py/unicode: Fix check for valid utf8 being stricter about contn chars.
This commit is contained in:
parent
d63ef86c6e
commit
7c85c7c210
@ -180,7 +180,7 @@ bool utf8_check(const byte *p, size_t len) {
|
|||||||
for (; p < end; p++) {
|
for (; p < end; p++) {
|
||||||
byte c = *p;
|
byte c = *p;
|
||||||
if (need) {
|
if (need) {
|
||||||
if (c >= 0x80) {
|
if (UTF8_IS_CONT(c)) {
|
||||||
need--;
|
need--;
|
||||||
} else {
|
} else {
|
||||||
// mismatch
|
// mismatch
|
||||||
|
@ -47,3 +47,7 @@ try:
|
|||||||
str(bytearray(b'ab\xc0a'), 'utf8')
|
str(bytearray(b'ab\xc0a'), 'utf8')
|
||||||
except UnicodeError:
|
except UnicodeError:
|
||||||
print('UnicodeError')
|
print('UnicodeError')
|
||||||
|
try:
|
||||||
|
str(b'\xf0\xe0\xed\xe8', 'utf8')
|
||||||
|
except UnicodeError:
|
||||||
|
print('UnicodeError')
|
||||||
|
Loading…
x
Reference in New Issue
Block a user