ObjFW  Diff

Differences From Artifact [fe52a06baf]:

To Artifact [6944810146]:


61
62
63
64
65
66
67
68
69


70
71
72

73
74
75
76
77
78
79
61
62
63
64
65
66
67


68
69
70


71
72
73
74
75
76
77
78







-
-
+
+

-
-
+







			if ((t = table[0][*p]) != 0)
				*p = t;

		return;
	}

	ulen = [self length];
	ustr = [self allocMemoryForNItems: [self length]
				 withSize: ulen];
	ustr = [self allocMemoryForNItems: ulen
				 withSize: sizeof(of_unichar_t)];

	i = 0;
	j = 0;
	i = j = 0;
	nlen = 0;

	while (i < length) {
		clen = of_string_utf8_to_unicode(string + i, length - i, &c);

		if (clen == 0 || c > 0x10FFFF) {
			[self freeMemory: ustr];
134
135
136
137
138
139
140





141
142
143
144
145
146
147
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151







+
+
+
+
+







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

	[self freeMemory: string];

	len = strlen(str);

	if (len >= 3 && !memcmp(str, "\xEF\xBB\xBF", 3)) {
		str += 3;
		len -= 3;
	}

	switch (of_string_check_utf8(str, len)) {
	case 0:
		isUTF8 = NO;
		break;
	case 1:
		isUTF8 = YES;
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
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







+
+
+
+
+


















+
+
+
+
+







}

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

	strlength = strlen(str);

	if (strlength >= 3 && !memcmp(str, "\xEF\xBB\xBF", 3)) {
		str += 3;
		strlength -= 3;
	}

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

	string = [self resizeMemory: string
			     toSize: length + strlength + 1];
	memcpy(string + length, str, strlength + 1);
	length += strlength;
}

- (void)appendCString: (const char*)str
	   withLength: (size_t)len
{
	if (len >= 3 && !memcmp(str, "\xEF\xBB\xBF", 3)) {
		str += 3;
		len -= 3;
	}

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







-
+









-
+










-
+





-
+















-
+















-
+


















-
+



-
+







			  atIndex: 0];
}

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

	madvise(string, len, MADV_SEQUENTIAL);
	madvise(string, length, 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 (!isUTF8) {
		madvise(string, len, MADV_NORMAL);
		madvise(string, length, MADV_NORMAL);
		return;
	}

	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);
			madvise(string, length, MADV_NORMAL);
			@throw [OFInvalidEncodingException newWithClass: isa];
		}

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

	madvise(string, len, MADV_NORMAL);
	madvise(string, length, MADV_NORMAL);
}

- (void)upper
{
	[self _applyTable: of_unicode_upper_table
		 withSize: OF_UNICODE_UPPER_TABLE_SIZE];
}