From ce1b747ff68754635b7b12870dfc527184ee3b39 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Wed, 6 Aug 2025 14:35:27 +0200 Subject: [PATCH] gh-58124: Avoid CP_UTF8 in UnicodeDecodeError (#137415) Fix name of the Python encoding in Unicode errors of the code page codec: use "cp65000" and "cp65001" instead of "CP_UTF7" and "CP_UTF8" which are not valid Python code names. --- Lib/test/test_codecs.py | 2 +- .../2025-08-05-17-22-24.gh-issue-58124.q1__53.rst | 3 +++ Objects/unicodeobject.c | 4 ---- Python/codecs.c | 2 +- 4 files changed, 5 insertions(+), 6 deletions(-) create mode 100644 Misc/NEWS.d/next/Core_and_Builtins/2025-08-05-17-22-24.gh-issue-58124.q1__53.rst diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index d8666f7290e7..fd7769e8c275 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -3293,7 +3293,7 @@ class CodePageTest(unittest.TestCase): codecs.code_page_encode, 932, '\xff') self.assertRaisesRegex(UnicodeDecodeError, 'cp932', codecs.code_page_decode, 932, b'\x81\x00', 'strict', True) - self.assertRaisesRegex(UnicodeDecodeError, 'CP_UTF8', + self.assertRaisesRegex(UnicodeDecodeError, 'cp65001', codecs.code_page_decode, self.CP_UTF8, b'\xff', 'strict', True) def check_decode(self, cp, tests): diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2025-08-05-17-22-24.gh-issue-58124.q1__53.rst b/Misc/NEWS.d/next/Core_and_Builtins/2025-08-05-17-22-24.gh-issue-58124.q1__53.rst new file mode 100644 index 000000000000..f875d4c5e785 --- /dev/null +++ b/Misc/NEWS.d/next/Core_and_Builtins/2025-08-05-17-22-24.gh-issue-58124.q1__53.rst @@ -0,0 +1,3 @@ +Fix name of the Python encoding in Unicode errors of the code page codec: +use "cp65000" and "cp65001" instead of "CP_UTF7" and "CP_UTF8" which are not +valid Python code names. Patch by Victor Stinner. diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index 8df7a48284dc..425e4681f0a4 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -7684,10 +7684,6 @@ code_page_name(UINT code_page, PyObject **obj) *obj = NULL; if (code_page == CP_ACP) return "mbcs"; - if (code_page == CP_UTF7) - return "CP_UTF7"; - if (code_page == CP_UTF8) - return "CP_UTF8"; *obj = PyBytes_FromFormat("cp%u", code_page); if (*obj == NULL) diff --git a/Python/codecs.c b/Python/codecs.c index caf8d9d5f3c1..4e9aecfe75c2 100644 --- a/Python/codecs.c +++ b/Python/codecs.c @@ -1204,7 +1204,7 @@ get_standard_encoding_impl(const char *encoding, int *bytelength) } } } - else if (strcmp(encoding, "CP_UTF8") == 0) { + else if (strcmp(encoding, "cp65001") == 0) { *bytelength = 3; return ENC_UTF8; } -- 2.47.2