2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 04:34:11 +08:00
linux-next/lib/ucs2_string.c
Jason Andryuk a68075908a lib/ucs2_string: Correct ucs2 -> utf8 conversion
The comparisons should be >= since 0x800 and 0x80 require an additional bit
to store.

For the 3 byte case, the existing shift would drop off 2 more bits than
intended.

For the 2 byte case, there should be 5 bits bits in byte 1, and 6 bits in
byte 2.

Signed-off-by: Jason Andryuk <jandryuk@gmail.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Matthew Garrett <mjg59@coreos.com>
Cc: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
2016-02-16 12:49:05 +00:00

114 lines
2.4 KiB
C

#include <linux/ucs2_string.h>
#include <linux/module.h>
/* Return the number of unicode characters in data */
unsigned long
ucs2_strnlen(const ucs2_char_t *s, size_t maxlength)
{
unsigned long length = 0;
while (*s++ != 0 && length < maxlength)
length++;
return length;
}
EXPORT_SYMBOL(ucs2_strnlen);
unsigned long
ucs2_strlen(const ucs2_char_t *s)
{
return ucs2_strnlen(s, ~0UL);
}
EXPORT_SYMBOL(ucs2_strlen);
/*
* Return the number of bytes is the length of this string
* Note: this is NOT the same as the number of unicode characters
*/
unsigned long
ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength)
{
return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t);
}
EXPORT_SYMBOL(ucs2_strsize);
int
ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
{
while (1) {
if (len == 0)
return 0;
if (*a < *b)
return -1;
if (*a > *b)
return 1;
if (*a == 0) /* implies *b == 0 */
return 0;
a++;
b++;
len--;
}
}
EXPORT_SYMBOL(ucs2_strncmp);
unsigned long
ucs2_utf8size(const ucs2_char_t *src)
{
unsigned long i;
unsigned long j = 0;
for (i = 0; i < ucs2_strlen(src); i++) {
u16 c = src[i];
if (c >= 0x800)
j += 3;
else if (c >= 0x80)
j += 2;
else
j += 1;
}
return j;
}
EXPORT_SYMBOL(ucs2_utf8size);
/*
* copy at most maxlength bytes of whole utf8 characters to dest from the
* ucs2 string src.
*
* The return value is the number of characters copied, not including the
* final NUL character.
*/
unsigned long
ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
{
unsigned int i;
unsigned long j = 0;
unsigned long limit = ucs2_strnlen(src, maxlength);
for (i = 0; maxlength && i < limit; i++) {
u16 c = src[i];
if (c >= 0x800) {
if (maxlength < 3)
break;
maxlength -= 3;
dest[j++] = 0xe0 | (c & 0xf000) >> 12;
dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
dest[j++] = 0x80 | (c & 0x003f);
} else if (c >= 0x80) {
if (maxlength < 2)
break;
maxlength -= 2;
dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
dest[j++] = 0x80 | (c & 0x03f);
} else {
maxlength -= 1;
dest[j++] = c & 0x7f;
}
}
if (maxlength)
dest[j] = '\0';
return j;
}
EXPORT_SYMBOL(ucs2_as_utf8);