(Result) |= ((Chars)[(Count)] & 0x3f); \
}
-unichar get_utf8_char(const unsigned char **ptr, int len)
+int get_utf8_char(const unsigned char **ptr, int len, unichar *chr_r)
{
int i, result, mask, chrlen;
mask = 0;
UTF8_COMPUTE(**ptr, mask, chrlen);
if (chrlen == -1)
- return (unichar) -2;
+ return -2;
if (chrlen > len)
- return (unichar) -1;
+ return -1;
UTF8_GET(result, *ptr, i, mask, chrlen);
if (result == -1)
- return (unichar) -2;
-
+ return -2;
+
+ *chr_r = (unichar) result;
*ptr += chrlen-1;
return result;
}
{
const unsigned char *p = (const unsigned char *) str;
int len;
+ unichar chr_r;
len = 0;
- while (*p != '\0' && get_utf8_char(&p, 6) > 0) {
+ while (*p != '\0' && get_utf8_char(&p, 6, &chr_r) > 0) {
len++;
p++;
}
*out = '\0';
}
+void utf16_to_utf8_with_pos(const unichar *str, int spos, char *out, int *opos)
+{
+ int len;
+ const unichar *sstart = str;
+ char *ostart = out;
+
+ *opos = 0;
+ while (*str != '\0') {
+ len = utf16_char_to_utf8(*str, out);
+ out += len;
+
+ str++;
+ if(str - sstart == spos)
+ *opos = out - ostart;
+ }
+ *out = '\0';
+}
+
static const unichar wcc[] = {
0x0, 0x300, 0x34F, 0x360, 0x363, 0x483, 0x487, 0x488, 0x48A, 0x591,
0x5A2, 0x5A3, 0x5BA, 0x5BB, 0x5BE, 0x5BF, 0x5C0, 0x5C1, 0x5C3, 0x5C4,