This patch adds a new builtin unistr() which behaves like str()

except that it always returns Unicode objects.

A new C API PyObject_Unicode() is also provided.

This closes patch #101664.

Written by Marc-Andre Lemburg. Copyright assigned to Guido van Rossum.

Doc/api/api.tex

@@ -4,7 +4,7 @@
 
 \input{boilerplate}
 
-\makeindex			% tell \index to actually write the .idx file
+\makeindex                      % tell \index to actually write the .idx file
 
 
 \begin{document}
@@ -1476,6 +1476,14 @@ by the \keyword{print} statement.
 \end{cfuncdesc}
 
 
+\begin{cfuncdesc}{PyObject*}{PyObject_Unicode}{PyObject *o}
+Compute a Unicode string representation of object \var{o}.  Returns the
+Unicode string representation on success, \NULL{} on failure.  This is
+the equivalent of the Python expression \samp{unistr(\var{o})}.
+Called by the \function{unistr()}\bifuncindex{unistr} built-in function.
+\end{cfuncdesc}
+
+
 \begin{cfuncdesc}{int}{PyCallable_Check}{PyObject *o}
 Determine if the object \var{o} is callable.  Return \code{1} if the
 object is callable and \code{0} otherwise.
@@ -3780,14 +3788,14 @@ Returns true if its argument is a \ctype{PyCObject}.
 \end{cfuncdesc}
 
 \begin{cfuncdesc}{PyObject*}{PyCObject_FromVoidPtr}{void* cobj, 
-	void (*destr)(void *)}
+        void (*destr)(void *)}
 Creates a \ctype{PyCObject} from the \code{void *}\var{cobj}.  The
 \var{destr} function will be called when the object is reclaimed, unless
 it is \NULL.
 \end{cfuncdesc}
 
 \begin{cfuncdesc}{PyObject*}{PyCObject_FromVoidPtrAndDesc}{void* cobj,
-	void* desc, void (*destr)(void *, void *) }
+        void* desc, void (*destr)(void *, void *) }
 Creates a \ctype{PyCObject} from the \ctype{void *}\var{cobj}.  The
 \var{destr} function will be called when the object is reclaimed.  The
 \var{desc} argument can be used to pass extra callback data for the
@@ -4661,11 +4669,11 @@ implementing new object types in C.
 \end{cfuncdesc}
 
 \begin{cfuncdesc}{PyObject*}{PyObject_Init}{PyObject *op,
-						PyTypeObject *type}
+                                                PyTypeObject *type}
 \end{cfuncdesc}
 
 \begin{cfuncdesc}{PyVarObject*}{PyObject_InitVar}{PyVarObject *op,
-						PyTypeObject *type, int size}
+                                                PyTypeObject *type, int size}
 \end{cfuncdesc}
 
 \begin{cfuncdesc}{\var{TYPE}*}{PyObject_New}{TYPE, PyTypeObject *type}
@@ -4909,6 +4917,6 @@ The function cannot fail.
 \chapter{Reporting Bugs}
 \input{reportingbugs}
 
-\input{api.ind}			% Index -- must be last
+\input{api.ind}                 % Index -- must be last
 
 \end{document}

Doc/lib/libfuncs.tex

@@ -694,6 +694,12 @@ to decode UTF-8 in strict mode, meaning that encoding errors raise
 \versionadded{2.0}
 \end{funcdesc}
 
+\begin{funcdesc}{unistr}{object}
+Return a Unicode string containing a nicely printable representation of an
+object.  For Unicode, this returns the Unicode string itself.  For
+all other objects, it tries to convert \code{str(\var{object})] to Unicode.
+\end{funcdesc}
+
 \begin{funcdesc}{vars}{\optional{object}}
 Without arguments, return a dictionary corresponding to the current
 local symbol table.  With a module, class or class instance object as

Include/abstract.h

@@ -271,6 +271,18 @@ xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx*/
 
        */
 
+     /* Implemented elsewhere:
+
+     PyObject *PyObject_Unicode(PyObject *o);
+
+	 Compute the unicode representation of object, o.  Returns the
+	 unicode representation on success, NULL on failure.  This is
+	 the equivalent of the Python expression: unistr(o).)
+
+	 Called by the unistr() built-in function.
+
+       */
+
      DL_IMPORT(int) PyCallable_Check(PyObject *o);
 
        /*

Include/object.h

@@ -266,6 +266,7 @@ extern DL_IMPORT(PyTypeObject) PyType_Type; /* The type of type objects */
 extern DL_IMPORT(int) PyObject_Print(PyObject *, FILE *, int);
 extern DL_IMPORT(PyObject *) PyObject_Repr(PyObject *);
 extern DL_IMPORT(PyObject *) PyObject_Str(PyObject *);
+extern DL_IMPORT(PyObject *) PyObject_Unicode(PyObject *);
 extern DL_IMPORT(int) PyObject_Compare(PyObject *, PyObject *);
 extern DL_IMPORT(PyObject *) PyObject_RichCompare(PyObject *, PyObject *, int);
 extern DL_IMPORT(int) PyObject_RichCompareBool(PyObject *, PyObject *, int);

Lib/test/output/test_builtin

@@ -45,6 +45,7 @@ repr
 round
 setattr
 str
+unistr
 tuple
 type
 vars

Lib/test/test_b2.py

@@ -214,6 +214,17 @@ if str(()) != '()': raise TestFailed, 'str(())'
 if str([]) != '[]': raise TestFailed, 'str([])'
 if str({}) != '{}': raise TestFailed, 'str({})'
 
+print 'unistr'
+if unistr('') <> u'': raise TestFailed, 'unistr(\'\')'
+if unistr('a') <> u'a': raise TestFailed, 'unistr(\'a\')'
+if unistr(u'') <> u'': raise TestFailed, 'unistr(u\'\')'
+if unistr(u'a') <> u'a': raise TestFailed, 'unistr(u\'a\')'
+if unistr(0) <> u'0': raise TestFailed, 'unistr(0)'
+if unistr(0L) <> u'0': raise TestFailed, 'unistr(0L)'
+if unistr(()) <> u'()': raise TestFailed, 'unistr(())'
+if unistr([]) <> u'[]': raise TestFailed, 'unistr([])'
+if unistr({}) <> u'{}': raise TestFailed, 'unistr({})'
+
 print 'tuple'
 if tuple(()) != (): raise TestFailed, 'tuple(())'
 if tuple((0, 1, 2, 3)) != (0, 1, 2, 3): raise TestFailed, 'tuple((0, 1, 2, 3))'

Misc/NEWS

@@ -3,6 +3,14 @@ What's New in Python 2.1 alpha 1?
 
 Core language, builtins, and interpreter
 
+- There is a new Unicode companion to the builtin str() function
+  called unistr(). Like str(), it calls either the tp_str slot of
+  objects or the "__str__" method and converts the returned value
+  to an Unicode object (in case this is necessary).
+
+  The unistr() is complemented by a new PyObject_Unicode() C API
+  which behaves in the same way.
+
 - The comparison operators support "rich comparison overloading" (PEP
   207).  C extension types can provide a rich comparison function in
   the new tp_richcompare slot in the type object.  The cmp() function

Objects/object.c

@@ -568,6 +568,53 @@ get_inprogress_dict(void)
 	return inprogress;
 }
 
+PyObject *
+PyObject_Unicode(PyObject *v)
+{
+	PyObject *res;
+	
+	if (v == NULL)
+		res = PyString_FromString("<NULL>");
+	else if (PyUnicode_Check(v)) {
+		Py_INCREF(v);
+		return v;
+	}
+	else if (PyString_Check(v))
+	    	res = v;
+	else if (v->ob_type->tp_str != NULL)
+		res = (*v->ob_type->tp_str)(v);
+	else {
+		PyObject *func;
+		static PyObject *strstr;
+		if (strstr == NULL) {
+			strstr= PyString_InternFromString("__str__");
+			if (strstr == NULL)
+				return NULL;
+		}
+		if (!PyInstance_Check(v) ||
+		    (func = PyObject_GetAttr(v, strstr)) == NULL) {
+			PyErr_Clear();
+			res = PyObject_Repr(v);
+		}
+		else {
+		    	res = PyEval_CallObject(func, (PyObject *)NULL);
+			Py_DECREF(func);
+		}
+	}
+	if (res == NULL)
+		return NULL;
+	if (!PyUnicode_Check(res)) {
+		PyObject* str;
+		str = PyUnicode_FromObject(res);
+		Py_DECREF(res);
+		if (str)
+			res = str;
+		else
+		    	return NULL;
+	}
+	return res;
+}
+
 static PyObject *
 make_pair(PyObject *v, PyObject *w)
 {

Objects/unicodeobject.c

@@ -413,6 +413,7 @@ PyObject *PyUnicode_FromEncodedObject(register PyObject *obj,
     }
     else 
 	v = PyUnicode_Decode(s, len, encoding, errors);
+
  done:
     if (owned) {
 	Py_DECREF(obj);

Python/bltinmodule.c

@@ -1927,6 +1927,23 @@ Return a nice string representation of the object.\n\
 If the argument is a string, the return value is the same object.";
 
 
+static PyObject *
+builtin_unistr(PyObject *self, PyObject *args)
+{
+	PyObject *v;
+
+	if (!PyArg_ParseTuple(args, "O:unistr", &v))
+		return NULL;
+	return PyObject_Unicode(v);
+}
+
+static char unistr_doc[] =
+"unistr(object) -> unicode\n\
+\n\
+Return a nice unicode representation of the object.\n\
+If the argument is a unicode, the return value is the same object.";
+
+
 static PyObject *
 builtin_tuple(PyObject *self, PyObject *args)
 {
@@ -2242,6 +2259,7 @@ static PyMethodDef builtin_methods[] = {
 	{"type",	builtin_type, 1, type_doc},
 	{"unicode",	builtin_unicode, 1, unicode_doc},
 	{"unichr",	builtin_unichr, 1, unichr_doc},
+	{"unistr",	builtin_unistr, 1, unistr_doc},
 	{"vars",	builtin_vars, 1, vars_doc},
 	{"xrange",	builtin_xrange, 1, xrange_doc},
  	{"zip",         builtin_zip, 1, zip_doc},