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

Fix segfaults when parsing very complex invalid input, like `import äˆ ð£„¯ð¢·žð±‹á”€ð””ð‘©±å®ä±¬ð©¾\nð—¶½`. Co-authored-by: Guido van Rossum <[email protected]> Co-authored-by: Pablo Galindo <[email protected]>
eltociear · May 18, 2020 · 7b7a21b · 7b7a21b
1 parent 08b47c3
commit 7b7a21b
Show file tree

Hide file tree

Showing 4 changed files with 1,603 additions and 8 deletions.
diff --git a/Lib/test/test_peg_parser.py b/Lib/test/test_peg_parser.py
@@ -591,6 +591,7 @@ def f(*a, b):
     ("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",

diff --git 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