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>
This commit is contained in:
Jason Andryuk 2016-02-12 23:13:33 +00:00 committed by Matt Fleming
parent e246eb568b
commit a68075908a

View file

@ -59,9 +59,9 @@ ucs2_utf8size(const ucs2_char_t *src)
for (i = 0; i < ucs2_strlen(src); i++) {
u16 c = src[i];
if (c > 0x800)
if (c >= 0x800)
j += 3;
else if (c > 0x80)
else if (c >= 0x80)
j += 2;
else
j += 1;
@ -88,19 +88,19 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
for (i = 0; maxlength && i < limit; i++) {
u16 c = src[i];
if (c > 0x800) {
if (c >= 0x800) {
if (maxlength < 3)
break;
maxlength -= 3;
dest[j++] = 0xe0 | (c & 0xf000) >> 12;
dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
dest[j++] = 0x80 | (c & 0x003f);
} else if (c > 0x80) {
} else if (c >= 0x80) {
if (maxlength < 2)
break;
maxlength -= 2;
dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
dest[j++] = 0x80 | (c & 0x01f);
dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
dest[j++] = 0x80 | (c & 0x03f);
} else {
maxlength -= 1;
dest[j++] = c & 0x7f;