ObjFW  Check-in [d968d32614]

Overview
Comment:Style improvements.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: d968d32614fe2cea6219e5a90da033702448b2ba0cad464ff85324a07120e81d
User & Date: js on 2011-04-30 23:33:51
Other Links: manifest | tags
Context
2011-05-01
00:35
Add +[OFString stringWithUnicodeString:]. check-in: e2bbfb45d0 user: js tags: trunk
2011-04-30
23:33
Style improvements. check-in: d968d32614 user: js tags: trunk
23:01
Copy exceptions/common.h into the resulting framework. check-in: a6e2eea3b5 user: js tags: trunk
Changes

Modified src/OFString.h from [bd128c526e] to [7edfd43e32].

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
 * \param string A UTF-8 encoded C string to initialize the OFString with
 * \param length The length of the UTF-8 encoded C string
 * \return A new autoreleased OFString
 */
+ stringWithCString: (const char*)string
	     length: (size_t)length;









/**
 * Creates a new OFString from a format string.
 * See printf for the format syntax.
 *
 * \param format A string used as format to initialize the OFString
 * \return A new autoreleased OFString
 */
+ stringWithFormat: (OFString*)format, ...;

/**
 * Creates a new OFString containing the constructed specified path.
 *
 * \param firstComponent The first component of the path
 * \return A new autoreleased OFString
 */
+ stringWithPath: (OFString*)firstComponent, ...;

/**
 * Creates a new OFString from another string.
 *
 * \param string A string to initialize the OFString with
 * \return A new autoreleased OFString
 */
+ stringWithString: (OFString*)string;

/**
 * Creates a new OFString with the contents of the specified UTF-8 encoded file.
 *
 * \param path The path to the file
 * \return A new autoreleased OFString
 */
+ stringWithContentsOfFile: (OFString*)path;







>
>
>
>
>
>
>
>

















<
<
<
<
<
<
<
<







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
 * \param string A UTF-8 encoded C string to initialize the OFString with
 * \param length The length of the UTF-8 encoded C string
 * \return A new autoreleased OFString
 */
+ stringWithCString: (const char*)string
	     length: (size_t)length;

/**
 * Creates a new OFString from another string.
 *
 * \param string A string to initialize the OFString with
 * \return A new autoreleased OFString
 */
+ stringWithString: (OFString*)string;

/**
 * Creates a new OFString from a format string.
 * See printf for the format syntax.
 *
 * \param format A string used as format to initialize the OFString
 * \return A new autoreleased OFString
 */
+ stringWithFormat: (OFString*)format, ...;

/**
 * Creates a new OFString containing the constructed specified path.
 *
 * \param firstComponent The first component of the path
 * \return A new autoreleased OFString
 */
+ stringWithPath: (OFString*)firstComponent, ...;









/**
 * Creates a new OFString with the contents of the specified UTF-8 encoded file.
 *
 * \param path The path to the file
 * \return A new autoreleased OFString
 */
+ stringWithContentsOfFile: (OFString*)path;
213
214
215
216
217
218
219








220
221
222
223
224
225
226
 * \param string A UTF-8 encoded C string to initialize the OFString with
 * \param length The length of the UTF-8 encoded C string
 * \return An initialized OFString
 */
- initWithCString: (const char*)string
	   length: (size_t)length;









/**
 * Initializes an already allocated OFString with a format string.
 * See printf for the format syntax.
 *
 * \param format A string used as format to initialize the OFString
 * \return An initialized OFString
 */







>
>
>
>
>
>
>
>







213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
 * \param string A UTF-8 encoded C string to initialize the OFString with
 * \param length The length of the UTF-8 encoded C string
 * \return An initialized OFString
 */
- initWithCString: (const char*)string
	   length: (size_t)length;

/**
 * Initializes an already allocated OFString with another string.
 *
 * \param string A string to initialize the OFString with
 * \return An initialized OFString
 */
- initWithString: (OFString*)string;

/**
 * Initializes an already allocated OFString with a format string.
 * See printf for the format syntax.
 *
 * \param format A string used as format to initialize the OFString
 * \return An initialized OFString
 */
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
 * \param firstComponent The first component of the path
 * \param arguments A va_list with the other components of the path
 * \return A new autoreleased OFString
 */
- initWithPath: (OFString*)firstComponent
     arguments: (va_list)arguments;

/**
 * Initializes an already allocated OFString with another string.
 *
 * \param string A string to initialize the OFString with
 * \return An initialized OFString
 */
- initWithString: (OFString*)string;

/**
 * Initializes an already allocated OFString with the contents of the specified
 * file in the specified encoding.
 *
 * \param path The path to the file
 * \return An initialized OFString
 */







<
<
<
<
<
<
<
<







261
262
263
264
265
266
267








268
269
270
271
272
273
274
 * \param firstComponent The first component of the path
 * \param arguments A va_list with the other components of the path
 * \return A new autoreleased OFString
 */
- initWithPath: (OFString*)firstComponent
     arguments: (va_list)arguments;









/**
 * Initializes an already allocated OFString with the contents of the specified
 * file in the specified encoding.
 *
 * \param path The path to the file
 * \return An initialized OFString
 */

Modified src/OFString.m from [02548d1e5f] to [e280f8208a].

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
	_OFString_Hashing_reference = 1;
	_OFString_URLEncoding_reference = 1;
	_OFString_XMLEscaping_reference = 1;
	_OFString_XMLUnescaping_reference = 1;
}

static inline int
memcasecmp(const char *first, const char *second, size_t len)
{
	size_t i;

	for (i = 0; i < len; i++) {
		if (tolower((int)first[i]) > tolower((int)second[i]))
			return OF_ORDERED_DESCENDING;
		if (tolower((int)first[i]) < tolower((int)second[i]))
			return OF_ORDERED_ASCENDING;
	}

	return OF_ORDERED_SAME;
}

int
of_string_check_utf8(const char *str, size_t len)
{
	size_t i;
	int utf8 = 0;

	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 = 1;

		/* 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;
}

size_t
of_string_unicode_to_utf8(of_unichar_t c, char *buf)
{
	size_t i = 0;

	if (c < 0x80) {
		buf[i] = c;
		return 1;
	}
	if (c < 0x800) {
		buf[i++] = 0xC0 | (c >> 6);
		buf[i] = 0x80 | (c & 0x3F);
		return 2;
	}
	if (c < 0x10000) {
		buf[i++] = 0xE0 | (c >> 12);
		buf[i++] = 0x80 | (c >> 6 & 0x3F);
		buf[i] = 0x80 | (c & 0x3F);
		return 3;
	}
	if (c < 0x110000) {
		buf[i++] = 0xF0 | (c >> 18);
		buf[i++] = 0x80 | (c >> 12 & 0x3F);
		buf[i++] = 0x80 | (c >> 6 & 0x3F);
		buf[i] = 0x80 | (c & 0x3F);
		return 4;
	}

	return 0;
}

size_t
of_string_utf8_to_unicode(const char *buf_, size_t len, of_unichar_t *ret)
{
	const uint8_t *buf = (const uint8_t*)buf_;

	if (!(*buf & 0x80)) {
		*ret = buf[0];
		return 1;
	}

	if ((*buf & 0xE0) == 0xC0) {
		if (OF_UNLIKELY(len < 2))
			return 0;

		*ret = ((buf[0] & 0x1F) << 6) | (buf[1] & 0x3F);
		return 2;
	}

	if ((*buf & 0xF0) == 0xE0) {
		if (OF_UNLIKELY(len < 3))
			return 0;

		*ret = ((buf[0] & 0x0F) << 12) | ((buf[1] & 0x3F) << 6) |
		    (buf[2] & 0x3F);
		return 3;
	}

	if ((*buf & 0xF8) == 0xF0) {
		if (OF_UNLIKELY(len < 4))
			return 0;

		*ret = ((buf[0] & 0x07) << 18) | ((buf[1] & 0x3F) << 12) |
		    ((buf[2] & 0x3F) << 6) | (buf[3] & 0x3F);
		return 4;
	}

	return 0;
}

size_t
of_string_position_to_index(const char *str, size_t pos)
{
	size_t i, idx = pos;

	for (i = 0; i < pos; i++)
		if (OF_UNLIKELY((str[i] & 0xC0) == 0x80))
			idx--;

	return idx;
}

size_t
of_string_index_to_position(const char *str, size_t idx, size_t len)
{
	size_t i;

	for (i = 0; i <= idx; i++)
		if (OF_UNLIKELY((str[i] & 0xC0) == 0x80))
			if (++idx > len)
				return OF_INVALID_INDEX;

	return idx;
}

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







|



|










|


|

|

|

|


|


|
|




|
>
|




|





|
>
|




|





|
>
|







|
|






|

|



|



|
|


|
|
|


|
|
|
|


|
|
|
|
|







|

|

|
|



|
|


|



|
|


|
|



|
|


|
|







|

|

|
|
|

|



|



|
|
|


|







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
	_OFString_Hashing_reference = 1;
	_OFString_URLEncoding_reference = 1;
	_OFString_XMLEscaping_reference = 1;
	_OFString_XMLUnescaping_reference = 1;
}

static inline int
memcasecmp(const char *first, const char *second, size_t length)
{
	size_t i;

	for (i = 0; i < length; i++) {
		if (tolower((int)first[i]) > tolower((int)second[i]))
			return OF_ORDERED_DESCENDING;
		if (tolower((int)first[i]) < tolower((int)second[i]))
			return OF_ORDERED_ASCENDING;
	}

	return OF_ORDERED_SAME;
}

int
of_string_check_utf8(const char *string, size_t length)
{
	size_t i;
	int isUTF8 = 0;

	madvise((void*)string, length, MADV_SEQUENTIAL);

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

		isUTF8 = 1;

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

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

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

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

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

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

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

		i += 3;
	}

	madvise((void*)string, length, MADV_NORMAL);

	return isUTF8;
}

size_t
of_string_unicode_to_utf8(of_unichar_t character, char *buffer)
{
	size_t i = 0;

	if (character < 0x80) {
		buffer[i] = character;
		return 1;
	}
	if (character < 0x800) {
		buffer[i++] = 0xC0 | (character >> 6);
		buffer[i] = 0x80 | (character & 0x3F);
		return 2;
	}
	if (character < 0x10000) {
		buffer[i++] = 0xE0 | (character >> 12);
		buffer[i++] = 0x80 | (character >> 6 & 0x3F);
		buffer[i] = 0x80 | (character & 0x3F);
		return 3;
	}
	if (character < 0x110000) {
		buffer[i++] = 0xF0 | (character >> 18);
		buffer[i++] = 0x80 | (character >> 12 & 0x3F);
		buffer[i++] = 0x80 | (character >> 6 & 0x3F);
		buffer[i] = 0x80 | (character & 0x3F);
		return 4;
	}

	return 0;
}

size_t
of_string_utf8_to_unicode(const char *buffer_, size_t length, of_unichar_t *ret)
{
	const uint8_t *buffer = (const uint8_t*)buffer_;

	if (!(*buffer & 0x80)) {
		*ret = buffer[0];
		return 1;
	}

	if ((*buffer & 0xE0) == 0xC0) {
		if (OF_UNLIKELY(length < 2))
			return 0;

		*ret = ((buffer[0] & 0x1F) << 6) | (buffer[1] & 0x3F);
		return 2;
	}

	if ((*buffer & 0xF0) == 0xE0) {
		if (OF_UNLIKELY(length < 3))
			return 0;

		*ret = ((buffer[0] & 0x0F) << 12) | ((buffer[1] & 0x3F) << 6) |
		    (buffer[2] & 0x3F);
		return 3;
	}

	if ((*buffer & 0xF8) == 0xF0) {
		if (OF_UNLIKELY(length < 4))
			return 0;

		*ret = ((buffer[0] & 0x07) << 18) | ((buffer[1] & 0x3F) << 12) |
		    ((buffer[2] & 0x3F) << 6) | (buffer[3] & 0x3F);
		return 4;
	}

	return 0;
}

size_t
of_string_position_to_index(const char *string, size_t position)
{
	size_t i, index = position;

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

	return index;
}

size_t
of_string_index_to_position(const char *string, size_t index, size_t length)
{
	size_t i;

	for (i = 0; i <= index; i++)
		if (OF_UNLIKELY((string[i] & 0xC0) == 0x80))
			if (++index > length)
				return OF_INVALID_INDEX;

	return index;
}

@implementation OFString
+ string
{
	return [[[self alloc] init] autorelease];
}
270
271
272
273
274
275
276





277
278
279
280
281
282
283

+ stringWithCString: (const char*)string
	     length: (size_t)length
{
	return [[[self alloc] initWithCString: string
				       length: length] autorelease];
}






+ stringWithFormat: (OFString*)format, ...
{
	id ret;
	va_list arguments;

	va_start(arguments, format);







>
>
>
>
>







273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291

+ stringWithCString: (const char*)string
	     length: (size_t)length
{
	return [[[self alloc] initWithCString: string
				       length: length] autorelease];
}

+ stringWithString: (OFString*)string
{
	return [[[self alloc] initWithString: string] autorelease];
}

+ stringWithFormat: (OFString*)format, ...
{
	id ret;
	va_list arguments;

	va_start(arguments, format);
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
	ret = [[[self alloc] initWithPath: firstComponent
				arguments: arguments] autorelease];
	va_end(arguments);

	return ret;
}

+ stringWithString: (OFString*)string
{
	return [[[self alloc] initWithString: string] autorelease];
}

+ stringWithContentsOfFile: (OFString*)path
{
	return [[[self alloc] initWithContentsOfFile: path] autorelease];
}

+ stringWithContentsOfFile: (OFString*)path
		  encoding: (of_string_encoding_t)encoding







<
<
<
<
<







305
306
307
308
309
310
311





312
313
314
315
316
317
318
	ret = [[[self alloc] initWithPath: firstComponent
				arguments: arguments] autorelease];
	va_end(arguments);

	return ret;
}






+ stringWithContentsOfFile: (OFString*)path
{
	return [[[self alloc] initWithContentsOfFile: path] autorelease];
}

+ stringWithContentsOfFile: (OFString*)path
		  encoding: (of_string_encoding_t)encoding
481
482
483
484
485
486
487




































488
489
490
491
492
493
494
- initWithCString: (const char*)string_
	   length: (size_t)length_
{
	return [self initWithCString: string_
			    encoding: OF_STRING_ENCODING_UTF_8
			      length: length_];
}





































- initWithFormat: (OFString*)format, ...
{
	id ret;
	va_list arguments;

	va_start(arguments, format);







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







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
- initWithCString: (const char*)string_
	   length: (size_t)length_
{
	return [self initWithCString: string_
			    encoding: OF_STRING_ENCODING_UTF_8
			      length: length_];
}

- initWithString: (OFString*)string_
{
	self = [super init];

	@try {
		/* We have no -[dealloc], so this is ok */
		string = (char*)[string_ cString];
		length = [string_ cStringLength];

		switch (of_string_check_utf8(string, length)) {
		case 1:
			isUTF8 = YES;
			break;
		case -1:;
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

		if ((string = strdup(string)) == NULL)
			@throw [OFOutOfMemoryException
			     newWithClass: isa
			    requestedSize: length + 1];

		@try {
			[self addMemoryToPool: string];
		} @catch (id e) {
			free(string);
			@throw e;
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- initWithFormat: (OFString*)format, ...
{
	id ret;
	va_list arguments;

	va_start(arguments, format);
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
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
			len = [component cStringLength];
			string[i] = OF_PATH_DELIM;
			memcpy(string + i + 1, [component cString], len);
			i += len + 1;
		}

		string[i] = '\0';
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}

- initWithString: (OFString*)string_
{
	self = [super init];

	@try {
		/* We have no -[dealloc], so this is ok */
		string = (char*)[string_ cString];
		length = [string_ cStringLength];

		switch (of_string_check_utf8(string, length)) {
		case 1:
			isUTF8 = YES;
			break;
		case -1:;
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

		if ((string = strdup(string)) == NULL)
			@throw [OFOutOfMemoryException
			     newWithClass: isa
			    requestedSize: length + 1];

		@try {
			[self addMemoryToPool: string];
		} @catch (id e) {
			free(string);
			@throw e;
		}
	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







639
640
641
642
643
644
645




































646
647
648
649
650
651
652
			len = [component cStringLength];
			string[i] = OF_PATH_DELIM;
			memcpy(string + i + 1, [component cString], len);
			i += len + 1;
		}

		string[i] = '\0';




































	} @catch (id e) {
		[self release];
		@throw e;
	}

	return self;
}