From 4fb3b6f230fbf96613531874d3960117b6892687 Mon Sep 17 00:00:00 2001
From: eternalrights <3147268827@qq.com>
Date: Fri, 15 May 2026 10:32:55 +0800
Subject: [PATCH 1/3] fix junitxml bin_xml_escape: use \U for supplementary
 plane range in illegal_xml_re

---
 changelog/14483.bugfix.rst |  1 +
 src/_pytest/junitxml.py    |  2 +-
 testing/test_junitxml.py   | 10 ++++++++--
 3 files changed, 10 insertions(+), 3 deletions(-)
 create mode 100644 changelog/14483.bugfix.rst

diff --git a/changelog/14483.bugfix.rst b/changelog/14483.bugfix.rst
new file mode 100644
index 00000000000..c1088d8f602
--- /dev/null
+++ b/changelog/14483.bugfix.rst
@@ -0,0 +1 @@
+Fixed ``bin_xml_escape`` in junitxml incorrectly escaping supplementary plane characters (U+10000 and above, including emoji) due to using ``\u`` instead of ``\U`` for the supplementary plane range in the ``illegal_xml_re`` regex.
diff --git a/src/_pytest/junitxml.py b/src/_pytest/junitxml.py
index ae8d2b94d36..a1f2eb265fd 100644
--- a/src/_pytest/junitxml.py
+++ b/src/_pytest/junitxml.py
@@ -56,7 +56,7 @@ def repl(matchobj: re.Match[str]) -> str:
     # Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
     # For an unknown(?) reason, we disallow #x7F (DEL) as well.
     illegal_xml_re = (
-        "[^\u0009\u000a\u000d\u0020-\u007e\u0080-\ud7ff\ue000-\ufffd\u10000-\u10ffff]"
+        "[^\u0009\u000a\u000d\u0020-\u007e\u0080-\ud7ff\ue000-\ufffd\U00010000-\U0010ffff]"
     )
     return re.sub(illegal_xml_re, repl, str(arg))
 
diff --git a/testing/test_junitxml.py b/testing/test_junitxml.py
index 5a603c05bc8..a774874f4c6 100644
--- a/testing/test_junitxml.py
+++ b/testing/test_junitxml.py
@@ -1122,8 +1122,7 @@ def test_invalid_xml_escape() -> None:
         0xFFFE,
         0x0FFFF,
     )  # , 0x110000)
-    valid = (0x9, 0xA, 0x20)
-    # 0xD, 0xD7FF, 0xE000, 0xFFFD, 0x10000, 0x10FFFF)
+    valid = (0x9, 0xA, 0x20, 0xD, 0xD7FF, 0xE000, 0xFFFD, 0x10000, 0x10FFFF)
 
     for i in invalid:
         got = bin_xml_escape(chr(i))
@@ -1136,6 +1135,13 @@ def test_invalid_xml_escape() -> None:
         assert chr(i) == bin_xml_escape(chr(i))
 
 
+def test_bin_xml_escape_supplementary_plane() -> None:
+    assert bin_xml_escape(chr(0x1F600)) == chr(0x1F600)
+    assert bin_xml_escape("test_😀") == "test_😀"
+    assert bin_xml_escape("test_𠀀") == "test_𠀀"
+    assert bin_xml_escape("test_𝄞") == "test_𝄞"
+
+
 def test_logxml_path_expansion(tmp_path: Path, monkeypatch: MonkeyPatch) -> None:
     home_tilde = Path(os.path.expanduser("~")).joinpath("test.xml")
     xml_tilde = LogXML(Path("~", "test.xml"), None)

From e694e4b7fb226a8228b8488cd9bd97b985e7d9b8 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 15 May 2026 02:33:34 +0000
Subject: [PATCH 2/3] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/_pytest/junitxml.py | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/src/_pytest/junitxml.py b/src/_pytest/junitxml.py
index a1f2eb265fd..30c93c88c07 100644
--- a/src/_pytest/junitxml.py
+++ b/src/_pytest/junitxml.py
@@ -55,9 +55,7 @@ def repl(matchobj: re.Match[str]) -> str:
     # The spec range of valid chars is:
     # Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
     # For an unknown(?) reason, we disallow #x7F (DEL) as well.
-    illegal_xml_re = (
-        "[^\u0009\u000a\u000d\u0020-\u007e\u0080-\ud7ff\ue000-\ufffd\U00010000-\U0010ffff]"
-    )
+    illegal_xml_re = "[^\u0009\u000a\u000d\u0020-\u007e\u0080-\ud7ff\ue000-\ufffd\U00010000-\U0010ffff]"
     return re.sub(illegal_xml_re, repl, str(arg))
 
 

From 7521f4dee7e191f7ca2f9113329eac764165a5b9 Mon Sep 17 00:00:00 2001
From: eternalrights <3147268827@qq.com>
Date: Fri, 15 May 2026 14:35:07 +0800
Subject: [PATCH 3/3] fold supplementary plane checks into existing
 test_invalid_xml_escape, drop separate function

---
 testing/test_junitxml.py | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/testing/test_junitxml.py b/testing/test_junitxml.py
index a774874f4c6..0e002d4dde2 100644
--- a/testing/test_junitxml.py
+++ b/testing/test_junitxml.py
@@ -1135,13 +1135,6 @@ def test_invalid_xml_escape() -> None:
         assert chr(i) == bin_xml_escape(chr(i))
 
 
-def test_bin_xml_escape_supplementary_plane() -> None:
-    assert bin_xml_escape(chr(0x1F600)) == chr(0x1F600)
-    assert bin_xml_escape("test_😀") == "test_😀"
-    assert bin_xml_escape("test_𠀀") == "test_𠀀"
-    assert bin_xml_escape("test_𝄞") == "test_𝄞"
-
-
 def test_logxml_path_expansion(tmp_path: Path, monkeypatch: MonkeyPatch) -> None:
     home_tilde = Path(os.path.expanduser("~")).joinpath("test.xml")
     xml_tilde = LogXML(Path("~", "test.xml"), None)