From 2a2bc82cef9c6ae0b8de833e2b4aee37519de9d7 Mon Sep 17 00:00:00 2001
From: Serhiy Storchaka <storchaka@gmail.com>
Date: Thu, 16 Oct 2025 10:54:41 +0300
Subject: [PATCH] gh-130567: Remove optimistic allocation in locale.strxfrm()
 (GH-137143)

On modern systems, the result of wcsxfrm() is much larger the size of
the input string (from 4+2*n on Windows to 4+5*n on Linux for simple
ASCII strings), so optimistic allocation of the buffer of the same size
never works.

The exception is if the locale is "C" (or unset), but in that case the `wcsxfrm`
call should be fast (and calling `locale.strxfrm()` doesn't make too much
sense in the first place).
---
 Modules/_localemodule.c | 36 ++++++++++++------------------------
 1 file changed, 12 insertions(+), 24 deletions(-)

diff --git a/Modules/_localemodule.c b/Modules/_localemodule.c
index cb448b14d8c..7174eebd0c9 100644
--- a/Modules/_localemodule.c
+++ b/Modules/_localemodule.c
@@ -455,35 +455,23 @@ _locale_strxfrm_impl(PyObject *module, PyObject *str)
         goto exit;
     }
 
-    /* assume no change in size, first */
-    n1 = n1 + 1;
-    /* Yet another +1 is needed to work around a platform bug in wcsxfrm()
-     * on macOS. See gh-130567. */
-    buf = PyMem_New(wchar_t, n1+1);
-    if (!buf) {
-        PyErr_NoMemory();
-        goto exit;
-    }
     errno = 0;
-    n2 = wcsxfrm(buf, s, n1);
+    n2 = wcsxfrm(NULL, s, 0);
     if (errno && errno != ERANGE) {
         PyErr_SetFromErrno(PyExc_OSError);
         goto exit;
     }
-    if (n2 >= (size_t)n1) {
-        /* more space needed */
-        wchar_t * new_buf = PyMem_Realloc(buf, (n2+1)*sizeof(wchar_t));
-        if (!new_buf) {
-            PyErr_NoMemory();
-            goto exit;
-        }
-        buf = new_buf;
-        errno = 0;
-        n2 = wcsxfrm(buf, s, n2+1);
-        if (errno) {
-            PyErr_SetFromErrno(PyExc_OSError);
-            goto exit;
-        }
+    buf = PyMem_New(wchar_t, n2+1);
+    if (!buf) {
+        PyErr_NoMemory();
+        goto exit;
+    }
+
+    errno = 0;
+    n2 = wcsxfrm(buf, s, n2+1);
+    if (errno) {
+        PyErr_SetFromErrno(PyExc_OSError);
+        goto exit;
     }
     /* The result is just a sequence of integers, they are not necessary
        Unicode code points, so PyUnicode_FromWideChar() cannot be used