SF patch 530070: pydoc regression, from Martin and Guido.

Change the way __doc__ is handled, to avoid blowing up on non-string
__doc__ values.

2 files changed, 30 insertions, 5 deletions

diff --git a/Lib/inspect.py b/Lib/inspect.py
index 806f526..9e2d23d 100644
--- a/Lib/inspect.py
+++ b/Lib/inspect.py
@@ -263,8 +263,17 @@ def getdoc(object):
     All tabs are expanded to spaces.  To clean up docstrings that are
     indented to line up with blocks of code, any whitespace than can be
     uniformly removed from the second line onwards is removed."""
-    if hasattr(object, '__doc__') and object.__doc__:
-        lines = string.split(string.expandtabs(object.__doc__), '\n')
+    try:
+        doc = object.__doc__
+    except AttributeError:
+        return None
+    if not isinstance(doc, (str, unicode)):
+        return None
+    try:
+        lines = string.split(string.expandtabs(doc), '\n')
+    except UnicodeError:
+        return None
+    else:
         margin = None
         for line in lines[1:]:
             content = len(string.lstrip(line))
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index ca7e64d..c938f52 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -79,10 +79,27 @@ type_dict(PyTypeObject *type, void *context)
 	return PyDictProxy_New(type->tp_dict);
 }
 
+static PyObject *
+type_get_doc(PyTypeObject *type, void *context)
+{
+	PyObject *result;
+	if (!(type->tp_flags & Py_TPFLAGS_HEAPTYPE)) {
+		if (type->tp_doc == NULL) {
+			Py_INCREF(Py_None);
+			return Py_None;
+		}
+		return PyString_FromString(type->tp_doc);
+	}
+	result = PyDict_GetItemString(type->tp_dict, "__doc__");
+	Py_INCREF(result);
+	return result;
+}
+
 static PyGetSetDef type_getsets[] = {
 	{"__name__", (getter)type_name, NULL, NULL},
 	{"__module__", (getter)type_module, (setter)type_set_module, NULL},
 	{"__dict__",  (getter)type_dict,  NULL, NULL},
+	{"__doc__", (getter)type_get_doc, NULL, NULL},
 	{0}
 };
 
@@ -1079,9 +1096,8 @@ type_new(PyTypeObject *metatype, PyObject *args, PyObject *kwds)
 	}
 
 	/* Set tp_doc to a copy of dict['__doc__'], if the latter is there
-	   and is a string.  Note that the tp_doc slot will only be used
-	   by C code -- python code will use the version in tp_dict, so
-	   it isn't that important that non string __doc__'s are ignored.
+	   and is a string.  The __doc__ accessor will first look for tp_doc;
+	   if that fails, it will still look into __dict__.
 	*/
 	{
 		PyObject *doc = PyDict_GetItemString(dict, "__doc__");