Make identifiers str (not str8) objects throughout.
This affects the parser, various object implementations,
and all places that put identifiers into C string literals.
In testing, a number of crashes occurred as code would
fail when the recursion limit was reached (such as the
Unicode interning dictionary having key/value pairs where
key is not value). To solve these, I added an overflowed
flag, which allows for 50 more recursions after the
limit was reached and the exception was raised, and
a recursion_critical flag, which indicates that recursion
absolutely must be allowed, i.e. that a certain call
must not cause a stack overflow exception.
There are still some places where both str and str8 are
accepted as identifiers; these should eventually be
removed.
diff --git a/Objects/codeobject.c b/Objects/codeobject.c
index 6763950..c735193 100644
--- a/Objects/codeobject.c
+++ b/Objects/codeobject.c
@@ -32,10 +32,10 @@
for (i = PyTuple_GET_SIZE(tuple); --i >= 0; ) {
PyObject *v = PyTuple_GET_ITEM(tuple, i);
- if (v == NULL || !PyString_CheckExact(v)) {
+ if (v == NULL || !PyUnicode_CheckExact(v)) {
Py_FatalError("non-string found in code slot");
}
- PyString_InternInPlace(&PyTuple_GET_ITEM(tuple, i));
+ PyUnicode_InternInPlace(&PyTuple_GET_ITEM(tuple, i));
}
}
@@ -58,7 +58,7 @@
varnames == NULL || !PyTuple_Check(varnames) ||
freevars == NULL || !PyTuple_Check(freevars) ||
cellvars == NULL || !PyTuple_Check(cellvars) ||
- name == NULL || !PyString_Check(name) ||
+ name == NULL || (!PyString_Check(name) && !PyUnicode_Check(name)) ||
filename == NULL || !PyString_Check(filename) ||
lnotab == NULL || !PyString_Check(lnotab) ||
!PyObject_CheckReadBuffer(code)) {
@@ -148,10 +148,10 @@
for (i = 0; i < len; i++) {
item = PyTuple_GET_ITEM(tup, i);
- if (PyString_CheckExact(item)) {
+ if (PyUnicode_CheckExact(item)) {
Py_INCREF(item);
}
- else if (!PyString_Check(item)) {
+ else if (!PyUnicode_Check(item)) {
PyErr_Format(
PyExc_TypeError,
"name tuples must contain only "
@@ -161,9 +161,9 @@
return NULL;
}
else {
- item = PyString_FromStringAndSize(
- PyString_AS_STRING(item),
- PyString_GET_SIZE(item));
+ item = PyUnicode_FromUnicode(
+ PyUnicode_AS_UNICODE(item),
+ PyUnicode_GET_SIZE(item));
if (item == NULL) {
Py_DECREF(newtuple);
return NULL;