Skip to content

gh-103824: fix use-after-free error in Parser/tokenizer.c #103993

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
merged 5 commits into from
May 1, 2023
Merged

gh-103824: fix use-after-free error in Parser/tokenizer.c #103993

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c120bc2
Fix use-after-free in tokenizer.c
chgnrdv Apr 29, 2023
a36418c
added test
chgnrdv Apr 30, 2023
0ef4f23
fixed test
chgnrdv Apr 30, 2023
a58adfd
Merge branch 'main' into fix-tokenizer-use-after-free
chgnrdv Apr 30, 2023
b198bc8
Update Parser/tokenizer.c
pablogsal May 1, 2023
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 14 additions & 1 deletion Lib/test/test_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from test.test_grammar import (VALID_UNDERSCORE_LITERALS,
INVALID_UNDERSCORE_LITERALS)
from test.support import os_helper
from test.support.script_helper import run_test_script, make_script
from test.support.script_helper import run_test_script, make_script, run_python_until_end
import os
import token

Expand Down Expand Up @@ -1470,6 +1470,19 @@ def test_comment_at_the_end_of_the_source_without_newline(self):
self.assertEqual(tok_name[tokens[i + 1].exact_type], tok_name[expected_tokens[i]])
self.assertEqual(tok_name[tokens[-1].exact_type], tok_name[token.ENDMARKER])

def test_invalid_character_in_fstring_middle(self):
# See gh-103824
script = b'''F"""
\xe5"""'''

with os_helper.temp_dir() as temp_dir:
filename = os.path.join(temp_dir, "script.py")
with open(filename, 'wb') as file:
file.write(script)
rs, _ = run_python_until_end(filename)
self.assertIn(b"SyntaxError", rs.err)


class UntokenizeTest(TestCase):

def test_bad_input_order(self):
Expand Down
3 changes: 3 additions & 0 deletions Parser/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2552,6 +2552,9 @@ tok_get_fstring_mode(struct tok_state *tok, tokenizer_mode* current_tok, struct
while (end_quote_size != current_tok->f_string_quote_size) {
int c = tok_nextc(tok);
if (c == EOF || (current_tok->f_string_quote_size == 1 && c == '\n')) {
if (tok->decoding_erred)
return MAKE_TOKEN(ERRORTOKEN);

assert(tok->multi_line_start != NULL);
// shift the tok_state's location into
// the start of string, and report the error
Expand Down