From 2515a28230b1a011205f30263da6b01c6bd167a3 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Tue, 30 Jun 2020 03:18:22 +0300
Subject: [PATCH] bpo-41152: IDLE: always use UTF-8 for standard IO streams
 (GH-21214)

---
 Lib/idlelib/NEWS.txt                          |  3 ++
 Lib/idlelib/idle_test/test_outwin.py          |  5 --
 Lib/idlelib/iomenu.py                         | 48 ++-----------------
 Lib/idlelib/outwin.py                         |  4 +-
 .../2020-06-29-14-51-15.bpo-41152.d6mV0C.rst  |  2 +
 5 files changed, 10 insertions(+), 52 deletions(-)
 create mode 100644 Misc/NEWS.d/next/IDLE/2020-06-29-14-51-15.bpo-41152.d6mV0C.rst

diff --git a/Lib/idlelib/NEWS.txt b/Lib/idlelib/NEWS.txt
index c270fcbae2b..7ae29af0b30 100644
--- a/Lib/idlelib/NEWS.txt
+++ b/Lib/idlelib/NEWS.txt
@@ -3,6 +3,9 @@ Released on 2020-10-05?
 ======================================
 
 
+bpo-41152: The encoding of ``stdin``, ``stdout`` and ``stderr`` in IDLE
+is now always UTF-8.
+
 bpo-41144: Make Open Module open a special module such as os.path.
 
 bpo-40723: Make test_idle pass when run after import.
diff --git a/Lib/idlelib/idle_test/test_outwin.py b/Lib/idlelib/idle_test/test_outwin.py
index cd099ecd841..e347bfca7f1 100644
--- a/Lib/idlelib/idle_test/test_outwin.py
+++ b/Lib/idlelib/idle_test/test_outwin.py
@@ -58,11 +58,6 @@ class OutputWindowTest(unittest.TestCase):
         get = self.text.get
         write = self.window.write
 
-        # Test bytes.
-        b = b'Test bytes.'
-        eq(write(b), len(b))
-        eq(get('1.0', '1.end'), b.decode())
-
         # No new line - insert stays on same line.
         delete('1.0', 'end')
         test_text = 'test text'
diff --git a/Lib/idlelib/iomenu.py b/Lib/idlelib/iomenu.py
index 4b2833b8ca5..7f3f656ee28 100644
--- a/Lib/idlelib/iomenu.py
+++ b/Lib/idlelib/iomenu.py
@@ -13,52 +13,12 @@ from tkinter.simpledialog import askstring
 import idlelib
 from idlelib.config import idleConf
 
-if idlelib.testing:  # Set True by test.test_idle to avoid setlocale.
-    encoding = 'utf-8'
-    errors = 'surrogateescape'
+encoding = 'utf-8'
+if sys.platform == 'win32':
+    errors = 'surrogatepass'
 else:
-    # Try setting the locale, so that we can find out
-    # what encoding to use
-    try:
-        import locale
-        locale.setlocale(locale.LC_CTYPE, "")
-    except (ImportError, locale.Error):
-        pass
+    errors = 'surrogateescape'
 
-    if sys.platform == 'win32':
-        encoding = 'utf-8'
-        errors = 'surrogateescape'
-    else:
-        try:
-            # Different things can fail here: the locale module may not be
-            # loaded, it may not offer nl_langinfo, or CODESET, or the
-            # resulting codeset may be unknown to Python. We ignore all
-            # these problems, falling back to ASCII
-            locale_encoding = locale.nl_langinfo(locale.CODESET)
-            if locale_encoding:
-                codecs.lookup(locale_encoding)
-        except (NameError, AttributeError, LookupError):
-            # Try getdefaultlocale: it parses environment variables,
-            # which may give a clue. Unfortunately, getdefaultlocale has
-            # bugs that can cause ValueError.
-            try:
-                locale_encoding = locale.getdefaultlocale()[1]
-                if locale_encoding:
-                    codecs.lookup(locale_encoding)
-            except (ValueError, LookupError):
-                pass
-
-        if locale_encoding:
-            encoding = locale_encoding.lower()
-            errors = 'strict'
-        else:
-            # POSIX locale or macOS
-            encoding = 'ascii'
-            errors = 'surrogateescape'
-        # Encoding is used in multiple files; locale_encoding nowhere.
-        # The only use of 'encoding' below is in _decode as initial value
-        # of deprecated block asking user for encoding.
-        # Perhaps use elsewhere should be reviewed.
 
 coding_re = re.compile(r'^[ \t\f]*#.*?coding[:=][ \t]*([-\w.]+)', re.ASCII)
 blank_re = re.compile(r'^[ \t\f]*(?:[#\r\n]|$)', re.ASCII)
diff --git a/Lib/idlelib/outwin.py b/Lib/idlelib/outwin.py
index 90272b6feb4..5ab08bbaf4b 100644
--- a/Lib/idlelib/outwin.py
+++ b/Lib/idlelib/outwin.py
@@ -6,7 +6,6 @@ import re
 from tkinter import messagebox
 
 from idlelib.editor import EditorWindow
-from idlelib import iomenu
 
 
 file_line_pats = [
@@ -110,8 +109,7 @@ class OutputWindow(EditorWindow):
         Return:
             Length of text inserted.
         """
-        if isinstance(s, bytes):
-            s = s.decode(iomenu.encoding, "replace")
+        assert isinstance(s, str)
         self.text.insert(mark, s, tags)
         self.text.see(mark)
         self.text.update()
diff --git a/Misc/NEWS.d/next/IDLE/2020-06-29-14-51-15.bpo-41152.d6mV0C.rst b/Misc/NEWS.d/next/IDLE/2020-06-29-14-51-15.bpo-41152.d6mV0C.rst
new file mode 100644
index 00000000000..434be10b530
--- /dev/null
+++ b/Misc/NEWS.d/next/IDLE/2020-06-29-14-51-15.bpo-41152.d6mV0C.rst
@@ -0,0 +1,2 @@
+The encoding of ``stdin``, ``stdout`` and ``stderr`` in IDLE is now always
+UTF-8.