bpo-29240: PEP 540: Add a new UTF-8 Mode (#855)
* Add -X utf8 command line option, PYTHONUTF8 environment variable
and a new sys.flags.utf8_mode flag.
* If the LC_CTYPE locale is "C" at startup: enable automatically the
UTF-8 mode.
* Add _winapi.GetACP(). encodings._alias_mbcs() now calls
_winapi.GetACP() to get the ANSI code page
* locale.getpreferredencoding() now returns 'UTF-8' in the UTF-8
mode. As a side effect, open() now uses the UTF-8 encoding by
default in this mode.
* Py_DecodeLocale() and Py_EncodeLocale() now use the UTF-8 encoding
in the UTF-8 Mode.
* Update subprocess._args_from_interpreter_flags() to handle -X utf8
* Skip some tests relying on the current locale if the UTF-8 mode is
enabled.
* Add test_utf8mode.py.
* _Py_DecodeUTF8_surrogateescape() gets a new optional parameter to
return also the length (number of wide characters).
* pymain_get_global_config() and pymain_set_global_config() now
always copy flag values, rather than only copying if the new value
is greater than the old value.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 8d4fea8..c7480a0 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -5079,16 +5079,17 @@
return NULL;
}
-#if defined(__APPLE__) || defined(__ANDROID__)
-/* Simplified UTF-8 decoder using surrogateescape error handler,
- used to decode the command line arguments on Mac OS X and Android.
+/* UTF-8 decoder using the surrogateescape error handler .
- Return a pointer to a newly allocated wide character string (use
- PyMem_RawFree() to free the memory), or NULL on memory allocation error. */
+ On success, return a pointer to a newly allocated wide character string (use
+ PyMem_RawFree() to free the memory) and write the output length (in number
+ of wchar_t units) into *p_wlen (if p_wlen is set).
+ On memory allocation failure, return -1 and write (size_t)-1 into *p_wlen
+ (if p_wlen is set). */
wchar_t*
-_Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size)
+_Py_DecodeUTF8_surrogateescape(const char *s, Py_ssize_t size, size_t *p_wlen)
{
const char *e;
wchar_t *unicode;
@@ -5096,11 +5097,20 @@
/* Note: size will always be longer than the resulting Unicode
character count */
- if (PY_SSIZE_T_MAX / (Py_ssize_t)sizeof(wchar_t) < (size + 1))
+ if (PY_SSIZE_T_MAX / (Py_ssize_t)sizeof(wchar_t) < (size + 1)) {
+ if (p_wlen) {
+ *p_wlen = (size_t)-1;
+ }
return NULL;
+ }
+
unicode = PyMem_RawMalloc((size + 1) * sizeof(wchar_t));
- if (!unicode)
+ if (!unicode) {
+ if (p_wlen) {
+ *p_wlen = (size_t)-1;
+ }
return NULL;
+ }
/* Unpack UTF-8 encoded data */
e = s + size;
@@ -5130,10 +5140,12 @@
}
}
unicode[outpos] = L'\0';
+ if (p_wlen) {
+ *p_wlen = outpos;
+ }
return unicode;
}
-#endif /* __APPLE__ or __ANDROID__ */
/* Primary internal function which creates utf8 encoded bytes objects.