commit 7b7a21bc4fd063b26a2d1882fddc458861497812
author Lysandros Nikolaou <lisandrosnik@gmail.com> Mon May 18 20:32:03 2020 +0300
committer GitHub <noreply@github.com> Mon May 18 18:32:03 2020 +0100
tree 31eb7583108b66930b3937546d786d2c9b0328d6
parent 08b47c367a08f571a986366aa33828d3951fa88d

bpo-40661: Fix segfault when parsing invalid input (GH-20165)

Fix segfaults when parsing very complex invalid input, like `import äˆ ð£„¯ð¢·žð±‹á”€ð””ð‘©±å®ä±¬ð©¾\n𗶽`.

Co-authored-by: Guido van Rossum <guido@python.org>
Co-authored-by: Pablo Galindo <pablogsal@gmail.com>

Lib/test/test_peg_parser.py

diff --git a/Lib/test/test_peg_parser.py b/Lib/test/test_peg_parser.py
index 9614e45..6ccb257 100644
--- a/Lib/test/test_peg_parser.py
+++ b/Lib/test/test_peg_parser.py
@@ -591,6 +591,7 @@
     ("f-string_single_closing_brace", "f'}'"),
     ("from_import_invalid", "from import import a"),
     ("from_import_trailing_comma", "from a import b,"),
+    ("import_non_ascii_syntax_error", "import ä £"),
     # This test case checks error paths involving tokens with uninitialized
     # values of col_offset and end_col_offset.
     ("invalid indentation",

Lib/test/test_syntax.py

diff --git a/Lib/test/test_syntax.py b/Lib/test/test_syntax.py
index 60c7d9f..87ceced 100644
--- a/Lib/test/test_syntax.py
+++ b/Lib/test/test_syntax.py
@@ -659,6 +659,9 @@
     Traceback (most recent call last):
     SyntaxError: cannot assign to __debug__
 
+    >>> import ä £
+    Traceback (most recent call last):
+    SyntaxError: invalid character '£' (U+00A3)
 """
 
 import re