From: Petr Viktorin Date: Fri, 5 Apr 2024 15:00:29 +0000 (+0200) Subject: gh-116608: Ignore UTF-16 BOM in importlib.resources._functional tests (GH-117569) X-Git-Tag: v3.13.0a6~28 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=4d4a6f1b6aea6dae131ac116f1735a38c3e32cd1;p=thirdparty%2FPython%2Fcpython.git gh-116608: Ignore UTF-16 BOM in importlib.resources._functional tests (GH-117569) gh-116609: Ignore UTF-16 BOM in importlib.resources._functional tests To test the `errors` argument, we read a UTF-16 file as UTF-8 with "backslashreplace" error handling. However, the utf-16 codec adds an endian-specific byte-order mark, so on big-endian machines the expectation doesn't match the test file (which was saved on a little-endian machine). Use endswith to ignore the BOM. --- diff --git a/Lib/test/test_importlib/resources/test_functional.py b/Lib/test/test_importlib/resources/test_functional.py index fd02fc7c0e7b..d60a2bedd897 100644 --- a/Lib/test/test_importlib/resources/test_functional.py +++ b/Lib/test/test_importlib/resources/test_functional.py @@ -32,6 +32,12 @@ class FunctionalAPIBase: with self.subTest(path_parts=path_parts): yield path_parts + def assertEndsWith(self, string, suffix): + """Assert that `string` ends with `suffix`. + + Used to ignore an architecture-specific UTF-16 byte-order mark.""" + self.assertEqual(string[-len(suffix):], suffix) + def test_read_text(self): self.assertEqual( resources.read_text(self.anchor01, 'utf-8.file'), @@ -65,12 +71,12 @@ class FunctionalAPIBase: ), '\x00\x01\x02\x03', ) - self.assertEqual( + self.assertEndsWith( # ignore the BOM resources.read_text( self.anchor01, 'utf-16.file', errors='backslashreplace', ), - 'Hello, UTF-16 world!\n'.encode('utf-16').decode( + 'Hello, UTF-16 world!\n'.encode('utf-16-le').decode( errors='backslashreplace', ), ) @@ -112,9 +118,9 @@ class FunctionalAPIBase: self.anchor01, 'utf-16.file', errors='backslashreplace', ) as f: - self.assertEqual( + self.assertEndsWith( # ignore the BOM f.read(), - 'Hello, UTF-16 world!\n'.encode('utf-16').decode( + 'Hello, UTF-16 world!\n'.encode('utf-16-le').decode( errors='backslashreplace', ), )