Issue #22088: Clarify base-64 alphabets and which characters are discarded

* There are only two base-64 alphabets defined by the RFCs, not three
* Due to the internal translation, plus (+) and slash (/) are never discarded
* standard_ and urlsafe_b64decode() discard characters as well

Also update the doc strings to clarify data types, based on revision
92760d2edc9e, correct the exception raised by b16decode(), and correct the
parameter name for the base-85 functions.

1 files changed, 18 insertions, 2 deletions

diff --git a/Lib/test/test_base64.py b/Lib/test/test_base64.py
index a0f548d..9b853a8 100644
--- a/Lib/test/test_base64.py
+++ b/Lib/test/test_base64.py
@@ -243,14 +243,26 @@ class BaseXYTestCase(unittest.TestCase):
                  (b'@@', b''),
                  (b'!', b''),
                  (b'YWJj\nYWI=', b'abcab'))
+        funcs = (
+            base64.b64decode,
+            base64.standard_b64decode,
+            base64.urlsafe_b64decode,
+        )
         for bstr, res in tests:
-            self.assertEqual(base64.b64decode(bstr), res)
-            self.assertEqual(base64.b64decode(bstr.decode('ascii')), res)
+            for func in funcs:
+                with self.subTest(bstr=bstr, func=func):
+                    self.assertEqual(func(bstr), res)
+                    self.assertEqual(func(bstr.decode('ascii')), res)
             with self.assertRaises(binascii.Error):
                 base64.b64decode(bstr, validate=True)
             with self.assertRaises(binascii.Error):
                 base64.b64decode(bstr.decode('ascii'), validate=True)
 
+        # Normal alphabet characters not discarded when alternative given
+        res = b'\xFB\xEF\xBE\xFF\xFF\xFF'
+        self.assertEqual(base64.b64decode(b'++[[//]]', b'[]'), res)
+        self.assertEqual(base64.urlsafe_b64decode(b'++--//__'), res)
+
     def test_b32encode(self):
         eq = self.assertEqual
         eq(base64.b32encode(b''), b'')
@@ -360,6 +372,10 @@ class BaseXYTestCase(unittest.TestCase):
            b'\x01\x02\xab\xcd\xef')
         eq(base64.b16decode(array('B', b"0102abcdef"), True),
            b'\x01\x02\xab\xcd\xef')
+        # Non-alphabet characters
+        self.assertRaises(binascii.Error, base64.b16decode, '0102AG')
+        # Incorrect "padding"
+        self.assertRaises(binascii.Error, base64.b16decode, '010')
 
     def test_a85encode(self):
         eq = self.assertEqual