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
|
of_string_check_utf8(const char *cString, size_t cStringLength, size_t *length)
{
size_t i, tmpLength = cStringLength;
int UTF8 = 0;
for (i = 0; i < cStringLength; i++) {
/* No sign of UTF-8 here */
if (OF_LIKELY(!(cString[i] & 0x80)))
continue;
UTF8 = 1;
/* We're missing a start byte here */
if (OF_UNLIKELY(!(cString[i] & 0x40)))
return -1;
/* 2 byte sequences for code points 0 - 127 are forbidden */
if (OF_UNLIKELY((cString[i] & 0x7E) == 0x40))
return -1;
/* We have at minimum a 2 byte character -> check next byte */
if (OF_UNLIKELY(cStringLength <= i + 1 ||
(cString[i + 1] & 0xC0) != 0x80))
return -1;
/* Check if we have at minimum a 3 byte character */
if (OF_LIKELY(!(cString[i] & 0x20))) {
i++;
tmpLength--;
continue;
}
/* We have at minimum a 3 byte char -> check second next byte */
if (OF_UNLIKELY(cStringLength <= i + 2 ||
(cString[i + 2] & 0xC0) != 0x80))
return -1;
/* Check if we have a 4 byte character */
if (OF_LIKELY(!(cString[i] & 0x10))) {
i += 2;
tmpLength -= 2;
continue;
}
/* We have a 4 byte character -> check third next byte */
if (OF_UNLIKELY(cStringLength <= i + 3 ||
(cString[i + 3] & 0xC0) != 0x80))
return -1;
/*
* Just in case, check if there's a 5th character, which is
* forbidden by UTF-8
*/
if (OF_UNLIKELY(cString[i] & 0x08))
return -1;
i += 3;
tmpLength -= 3;
}
if (length != NULL)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
of_string_check_utf8(const char *cString, size_t cStringLength, size_t *length)
{
size_t i, tmpLength = cStringLength;
int UTF8 = 0;
for (i = 0; i < cStringLength; i++) {
/* No sign of UTF-8 here */
if OF_LIKELY (!(cString[i] & 0x80))
continue;
UTF8 = 1;
/* We're missing a start byte here */
if OF_UNLIKELY (!(cString[i] & 0x40))
return -1;
/* 2 byte sequences for code points 0 - 127 are forbidden */
if OF_UNLIKELY ((cString[i] & 0x7E) == 0x40)
return -1;
/* We have at minimum a 2 byte character -> check next byte */
if OF_UNLIKELY (cStringLength <= i + 1 ||
(cString[i + 1] & 0xC0) != 0x80)
return -1;
/* Check if we have at minimum a 3 byte character */
if OF_LIKELY (!(cString[i] & 0x20)) {
i++;
tmpLength--;
continue;
}
/* We have at minimum a 3 byte char -> check second next byte */
if OF_UNLIKELY (cStringLength <= i + 2 ||
(cString[i + 2] & 0xC0) != 0x80)
return -1;
/* Check if we have a 4 byte character */
if OF_LIKELY (!(cString[i] & 0x10)) {
i += 2;
tmpLength -= 2;
continue;
}
/* We have a 4 byte character -> check third next byte */
if OF_UNLIKELY (cStringLength <= i + 3 ||
(cString[i + 3] & 0xC0) != 0x80)
return -1;
/*
* Just in case, check if there's a 5th character, which is
* forbidden by UTF-8
*/
if OF_UNLIKELY (cString[i] & 0x08)
return -1;
i += 3;
tmpLength -= 3;
}
if (length != NULL)
|
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
|
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;
}
size_t
|
|
|
|
|
|
|
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
|
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;
}
size_t
|