diff options
| author | Martin v. Löwis <martin@v.loewis.de> | 2012-04-20 12:36:47 (GMT) |
|---|---|---|
| committer | Martin v. Löwis <martin@v.loewis.de> | 2012-04-20 12:36:47 (GMT) |
| commit | 63674f4b52aa7c2832fec09a026e24cd521e491b (patch) | |
| tree | 666adcb3196093e019e256d5ab9408df9436ea22 /Lib/test/test_tokenize.py | |
| parent | 8e6e0fdb7fee3796df8b578c1311b5e46005f2d9 (diff) | |
| download | cpython-63674f4b52aa7c2832fec09a026e24cd521e491b.zip cpython-63674f4b52aa7c2832fec09a026e24cd521e491b.tar.gz cpython-63674f4b52aa7c2832fec09a026e24cd521e491b.tar.bz2 | |
Issue #14629: Raise SyntaxError in tokenizer.detect_encoding
if the first two lines have non-UTF-8 characters without an encoding declaration.
Diffstat (limited to 'Lib/test/test_tokenize.py')
| -rw-r--r-- | Lib/test/test_tokenize.py | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/Lib/test/test_tokenize.py b/Lib/test/test_tokenize.py index 9e9656c..63d084d 100644 --- a/Lib/test/test_tokenize.py +++ b/Lib/test/test_tokenize.py @@ -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") |