ObjFW  Check-in [b4a4e95798]

Overview
Comment:Initial UTF-8 support for OFString.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: b4a4e9579803c9f230b72c6d0f7d5d1c47ba159ea48c38b2cf2d8144d6a6473a
User & Date: js on 2008-12-21 15:42:52
Other Links: manifest | tags
Context
2008-12-21
15:54
Nicer exception catching in tests. check-in: 1c77f45484 user: js tags: trunk
15:42
Initial UTF-8 support for OFString. check-in: b4a4e95798 user: js tags: trunk
2008-12-20
14:41
Don't put void* in lists, but objects. check-in: b2c9f574cb user: js tags: trunk
Changes

Modified src/OFExceptions.h from [e7cf625e34] to [e908641783].

130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
/**
 * \return An error message for the exception as a C String
 */
- (const char*)cString;
@end

/**
 * An OFException indicating that the conversation between two charsets failed.
 */
@interface OFCharsetConversionFailedException: OFException {}
/**
 * \return An error message for the exception as a C String
 */
- (const char*)cString;
@end

/**







|

|







130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
/**
 * \return An error message for the exception as a C String
 */
- (const char*)cString;
@end

/**
 * An OFException indicating that the encoding is invalid for this object.
 */
@interface OFInvalidEncodingException: OFException {}
/**
 * \return An error message for the exception as a C String
 */
- (const char*)cString;
@end

/**

Modified src/OFExceptions.m from [1c2da67154] to [7e98f0feae].

137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
	asprintf(&string, "Value out of range in object of class %s!",
	    object != nil ? [object name] : "(null)");

	return string;
}
@end

@implementation OFCharsetConversionFailedException
- (const char*)cString
{
	if (string != NULL)
		return string;
	
	asprintf(&string, "Charset conversion failed in object of classs %s!",
	    [object name]);

	return string;
}
@end

@implementation OFOpenFileFailedException







|





|







137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
	asprintf(&string, "Value out of range in object of class %s!",
	    object != nil ? [object name] : "(null)");

	return string;
}
@end

@implementation OFInvalidEncodingException
- (const char*)cString
{
	if (string != NULL)
		return string;
	
	asprintf(&string, "The encoding is invalid for object of classs %s!",
	    [object name]);

	return string;
}
@end

@implementation OFOpenFileFailedException

Modified src/OFString.h from [80f285a39b] to [e46bf07ec6].

14
15
16
17
18
19
20

21
22
23
24
25
26
27
/**
 * A class for storing and modifying strings.
 */
@interface OFString: OFObject
{
	char   *string;
	size_t length;

}

/**
 * Creates a new OFString.
 * 
 * \return An initialized OFString
 */







>







14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
/**
 * A class for storing and modifying strings.
 */
@interface OFString: OFObject
{
	char   *string;
	size_t length;
	BOOL   is_utf8;
}

/**
 * Creates a new OFString.
 * 
 * \return An initialized OFString
 */

Modified src/OFString.m from [737d54ed05] to [f391445888].

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

#import <stdlib.h>
#import <string.h>
#import <ctype.h>

#import "OFString.h"
#import "OFExceptions.h"





























































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

+ newFromCString: (const char*)str
{
	return [[self alloc] initFromCString: str];
}

- init
{
	if ((self = [super init])) {
		length = 0;
		string = NULL;

	}

	return self;
}

- initFromCString: (const char*)str
{
	if ((self = [super init])) {
		if (str == NULL) {
			length = 0;
			string = NULL;

		} else {







			length = strlen(str);
			string = [self getMemWithSize: length + 1];
			memcpy(string, str, length + 1);
		}
	}

	return self;
}







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

















>








|
|
|
>
|
>
>
>
>
>
>
>
|







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

#import <stdlib.h>
#import <string.h>
#import <ctype.h>

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

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

	utf8 = NO;

	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))
			return -1;

		/* We have at minimum a 2 byte character -> check next byte */
		if (OF_UNLIKELY(len < i + 1 || ~str[i + 1] & 0x80 ||
		    str[i + 1] & 0x40))
			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] & 0x80 ||
		    str[i + 2] & 0x40))
			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] & 0x80 ||
		    str[i + 3] & 0x40))
			return -1;

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

		i += 3;
	}

	return (utf8 ? 1 : 0);
}

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

+ newFromCString: (const char*)str
{
	return [[self alloc] initFromCString: str];
}

- init
{
	if ((self = [super init])) {
		length = 0;
		string = NULL;
		is_utf8 = NO;
	}

	return self;
}

- initFromCString: (const char*)str
{
	if ((self = [super init])) {
		if (str != NULL) {
			length = strlen(str);

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

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

	return self;
}
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
	char   *newstr;
	size_t newlen, strlength;

	if (string == NULL) 
		return [self setTo: [OFString newFromCString: str]];

	strlength = strlen(str);
	newlen = length + strlength;









	newstr = [self resizeMem: string
			  toSize: newlen + 1];

	memcpy(newstr + length, str, strlength + 1);

	length = newlen;
	string = newstr;

	return self;
}

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


	for (i = 0, j = length - 1; i < len; i++, j--) {
		string[i] ^= string[j];
		string[j] ^= string[i];
		string[i] ^= string[j];
	}


	return self;
}






























































- upper
{
	size_t i = length;




	while (i--) 
		string[i] = toupper(string[i]);

	return self;
}

- lower
{
	size_t i = length;




	while (i--) 
		string[i] = tolower(string[i]);

	return self;
}
@end







|
>
>
>
>
>
>
|
>
>















>






>
|
|
>
>
>
>

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




>
>
>










>
>
>






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
	char   *newstr;
	size_t newlen, strlength;

	if (string == NULL) 
		return [self setTo: [OFString newFromCString: str]];

	strlength = strlen(str);

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

	newlen = length + strlength;
	newstr = [self resizeMem: string
			  toSize: newlen + 1];

	memcpy(newstr + length, str, strlength + 1);

	length = newlen;
	string = newstr;

	return self;
}

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

	/* 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)
		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))
			@throw [OFInvalidEncodingException newWithObject: self];

		/* Next byte must not be ASCII */
		if (OF_UNLIKELY(length < i + 1 || ~string[i + 1] & 0x80))
			@throw [OFInvalidEncodingException newWithObject: self];

		/* 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))
			@throw [OFInvalidEncodingException newWithObject: self];

		/* 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))
			@throw [OFInvalidEncodingException newWithObject: self];

		/* 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 */
		@throw [OFInvalidEncodingException newWithObject: self];
	}

	return self;
}

- upper
{
	size_t i = length;

	if (is_utf8)
		@throw [OFInvalidEncodingException newWithObject: self];

	while (i--) 
		string[i] = toupper(string[i]);

	return self;
}

- lower
{
	size_t i = length;

	if (is_utf8)
		@throw [OFInvalidEncodingException newWithObject: self];

	while (i--) 
		string[i] = tolower(string[i]);

	return self;
}
@end

Modified tests/OFString/OFString.m from [acd4c64051] to [09c95b9e26].

11
12
13
14
15
16
17

18
19
20
21
22
23
24

#import "config.h"

#import <stdio.h>
#import <string.h>

#import "OFString.h"


int
main()
{
	OFString *s1 = [OFString newFromCString: "test"];
	OFString *s2 = [OFString newFromCString: ""];
	OFString *s3;







>







11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

#import "config.h"

#import <stdio.h>
#import <string.h>

#import "OFString.h"
#import "OFExceptions.h"

int
main()
{
	OFString *s1 = [OFString newFromCString: "test"];
	OFString *s2 = [OFString newFromCString: ""];
	OFString *s3;
79
80
81
82
83
84
85
86



























87
88
	}

	/* Also clears all the memory of the returned C strings */
	[s1 free];
	[s2 free];
	[s3 free];
	[s4 free];




























	return 0;
}








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


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
	}

	/* Also clears all the memory of the returned C strings */
	[s1 free];
	[s2 free];
	[s3 free];
	[s4 free];

	/* UTF-8 tests */
	@try {
		s1 = [OFString newFromCString: "\xE0\x80"];

		puts("First invalid UTF-8 not detected!");
		return 1;
	} @catch (OFInvalidEncodingException *e) {
		puts("First invalid UTF-8 successfully detected!");
	}

	@try {
		s1 = [OFString newFromCString: "\xF0\x80\x80\xC0"];

		puts("Second UTF-8 not detected!");
		return 1;
	} @catch (OFInvalidEncodingException *e) {
		puts("Second UTF-8 successfully detected!");
	}

	s1 = [OFString newFromCString: "äöü€𝄞"];
	if (!strcmp([[s1 reverse] cString], "𝄞€üöä"))
		puts("Reversed UTF-8 string is expected string! GOOD!");
	else {
		puts("Reversed UTF-8 string is NOT expected string!");
		return 1;
	}

	return 0;
}