Merged revisions 77045 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r77045 | ezio.melotti | 2009-12-25 00:25:17 +0200 (Fri, 25 Dec 2009) | 1 line

  #6108: unicode(exception) and str(exception) should return the same message
........

diff --git a/Lib/test/test_exceptions.py b/Lib/test/test_exceptions.py
index aa5c7efc36720b3f9ec2544885ae9524ae8dfa5b..72c40ce74d7383ad701cbe451c7ae9eea7d46eee 100644 (file)
--- a/Lib/test/test_exceptions.py
+++ b/Lib/test/test_exceptions.py
@@ -429,8 +429,116 @@ class ExceptionTests(unittest.TestCase):
             self.assert_("maximum recursion depth exceeded" in str(v), v)
 
 
+
+# Helper class used by TestSameStrAndUnicodeMsg
+class ExcWithOverriddenStr(Exception):
+    """Subclass of Exception that accepts a keyword 'msg' arg that is
+    returned by __str__. 'msg' won't be included in self.args"""
+    def __init__(self, *args, **kwargs):
+        self.msg = kwargs.pop('msg') # msg should always be present
+        super(ExcWithOverriddenStr, self).__init__(*args, **kwargs)
+    def __str__(self):
+        return self.msg
+
+
+class TestSameStrAndUnicodeMsg(unittest.TestCase):
+    """unicode(err) should return the same message of str(err). See #6108"""
+
+    def check_same_msg(self, exc, msg):
+        """Helper function that checks if str(exc) == unicode(exc) == msg"""
+        self.assertEqual(str(exc), msg)
+        self.assertEqual(str(exc), unicode(exc))
+
+    def test_builtin_exceptions(self):
+        """Check same msg for built-in exceptions"""
+        # These exceptions implement a __str__ method that uses the args
+        # to create a better error message. unicode(e) should return the same
+        # message.
+        exceptions = [
+            SyntaxError('invalid syntax', ('<string>', 1, 3, '2+*3')),
+            IOError(2, 'No such file or directory'),
+            KeyError('both should have the same quotes'),
+            UnicodeDecodeError('ascii', '\xc3\xa0', 0, 1,
+                               'ordinal not in range(128)'),
+            UnicodeEncodeError('ascii', u'\u1234', 0, 1,
+                               'ordinal not in range(128)')
+        ]
+        for exception in exceptions:
+            self.assertEqual(str(exception), unicode(exception))
+
+    def test_0_args(self):
+        """Check same msg for Exception with 0 args"""
+        # str() and unicode() on an Exception with no args should return an
+        # empty string
+        self.check_same_msg(Exception(), '')
+
+    def test_0_args_with_overridden___str__(self):
+        """Check same msg for exceptions with 0 args and overridden __str__"""
+        # str() and unicode() on an exception with overridden __str__ that
+        # returns an ascii-only string should return the same string
+        for msg in ('foo', u'foo'):
+            self.check_same_msg(ExcWithOverriddenStr(msg=msg), msg)
+
+        # if __str__ returns a non-ascii unicode string str() should fail
+        # but unicode() should return the unicode string
+        e = ExcWithOverriddenStr(msg=u'f\xf6\xf6') # no args
+        self.assertRaises(UnicodeEncodeError, str, e)
+        self.assertEqual(unicode(e), u'f\xf6\xf6')
+
+    def test_1_arg(self):
+        """Check same msg for Exceptions with 1 arg"""
+        for arg in ('foo', u'foo'):
+            self.check_same_msg(Exception(arg), arg)
+
+        # if __str__ is not overridden and self.args[0] is a non-ascii unicode
+        # string, str() should try to return str(self.args[0]) and fail.
+        # unicode() should return unicode(self.args[0]) and succeed.
+        e = Exception(u'f\xf6\xf6')
+        self.assertRaises(UnicodeEncodeError, str, e)
+        self.assertEqual(unicode(e), u'f\xf6\xf6')
+
+    def test_1_arg_with_overridden___str__(self):
+        """Check same msg for exceptions with overridden __str__ and 1 arg"""
+        # when __str__ is overridden and __unicode__ is not implemented
+        # unicode(e) returns the same as unicode(e.__str__()).
+        for msg in ('foo', u'foo'):
+            self.check_same_msg(ExcWithOverriddenStr('arg', msg=msg), msg)
+
+        # if __str__ returns a non-ascii unicode string, str() should fail
+        # but unicode() should succeed.
+        e = ExcWithOverriddenStr('arg', msg=u'f\xf6\xf6') # 1 arg
+        self.assertRaises(UnicodeEncodeError, str, e)
+        self.assertEqual(unicode(e), u'f\xf6\xf6')
+
+    def test_many_args(self):
+        """Check same msg for Exceptions with many args"""
+        argslist = [
+            (3, 'foo'),
+            (1, u'foo', 'bar'),
+            (4, u'f\xf6\xf6', u'bar', 'baz')
+        ]
+        # both str() and unicode() should return a repr() of the args
+        for args in argslist:
+            self.check_same_msg(Exception(*args), repr(args))
+
+    def test_many_args_with_overridden___str__(self):
+        """Check same msg for exceptions with overridden __str__ and many args"""
+        # if __str__ returns an ascii string / ascii unicode string
+        # both str() and unicode() should succeed
+        for msg in ('foo', u'foo'):
+            e = ExcWithOverriddenStr('arg1', u'arg2', u'f\xf6\xf6', msg=msg)
+            self.check_same_msg(e, msg)
+
+        # if __str__ returns a non-ascii unicode string, str() should fail
+        # but unicode() should succeed
+        e = ExcWithOverriddenStr('arg1', u'f\xf6\xf6', u'arg3', # 3 args
+                                 msg=u'f\xf6\xf6')
+        self.assertRaises(UnicodeEncodeError, str, e)
+        self.assertEqual(unicode(e), u'f\xf6\xf6')
+
+
 def test_main():
-    run_unittest(ExceptionTests)
+    run_unittest(ExceptionTests, TestSameStrAndUnicodeMsg)
 
 if __name__ == '__main__':
     test_main()

diff --git a/Misc/NEWS b/Misc/NEWS
index adc053b6a83db633cfe6b078a5f66e2135e14f81..234e55af8a90c5eba98afef409baa2b37cfa96eb 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -12,6 +12,9 @@ What's New in Python 2.6.5
 Core and Builtins
 -----------------
 
+- Issue #6108: unicode(exception) and str(exception) should return the same
+  message when only __str__ (and not __unicode__) is overridden in the subclass.
+
 - Issue #7491: Metaclass's __cmp__ method was ignored.
 
 - Add Py3k warnings for parameter names in parenthesis.

diff --git a/Objects/exceptions.c b/Objects/exceptions.c
index 0a5282023a7282ef20de94058a5bf98811177976..4f188029945e149ecd6cd4e210b5e939ce974a8f 100644 (file)
--- a/Objects/exceptions.c
+++ b/Objects/exceptions.c
@@ -123,6 +123,21 @@ BaseException_unicode(PyBaseExceptionObject *self)
 {
     PyObject *out;
 
+    /* issue6108: if __str__ has been overridden in the subclass, unicode()
+       should return the message returned by __str__ as used to happen
+       before this method was implemented. */
+    if (Py_TYPE(self)->tp_str != (reprfunc)BaseException_str) {
+        PyObject *str;
+        /* Unlike PyObject_Str, tp_str can return unicode (i.e. return the
+           equivalent of unicode(e.__str__()) instead of unicode(str(e))). */
+        str = Py_TYPE(self)->tp_str((PyObject*)self);
+        if (str == NULL)
+            return NULL;
+        out = PyObject_Unicode(str);
+        Py_DECREF(str);
+        return out;
+    }
+
     switch (PyTuple_GET_SIZE(self->args)) {
     case 0:
         out = PyUnicode_FromString("");