Issue #4388: On Mac OS X, decode command line arguments from UTF-8, instead of
the locale encoding. If the LANG (and LC_ALL and LC_CTYPE) environment variable
is not set, the locale encoding is ISO-8859-1, whereas most programs (including
Python) expect UTF-8. Python already uses UTF-8 for the filesystem encoding and
to encode command line arguments on this OS.
diff --git a/Modules/python.c b/Modules/python.c
index 47685a4..18f9b3d 100644
--- a/Modules/python.c
+++ b/Modules/python.c
@@ -15,6 +15,10 @@
}
#else
+#ifdef __APPLE__
+extern wchar_t* _Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size);
+#endif
+
int
main(int argc, char **argv)
{
@@ -41,7 +45,11 @@
oldloc = strdup(setlocale(LC_ALL, NULL));
setlocale(LC_ALL, "");
for (i = 0; i < argc; i++) {
+#ifdef __APPLE__
+ argv_copy[i] = _Py_DecodeUTF8_surrogateescape(argv[i], strlen(argv[i]));
+#else
argv_copy[i] = _Py_char2wchar(argv[i], NULL);
+#endif
if (!argv_copy[i])
return 1;
argv_copy2[i] = argv_copy[i];