From e991645c461f1565ab478a3d84cf9d66ae143270 Mon Sep 17 00:00:00 2001
From: Rujul Talekar <113801876+Roojool@users.noreply.github.com>
Date: Mon, 12 Oct 2026 12:56:25 +0530
Subject: [PATCH] fix(tools): simulate cp1252 default encoding on Python 3.10
 in pr_overlap tests

command_output patched subprocess._text_encoding, which does not exist on Python 3.10, so all eight tests errored before their assertions. Use subprocess._text_encoding where available and map io.TextIOWrapper locale to cp1252 on older interpreters, so a subprocess with no explicit encoding decodes as cp1252 on both. Add a behavioral check that default decodes as cp1252 while explicit utf-8 stays correct.

Authored by Rujul Talekar, with Muse Spark 1.3 assistance.
---
 tools/tests/test_pr_overlap_encoding.py | 28 ++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/tools/tests/test_pr_overlap_encoding.py b/tools/tests/test_pr_overlap_encoding.py
index 2d2b92c42..73082080d 100644
--- a/tools/tests/test_pr_overlap_encoding.py
+++ b/tools/tests/test_pr_overlap_encoding.py
@@ -1,4 +1,5 @@
 from contextlib import contextmanager
+import io
 import json
 import os
 from pathlib import Path
@@ -16,6 +17,23 @@ UNICODE = "Quoted \u201cmetadata\u201d, Y\u014dtei and \U0001f3ae"
 TREE = "a" * 40
 
 
+@contextmanager
+def simulated_cp1252():
+    if hasattr(subprocess, "_text_encoding"):
+        with patch.object(subprocess, "_text_encoding", return_value="cp1252"):
+            yield
+    else:
+        wrapper = io.TextIOWrapper
+
+        def fake_wrapper(buffer, encoding=None, *args, **kwargs):
+            if encoding == "locale":
+                encoding = "cp1252"
+            return wrapper(buffer, encoding=encoding, *args, **kwargs)
+
+        with patch.object(io, "TextIOWrapper", new=fake_wrapper):
+            yield
+
+
 @contextmanager
 def command_output(stdout, stderr="", returncode=0):
     code = ("import os, sys\n"
@@ -26,7 +44,7 @@ def command_output(stdout, stderr="", returncode=0):
     def run(command, **kwargs):
         return RUN([sys.executable, "-c", code], **kwargs)
 
-    with patch.object(subprocess, "_text_encoding", return_value="cp1252"), \
+    with simulated_cp1252(), \
             patch.object(subprocess, "run", side_effect=run):
         yield
 
@@ -75,6 +93,14 @@ class EncodingTests(unittest.TestCase):
             with self.assertRaisesRegex(RuntimeError, UNICODE):
                 pr_overlap.merge("main", "topic")
 
+    def test_default_encoding_uses_simulated_cp1252(self):
+        code = "import os;os.write(1," + repr(UNICODE.encode("utf-8")) + ")"
+        with simulated_cp1252():
+            default = RUN([sys.executable, "-c", code], capture_output=True, text=True, errors="replace")
+            self.assertEqual(default.stdout, UNICODE.encode("utf-8").decode("cp1252", errors="replace"))
+            explicit = RUN([sys.executable, "-c", code], capture_output=True, text=True, encoding="utf-8")
+            self.assertEqual(explicit.stdout, UNICODE)
+
     def test_git_diff_survives_invalid_utf8(self):
         with TemporaryDirectory() as directory:
             repo = Path(directory)