This patch finalizes the move from UTF-8 to a default encoding in
the Python Unicode implementation.
The internal buffer used for implementing the buffer protocol
is renamed to defenc to make this change visible. It now holds the
default encoded version of the Unicode object and is calculated
on demand (NULL otherwise).
Since the default encoding defaults to ASCII, this will mean that
Unicode objects which hold non-ASCII characters will no longer
work on C APIs using the "s" or "t" parser markers. C APIs must now
explicitly provide Unicode support via the "u", "U" or "es"/"es#"
parser markers in order to work with non-ASCII Unicode strings.
(Note: this patch will also have to be applied to the 1.6 branch
of the CVS tree.)
diff --git a/Python/getargs.c b/Python/getargs.c
index f1835ba..ceaf6cb 100644
--- a/Python/getargs.c
+++ b/Python/getargs.c
@@ -372,7 +372,7 @@
/* Internal API needed by convertsimple1(): */
extern
-PyObject *_PyUnicode_AsUTF8String(PyObject *unicode,
+PyObject *_PyUnicode_AsDefaultEncodedString(PyObject *unicode,
const char *errors);
/* Convert a non-tuple argument. Return NULL if conversion went OK,
@@ -567,7 +567,8 @@
if (PyString_Check(arg))
*p = PyString_AS_STRING(arg);
else if (PyUnicode_Check(arg)) {
- arg = _PyUnicode_AsUTF8String(arg, NULL);
+ arg = _PyUnicode_AsDefaultEncodedString(
+ arg, NULL);
if (arg == NULL)
return "unicode conversion error";
*p = PyString_AS_STRING(arg);
@@ -612,7 +613,8 @@
else if (PyString_Check(arg))
*p = PyString_AsString(arg);
else if (PyUnicode_Check(arg)) {
- arg = _PyUnicode_AsUTF8String(arg, NULL);
+ arg = _PyUnicode_AsDefaultEncodedString(
+ arg, NULL);
if (arg == NULL)
return "unicode conversion error";
*p = PyString_AS_STRING(arg);
@@ -644,7 +646,7 @@
/* Get 'e' parameter: the encoding name */
encoding = (const char *)va_arg(*p_va, const char *);
if (encoding == NULL)
- return "(encoding is NULL)";
+ encoding = PyUnicode_GetDefaultEncoding();
/* Get 's' parameter: the output buffer to use */
if (*format != 's')