Write tests for invalid characters (U+00110000)

Victor Stinner · Victor Stinner · commit e3b47152a481 · 2011-12-09T20:49:49.000+01:00
Test the following functions:

 * codecs.raw_unicode_escape_decode()
 * PyUnicode_FromWideChar()
 * PyUnicode_FromUnicode()
 * "unicode_internal" and "unicode_escape" decoders
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
@@ -1034,6 +1034,16 @@ def test_bug1251300(self):
                                          'deprecated', DeprecationWarning)):
                 self.assertRaises(UnicodeDecodeError, internal.decode,
                                   "unicode_internal")
+        if sys.byteorder == "little":
+            invalid = b"\x00\x00\x11\x00"
+        else:
+            invalid = b"\x00\x11\x00\x00"
+        with support.check_warnings():
+            self.assertRaises(UnicodeDecodeError,
+                              invalid.decode, "unicode_internal")
+        with support.check_warnings():
+            self.assertEqual(invalid.decode("unicode_internal", "replace"),
+                             '\ufffd')
 
     @unittest.skipUnless(SIZEOF_WCHAR_T == 4, 'specific to 32-bit wchar_t')
     def test_decode_error_attributes(self):
@@ -1729,6 +1739,12 @@ def test_unicode_escape(self):
         self.assertEqual(codecs.raw_unicode_escape_decode(r"\u1234"), ("\u1234", 6))
         self.assertEqual(codecs.raw_unicode_escape_decode(br"\u1234"), ("\u1234", 6))
 
+        self.assertRaises(UnicodeDecodeError, codecs.unicode_escape_decode, br"\U00110000")
+        self.assertEqual(codecs.unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10))
+
+        self.assertRaises(UnicodeDecodeError, codecs.raw_unicode_escape_decode, br"\U00110000")
+        self.assertEqual(codecs.raw_unicode_escape_decode(r"\U00110000", "replace"), ("\ufffd", 10))
+
 class SurrogateEscapeTest(unittest.TestCase):
 
     def test_utf8(self):
diff --git a/Modules/_testcapimodule.c b/Modules/_testcapimodule.c
@@ -1409,6 +1409,7 @@ test_widechar(PyObject *self)
 #if defined(SIZEOF_WCHAR_T) && (SIZEOF_WCHAR_T == 4)
     const wchar_t wtext[2] = {(wchar_t)0x10ABCDu};
     size_t wtextlen = 1;
+    const wchar_t invalid[1] = {(wchar_t)0x110000u};
 #else
     const wchar_t wtext[3] = {(wchar_t)0xDBEAu, (wchar_t)0xDFCDu};
     size_t wtextlen = 2;
@@ -1444,6 +1445,23 @@ test_widechar(PyObject *self)
 
     Py_DECREF(wide);
     Py_DECREF(utf8);
+
+#if defined(SIZEOF_WCHAR_T) && (SIZEOF_WCHAR_T == 4)
+    wide = PyUnicode_FromWideChar(invalid, 1);
+    if (wide == NULL)
+        PyErr_Clear();
+    else
+        return raiseTestError("test_widechar",
+                              "PyUnicode_FromWideChar(L\"\\U00110000\", 1) didn't fail");
+
+    wide = PyUnicode_FromUnicode(invalid, 1);
+    if (wide == NULL)
+        PyErr_Clear();
+    else
+        return raiseTestError("test_widechar",
+                              "PyUnicode_FromUnicode(L\"\\U00110000\", 1) didn't fail");
+#endif
+
     Py_RETURN_NONE;
 }
 
