ObjFW  Diff

Differences From Artifact [0c1768f337]:

To Artifact [c5b8e74c51]:


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
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
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
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
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













-
-
-


-

-
-
-
-
-
-

-
+



-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-



-
+




-
+








-
-
+
+








-
-
+
+








-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-



















-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-


-
+
-









-
+
-

















+
+
+
+
+
+



-
+
+




-
-
-
-
-
-
-
-
-
-
+
-
-
+
-
-
-
-
-
-




-
-
-
+
-
-
-
-
-
+
-





-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
-
-
-
-
-
+

-
-
-


-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
-
-
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-




-
-
-
-
-
+
+
-
-
-
-




-
-
-
-
-
+
+
-
-
-
+
-
-

/*
 * Copyright (c) 2008 - 2009
 *   Jonathan Schleifer <js@webkeks.org>
 *
 * All rights reserved.
 *
 * This file is part of libobjfw. It may be distributed under the terms of the
 * Q Public License 1.0, which can be found in the file LICENSE included in
 * the packaging of this file.
 */

#import "config.h"

#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <stdarg.h>
#include <string.h>
#include <ctype.h>

#ifdef HAVE_SYS_MMAN_H
#include <sys/mman.h>
#else
#define madvise(addr, len, advise)
#endif

#import "OFString.h"
#import "OFConstString.h"
#import "OFMutableString.h"
#import "OFExceptions.h"
#import "OFMacros.h"

#ifndef HAVE_ASPRINTF
#import "asprintf.h"
#endif

static OF_INLINE int
check_utf8(const char *str, size_t len)
{
	size_t i;
	BOOL utf8;

	utf8 = NO;

	madvise((void*)str, len, MADV_SEQUENTIAL);

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

		utf8 = YES;

		/* We're missing a start byte here */
		if (OF_UNLIKELY(!(str[i] & 0x40))) {
			madvise((void*)str, len, MADV_NORMAL);
			return -1;
		}

		/* We have at minimum a 2 byte character -> check next byte */
		if (OF_UNLIKELY(len < i + 1 || (str[i + 1] & 0xC0) != 0x80)) {
			madvise((void*)str, len, MADV_NORMAL);
			return -1;
		}

		/* Check if we have at minimum a 3 byte character */
		if (OF_LIKELY(!(str[i] & 0x20))) {
			i++;
			continue;
		}

		/* We have at minimum a 3 byte char -> check second next byte */
		if (OF_UNLIKELY(len < i + 2 || (str[i + 2] & 0xC0) != 0x80)) {
			madvise((void*)str, len, MADV_NORMAL);
			return -1;
		}

		/* Check if we have a 4 byte character */
		if (OF_LIKELY(!(str[i] & 0x10))) {
			i += 2;
			continue;
		}

		/* We have a 4 byte character -> check third next byte */
		if (OF_UNLIKELY(len < i + 3 || (str[i + 3] & 0xC0) != 0x80)) {
			madvise((void*)str, len, MADV_NORMAL);
			return -1;
		}

		/*
		 * Just in case, check if there's a 5th character, which is
		 * forbidden by UTF-8
		 */
		if (OF_UNLIKELY(str[i] & 0x08)) {
			madvise((void*)str, len, MADV_NORMAL);
			return -1;
		}

		i += 3;
	}

	madvise((void*)str, len, MADV_NORMAL);

	return (utf8 ? 1 : 0);
}

@implementation OFString
+ string
{
	return [[[OFString alloc] init] autorelease];
	return [[[OFMutableString alloc] init] autorelease];
}

+ stringWithCString: (const char*)str
{
	return [[[OFString alloc] initWithCString: str] autorelease];
	return [[[OFMutableString alloc] initWithCString: str] autorelease];
}

+ stringWithFormat: (const char*)fmt, ...
{
	id ret;
	va_list args;

	va_start(args, fmt);
	ret = [[[OFString alloc] initWithFormat: fmt
			       andArguments: args] autorelease];
	ret = [[[OFMutableString alloc] initWithFormat: fmt
					  andArguments: args] autorelease];
	va_end(args);

	return ret;
}

+ stringWithFormat: (const char*)fmt
      andArguments: (va_list)args
{
	return [[[OFString alloc] initWithFormat: fmt
				andArguments: args] autorelease];
	return [[[OFMutableString alloc] initWithFormat: fmt
					   andArguments: args] autorelease];
}

- init
{
	[super init];

	length = 0;
	string = NULL;
	is_utf8 = NO;

	return self;
}

- initWithCString: (const char*)str
{
	Class c;

	self = [super init];

	if (str != NULL) {
		length = strlen(str);

		switch (check_utf8(str, length)) {
			case 1:
				is_utf8 = YES;
				break;
			case -1:
				c = isa;
				[super free];
				@throw [OFInvalidEncodingException
					newWithClass: c];
		}

		@try {
			string = [self allocWithSize: length + 1];
		} @catch (OFException *e) {
			/*
			 * We can't use [super free] on OS X here. Compiler bug?
			 * [self free] will do here as we don't reimplement
			 * free.
			 */
			[self free];
			@throw e;
		}
		memcpy(string, str, length + 1);
	}

	return self;
}

- initWithFormat: (const char*)fmt, ...
{
	id ret;
	va_list args;

	va_start(args, fmt);
	ret = [self initWithFormat: fmt
		      andArguments: args];
	va_end(args);

	return ret;
}

- initWithFormat: (const char*)fmt
    andArguments: (va_list)args
{
	int t;
	Class c;

	self = [super init];

	if (fmt == NULL) {
		c = isa;
		[super free];
		@throw [OFInvalidFormatException newWithClass: c];
	}

	if ((t = vasprintf(&string, fmt, args)) == -1) {
		c = isa;
		[super free];
		@throw [OFInitializationFailedException newWithClass: c];
	}
	length = t;

	switch (check_utf8(string, length)) {
		case 1:
			is_utf8 = YES;
			break;
		case -1:
			free(string);
			c = isa;
			[super free];
			@throw [OFInvalidEncodingException newWithClass: c];
	}

	@try {
		[self addToMemoryPool: string];
	} @catch (OFException *e) {
		free(string);
		@throw e;
	}

	return self;
}

- (const char*)cString
{
	return string;
}

- (size_t)length
{
	return length;
}

- (id)copy
{
	return [OFString stringWithCString: string];
}

- setTo: (const char*)str
{
	size_t len;

	if (string != NULL)
		[self freeMem: string];

	len = strlen(str);

	switch (check_utf8(str, len)) {
	case 1:
		is_utf8 = YES;
		break;
	case -1:
		string = NULL;
		length = 0;
		is_utf8 = NO;

		@throw [OFInvalidEncodingException newWithClass: isa];
	}

	length = len;
	string = [self allocWithSize: length + 1];
	memcpy(string, str, length + 1);

	return self;
}

- (BOOL)isEqual: (id)obj
{
	if (![obj isKindOf: [OFString class]] &&
	if (![obj isKindOf: [OFString class]])
	    ![obj isKindOf: [OFConstString class]])
		return NO;
	if (strcmp(string, [obj cString]))
		return NO;

	return YES;
}

- (int)compare: (id)obj
{
	if (![obj isKindOf: [OFString class]] &&
	if (![obj isKindOf: [OFString class]])
	    ![obj isKindOf: [OFConstString class]])
		@throw [OFInvalidArgumentException newWithClass: isa];

	return strcmp(string, [obj cString]);
}

- (uint32_t)hash
{
	uint32_t hash;
	size_t i;

	OF_HASH_INIT(hash);
	for (i = 0; i < length; i++)
		OF_HASH_ADD(hash, string[i]);
	OF_HASH_FINALIZE(hash);

	return hash;
}

- setTo: (const char*)str
{
	@throw [OFNotImplementedException newWithClass: isa
					   andSelector: _cmd];
}

- append: (OFString*)str
{
	return [self appendCString: [str cString]];
	@throw [OFNotImplementedException newWithClass: isa
					   andSelector: _cmd];
}

- appendCString: (const char*)str
{
	size_t strlength;

	strlength = strlen(str);

	switch (check_utf8(str, strlength)) {
	case 1:
		is_utf8 = YES;
		break;
	case -1:
		@throw [OFInvalidEncodingException newWithClass: isa];
	@throw [OFNotImplementedException newWithClass: isa
	}

					   andSelector: _cmd];
	string = [self resizeMem: string
			  toSize: length + strlength + 1];
	memcpy(string + length, str, strlength + 1);
	length += strlength;

	return self;
}

- appendWithFormatCString: (const char*)fmt, ...
{
	id ret;
	va_list args;

	@throw [OFNotImplementedException newWithClass: isa
	va_start(args, fmt);
	ret = [self appendWithFormatCString: fmt
			       andArguments: args];
	va_end(args);

					   andSelector: _cmd];
	return ret;
}

- appendWithFormatCString: (const char*)fmt
	     andArguments: (va_list)args
{
	char *t;

	if (fmt == NULL)
		@throw [OFInvalidFormatException newWithClass: isa];

	if ((vasprintf(&t, fmt, args)) == -1)
		/*
		 * This is only the most likely error to happen.
		 * Unfortunately, as errno isn't always thread-safe, there's
		 * no good way for us to find out what really happened.
		 */
		@throw [OFNoMemException newWithClass: isa];

	@throw [OFNotImplementedException newWithClass: isa
					   andSelector: _cmd];
	@try {
		[self appendCString: t];
	} @finally {
		free(t);
	}
}

	return self;
}

- reverse
{
	size_t i, j, len = length / 2;

	madvise(string, len, MADV_SEQUENTIAL);

	/* We reverse all bytes and restore UTF-8 later, if necessary */
	for (i = 0, j = length - 1; i < len; i++, j--) {
		string[i] ^= string[j];
		string[j] ^= string[i];
		string[i] ^= string[j];
	}

	if (!is_utf8) {
		madvise(string, len, MADV_NORMAL);
		return self;
	}

	for (i = 0; i < length; i++) {
		/* ASCII */
		if (OF_LIKELY(!(string[i] & 0x80)))
			continue;

		/* A start byte can't happen first as we reversed everything */
		if (OF_UNLIKELY(string[i] & 0x40)) {
			madvise(string, len, MADV_NORMAL);
			@throw [OFInvalidEncodingException newWithClass: isa];
	@throw [OFNotImplementedException newWithClass: isa
		}

					   andSelector: _cmd];
		/* Next byte must not be ASCII */
		if (OF_UNLIKELY(length < i + 1 || !(string[i + 1] & 0x80))) {
			madvise(string, len, MADV_NORMAL);
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

		/* Next byte is the start byte */
		if (OF_LIKELY(string[i + 1] & 0x40)) {
			string[i] ^= string[i + 1];
			string[i + 1] ^= string[i];
			string[i] ^= string[i + 1];

			i++;
			continue;
		}

		/* Second next byte must not be ASCII */
		if (OF_UNLIKELY(length < i + 2 || !(string[i + 2] & 0x80))) {
			madvise(string, len, MADV_NORMAL);
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

		/* Second next byte is the start byte */
		if (OF_LIKELY(string[i + 2] & 0x40)) {
			string[i] ^= string[i + 2];
			string[i + 2] ^= string[i];
			string[i] ^= string[i + 2];

			i += 2;
			continue;
		}

		/* Third next byte must not be ASCII */
		if (OF_UNLIKELY(length < i + 3 || !(string[i + 3] & 0x80))) {
			madvise(string, len, MADV_NORMAL);
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

		/* Third next byte is the start byte */
		if (OF_LIKELY(string[i + 3] & 0x40)) {
			string[i] ^= string[i + 3];
			string[i + 3] ^= string[i];
			string[i] ^= string[i + 3];

			string[i + 1] ^= string[i + 2];
			string[i + 2] ^= string[i + 1];
			string[i + 1] ^= string[i + 2];

			i += 3;
			continue;
		}

		/* UTF-8 does not allow more than 4 bytes per character */
		madvise(string, len, MADV_NORMAL);
		@throw [OFInvalidEncodingException newWithClass: isa];
	}

	madvise(string, len, MADV_NORMAL);

	return self;
}

- upper
{
	char *p = string + length;

	if (is_utf8)
		@throw [OFInvalidEncodingException newWithClass: isa];

	@throw [OFNotImplementedException newWithClass: isa
					   andSelector: _cmd];
	while (--p >= string)
		*p = toupper((int)*p);

	return self;
}

- lower
{
	char *p = string + length;

	if (is_utf8)
		@throw [OFInvalidEncodingException newWithClass: isa];

	@throw [OFNotImplementedException newWithClass: isa
					   andSelector: _cmd];
	while (--p >= string)
		*p = tolower((int)*p);

}
	return self;
}
@end