mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-31 05:58:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

Issue #14629: Raise SyntaxError in tokenizer.detect_encoding

Browse source 
if the first two lines have non-UTF-8 characters without an encoding declaration.
This commit is contained in:
Martin v. Löwis 2012-04-20 14:36:47 +02:00
parent 8e6e0fdb7f
commit 63674f4b52
3 changed files with 18 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

10
Lib/test/test_tokenize.py
View file

@ -825,6 +825,16 @@ class TestDetectEncoding(TestCase):
found, consumed_lines = detect_encoding(rl)
self.assertEqual(found, "iso-8859-1")
def test_syntaxerror_latin1(self):
# Issue 14629: need to raise SyntaxError if the first
# line(s) have non-UTF-8 characters
lines = (
b'print("\xdf")', # Latin-1: LATIN SMALL LETTER SHARP S
)
readline = self.get_readline(lines)
self.assertRaises(SyntaxError, detect_encoding, readline)
def test_utf8_normalization(self):
# See get_normal_name() in tokenizer.c.
encodings = ("utf-8", "utf-8-mac", "utf-8-unix")