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.

4 files changed, 50 insertions, 7 deletions

diff --git a/Include/ceval.h b/Include/ceval.h
index 15b29c6..c9c59eb 100644
--- a/Include/ceval.h
+++ b/Include/ceval.h
@@ -50,7 +50,10 @@ PyAPI_FUNC(int) Py_GetRecursionLimit(void);
 	    (_Py_MakeRecCheck(PyThreadState_GET()->recursion_depth) &&  \
 	     _Py_CheckRecursiveCall(where))
 #define Py_LeaveRecursiveCall()				\
-	    (--PyThreadState_GET()->recursion_depth)
+    do{ if((--PyThreadState_GET()->recursion_depth) <   \
+	   _Py_CheckRecursionLimit - 50);               \
+	  PyThreadState_GET()->overflowed = 0;          \
+    } while(0)
 PyAPI_FUNC(int) _Py_CheckRecursiveCall(char *where);
 PyAPI_DATA(int) _Py_CheckRecursionLimit;
 #ifdef USE_STACKCHECK
@@ -59,6 +62,14 @@ PyAPI_DATA(int) _Py_CheckRecursionLimit;
 #  define _Py_MakeRecCheck(x)  (++(x) > _Py_CheckRecursionLimit)
 #endif
 
+#define Py_ALLOW_RECURSION \
+  do { unsigned char _old = PyThreadState_GET()->recursion_critical;\
+    PyThreadState_GET()->recursion_critical = 1;
+
+#define Py_END_ALLOW_RECURSION \
+    PyThreadState_GET()->recursion_critical = _old; \
+  } while(0);
+
 PyAPI_FUNC(const char *) PyEval_GetFuncName(PyObject *);
 PyAPI_FUNC(const char *) PyEval_GetFuncDesc(PyObject *);
 
diff --git a/Include/pystate.h b/Include/pystate.h
index 4919d99..0681e65 100644
--- a/Include/pystate.h
+++ b/Include/pystate.h
@@ -61,6 +61,10 @@ typedef struct _ts {
 
     struct _frame *frame;
     int recursion_depth;
+    char overflowed; /* The stack has overflowed. Allow 50 more calls
+		        to handle the runtime error. */
+    char recursion_critical; /* The current calls must not cause 
+				a stack overflow. */
     /* 'tracing' keeps track of the execution depth when tracing/profiling.
        This is to prevent the actual trace/profile code from being recorded in
        the trace/profile. */
diff --git a/Include/stringobject.h b/Include/stringobject.h
index 2b8cc2f..0a932f0 100644
--- a/Include/stringobject.h
+++ b/Include/stringobject.h
@@ -84,8 +84,8 @@ PyAPI_FUNC(void) _Py_ReleaseInternedStrings(void);
 #define PyString_CHECK_INTERNED(op) (((PyStringObject *)(op))->ob_sstate)
 
 /* Macro, trading safety for speed */
-#define PyString_AS_STRING(op) (((PyStringObject *)(op))->ob_sval)
-#define PyString_GET_SIZE(op)  (((PyStringObject *)(op))->ob_size)
+#define PyString_AS_STRING(op) (assert(PyString_Check(op)),(((PyStringObject *)(op))->ob_sval))
+#define PyString_GET_SIZE(op)  (assert(PyString_Check(op)),(((PyStringObject *)(op))->ob_size))
 
 /* _PyString_Join(sep, x) is like sep.join(x).  sep must be PyStringObject*,
    x must be an iterable object. */
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 2a27dbc..1f6b729 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -410,13 +410,13 @@ PyAPI_DATA(PyTypeObject) PyUnicode_Type;
 
 /* Fast access macros */
 #define PyUnicode_GET_SIZE(op) \
-        (((PyUnicodeObject *)(op))->length)
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->length))
 #define PyUnicode_GET_DATA_SIZE(op) \
-        (((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE))
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE)))
 #define PyUnicode_AS_UNICODE(op) \
-        (((PyUnicodeObject *)(op))->str)
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->str))
 #define PyUnicode_AS_DATA(op) \
-        ((const char *)((PyUnicodeObject *)(op))->str)
+        (assert(PyUnicode_Check(op)),((const char *)((PyUnicodeObject *)(op))->str))
 
 /* --- Constants ---------------------------------------------------------- */
 
@@ -627,6 +627,13 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
 PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
     PyObject *, const char *);
 
+/* Return a char* holding the default encoded value of the
+   Unicode object. 
+*/
+
+PyAPI_FUNC(char *) PyUnicode_AsString(PyObject*);
+
+
 /* Returns the currently active default encoding.
 
    The default encoding is currently implemented as run-time settable
@@ -1193,6 +1200,11 @@ PyAPI_FUNC(int) PyUnicode_Compare(
     PyObject *right		/* Right string */
     );
 
+PyAPI_FUNC(int) PyUnicode_CompareWithASCIIString(
+    PyObject *left,
+    const char *right
+    );
+
 /* Rich compare two strings and return one of the following:
 
    - NULL in case an exception was raised
@@ -1310,6 +1322,22 @@ PyAPI_FUNC(int) _PyUnicode_IsAlpha(
     Py_UNICODE ch 	/* Unicode character */
     );
 
+PyAPI_FUNC(size_t) Py_UNICODE_strlen(const Py_UNICODE *u);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
+    Py_UNICODE *s1, const Py_UNICODE *s2);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
+    Py_UNICODE *s1, const Py_UNICODE *s2, size_t n);
+
+PyAPI_FUNC(int) Py_UNICODE_strcmp(
+    const Py_UNICODE *s1, const Py_UNICODE *s2);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
+    const Py_UNICODE *s, Py_UNICODE c
+    );
+
+
 #ifdef __cplusplus
 }
 #endif