Checkpoint. Manipulated things so that string literals are always
unicode, and a few other compensating changes, e.g. str <- unicode,
chr <- unichr, and repr() of a unicode string no longer starts
with 'u'. Lots of unit tests are broken, but some basic things
work, in particular distutils works so the extensions can be built,
and test_builtin.py works.
diff --git a/Objects/moduleobject.c b/Objects/moduleobject.c
index e454fcf..18914d8 100644
--- a/Objects/moduleobject.c
+++ b/Objects/moduleobject.c
@@ -59,6 +59,7 @@
{
PyObject *d;
PyObject *nameobj;
+ char *s;
if (!PyModule_Check(m)) {
PyErr_BadArgument();
return NULL;
@@ -66,11 +67,13 @@
d = ((PyModuleObject *)m)->md_dict;
if (d == NULL ||
(nameobj = PyDict_GetItemString(d, "__name__")) == NULL ||
- !PyString_Check(nameobj))
+ !(PyString_Check(nameobj) || PyUnicode_Check(nameobj)))
{
PyErr_SetString(PyExc_SystemError, "nameless module");
return NULL;
}
+ if (PyUnicode_Check(nameobj))
+ nameobj = _PyUnicode_AsDefaultEncodedString(nameobj, "replace");
return PyString_AsString(nameobj);
}
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index ce28692..e2f1b2f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -2072,7 +2072,6 @@
p = PyString_AS_STRING(repr);
if (quotes) {
- *p++ = 'u';
*p++ = (findchar(s, size, '\'') &&
!findchar(s, size, '"')) ? '"' : '\'';
}
@@ -2081,7 +2080,7 @@
/* Escape quotes and backslashes */
if ((quotes &&
- ch == (Py_UNICODE) PyString_AS_STRING(repr)[1]) || ch == '\\') {
+ ch == (Py_UNICODE) PyString_AS_STRING(repr)[0]) || ch == '\\') {
*p++ = '\\';
*p++ = (char) ch;
continue;
@@ -2167,7 +2166,7 @@
*p++ = (char) ch;
}
if (quotes)
- *p++ = PyString_AS_STRING(repr)[1];
+ *p++ = PyString_AS_STRING(repr)[0];
*p = '\0';
_PyString_Resize(&repr, p - PyString_AS_STRING(repr));