From 7915c96ffd7ddc5cb6d54015ee4c31255a416892 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C5=81ukasz=20Langa?= <lukasz@langa.pl>
Date: Fri, 16 Jul 2021 15:24:02 +0200
Subject:  bpo-44647: Add a permanent Unicode-valued env var to regrtest 
 (#27187)

---
 Lib/test/libregrtest/setup.py                                  | 10 ++++++++++
 Lib/test/test_regrtest.py                                      | 10 +++++++++-
 .../NEWS.d/next/Tests/2021-07-16-14-02-33.bpo-44647.5LzqIy.rst |  4 ++++
 3 files changed, 23 insertions(+), 1 deletion(-)
 create mode 100644 Misc/NEWS.d/next/Tests/2021-07-16-14-02-33.bpo-44647.5LzqIy.rst

diff --git a/Lib/test/libregrtest/setup.py b/Lib/test/libregrtest/setup.py
index 345b584..f9460ae 100644
--- a/Lib/test/libregrtest/setup.py
+++ b/Lib/test/libregrtest/setup.py
@@ -14,6 +14,9 @@ from test.libregrtest.utils import (setup_unraisable_hook,
                                     setup_threading_excepthook)
 
 
+UNICODE_GUARD_ENV = "PYTHONREGRTEST_UNICODE_GUARD"
+
+
 def setup_tests(ns):
     try:
         stderr_fd = sys.__stderr__.fileno()
@@ -98,6 +101,13 @@ def setup_tests(ns):
         from test.support.testresult import RegressionTestResult
         RegressionTestResult.USE_XML = True
 
+    # Ensure there's a non-ASCII character in env vars at all times to force
+    # tests consider this case. See BPO-44647 for details.
+    os.environ.setdefault(
+        UNICODE_GUARD_ENV,
+        "\N{SMILING FACE WITH SUNGLASSES}",
+    )
+
 
 def replace_stdout():
     """Set stdout encoder error handler to backslashreplace (as stderr error
diff --git a/Lib/test/test_regrtest.py b/Lib/test/test_regrtest.py
index 054776c..75fa6f2 100644
--- a/Lib/test/test_regrtest.py
+++ b/Lib/test/test_regrtest.py
@@ -19,7 +19,7 @@ import unittest
 from test import libregrtest
 from test import support
 from test.support import os_helper
-from test.libregrtest import utils
+from test.libregrtest import utils, setup
 
 
 Py_DEBUG = hasattr(sys, 'gettotalrefcount')
@@ -1298,6 +1298,14 @@ class ArgsTestCase(BaseTestCase):
         self.assertIn("Warning -- Uncaught thread exception", output)
         self.assertIn("Exception: bug in thread", output)
 
+    def test_unicode_guard_env(self):
+        guard = os.environ.get(setup.UNICODE_GUARD_ENV)
+        self.assertIsNotNone(guard, f"{setup.UNICODE_GUARD_ENV} not set")
+        if guard != "\N{SMILING FACE WITH SUNGLASSES}":
+            # Skip to signify that the env var value was changed by the user;
+            # possibly to something ASCII to work around Unicode issues.
+            self.skipTest("Modified guard")
+
     def test_cleanup(self):
         dirname = os.path.join(self.tmptestdir, "test_python_123")
         os.mkdir(dirname)
diff --git a/Misc/NEWS.d/next/Tests/2021-07-16-14-02-33.bpo-44647.5LzqIy.rst b/Misc/NEWS.d/next/Tests/2021-07-16-14-02-33.bpo-44647.5LzqIy.rst
new file mode 100644
index 0000000..e4b2be2
--- /dev/null
+++ b/Misc/NEWS.d/next/Tests/2021-07-16-14-02-33.bpo-44647.5LzqIy.rst
@@ -0,0 +1,4 @@
+Added a permanent Unicode-valued environment variable to regression tests to
+ensure they handle this use case in the future. If your test environment
+breaks because of that, report a bug to us, and temporarily set
+PYTHONREGRTEST_UNICODE_GUARD=0 in your test environment.
-- 
cgit v0.12