harec

commit f674e4cac551546cfee5dc1521f6f013e6b44522
parent c3480506fea714cc9dff999329e33535f575127d
Author: Jose Lombera <jose@lombera.dev>
Date:   Sun, 11 Sep 2022 20:03:03 -0500

utf8: fix codepoint byte length decoding

Signed-off-by: Jose Lombera <jose@lombera.dev>

Diffstat:
M
src/utf8.c
 | 
4
++--

1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/src/utf8.c b/src/utf8.c
@@ -21,7 +21,7 @@ struct {
 	{ 0xF0, 0xE0, 3 },
 	{ 0xF8, 0xF0, 4 },
 	{ 0xFC, 0xF8, 5 },
-	{ 0xFE, 0xF8, 6 },
+	{ 0xFE, 0xFC, 6 },
 	{ 0x80, 0x80, -1 },
 };
 
@@ -99,7 +99,7 @@ int
 utf8_size(const char *s)
 {
 	uint8_t c = (uint8_t)*s;
-	for (size_t i = 0; i < sizeof(sizes) / 2; ++i) {
+	for (size_t i = 0; i < sizeof(sizes) / sizeof(sizes[0]); ++i) {
 		if ((c & sizes[i].mask) == sizes[i].result) {
 			return sizes[i].octets;
 		}