Rename the surrogates error handler to surrogatepass.

Author: loewis

Doc/library/codecs.rst

@@ -327,15 +327,15 @@ and implemented by all standard Python codecs:
 
 In addition, the following error handlers are specific to a single codec:
 
-+------------------+---------+--------------------------------------------+
-| Value            | Codec   | Meaning                                    |
-+==================+=========+============================================+
-| ``'surrogates'`` | utf-8   | Allow encoding and decoding of surrogate   |
-|                  |         | codes in UTF-8.                            |
-+------------------+---------+--------------------------------------------+
++-------------------+---------+-------------------------------------------+
+| Value             | Codec   | Meaning                                   |
++===================+=========+===========================================+
+|``'surrogatepass'``| utf-8   | Allow encoding and decoding of surrogate  |
+|                   |         | codes in UTF-8.                           |
++-------------------+---------+-------------------------------------------+
 
 .. versionadded:: 3.1
-   The ``'utf8b'`` and ``'surrogates'`` error handlers.
+   The ``'utf8b'`` and ``'surrogatepass'`` error handlers.
 
 The set of allowed values can be extended via :meth:`register_error`.
 

Lib/test/test_codecs.py

@@ -545,12 +545,12 @@ def test_lone_surrogates(self):
         self.assertRaises(UnicodeEncodeError, "\ud800".encode, "utf-8")
         self.assertRaises(UnicodeDecodeError, b"\xed\xa0\x80".decode, "utf-8")
 
-    def test_surrogates_handler(self):
-        self.assertEquals("abc\ud800def".encode("utf-8", "surrogates"),
+    def test_surrogatepass_handler(self):
+        self.assertEquals("abc\ud800def".encode("utf-8", "surrogatepass"),
                           b"abc\xed\xa0\x80def")
-        self.assertEquals(b"abc\xed\xa0\x80def".decode("utf-8", "surrogates"),
+        self.assertEquals(b"abc\xed\xa0\x80def".decode("utf-8", "surrogatepass"),
                           "abc\ud800def")
-        self.assertTrue(codecs.lookup_error("surrogates"))
+        self.assertTrue(codecs.lookup_error("surrogatepass"))
 
 class UTF7Test(ReadTest):
     encoding = "utf-7"
@@ -1040,12 +1040,12 @@ def test_nameprep(self):
                 # Skipped
                 continue
             # The Unicode strings are given in UTF-8
-            orig = str(orig, "utf-8", "surrogates")
+            orig = str(orig, "utf-8", "surrogatepass")
             if prepped is None:
                 # Input contains prohibited characters
                 self.assertRaises(UnicodeError, nameprep, orig)
             else:
-                prepped = str(prepped, "utf-8", "surrogates")
+                prepped = str(prepped, "utf-8", "surrogatepass")
                 try:
                     self.assertEquals(nameprep(orig), prepped)
                 except Exception as e:

Lib/test/test_unicode.py

@@ -906,10 +906,10 @@ def test_codecs_utf8(self):
         self.assertEqual('\u20ac'.encode('utf-8'), b'\xe2\x82\xac')
         self.assertEqual('\ud800\udc02'.encode('utf-8'), b'\xf0\x90\x80\x82')
         self.assertEqual('\ud84d\udc56'.encode('utf-8'), b'\xf0\xa3\x91\x96')
-        self.assertEqual('\ud800'.encode('utf-8', 'surrogates'), b'\xed\xa0\x80')
-        self.assertEqual('\udc00'.encode('utf-8', 'surrogates'), b'\xed\xb0\x80')
+        self.assertEqual('\ud800'.encode('utf-8', 'surrogatepass'), b'\xed\xa0\x80')
+        self.assertEqual('\udc00'.encode('utf-8', 'surrogatepass'), b'\xed\xb0\x80')
         self.assertEqual(
-            ('\ud800\udc02'*1000).encode('utf-8', 'surrogates'),
+            ('\ud800\udc02'*1000).encode('utf-8', 'surrogatepass'),
             b'\xf0\x90\x80\x82'*1000
         )
         self.assertEqual(

Misc/NEWS

@@ -56,7 +56,7 @@ Core and Builtins
 - Issue #4426: The UTF-7 decoder was too strict and didn't accept some legal
   sequences. Patch by Nick Barnes and Victor Stinner.
 
-- Issue #3672: Reject surrogates in utf-8 codec; add surrogates error handler.
+- Issue #3672: Reject surrogates in utf-8 codec; add surrogatepass error handler.
 
 - Issue #5883: In the io module, the BufferedIOBase and TextIOBase ABCs have
   received a new method, detach().  detach() disconnects the underlying stream

Python/codecs.c

@@ -751,7 +751,7 @@ PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
 /* This handler is declared static until someone demonstrates
    a need to call it directly. */
 static PyObject *
-PyCodec_SurrogateErrors(PyObject *exc)
+PyCodec_SurrogatePassErrors(PyObject *exc)
 {
     PyObject *restuple;
     PyObject *object;
@@ -935,9 +935,9 @@ static PyObject *backslashreplace_errors(PyObject *self, PyObject *exc)
     return PyCodec_BackslashReplaceErrors(exc);
 }
 
-static PyObject *surrogates_errors(PyObject *self, PyObject *exc)
+static PyObject *surrogatepass_errors(PyObject *self, PyObject *exc)
 {
-    return PyCodec_SurrogateErrors(exc);
+    return PyCodec_SurrogatePassErrors(exc);
 }
 
 static PyObject *utf8b_errors(PyObject *self, PyObject *exc)
@@ -993,10 +993,10 @@ static int _PyCodecRegistry_Init(void)
 	    }
 	},
 	{
-	    "surrogates",
+	    "surrogatepass",
 	    {
-		"surrogates",
-		surrogates_errors,
+		"surrogatepass",
+		surrogatepass_errors,
 		METH_O
 	    }
 	},

Python/marshal.c

@@ -314,7 +314,7 @@ w_object(PyObject *v, WFILE *p)
 	        PyObject *utf8;
 		utf8 = PyUnicode_EncodeUTF8(PyUnicode_AS_UNICODE(v),
 					    PyUnicode_GET_SIZE(v),
-					    "surrogates");
+					    "surrogatepass");
 		if (utf8 == NULL) {
 			p->depth--;
 			p->error = WFERR_UNMARSHALLABLE;
@@ -809,7 +809,7 @@ r_object(RFILE *p)
 			retval = NULL;
 			break;
 		}
-		v = PyUnicode_DecodeUTF8(buffer, n, "surrogates");
+		v = PyUnicode_DecodeUTF8(buffer, n, "surrogatepass");
 		PyMem_DEL(buffer);
 		retval = v;
 		break;