Add a C API for sets and frozensets.

5 files changed, 210 insertions, 12 deletions

diff --git a/Doc/api/concrete.tex b/Doc/api/concrete.tex
index e174bee..2f37be5 100644
--- a/Doc/api/concrete.tex
+++ b/Doc/api/concrete.tex
@@ -2897,3 +2897,128 @@ Macros for the convenience of modules implementing the DB API:
   tuple suitable for passing to \code{datetime.date.fromtimestamp()}.
   \versionadded{2.4}
 \end{cfuncdesc}
+
+
+\subsection{Set Objects \label{setObjects}}
+\sectionauthor{Raymond D. Hettinger}{python@rcn.com}                     
+
+\obindex{set}
+\obindex{frozenset}
+\versionadded{2.5}
+
+This section details the public API for \class{set} and \class{frozenset}
+objects.  Any functionality not listed below is best accessed using the
+abstract object API (including
+\cfunction{PyObject_CallMethod()}, \cfunction{PyObject_RichCompareBool()}, 
+\cfunction{PyObject_Hash()}, \cfunction{PyObject_Repr()}, 
+\cfunction{PyObject_IsTrue()}, \cfunction{PyObject_Print()}, and
+\cfunction{PyObject_GetIter()}).                  
+                      
+\begin{ctypedesc}{PySetObject}
+  This subtype of \ctype{PyObject} is used to hold the internal data for
+  both \class{set} and \class{frozenset} objects.  It is like a
+  \ctype{PyDictObject} in that it is a fixed size for small sets
+  (much like tuple storage) and will point to a separate, variable sized
+  block of memory for medium and large sized sets (much like list storage).
+  None of the fields of this structure should be considered public and
+  are subject to change.  All access should be done through the
+  documented API.  
+
+\end{ctypedesc}
+
+\begin{cvardesc}{PyTypeObject}{PySet_Type}
+  This is an instance of \ctype{PyTypeObject} representing the Python
+  \class{set} type.
+\end{cvardesc}
+
+\begin{cvardesc}{PyTypeObject}{PyFrozenSet_Type}
+  This is an instance of \ctype{PyTypeObject} representing the Python
+  \class{frozenset} type.
+\end{cvardesc}
+
+
+The following type check macros work on pointers to any Python object.
+Likewise, the constructor functions work with any iterable Python object.
+
+\begin{cfuncdesc}{int}{PyAnySet_Check}{PyObject *p}
+  Returns true if \var{p} is a \class{set} object, a \class{frozenset} 
+  object, or an instance of a subtype.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyAnySet_CheckExact}{PyObject *p}
+  Returns true if \var{p} is a \class{set} object or a \class{frozenset}
+  object but not an instance of a subtype.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PyFrozenSet_CheckExact}{PyObject *p}
+  Returns true if \var{p} is a \class{frozenset} object
+  but not an instance of a subtype.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PySet_New}{PyObject *iterable}
+  Returns a new \class{set} containing objects returned by the
+  \var{iterable}.  The \var{iterable} may be \NULL{} to create a
+  new empty set.  Returns the new set on success or \NULL{} on
+  failure.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PyFrozenSet_New}{PyObject *iterable}
+  Returns a new \class{frozenset} containing objects returned by the
+  \var{iterable}.  The \var{iterable} may be \NULL{} to create a
+  new empty frozenset.  Returns the new set on success or \NULL{} on
+  failure.
+\end{cfuncdesc}
+
+
+The following functions and macros are available for instances of
+\class{set} or \class{frozenset} or instances of their subtypes.
+
+\begin{cfuncdesc}{int}{PySet_Size}{PyObject *anyset}
+  Returns the length of a \class{set} or \class{frozenset} object.
+  Equivalent to \samp{len(\var{anyset})}.  Raises a
+  \exception{PyExc_SystemError} if the argument is not a \class{set},
+  \class{frozenset}, or an instance of a subtype.
+  \bifuncindex{len}
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PySet_GET_SIZE}{PyObject *anyset}
+  Macro form of \cfunction{PySet_Size()} without error checking.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PySet_Contains}{PyObject *anyset, PyObject *key}
+  Returns 1 if found, 0 if not found, and -1 if an error is
+  encountered.  Unlike the Python \method{__contains__()} method, this
+  function does not automatically convert unhashable sets into temporary
+  frozensets.  Raises a \exception{TypeError} if the key is unhashable.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{int}{PySet_Discard}{PyObject *anyset, PyObject *key}
+  Returns 1 if found and removed, 0 if not found (no action taken),
+  and -1 if an error is encountered.  Does not raise \exception{KeyError}
+  for missing keys.  Raises a \exception{TypeError} if the key is unhashable.
+  Unlike the Python \method{discard()} method, this function does
+  not automatically convert unhashable sets into temporary frozensets.  
+\end{cfuncdesc}
+
+
+The following functions are available for instances of \class{set} or
+its subtypes but not for instances of \class{frozenset} or its subtypes.
+
+\begin{cfuncdesc}{int}{PySet_Add}{PyObject *set, PyObject *key}
+  Adds \var{key} to a \class{set} instance.  Does not apply to
+  \class{frozenset} instances.  Returns 0 on success or -1 on failure.
+  Raises a \exception{TypeError} if the key is unhashable.
+  Raises a \exception{MemoryError} if there is no room to grow.
+  Raises a \exception{SystemError} if \var{key} is an not an instance
+  of \class{set} or its subtype.
+\end{cfuncdesc}
+
+\begin{cfuncdesc}{PyObject*}{PySet_Pop}{PyObject *set}
+  Returns a new reference to an arbitrary object in the \var{set},
+  and removes the object from the \var{set}.  Returns \NULL{} on
+  failure.  Raises \exception{KeyError} if the set is empty.
+  Raises a \exception{SystemError} if \var{key} is an not an instance
+  of \class{set} or its subtype.                        
+\end{cfuncdesc}
+
+
diff --git a/Include/setobject.h b/Include/setobject.h
index 6a829f0..b6849e1 100644
--- a/Include/setobject.h
+++ b/Include/setobject.h
@@ -74,6 +74,15 @@ PyAPI_DATA(PyTypeObject) PyFrozenSet_Type;
 	  PyType_IsSubtype((ob)->ob_type, &PySet_Type) || \
 	  PyType_IsSubtype((ob)->ob_type, &PyFrozenSet_Type))
 
+PyAPI_FUNC(PyObject *) PySet_New(PyObject *);
+PyAPI_FUNC(PyObject *) PyFrozenSet_New(PyObject *);
+PyAPI_FUNC(int) PySet_Size(PyObject *anyset);
+#define PySet_GET_SIZE(so) (((PySetObject *)(so))->used)
+PyAPI_FUNC(int) PySet_Contains(PyObject *anyset, PyObject *key);
+PyAPI_FUNC(int) PySet_Discard(PyObject *anyset, PyObject *key);
+PyAPI_FUNC(int) PySet_Add(PyObject *set, PyObject *key);
+PyAPI_FUNC(PyObject *) PySet_Pop(PyObject *set);
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/Misc/NEWS b/Misc/NEWS
index 62e6656..e3fbbab 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -439,6 +439,8 @@ Build
 C API
 -----
 
+- Added a C API for set and frozenset objects.
+
 - Removed PyRange_New().
 
 
diff --git a/Objects/setobject.c b/Objects/setobject.c
index c522549..978d613 100644
--- a/Objects/setobject.c
+++ b/Objects/setobject.c
@@ -843,7 +843,7 @@ frozenset_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
 			return iterable;
 		}
 		result = make_new_set(type, iterable);
-		if (result == NULL || set_len(result))
+		if (result == NULL || PySet_GET_SIZE(result))
 			return result;
 		Py_DECREF(result);
 	}
@@ -1052,7 +1052,7 @@ set_intersection(PySetObject *so, PyObject *other)
 		int pos = 0;
 		setentry *entry;
 
-		if (set_len(other) > set_len((PyObject *)so)) {
+		if (PySet_GET_SIZE(other) > PySet_GET_SIZE(so)) {
 			tmp = (PyObject *)so;
 			so = (PySetObject *)other;
 			other = tmp;
@@ -1381,7 +1381,7 @@ set_issubset(PySetObject *so, PyObject *other)
 		Py_DECREF(tmp);
 		return result;
 	}
-	if (set_len((PyObject *)so) > set_len(other)) 
+	if (PySet_GET_SIZE(so) > PySet_GET_SIZE(other)) 
 		Py_RETURN_FALSE;
 
 	while (set_next(so, &pos, &entry)) {
@@ -1426,11 +1426,11 @@ set_richcompare(PySetObject *v, PyObject *w, int op)
 	}
 	switch (op) {
 	case Py_EQ:
-		if (set_len((PyObject *)v) != set_len(w))
+		if (PySet_GET_SIZE(v) != PySet_GET_SIZE(w))
 			Py_RETURN_FALSE;
 		return set_issubset(v, w);
 	case Py_NE:
-		if (set_len((PyObject *)v) != set_len(w))
+		if (PySet_GET_SIZE(v) != PySet_GET_SIZE(w))
 			Py_RETURN_TRUE;
 		r1 = set_issubset(v, w);
 		assert (r1 != NULL);
@@ -1442,11 +1442,11 @@ set_richcompare(PySetObject *v, PyObject *w, int op)
 	case Py_GE:
 		return set_issuperset(v, w);
 	case Py_LT:
-		if (set_len((PyObject *)v) >= set_len(w))
+		if (PySet_GET_SIZE(v) >= PySet_GET_SIZE(w))
 			Py_RETURN_FALSE;		
 		return set_issubset(v, w);
 	case Py_GT:
-		if (set_len((PyObject *)v) <= set_len(w))
+		if (PySet_GET_SIZE(v) <= PySet_GET_SIZE(w))
 			Py_RETURN_FALSE;
 		return set_issuperset(v, w);
 	}
@@ -1472,7 +1472,7 @@ frozenset_hash(PyObject *self)
 	if (so->hash != -1)
 		return so->hash;
 
-	hash *= set_len(self) + 1;
+	hash *= PySet_GET_SIZE(self) + 1;
 	while (set_next(so, &pos, &entry)) {
 		/* Work to increase the bit dispersion for closely spaced hash
 		   values.  The is important because some use cases have many 
@@ -1918,3 +1918,67 @@ PyTypeObject PyFrozenSet_Type = {
 	frozenset_new,			/* tp_new */
 	PyObject_GC_Del,		/* tp_free */
 };
+
+
+/***** C API functions *************************************************/
+
+PyObject *
+PySet_New(PyObject *iterable)
+{
+	return make_new_set(&PySet_Type, iterable);
+}
+
+PyObject *
+PyFrozenSet_New(PyObject *iterable)
+{
+	PyObject *args = NULL, *result;
+
+	if (iterable != NULL) {
+		args = PyTuple_Pack(1, iterable);
+		if (args == NULL)
+			return NULL;
+	}
+	result = frozenset_new(&PyFrozenSet_Type, args, NULL);
+	Py_DECREF(args);
+	return result;
+}
+
+int
+PySet_Contains(PyObject *anyset, PyObject *key)
+{
+	if (!PyAnySet_Check(anyset)) {
+		PyErr_BadInternalCall();
+		return -1;
+	}
+	return set_contains_key((PySetObject *)anyset, key);
+}
+
+int
+PySet_Discard(PyObject *anyset, PyObject *key)
+{
+	if (!PyAnySet_Check(anyset)) {
+		PyErr_BadInternalCall();
+		return -1;
+	}
+	return set_discard_key((PySetObject *)anyset, key);
+}
+
+int
+PySet_Add(PyObject *set, PyObject *key)
+{
+	if (!PyType_IsSubtype(set->ob_type, &PySet_Type)) {
+		PyErr_BadInternalCall();
+		return -1;
+	}
+	return set_add_key((PySetObject *)set, key);
+}
+
+PyObject *
+PySet_Pop(PyObject *set)
+{
+	if (!PyType_IsSubtype(set->ob_type, &PySet_Type)) {
+		PyErr_BadInternalCall();
+		return NULL;
+	}
+	return set_pop((PySetObject *)set);
+}
diff --git a/Python/marshal.c b/Python/marshal.c
index 3eb7b1e..20d637d 100644
--- a/Python/marshal.c
+++ b/Python/marshal.c
@@ -773,11 +773,9 @@ r_object(RFILE *p)
 		if (v == NULL)
 			return v;
 		if (type == TYPE_SET)
-			v3 = PyObject_CallFunctionObjArgs(
-				(PyObject *)&PySet_Type, v, NULL);
+			v3 = PySet_New(v);
 		else
-			v3 = PyObject_CallFunctionObjArgs(
-				(PyObject *)&PyFrozenSet_Type, v, NULL);
+			v3 = PyFrozenSet_New(v);
 		Py_DECREF(v);
 		return v3;