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
|
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);
|
|
|
|
|
|
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
|
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);
|
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
|
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 newWithObject: self];
}
/* Next byte must not be ASCII */
if (OF_UNLIKELY(length < i + 1 || ~string[i + 1] & 0x80)) {
madvise(string, len, MADV_NORMAL);
@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)) {
madvise(string, len, MADV_NORMAL);
@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)) {
madvise(string, len, MADV_NORMAL);
@throw [OFInvalidEncodingException newWithObject: self];
}
/* Third next byte is the start byte */
if (OF_LIKELY(string[i + 3] & 0x40)) {
string[i] ^= string[i + 3];
|
|
|
|
|
|
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
|
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 newWithObject: self];
}
/* Next byte must not be ASCII */
if (OF_UNLIKELY(length < i + 1 || !(string[i + 1] & 0x80))) {
madvise(string, len, MADV_NORMAL);
@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))) {
madvise(string, len, MADV_NORMAL);
@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))) {
madvise(string, len, MADV_NORMAL);
@throw [OFInvalidEncodingException newWithObject: self];
}
/* Third next byte is the start byte */
if (OF_LIKELY(string[i + 3] & 0x40)) {
string[i] ^= string[i + 3];
|