Skip to content

bpo-24214: Fixed the UTF-8 and UTF-16 incremental decoders. #14304

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions Lib/test/test_codecs.py
Original file line number Diff line number Diff line change
Expand Up @@ -429,11 +429,18 @@ def test_lone_surrogates(self):
def test_incremental_surrogatepass(self):
# Test incremental decoder for surrogatepass handler:
# see issue #24214
# High surrogate
data = '\uD901'.encode(self.encoding, 'surrogatepass')
for i in range(1, len(data)):
dec = codecs.getincrementaldecoder(self.encoding)('surrogatepass')
self.assertEqual(dec.decode(data[:i]), '')
self.assertEqual(dec.decode(data[i:], True), '\uD901')
# Low surrogate
data = '\uDC02'.encode(self.encoding, 'surrogatepass')
for i in range(1, len(data)):
dec = codecs.getincrementaldecoder(self.encoding)('surrogatepass')
self.assertEqual(dec.decode(data[:i]), '')
self.assertEqual(dec.decode(data[i:]), '\uDC02')


class UTF32Test(ReadTest, unittest.TestCase):
Expand Down Expand Up @@ -874,6 +881,23 @@ def test_surrogatepass_handler(self):
with self.assertRaises(UnicodeDecodeError):
b"abc\xed\xa0z".decode(self.encoding, "surrogatepass")

def test_incremental_errors(self):
# Test that the incremental decoder can fail with final=False.
# See issue #24214
cases = [b'\x80', b'\xBF', b'\xC0', b'\xC1', b'\xF5', b'\xF6', b'\xFF']
for prefix in (b'\xC2', b'\xDF', b'\xE0', b'\xE0\xA0', b'\xEF',
b'\xEF\xBF', b'\xF0', b'\xF0\x90', b'\xF0\x90\x80',
b'\xF4', b'\xF4\x8F', b'\xF4\x8F\xBF'):
for suffix in b'\x7F', b'\xC0':
cases.append(prefix + suffix)
cases.extend((b'\xE0\x80', b'\xE0\x9F', b'\xED\xA0\x80',
b'\xED\xBF\xBF', b'\xF0\x80', b'\xF0\x8F', b'\xF4\x90'))

for data in cases:
with self.subTest(data=data):
dec = codecs.getincrementaldecoder(self.encoding)()
self.assertRaises(UnicodeDecodeError, dec.decode, data)


class UTF7Test(ReadTest, unittest.TestCase):
encoding = "utf-7"
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Improved support of the surrogatepass error handler in the UTF-8 and UTF-16
incremental decoders.
6 changes: 3 additions & 3 deletions Objects/stringlib/codecs.h
Original file line number Diff line number Diff line change
Expand Up @@ -207,7 +207,7 @@ STRINGLIB(utf8_decode)(const char **inptr, const char *end,
goto InvalidContinuation1;
} else if (ch == 0xF4 && ch2 >= 0x90) {
/* invalid sequence
\xF4\x90\x80\80- -- 110000- overflow */
\xF4\x90\x80\x80- -- 110000- overflow */
goto InvalidContinuation1;
}
if (!IS_CONTINUATION_BYTE(ch3)) {
Expand Down Expand Up @@ -573,10 +573,10 @@ STRINGLIB(utf16_decode)(const unsigned char **inptr, const unsigned char *e,
}

/* UTF-16 code pair: */
if (q >= e)
goto UnexpectedEnd;
if (!Py_UNICODE_IS_HIGH_SURROGATE(ch))
goto IllegalEncoding;
if (q >= e)
goto UnexpectedEnd;
ch2 = (q[ihi] << 8) | q[ilo];
q += 2;
if (!Py_UNICODE_IS_LOW_SURROGATE(ch2))
Expand Down
10 changes: 7 additions & 3 deletions Objects/unicodeobject.c
Original file line number Diff line number Diff line change
Expand Up @@ -4937,11 +4937,15 @@ unicode_decode_utf8(const char *s, Py_ssize_t size,
endinpos = startinpos + 1;
break;
case 2:
case 3:
case 4:
if (s == end || consumed) {
if (consumed && (unsigned char)s[0] == 0xED && end - s == 2
&& (unsigned char)s[1] >= 0xA0 && (unsigned char)s[1] <= 0xBF)
{
/* Truncated surrogate code in range D800-DFFF */
goto End;
}
/* fall through */
case 3:
case 4:
errmsg = "invalid continuation byte";
startinpos = s - starts;
endinpos = startinpos + ch - 1;
Expand Down