bpo-47000: Make `io.text_encoding()` respects UTF-8 mode (GH-32003)

Co-authored-by: Eric Snow <ericsnowcurrently@gmail.com>

3 files changed, 21 insertions, 6 deletions

diff --git a/Lib/_pyio.py b/Lib/_pyio.py
index fd00d65..e3ff59e 100644
--- a/Lib/_pyio.py
+++ b/Lib/_pyio.py
@@ -44,8 +44,9 @@ def text_encoding(encoding, stacklevel=2):
     """
     A helper function to choose the text encoding.
 
-    When encoding is not None, just return it.
-    Otherwise, return the default text encoding (i.e. "locale").
+    When encoding is not None, this function returns it.
+    Otherwise, this function returns the default text encoding
+    (i.e. "locale" or "utf-8" depends on UTF-8 mode).
 
     This function emits an EncodingWarning if *encoding* is None and
     sys.flags.warn_default_encoding is true.
@@ -55,7 +56,10 @@ def text_encoding(encoding, stacklevel=2):
     However, please consider using encoding="utf-8" for new APIs.
     """
     if encoding is None:
-        encoding = "locale"
+        if sys.flags.utf8_mode:
+            encoding = "utf-8"
+        else:
+            encoding = "locale"
         if sys.flags.warn_default_encoding:
             import warnings
             warnings.warn("'encoding' argument not specified.",
diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py
index 2d0ca87..67be108 100644
--- a/Lib/test/test_io.py
+++ b/Lib/test/test_io.py
@@ -4289,6 +4289,17 @@ class MiscIOTest(unittest.TestCase):
         self.assertTrue(
             warnings[1].startswith(b"<string>:8: EncodingWarning: "))
 
+    def test_text_encoding(self):
+        # PEP 597, bpo-47000. io.text_encoding() returns "locale" or "utf-8"
+        # based on sys.flags.utf8_mode
+        code = "import io; print(io.text_encoding(None))"
+
+        proc = assert_python_ok('-X', 'utf8=0', '-c', code)
+        self.assertEqual(b"locale", proc.out.strip())
+
+        proc = assert_python_ok('-X', 'utf8=1', '-c', code)
+        self.assertEqual(b"utf-8", proc.out.strip())
+
     @support.cpython_only
     # Depending if OpenWrapper was already created or not, the warning is
     # emitted or not. For example, the attribute is already created when this
diff --git a/Lib/test/test_utf8_mode.py b/Lib/test/test_utf8_mode.py
index 2b96f76..308e8e8 100644
--- a/Lib/test/test_utf8_mode.py
+++ b/Lib/test/test_utf8_mode.py
@@ -161,7 +161,7 @@ class UTF8ModeTests(unittest.TestCase):
         filename = __file__
 
         out = self.get_output('-c', code, filename, PYTHONUTF8='1')
-        self.assertEqual(out, 'UTF-8/strict')
+        self.assertEqual(out.lower(), 'utf-8/strict')
 
     def _check_io_encoding(self, module, encoding=None, errors=None):
         filename = __file__
@@ -183,10 +183,10 @@ class UTF8ModeTests(unittest.TestCase):
                               PYTHONUTF8='1')
 
         if not encoding:
-            encoding = 'UTF-8'
+            encoding = 'utf-8'
         if not errors:
             errors = 'strict'
-        self.assertEqual(out, f'{encoding}/{errors}')
+        self.assertEqual(out.lower(), f'{encoding}/{errors}')
 
     def check_io_encoding(self, module):
         self._check_io_encoding(module, encoding="latin1")