141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
|
}
of_unichar_t
of_string_utf8_to_unicode(const char *buf_, size_t len)
{
const uint8_t *buf = (const uint8_t*)buf_;
if (*buf < 0x80)
return buf[0];
switch (*buf & 0xF0) {
case 0xC0:
case 0xD0:
if (OF_UNLIKELY(len < 2))
return OF_INVALID_UNICHAR;
return ((buf[0] & 0x1F) << 6) | (buf[1] & 0x3F);
case 0xE0:
case 0xF0:
|
|
|
<
<
>
|
>
>
|
>
|
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
}
of_unichar_t
of_string_utf8_to_unicode(const char *buf_, size_t len)
{
const uint8_t *buf = (const uint8_t*)buf_;
if (!(*buf & 0x80))
return buf[0];
if ((*buf & 0xE0) == 0xC0) {
if (OF_UNLIKELY(len < 2))
return OF_INVALID_UNICHAR;
return ((buf[0] & 0x1F) << 6) | (buf[1] & 0x3F);
}
if ((*buf & 0xF0) == 0xE0) {
if (OF_UNLIKELY(len < 3))
return OF_INVALID_UNICHAR;
return ((buf[0] & 0x0F) << 12) | ((buf[1] & 0x3F) << 6) |
(buf[2] & 0x3F);
}
if ((*buf & 0xF8) == 0xF0) {
if (OF_UNLIKELY(len < 4))
return OF_INVALID_UNICHAR;
return ((buf[0] & 0x07) << 18) | ((buf[1] & 0x3F) << 12) |
((buf[2] & 0x3F) << 6) | (buf[3] & 0x3F);
}
|
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
|
string[length] = 0;
break;
case OF_STRING_ENCODING_ISO_8859_1:
case OF_STRING_ENCODING_ISO_8859_15:
case OF_STRING_ENCODING_WINDOWS_1252:
for (i = j = 0; i < len; i++) {
if ((uint8_t)str[i] < 0x80)
string[j++] = str[i];
else {
char buf[4];
of_unichar_t chr;
size_t chr_bytes;
switch (encoding) {
|
|
|
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
|
string[length] = 0;
break;
case OF_STRING_ENCODING_ISO_8859_1:
case OF_STRING_ENCODING_ISO_8859_15:
case OF_STRING_ENCODING_WINDOWS_1252:
for (i = j = 0; i < len; i++) {
if (!(str[i] & 0x80))
string[j++] = str[i];
else {
char buf[4];
of_unichar_t chr;
size_t chr_bytes;
switch (encoding) {
|