->cString[j] = '\0';
		_s->cStringLength = j;

		@try {
			_s->cString = OFResizeMemory(_s->cString, j + 1, 1);
		} @catch (OFOutOfMemoryException *e) {
			/* We don't care, as we only tried to make it smaller */
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
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
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
		int cStringLength;

		if (format == nil)
			@throw [OFInvalidArgumentException exception];

		_s = &_storage;

		if ((cStringLength = of_vasprintf(&tmp, format.UTF8String,
		    arguments)) == -1)
			@throw [OFInvalidFormatException exception];

		_s->cStringLength = cStringLength;

		@try {
			switch (of_string_utf8_check(tmp, cStringLength,
			    &_s->length)) {
			case 1:
				_s->isUTF8 = true;
				break;
			case -1:
				@throw [OFInvalidEncodingException exception];
			}

			_s->cString = of_alloc(cStringLength + 1, 1);
			memcpy(_s->cString, tmp, cStringLength + 1);
			_s->freeWhenDone = true;
		} @finally {
			free(tmp);
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (void)dealloc
{
	if (_s != NULL && _s->freeWhenDone)
		free(_s->cString);

	[super dealloc];
}

- (size_t)getCString: (char *)cString
	   maxLength: (size_t)maxLength
	    encoding: (of_string_encoding_t)encoding
{
	switch (encoding) {
	case OF_STRING_ENCODING_ASCII:
		if (_s->isUTF8)
			@throw [OFInvalidEncodingException exception];
		/* intentional fall-through */
	case OF_STRING_ENCODING_UTF_8:
		if (_s->cStringLength + 1 > maxLength)
			@throw [OFOutOfRangeException exception];

		memcpy(cString, _s->cString, _s->cStringLength + 1);

		return _s->cStringLength;
	default:
		return [super getCString: cString
			       maxLength: maxLength
				encoding: encoding];
	}
}

- (const char *)cStringWithEncoding: (of_string_encoding_t)encoding
{
	switch (encoding) {
	case OF_STRING_ENCODING_ASCII:
		if (_s->isUTF8)
			@throw [OFInvalidEncodingException exception];
		/* intentional fall-through */
	case OF_STRING_ENCODING_UTF_8:
		return _s->cString;
	default:
		return [super cStringWithEncoding: encoding];
	}
}

- (const char *)UTF8String
{
	return _s->cString;
}

- (size_t)length
{
	return _s->length;
}

- (size_t)cStringLengthWithEncoding: (of_string_encoding_t)encoding
{
	switch (encoding) {
	case OF_STRING_ENCODING_UTF_8:
	case OF_STRING_ENCODING_ASCII:
		return _s->cStringLength;
	default:
		return [super cStringLengthWithEncoding: encoding];
	}
}

- (size_t)UTF8StringLength
{
	return _s->cStringLength;
}

- (bool)isEqual: (id)object
{
	OFUTF8String *otherString;

	if (object == self)
		return true;

	if (![object isKindOfClass: [OFString class]])
		return false;

	otherString = object;

	if (otherString.UTF8StringLength != _s->cStringLength ||
	    otherString.length != _s->length)
		return false;

	if (([otherString isKindOfClass: [OFUTF8String class]] ||
	    [otherString isKindOfClass: [OFMutableUTF8String class]]) &&
	    _s->hashed && otherString->_s->hashed &&
	    _s->hash != otherString->_s->hash)
		return false;

	if (strcmp(_s->cString, otherString.UTF8String) != 0)
		return false;

	return true;
}

- (of_comparison_result_t)compare: (id <OFComparing>)object
{
	OFString *otherString;
	size_t otherCStringLength, minimumCStringLength;
	int compare;

	if (object == self)
		return OF_ORDERED_SAME;

	if (![(id)object isKindOfClass: [OFString class]])
		@throw [OFInvalidArgumentException exception];

	otherString = (OFString *)object;
	otherCStringLength = otherString.UTF8StringLength;
	minimumCStringLength = (_s->cStringLength > otherCStringLength
	    ? otherCStringLength : _s->cStringLength);

	if ((compare = memcmp(_s->cString, otherString.UTF8String,
	    minimumCStringLength)) == 0) {
		if (_s->cStringLength > otherCStringLength)
			return OF_ORDERED_DESCENDING;
		if (_s->cStringLength < otherCStringLength)
			return OF_ORDERED_ASCENDING;
		return OF_ORDERED_SAME;
	}

	if (compare > 0)
		return OF_ORDERED_DESCENDING;
	else
		return OF_ORDERED_ASCENDING;
}

- (of_comparison_result_t)caseInsensitiveCompare: (OFString *)otherString
{
	const char *otherCString;
	size_t otherCStringLength, minimumCStringLength;
#ifdef OF_HAVE_UNICODE_TABLES
	size_t i, j;
#endif
	int compare;

	if (otherString == self)
		return OF_ORDERED_SAME;

	if (![otherString isKindOfClass: [OFString class]])
		@throw [OFInvalidArgumentException exception];

	otherCString = otherString.UTF8String;
	otherCStringLength = otherString.UTF8StringLength;

#ifdef OF_HAVE_UNICODE_TABLES
	if (!_s->isUTF8) {
#endif
		minimumCStringLength = (_s->cStringLength > otherCStringLength
		    ? otherCStringLength : _s->cStringLength);

		if ((compare = memcasecmp(_s->cString, otherCString,
		    minimumCStringLength)) == 0) {
			if (_s->cStringLength > otherCStringLength)
				return OF_ORDERED_DESCENDING;
			if (_s->cStringLength < otherCStringLength)
				return OF_ORDERED_ASCENDING;
			return OF_ORDERED_SAME;
		}

		if (compare > 0)
			return OF_ORDERED_DESCENDING;
		else
			return OF_ORDERED_ASCENDING;
#ifdef OF_HAVE_UNICODE_TABLES
	}

	i = j = 0;

	while (i < _s->cStringLength && j < otherCStringLength) {
		of_unichar_t c1, c2;
		ssize_t l1, l2;

		l1 = of_string_utf8_decode(_s->cString + i,
		    _s->cStringLength - i, &c1);
		l2 = of_string_utf8_decode(otherCString + j,
		    otherCStringLength - j, &c2);

		if (l1 <= 0 || l2 <= 0 || c1 > 0x10FFFF || c2 > 0x10FFFF)
			@throw [OFInvalidEncodingException exception];

		if (c1 >> 8 < OF_UNICODE_CASEFOLDING_TABLE_SIZE) {
			of_unichar_t tc =
			    of_unicode_casefolding_table[c1 >> 8][c1 & 0xFF];

			if (tc)
				c1 = tc;
		}

		if (c2 >> 8 < OF_UNICODE_CASEFOLDING_TABLE_SIZE) {
			of_unichar_t tc =
			    of_unicode_casefolding_table[c2 >> 8][c2 & 0xFF];

			if (tc)
				c2 = tc;
		}

		if (c1 > c2)
			return OF_ORDERED_DESCENDING;
		if (c1 < c2)
			return OF_ORDERED_ASCENDING;

		i += l1;
		j += l2;
	}

	if (_s->cStringLength - i > otherCStringLength - j)
		return OF_ORDERED_DESCENDING;
	else if (_s->cStringLength - i < otherCStringLength - j)
		return OF_ORDERED_ASCENDING;
#endif

	return OF_ORDERED_SAME;
}

- (unsigned long)hash
{
	uint32_t hash;

	if (_s->hashed)
		return _s->hash;

	OF_HASH_INIT(hash);

	for (size_t i = 0; i < _s->cStringLength; i++) {
		of_unichar_t c;
		ssize_t length;

		if ((length = of_string_utf8_decode(_s->cString + i,
		    _s->cStringLength - i, &c)) <= 0)
			@throw [OFInvalidEncodingException exception];

		OF_HASH_ADD(hash, (c & 0xFF0000) >> 16);
		OF_HASH_ADD(hash, (c & 0x00FF00) >> 8);
		OF_HASH_ADD(hash, c & 0x0000FF);

		i += length - 1;
	}

	OF_HASH_FINALIZE(hash);

	_s->hash = hash;
	_s->hashed = true;

	return hash;
}

- (of_unichar_t)characterAtIndex: (size_t)idx
{
	of_unichar_t character;

	if (idx >= _s->length)
		@throw [OFOutOfRangeException exception];

	if (!_s->isUTF8)
		return _s->cString[idx];

	idx = of_string_utf8_get_position(_s->cString, idx, _s->cStringLength);

	if (of_string_utf8_decode(_s->cString + idx,
	    _s->cStringLength - idx, &character) <= 0)
		@throw [OFInvalidEncodingException exception];

	return character;
}

- (void)getCharacters: (of_unichar_t *)buffer
	      inRange: (of_range_t)range
{
	/* TODO: Could be slightly optimized */
	void *pool = objc_autoreleasePoolPush();
	const of_unichar_t *characters = self.characters;

	if (range.length > SIZE_MAX - range.location ||
	    range.location + range.length > _s->length)
		@throw [OFOutOfRangeException exception];

	memcpy(buffer, characters + range.location,
	    range.length * sizeof(of_unichar_t));

	objc_autoreleasePoolPop(pool);
}

- (of_range_t)rangeOfString: (OFString *)string
		    options: (int)options
		      range: (of_range_t)range
{
	const char *cString = string.UTF8String;
	size_t cStringLength = string.UTF8StringLength;
	size_t rangeLocation, rangeLength;

	if (range.length > SIZE_MAX - range.location ||
	    range.location + range.length > _s->length)
		@throw [OFOutOfRangeException exception];

	if (_s->isUTF8) {
		rangeLocation = of_string_utf8_get_position(
		    _s->cString, range.location, _s->cStringLength);
		rangeLength = of_string_utf8_get_position(
		    _s->cString + rangeLocation, range.length,
		    _s->cStringLength - rangeLocation);
	} else {
		rangeLocation = range.location;
		rangeLength = range.length;
	}

	if (cStringLength == 0)
		return of_range(0, 0);

	if (cStringLength > rangeLength)
		return of_range(OF_NOT_FOUND, 0);

	if (options & OF_STRING_SEARCH_BACKWARDS) {
		for (size_t i = rangeLength - cStringLength;; i--) {
			if (memcmp(_s->cString + rangeLocation + i, cString,
			    cStringLength) == 0) {
				range.location += of_string_utf8_get_index(
				    _s->cString + rangeLocation, i);
				range.length = string.length;

				return range;
			}

			/* Did not match and we're at the last char */
			if (i == 0)
				return of_range(OF_NOT_FOUND, 0);
		}
	} else {
		for (size_t i = 0; i <= rangeLength - cStringLength; i++) {
			if (memcmp(_s->cString + rangeLocation + i, cString,
			    cStringLength) == 0) {
				range.location += of_string_utf8_get_index(
				    _s->cString + rangeLocation, i);
				range.length = string.length;

				return range;
			}
		}
	}

	return of_range(OF_NOT_FOUND, 0);
}

- (bool)containsString: (OFString *)string
{
	const char *cString = string.UTF8String;
	size_t cStringLength = string.UTF8StringLength;

	if (cStringLength == 0)
		return true;

	if (cStringLength > _s->cStringLength)
		return false;

	for (size_t i = 0; i <= _s->cStringLength - cStringLength; i++)
		if (memcmp(_s->cString + i, cString, cStringLength) == 0)
			return true;

	return false;
}

- (OFString *)substringWithRange: (of_range_t)range
{
	size_t start = range.location;
	size_t end = range.location + range.length;

	if (range.length > SIZE_MAX - range.location || end > _s->length)
		@throw [OFOutOfRangeException exception];

	if (_s->isUTF8) {
		start = of_string_utf8_get_position(_s->cString, start,
		    _s->cStringLength);
		end = of_string_utf8_get_position(_s->cString, end,
		    _s->cStringLength);
	}

	return [OFString stringWithUTF8String: _s->cString + start
				       length: end - start];
}








|






|








|



|












|






|


|



|













|


|



|
















|


|
|













|







|

|
|


|
|
<
|


|





|

<



|
|

|


<
|



|


|

|
|



|

|


|








|
|

<
<
<
|
|










|

|
|



|

|






|


|

|





|
|
|





|
|
|






|

|






|

|


|




|

|


|


|


|



|
|
|




|


|




|

|







|

|
|





|
<



|






|




|
|
|










|

|








|


|

|



|








|





|








|




















|








|

|







668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793

794
795
796
797
798
799
800
801
802
803
804

805
806
807
808
809
810
811
812
813

814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844



845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
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
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
		int cStringLength;

		if (format == nil)
			@throw [OFInvalidArgumentException exception];

		_s = &_storage;

		if ((cStringLength = OFVASPrintF(&tmp, format.UTF8String,
		    arguments)) == -1)
			@throw [OFInvalidFormatException exception];

		_s->cStringLength = cStringLength;

		@try {
			switch (OFUTF8StringCheck(tmp, cStringLength,
			    &_s->length)) {
			case 1:
				_s->isUTF8 = true;
				break;
			case -1:
				@throw [OFInvalidEncodingException exception];
			}

			_s->cString = OFAllocMemory(cStringLength + 1, 1);
			memcpy(_s->cString, tmp, cStringLength + 1);
			_s->freeWhenDone = true;
		} @finally {
			OFFreeMemory(tmp);
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- (void)dealloc
{
	if (_s != NULL && _s->freeWhenDone)
		OFFreeMemory(_s->cString);

	[super dealloc];
}

- (size_t)getCString: (char *)cString
	   maxLength: (size_t)maxLength
	    encoding: (OFStringEncoding)encoding
{
	switch (encoding) {
	case OFStringEncodingASCII:
		if (_s->isUTF8)
			@throw [OFInvalidEncodingException exception];
		/* intentional fall-through */
	case OFStringEncodingUTF8:
		if (_s->cStringLength + 1 > maxLength)
			@throw [OFOutOfRangeException exception];

		memcpy(cString, _s->cString, _s->cStringLength + 1);

		return _s->cStringLength;
	default:
		return [super getCString: cString
			       maxLength: maxLength
				encoding: encoding];
	}
}

- (const char *)cStringWithEncoding: (OFStringEncoding)encoding
{
	switch (encoding) {
	case OFStringEncodingASCII:
		if (_s->isUTF8)
			@throw [OFInvalidEncodingException exception];
		/* intentional fall-through */
	case OFStringEncodingUTF8:
		return _s->cString;
	default:
		return [super cStringWithEncoding: encoding];
	}
}

- (const char *)UTF8String
{
	return _s->cString;
}

- (size_t)length
{
	return _s->length;
}

- (size_t)cStringLengthWithEncoding: (OFStringEncoding)encoding
{
	switch (encoding) {
	case OFStringEncodingUTF8:
	case OFStringEncodingASCII:
		return _s->cStringLength;
	default:
		return [super cStringLengthWithEncoding: encoding];
	}
}

- (size_t)UTF8StringLength
{
	return _s->cStringLength;
}

- (bool)isEqual: (id)object
{
	OFUTF8String *string;

	if (object == self)
		return true;

	if (![object isKindOfClass: [OFString class]])
		return false;

	string = object;

	if (string.UTF8StringLength != _s->cStringLength ||
	    string.length != _s->length)
		return false;

	if (([string isKindOfClass: [OFUTF8String class]] ||
	    [string isKindOfClass: [OFMutableUTF8String class]]) &&

	    _s->hasHash && string->_s->hasHash && _s->hash != string->_s->hash)
		return false;

	if (strcmp(_s->cString, string.UTF8String) != 0)
		return false;

	return true;
}

- (OFComparisonResult)compare: (OFString *)string
{

	size_t otherCStringLength, minimumCStringLength;
	int compare;

	if (string == self)
		return OFOrderedSame;

	if (![string isKindOfClass: [OFString class]])
		@throw [OFInvalidArgumentException exception];


	otherCStringLength = string.UTF8StringLength;
	minimumCStringLength = (_s->cStringLength > otherCStringLength
	    ? otherCStringLength : _s->cStringLength);

	if ((compare = memcmp(_s->cString, string.UTF8String,
	    minimumCStringLength)) == 0) {
		if (_s->cStringLength > otherCStringLength)
			return OFOrderedDescending;
		if (_s->cStringLength < otherCStringLength)
			return OFOrderedAscending;
		return OFOrderedSame;
	}

	if (compare > 0)
		return OFOrderedDescending;
	else
		return OFOrderedAscending;
}

- (OFComparisonResult)caseInsensitiveCompare: (OFString *)string
{
	const char *otherCString;
	size_t otherCStringLength, minimumCStringLength;
#ifdef OF_HAVE_UNICODE_TABLES
	size_t i, j;
#endif
	int compare;

	if (string == self)
		return OFOrderedSame;




	otherCString = string.UTF8String;
	otherCStringLength = string.UTF8StringLength;

#ifdef OF_HAVE_UNICODE_TABLES
	if (!_s->isUTF8) {
#endif
		minimumCStringLength = (_s->cStringLength > otherCStringLength
		    ? otherCStringLength : _s->cStringLength);

		if ((compare = memcasecmp(_s->cString, otherCString,
		    minimumCStringLength)) == 0) {
			if (_s->cStringLength > otherCStringLength)
				return OFOrderedDescending;
			if (_s->cStringLength < otherCStringLength)
				return OFOrderedAscending;
			return OFOrderedSame;
		}

		if (compare > 0)
			return OFOrderedDescending;
		else
			return OFOrderedAscending;
#ifdef OF_HAVE_UNICODE_TABLES
	}

	i = j = 0;

	while (i < _s->cStringLength && j < otherCStringLength) {
		OFUnichar c1, c2;
		ssize_t l1, l2;

		l1 = OFUTF8StringDecode(_s->cString + i,
		    _s->cStringLength - i, &c1);
		l2 = OFUTF8StringDecode(otherCString + j,
		    otherCStringLength - j, &c2);

		if (l1 <= 0 || l2 <= 0 || c1 > 0x10FFFF || c2 > 0x10FFFF)
			@throw [OFInvalidEncodingException exception];

		if (c1 >> 8 < OFUnicodeCaseFoldingTableSize) {
			OFUnichar tc =
			    OFUnicodeCaseFoldingTable[c1 >> 8][c1 & 0xFF];

			if (tc)
				c1 = tc;
		}

		if (c2 >> 8 < OFUnicodeCaseFoldingTableSize) {
			OFUnichar tc =
			    OFUnicodeCaseFoldingTable[c2 >> 8][c2 & 0xFF];

			if (tc)
				c2 = tc;
		}

		if (c1 > c2)
			return OFOrderedDescending;
		if (c1 < c2)
			return OFOrderedAscending;

		i += l1;
		j += l2;
	}

	if (_s->cStringLength - i > otherCStringLength - j)
		return OFOrderedDescending;
	else if (_s->cStringLength - i < otherCStringLength - j)
		return OFOrderedAscending;
#endif

	return OFOrderedSame;
}

- (unsigned long)hash
{
	unsigned long hash;

	if (_s->hasHash)
		return _s->hash;

	OFHashInit(&hash);

	for (size_t i = 0; i < _s->cStringLength; i++) {
		OFUnichar c;
		ssize_t length;

		if ((length = OFUTF8StringDecode(_s->cString + i,
		    _s->cStringLength - i, &c)) <= 0)
			@throw [OFInvalidEncodingException exception];

		OFHashAdd(&hash, (c & 0xFF0000) >> 16);
		OFHashAdd(&hash, (c & 0x00FF00) >> 8);
		OFHashAdd(&hash, c & 0x0000FF);

		i += length - 1;
	}

	OFHashFinalize(&hash);

	_s->hash = hash;
	_s->hasHash = true;

	return hash;
}

- (OFUnichar)characterAtIndex: (size_t)idx
{
	OFUnichar character;

	if (idx >= _s->length)
		@throw [OFOutOfRangeException exception];

	if (!_s->isUTF8)
		return _s->cString[idx];

	idx = OFUTF8StringIndexToPosition(_s->cString, idx, _s->cStringLength);

	if (OFUTF8StringDecode(_s->cString + idx, _s->cStringLength - idx,
	    &character) <= 0)
		@throw [OFInvalidEncodingException exception];

	return character;
}

- (void)getCharacters: (OFUnichar *)buffer inRange: (OFRange)range

{
	/* TODO: Could be slightly optimized */
	void *pool = objc_autoreleasePoolPush();
	const OFUnichar *characters = self.characters;

	if (range.length > SIZE_MAX - range.location ||
	    range.location + range.length > _s->length)
		@throw [OFOutOfRangeException exception];

	memcpy(buffer, characters + range.location,
	    range.length * sizeof(OFUnichar));

	objc_autoreleasePoolPop(pool);
}

- (OFRange)rangeOfString: (OFString *)string
		 options: (OFStringSearchOptions)options
		   range: (OFRange)range
{
	const char *cString = string.UTF8String;
	size_t cStringLength = string.UTF8StringLength;
	size_t rangeLocation, rangeLength;

	if (range.length > SIZE_MAX - range.location ||
	    range.location + range.length > _s->length)
		@throw [OFOutOfRangeException exception];

	if (_s->isUTF8) {
		rangeLocation = OFUTF8StringIndexToPosition(
		    _s->cString, range.location, _s->cStringLength);
		rangeLength = OFUTF8StringIndexToPosition(
		    _s->cString + rangeLocation, range.length,
		    _s->cStringLength - rangeLocation);
	} else {
		rangeLocation = range.location;
		rangeLength = range.length;
	}

	if (cStringLength == 0)
		return OFRangeMake(0, 0);

	if (cStringLength > rangeLength)
		return OFRangeMake(OFNotFound, 0);

	if (options & OFStringSearchBackwards) {
		for (size_t i = rangeLength - cStringLength;; i--) {
			if (memcmp(_s->cString + rangeLocation + i, cString,
			    cStringLength) == 0) {
				range.location += positionToIndex(
				    _s->cString + rangeLocation, i);
				range.length = string.length;

				return range;
			}

			/* Did not match and we're at the last char */
			if (i == 0)
				return OFRangeMake(OFNotFound, 0);
		}
	} else {
		for (size_t i = 0; i <= rangeLength - cStringLength; i++) {
			if (memcmp(_s->cString + rangeLocation + i, cString,
			    cStringLength) == 0) {
				range.location += positionToIndex(
				    _s->cString + rangeLocation, i);
				range.length = string.length;

				return range;
			}
		}
	}

	return OFRangeMake(OFNotFound, 0);
}

- (bool)containsString: (OFString *)string
{
	const char *cString = string.UTF8String;
	size_t cStringLength = string.UTF8StringLength;

	if (cStringLength == 0)
		return true;

	if (cStringLength > _s->cStringLength)
		return false;

	for (size_t i = 0; i <= _s->cStringLength - cStringLength; i++)
		if (memcmp(_s->cString + i, cString, cStringLength) == 0)
			return true;

	return false;
}

- (OFString *)substringWithRange: (OFRange)range
{
	size_t start = range.location;
	size_t end = range.location + range.length;

	if (range.length > SIZE_MAX - range.location || end > _s->length)
		@throw [OFOutOfRangeException exception];

	if (_s->isUTF8) {
		start = OFUTF8StringIndexToPosition(_s->cString, start,
		    _s->cStringLength);
		end = OFUTF8StringIndexToPosition(_s->cString, end,
		    _s->cStringLength);
	}

	return [OFString stringWithUTF8String: _s->cString + start
				       length: end - start];
}

1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
		return false;

	return (memcmp(_s->cString + (_s->cStringLength - cStringLength),
	    suffix.UTF8String, cStringLength) == 0);
}

- (OFArray *)componentsSeparatedByString: (OFString *)delimiter
				 options: (int)options
{
	void *pool;
	OFMutableArray *array;
	const char *cString;
	size_t cStringLength;
	bool skipEmpty = (options & OF_STRING_SKIP_EMPTY);
	size_t last;
	OFString *component;

	if (delimiter == nil)
		@throw [OFInvalidArgumentException exception];

	if (delimiter.length == 0)







|





|







1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
		return false;

	return (memcmp(_s->cString + (_s->cStringLength - cStringLength),
	    suffix.UTF8String, cStringLength) == 0);
}

- (OFArray *)componentsSeparatedByString: (OFString *)delimiter
				 options: (OFStringSeparationOptions)options
{
	void *pool;
	OFMutableArray *array;
	const char *cString;
	size_t cStringLength;
	bool skipEmpty = (options & OFStringSkipEmptyComponents);
	size_t last;
	OFString *component;

	if (delimiter == nil)
		@throw [OFInvalidArgumentException exception];

	if (delimiter.length == 0)
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244

1245
1246
1247
1248
1249
1250
1251
	[array makeImmutable];

	objc_autoreleasePoolPop(pool);

	return array;
}

- (const of_unichar_t *)characters
{
	of_unichar_t *buffer = of_alloc(_s->length, sizeof(of_unichar_t));
	size_t i = 0, j = 0;

	while (i < _s->cStringLength) {
		of_unichar_t c;
		ssize_t cLen;

		cLen = of_string_utf8_decode(_s->cString + i,
		    _s->cStringLength - i, &c);

		if (cLen <= 0 || c > 0x10FFFF) {
			free(buffer);
			@throw [OFInvalidEncodingException exception];
		}

		buffer[j++] = c;
		i += cLen;
	}

	return [[OFData dataWithItemsNoCopy: buffer
				      count: _s->length
				   itemSize: sizeof(of_unichar_t)
			       freeWhenDone: true] items];
}

- (const of_char32_t *)UTF32StringWithByteOrder: (of_byte_order_t)byteOrder
{
	of_char32_t *buffer = of_alloc(_s->length + 1, sizeof(of_char32_t));
	size_t i = 0, j = 0;

	while (i < _s->cStringLength) {
		of_char32_t c;
		ssize_t cLen;

		cLen = of_string_utf8_decode(_s->cString + i,
		    _s->cStringLength - i, &c);

		if (cLen <= 0 || c > 0x10FFFF) {
			free(buffer);
			@throw [OFInvalidEncodingException exception];
		}

		if (byteOrder != OF_BYTE_ORDER_NATIVE)
			buffer[j++] = OF_BSWAP32(c);
		else
			buffer[j++] = c;

		i += cLen;
	}
	buffer[j] = 0;

	return [[OFData dataWithItemsNoCopy: buffer
				      count: _s->length + 1
				   itemSize: sizeof(of_char32_t)
			       freeWhenDone: true] items];
}

#ifdef OF_HAVE_BLOCKS
- (void)enumerateLinesUsingBlock: (of_string_line_enumeration_block_t)block
{
	void *pool;
	const char *cString = _s->cString;
	const char *last = cString;
	bool stop = false, lastCarriageReturn = false;

	while (!stop && *cString != 0) {
		if (lastCarriageReturn && *cString == '\n') {
			lastCarriageReturn = false;

			cString++;
			last++;

			continue;
		}

		if (*cString == '\n' || *cString == '\r') {
			pool = objc_autoreleasePoolPush();

			block([OFString
			    stringWithUTF8String: last
					  length: cString - last], &stop);

			last = cString + 1;

			objc_autoreleasePoolPop(pool);
		}

		lastCarriageReturn = (*cString == '\r');
		cString++;







|

|



|


|



|









|



|

|



|


|



|



|
|









|




|



















|
<
|
>







1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236

1237
1238
1239
1240
1241
1242
1243
1244
1245
	[array makeImmutable];

	objc_autoreleasePoolPop(pool);

	return array;
}

- (const OFUnichar *)characters
{
	OFUnichar *buffer = OFAllocMemory(_s->length, sizeof(OFUnichar));
	size_t i = 0, j = 0;

	while (i < _s->cStringLength) {
		OFUnichar c;
		ssize_t cLen;

		cLen = OFUTF8StringDecode(_s->cString + i,
		    _s->cStringLength - i, &c);

		if (cLen <= 0 || c > 0x10FFFF) {
			OFFreeMemory(buffer);
			@throw [OFInvalidEncodingException exception];
		}

		buffer[j++] = c;
		i += cLen;
	}

	return [[OFData dataWithItemsNoCopy: buffer
				      count: _s->length
				   itemSize: sizeof(OFUnichar)
			       freeWhenDone: true] items];
}

- (const OFChar32 *)UTF32StringWithByteOrder: (OFByteOrder)byteOrder
{
	OFChar32 *buffer = OFAllocMemory(_s->length + 1, sizeof(OFChar32));
	size_t i = 0, j = 0;

	while (i < _s->cStringLength) {
		OFChar32 c;
		ssize_t cLen;

		cLen = OFUTF8StringDecode(_s->cString + i,
		    _s->cStringLength - i, &c);

		if (cLen <= 0 || c > 0x10FFFF) {
			OFFreeMemory(buffer);
			@throw [OFInvalidEncodingException exception];
		}

		if (byteOrder != OFByteOrderNative)
			buffer[j++] = OFByteSwap32(c);
		else
			buffer[j++] = c;

		i += cLen;
	}
	buffer[j] = 0;

	return [[OFData dataWithItemsNoCopy: buffer
				      count: _s->length + 1
				   itemSize: sizeof(OFChar32)
			       freeWhenDone: true] items];
}

#ifdef OF_HAVE_BLOCKS
- (void)enumerateLinesUsingBlock: (OFStringLineEnumerationBlock)block
{
	void *pool;
	const char *cString = _s->cString;
	const char *last = cString;
	bool stop = false, lastCarriageReturn = false;

	while (!stop && *cString != 0) {
		if (lastCarriageReturn && *cString == '\n') {
			lastCarriageReturn = false;

			cString++;
			last++;

			continue;
		}

		if (*cString == '\n' || *cString == '\r') {
			pool = objc_autoreleasePoolPush();

			block([OFString stringWithUTF8String: last

						      length: cString - last],
			    &stop);
			last = cString + 1;

			objc_autoreleasePoolPop(pool);
		}

		lastCarriageReturn = (*cString == '\r');
		cString++;