Issue #3080: Add PyModule_GetNameObject()

repr(module) uses %R to format module name and filenames, instead of '%s' and
'%U', so surrogates from undecodable bytes in a filename (PEP 383) are escaped.

3 files changed, 45 insertions, 21 deletions

diff --git a/Doc/c-api/module.rst b/Doc/c-api/module.rst
index 1a64947..a31046c 100644
--- a/Doc/c-api/module.rst
+++ b/Doc/c-api/module.rst
@@ -52,7 +52,7 @@ There are only a few functions special to module objects.
    manipulate a module's :attr:`__dict__`.
 
 
-.. c:function:: char* PyModule_GetName(PyObject *module)
+.. c:function:: PyObject* PyModule_GetNameObject(PyObject *module)
 
    .. index::
       single: __name__ (module attribute)
@@ -61,15 +61,13 @@ There are only a few functions special to module objects.
    Return *module*'s :attr:`__name__` value.  If the module does not provide one,
    or if it is not a string, :exc:`SystemError` is raised and *NULL* is returned.
 
+   .. versionadded:: 3.3
 
-.. c:function:: char* PyModule_GetFilename(PyObject *module)
 
-   Similar to :c:func:`PyModule_GetFilenameObject` but return the filename
-   encoded to 'utf-8'.
+.. c:function:: char* PyModule_GetName(PyObject *module)
 
-   .. deprecated:: 3.2
-      :c:func:`PyModule_GetFilename` raises :c:type:`UnicodeEncodeError` on
-      unencodable filenames, use :c:func:`PyModule_GetFilenameObject` instead.
+   Similar to :c:func:`PyModule_GetNameObject` but return the name encoded to
+   ``'utf-8'``.
 
 
 .. c:function:: PyObject* PyModule_GetFilenameObject(PyObject *module)
@@ -86,6 +84,16 @@ There are only a few functions special to module objects.
    .. versionadded:: 3.2
 
 
+.. c:function:: char* PyModule_GetFilename(PyObject *module)
+
+   Similar to :c:func:`PyModule_GetFilenameObject` but return the filename
+   encoded to 'utf-8'.
+
+   .. deprecated:: 3.2
+      :c:func:`PyModule_GetFilename` raises :c:type:`UnicodeEncodeError` on
+      unencodable filenames, use :c:func:`PyModule_GetFilenameObject` instead.
+
+
 .. c:function:: void* PyModule_GetState(PyObject *module)
 
    Return the "state" of the module, that is, a pointer to the block of memory
diff --git a/Include/moduleobject.h b/Include/moduleobject.h
index 7b2bf1c..79ca7ec 100644
--- a/Include/moduleobject.h
+++ b/Include/moduleobject.h
@@ -16,6 +16,7 @@ PyAPI_FUNC(PyObject *) PyModule_New(
     const char *name            /* UTF-8 encoded string */
     );
 PyAPI_FUNC(PyObject *) PyModule_GetDict(PyObject *);
+PyAPI_FUNC(PyObject *) PyModule_GetNameObject(PyObject *);
 PyAPI_FUNC(const char *) PyModule_GetName(PyObject *);
 PyAPI_FUNC(const char *) PyModule_GetFilename(PyObject *);
 PyAPI_FUNC(PyObject *) PyModule_GetFilenameObject(PyObject *);
diff --git a/Objects/moduleobject.c b/Objects/moduleobject.c
index f31b5da..103ac83 100644
--- a/Objects/moduleobject.c
+++ b/Objects/moduleobject.c
@@ -169,24 +169,35 @@ PyModule_GetDict(PyObject *m)
     return d;
 }
 
-const char *
-PyModule_GetName(PyObject *m)
+PyObject*
+PyModule_GetNameObject(PyObject *m)
 {
     PyObject *d;
-    PyObject *nameobj;
+    PyObject *name;
     if (!PyModule_Check(m)) {
         PyErr_BadArgument();
         return NULL;
     }
     d = ((PyModuleObject *)m)->md_dict;
     if (d == NULL ||
-        (nameobj = PyDict_GetItemString(d, "__name__")) == NULL ||
-        !PyUnicode_Check(nameobj))
+        (name = PyDict_GetItemString(d, "__name__")) == NULL ||
+        !PyUnicode_Check(name))
     {
         PyErr_SetString(PyExc_SystemError, "nameless module");
         return NULL;
     }
-    return _PyUnicode_AsString(nameobj);
+    Py_INCREF(name);
+    return name;
+}
+
+const char *
+PyModule_GetName(PyObject *m)
+{
+    PyObject *name = PyModule_GetNameObject(m);
+    if (name == NULL)
+        return NULL;
+    Py_DECREF(name);   /* module dict has still a reference */
+    return _PyUnicode_AsString(name);
 }
 
 PyObject*
@@ -219,7 +230,7 @@ PyModule_GetFilename(PyObject *m)
     if (fileobj == NULL)
         return NULL;
     utf8 = _PyUnicode_AsString(fileobj);
-    Py_DECREF(fileobj);
+    Py_DECREF(fileobj);   /* module dict has still a reference */
     return utf8;
 }
 
@@ -347,21 +358,25 @@ module_dealloc(PyModuleObject *m)
 static PyObject *
 module_repr(PyModuleObject *m)
 {
-    const char *name;
-    PyObject *filename, *repr;
+    PyObject *name, *filename, *repr;
 
-    name = PyModule_GetName((PyObject *)m);
+    name = PyModule_GetNameObject((PyObject *)m);
     if (name == NULL) {
         PyErr_Clear();
-        name = "?";
+        name = PyUnicode_FromStringAndSize("?", 1);
+        if (name == NULL)
+            return NULL;
     }
     filename = PyModule_GetFilenameObject((PyObject *)m);
     if (filename == NULL) {
         PyErr_Clear();
-        return PyUnicode_FromFormat("<module '%s' (built-in)>", name);
+        repr = PyUnicode_FromFormat("<module %R (built-in)>", name);
+    }
+    else {
+        repr = PyUnicode_FromFormat("<module %R from %R>", name, filename);
+        Py_DECREF(filename);
     }
-    repr = PyUnicode_FromFormat("<module '%s' from '%U'>", name, filename);
-    Py_DECREF(filename);
+    Py_DECREF(name);
     return repr;
 }