Skip to content

[3.7] bpo-35372: Fix the code page decoder for input > 2 GiB. (GH-10848) #10859

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.

Sign up for GitHub

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
miss-islington merged 1 commit into from
Dec 3, 2018
Merged

[3.7] bpo-35372: Fix the code page decoder for input > 2 GiB. (GH-10848) #10859

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
18 changes: 18 additions & 0 deletions Lib/test/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3185,6 +3185,24 @@ def test_mbcs_alias(self):
codec = codecs.lookup('cp123')
self.assertEqual(codec.name, 'mbcs')

@support.bigmemtest(size=2**31, memuse=7, dry_run=False)
def test_large_input(self):
# Test input longer than INT_MAX.
# Input should contain undecodable bytes before and after
# the INT_MAX limit.
encoded = (b'01234567' * (2**28-1) +
b'\x85\x86\xea\xeb\xec\xef\xfc\xfd\xfe\xff')
self.assertEqual(len(encoded), 2**31+2)
decoded = codecs.code_page_decode(932, encoded, 'surrogateescape', True)
self.assertEqual(decoded[1], len(encoded))
del encoded
self.assertEqual(len(decoded[0]), decoded[1])
self.assertEqual(decoded[0][:10], '0123456701')
self.assertEqual(decoded[0][-20:],
'6701234567'
'\udc85\udc86\udcea\udceb\udcec'
'\udcef\udcfc\udcfd\udcfe\udcff')


class ASCIITest(unittest.TestCase):
def test_encode(self):
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Core and Builtins/2018-12-01-19-20-53.bpo-35372.RwVJjZ.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Fixed the code page decoder for input longer than 2 GiB containing
undecodable bytes.
9 changes: 4 additions & 5 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7178,7 +7178,7 @@ decode_code_page_errors(UINT code_page,
"in the target code page.";
/* each step cannot decode more than 1 character, but a character can be
represented as a surrogate pair */
wchar_t buffer[2], *startout, *out;
wchar_t buffer[2], *out;
int insize;
Py_ssize_t outsize;
PyObject *errorHandler = NULL;
Expand Down Expand Up @@ -7215,7 +7215,7 @@ decode_code_page_errors(UINT code_page,
*v = (PyObject*)_PyUnicode_New(size * Py_ARRAY_LENGTH(buffer));
if (*v == NULL)
goto error;
startout = PyUnicode_AS_UNICODE(*v);
out = PyUnicode_AS_UNICODE(*v);
}
else {
/* Extend unicode object */
Expand All @@ -7226,11 +7226,10 @@ decode_code_page_errors(UINT code_page,
}
if (unicode_resize(v, n + size * Py_ARRAY_LENGTH(buffer)) < 0)
goto error;
startout = PyUnicode_AS_UNICODE(*v) + n;
out = PyUnicode_AS_UNICODE(*v) + n;
}

/* Decode the byte string character per character */
out = startout;
while (in < endin)
{
/* Decode a character */
Expand Down Expand Up @@ -7285,7 +7284,7 @@ decode_code_page_errors(UINT code_page,
*out = 0;

/* Extend unicode object */
outsize = out - startout;
outsize = out - PyUnicode_AS_UNICODE(*v);
assert(outsize <= PyUnicode_WSTR_LENGTH(*v));
if (unicode_resize(v, outsize) < 0)
goto error;
Expand Down