ObjFW  Check-in [898c2a781b]

Overview
Comment:OFString+XMLUnescaping: Get rid of -[appendCStringWithoutUTF8Checking:].

-[appendCStringWithoutUTF8Checking:] will be removed soon, as it is
dangerous and not compatible with a few planned optimizations!

Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: 898c2a781bbaabe24a1d269d079adeb03f76c3587203f7700b86ab8884de37cd
User & Date: js on 2011-07-09 13:29:03
Other Links: manifest | tags
Context
2011-07-09
13:33
Get rid of -[appendCStringWithoutUTF8Checking:] in base64.m. check-in: 56c98bf847 user: js tags: trunk
13:29
OFString+XMLUnescaping: Get rid of -[appendCStringWithoutUTF8Checking:]. check-in: 898c2a781b user: js tags: trunk
13:15
Use OFDataArray instead of OFMutableString in OFXMLElement. check-in: a2c6391204 user: js tags: trunk
Changes

Modified src/OFString+XMLUnescaping.m from [55d286875d] to [f26dc131a5].

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
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







-
-
-
-
-
-
-





-
-
+
+








-
-
+
+

-
-
+
+


-
-
+
+


-
-
+
+

-
-
+
+







	OFMutableString *ret;

	string = [self cString];
	length = [self cStringLength];

	ret = [OFMutableString string];

	/*
	 * This is safe as we already called -[cString] on self and thus can be
	 * sure the string is correctly initialized, even if it is a constant
	 * string.
	 */
	((OFString*)ret)->s->isUTF8 = s->isUTF8;

	last = 0;
	inEntity = NO;

	for (i = 0; i < length; i++) {
		if (!inEntity && string[i] == '&') {
			[ret appendCStringWithoutUTF8Checking: string + last
						       length: i - last];
			[ret appendCString: string + last
				withLength: i - last];

			last = i + 1;
			inEntity = YES;
		} else if (inEntity && string[i] == ';') {
			const char *entity = string + last;
			size_t entityLength = i - last;

			if (entityLength == 2 && !memcmp(entity, "lt", 2))
				[ret appendCStringWithoutUTF8Checking: "<"
							       length: 1];
				[ret appendCString: "<"
					withLength: 1];
			else if (entityLength == 2 && !memcmp(entity, "gt", 2))
				[ret appendCStringWithoutUTF8Checking: ">"
							       length: 1];
				[ret appendCString: ">"
					withLength: 1];
			else if (entityLength == 4 &&
			    !memcmp(entity, "quot", 4))
				[ret appendCStringWithoutUTF8Checking: "\""
							       length: 1];
				[ret appendCString: "\""
					withLength: 1];
			else if (entityLength == 4 &&
			    !memcmp(entity, "apos", 4))
				[ret appendCStringWithoutUTF8Checking: "'"
							       length: 1];
				[ret appendCString: "'"
					withLength: 1];
			else if (entityLength == 3 && !memcmp(entity, "amp", 3))
				[ret appendCStringWithoutUTF8Checking: "&"
							       length: 1];
				[ret appendCString: "&"
					withLength: 1];
			else if (entity[0] == '#') {
				OFAutoreleasePool *pool;
				OFString *tmp;

				pool = [[OFAutoreleasePool alloc] init];
				tmp = parse_numeric_entity(entity,
				    entityLength);
171
172
173
174
175
176
177
178
179


180
181
182
183
184
185
186
164
165
166
167
168
169
170


171
172
173
174
175
176
177
178
179







-
-
+
+







			inEntity = NO;
		}
	}

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

	[ret appendCStringWithoutUTF8Checking: string + last
				       length: i - last];
	[ret appendCString: string + last
		withLength: i - last];

	/*
	 * Class swizzle the string to be immutable. We declared the return type
	 * to be OFString*, so it can't be modified anyway. But not swizzling it
	 * would create a real copy each time -[copy] is called.
	 */
	ret->isa = [OFString class];
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
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







-
-
-
-
-
-
-





-
-
+
+








-
-
+
+

-
-
+
+


-
-
+
+


-
-
+
+

-
-
+
+







	OFMutableString *ret;

	string = [self cString];
	length = [self cStringLength];

	ret = [OFMutableString string];

	/*
	 * This is safe as we already called -[cString] on self and thus can be
	 * sure the string is correctly initialized, even if it is a constant
	 * string.
	 */
	((OFString*)ret)->s->isUTF8 = s->isUTF8;

	last = 0;
	inEntity = NO;

	for (i = 0; i < length; i++) {
		if (!inEntity && string[i] == '&') {
			[ret appendCStringWithoutUTF8Checking: string + last
						       length: i - last];
			[ret appendCString: string + last
				withLength: i - last];

			last = i + 1;
			inEntity = YES;
		} else if (inEntity && string[i] == ';') {
			const char *entity = string + last;
			size_t entityLength = i - last;

			if (entityLength == 2 && !memcmp(entity, "lt", 2))
				[ret appendCStringWithoutUTF8Checking: "<"
							       length: 1];
				[ret appendCString: "<"
					withLength: 1];
			else if (entityLength == 2 && !memcmp(entity, "gt", 2))
				[ret appendCStringWithoutUTF8Checking: ">"
							       length: 1];
				[ret appendCString: ">"
					withLength: 1];
			else if (entityLength == 4 &&
			    !memcmp(entity, "quot", 4))
				[ret appendCStringWithoutUTF8Checking: "\""
							       length: 1];
				[ret appendCString: "\""
					withLength: 1];
			else if (entityLength == 4 &&
			    !memcmp(entity, "apos", 4))
				[ret appendCStringWithoutUTF8Checking: "'"
							       length: 1];
				[ret appendCString: "'"
					withLength: 1];
			else if (entityLength == 3 && !memcmp(entity, "amp", 3))
				[ret appendCStringWithoutUTF8Checking: "&"
							       length: 1];
				[ret appendCString: "&"
					withLength: 1];
			else if (entity[0] == '#') {
				OFAutoreleasePool *pool;
				OFString *tmp;

				pool = [[OFAutoreleasePool alloc] init];
				tmp = parse_numeric_entity(entity,
				    entityLength);
276
277
278
279
280
281
282
283
284


285
286
287
288
289
290
291
292
293
294
295
262
263
264
265
266
267
268


269
270
271
272
273
274
275
276
277
278
279
280
281







-
-
+
+











			inEntity = NO;
		}
	}

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

	[ret appendCStringWithoutUTF8Checking: string + last
				       length: i - last];
	[ret appendCString: string + last
		withLength: i - last];

	/*
	 * Class swizzle the string to be immutable. We declared the return type
	 * to be OFString*, so it can't be modified anyway. But not swizzling it
	 * would create a real copy each time -[copy] is called.
	 */
	ret->isa = [OFString class];
	return ret;
}
#endif
@end