Issue #7820: The parser tokenizer restores all bytes in the right if the BOM

check fails.

Fix an assertion in pydebug mode.

1 files changed, 11 insertions, 0 deletions

diff --git a/Lib/test/test_pep263.py b/Lib/test/test_pep263.py
index e4faa9f..9286467 100644
--- a/Lib/test/test_pep263.py
+++ b/Lib/test/test_pep263.py
@@ -30,6 +30,17 @@ class PEP263Test(unittest.TestCase):
         self.assertEqual(d['a'], d['b'])
         self.assertEqual(len(d['a']), len(d['b']))
 
+    def test_issue7820(self):
+        # Ensure that check_bom() restores all bytes in the right order if
+        # check_bom() fails in pydebug mode: a buffer starts with the first
+        # byte of a valid BOM, but next bytes are different
+
+        # one byte in common with the UTF-16-LE BOM
+        self.assertRaises(SyntaxError, eval, '\xff\x20')
+
+        # two bytes in common with the UTF-8 BOM
+        self.assertRaises(SyntaxError, eval, '\xef\xbb\x20')
+
 def test_main():
     test_support.run_unittest(PEP263Test)