gh-116608: Ignore UTF-16 BOM in importlib.resources._functional tests (GH-117569)

encukou · jaraco · commit 8c274e5e6663 · 2024-08-14T16:45:15.000-04:00
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/importlib_resources/tests/test_functional.py b/importlib_resources/tests/test_functional.py
@@ -36,6 +36,12 @@ def _gen_resourcetxt_path_parts(self):
             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'),
@@ -76,13 +82,13 @@ def test_read_text(self):
             ),
             '\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',
             ),
         )
@@ -128,9 +134,9 @@ def test_open_text(self):
             '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',
                 ),
             )
