junitxml: fix supplementary plane characters incorrectly escaped (#14484)

Closes #14483

Author: EternalRights

changelog/14483.bugfix.rst

@@ -0,0 +1 @@
+Fixed JUnit XML report incorrectly escaping high Unicode codepoints (supplementary plane characters like emoji) in test failure messages. -- by :user:`EternalRights`

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\u10000-\u10ffff]"
-    )
+    illegal_xml_re = "[^\u0009\u000a\u000d\u0020-\u007e\u0080-\ud7ff\ue000-\ufffd\U00010000-\U0010ffff]"
     return re.sub(illegal_xml_re, repl, str(arg))
 
 

testing/test_junitxml.py

@@ -1114,9 +1114,6 @@ def test_invalid_xml_escape() -> None:
     # Test some more invalid xml chars, the full range should be
     # tested really but let's just test the edges of the ranges
     # instead.
-    # XXX This only tests low unicode character points for now as
-    #     there are some issues with the testing infrastructure for
-    #     the higher ones.
     # XXX Testing 0xD (\r) is tricky as it overwrites the just written
     #     line in the output, so we skip it too.
     invalid = (
@@ -1131,9 +1128,8 @@ def test_invalid_xml_escape() -> None:
         0xDFFF,
         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))