"unicode_internal" codec has been deprecated: fix related tests

Lib/test/test_codeccallbacks.py

-import test.support, unittest
-import sys, codecs, html.entities, unicodedata
+import codecs
+import html.entities
+import sys
+import test.support
+import unicodedata
+import unittest
+import warnings
 
 try:
     import ctypes
@@ -621,12 +626,15 @@ class CodecCallbackTest(unittest.TestCase):
                 ("utf-7", b"+x-"),
                 ("unicode-internal", b"\x00"),
             ):
-                self.assertRaises(
-                    TypeError,
-                    bytes.decode,
-                    enc,
-                    "test.badhandler"
-                )
+                with warnings.catch_warnings():
+                    # unicode-internal has been deprecated
+                    warnings.simplefilter("ignore", DeprecationWarning)
+                    self.assertRaises(
+                        TypeError,
+                        bytes.decode,
+                        enc,
+                        "test.badhandler"
+                    )
 
     def test_lookup(self):
         self.assertEqual(codecs.strict_errors, codecs.lookup_error("strict"))
@@ -842,8 +850,11 @@ class CodecCallbackTest(unittest.TestCase):
             else:
                 raise TypeError("don't know how to handle %r" % exc)
         codecs.register_error("test.replacing", replacing)
-        for (encoding, data) in baddata:
-            self.assertRaises(TypeError, data.decode, encoding, "test.replacing")
+        with warnings.catch_warnings():
+            # unicode-internal has been deprecated
+            warnings.simplefilter("ignore", DeprecationWarning)
+            for (encoding, data) in baddata:
+                self.assertRaises(TypeError, data.decode, encoding, "test.replacing")
 
         def mutating(exc):
             if isinstance(exc, UnicodeDecodeError):

Lib/test/test_codecs.py

-from test import support
-import unittest
+import _testcapi
 import codecs
+import io
 import locale
-import sys, _testcapi, io
+import sys
+import unittest
+import warnings
+
+from test import support
 
 if sys.platform == 'win32':
     VISTA_OR_LATER = (sys.getwindowsversion().major >= 6)
@@ -1051,12 +1055,16 @@ class UnicodeInternalTest(unittest.TestCase):
         self.assertEqual(("ab", 12), ignored)
 
     def test_encode_length(self):
-        # Issue 3739
-        encoder = codecs.getencoder("unicode_internal")
-        self.assertEqual(encoder("a")[1], 1)
-        self.assertEqual(encoder("\xe9\u0142")[1], 2)
+        with warnings.catch_warnings():
+            # unicode-internal has been deprecated
+            warnings.simplefilter("ignore", DeprecationWarning)
+
+            # Issue 3739
+            encoder = codecs.getencoder("unicode_internal")
+            self.assertEqual(encoder("a")[1], 1)
+            self.assertEqual(encoder("\xe9\u0142")[1], 2)
 
-        self.assertEqual(codecs.escape_encode(br'\x00')[1], 4)
+            self.assertEqual(codecs.escape_encode(br'\x00')[1], 4)
 
 # From http://www.gnu.org/software/libidn/draft-josefsson-idn-test-vectors.html
 nameprep_tests = [
@@ -1512,10 +1520,15 @@ class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling):
             elif encoding == "latin_1":
                 name = "latin_1"
             self.assertEqual(encoding.replace("_", "-"), name.replace("_", "-"))
-            (b, size) = codecs.getencoder(encoding)(s)
-            self.assertEqual(size, len(s), "%r != %r (encoding=%r)" % (size, len(s), encoding))
-            (chars, size) = codecs.getdecoder(encoding)(b)
-            self.assertEqual(chars, s, "%r != %r (encoding=%r)" % (chars, s, encoding))
+
+            with warnings.catch_warnings():
+                # unicode-internal has been deprecated
+                warnings.simplefilter("ignore", DeprecationWarning)
+
+                (b, size) = codecs.getencoder(encoding)(s)
+                self.assertEqual(size, len(s), "%r != %r (encoding=%r)" % (size, len(s), encoding))
+                (chars, size) = codecs.getdecoder(encoding)(b)
+                self.assertEqual(chars, s, "%r != %r (encoding=%r)" % (chars, s, encoding))
 
             if encoding not in broken_unicode_with_streams:
                 # check stream reader/writer

Lib/test/test_unicode.py

@@ -5,13 +5,13 @@ Written by Marc-Andre Lemburg (mal@lemburg.com).
 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
 
 """#"
+import _string
 import codecs
 import struct
 import sys
 import unittest
 import warnings
 from test import support, string_tests
-import _string
 
 # Error handling (bad decoder return)
 def search_function(encoding):
@@ -1394,7 +1394,11 @@ class UnicodeTest(string_tests.CommonTest,
             for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
                              'utf-16-be', 'raw_unicode_escape',
                              'unicode_escape', 'unicode_internal'):
-                self.assertEqual(str(u.encode(encoding),encoding), u)
+                with warnings.catch_warnings():
+                    # unicode-internal has been deprecated
+                    warnings.simplefilter("ignore", DeprecationWarning)
+
+                    self.assertEqual(str(u.encode(encoding),encoding), u)
 
         # Roundtrip safety for BMP (just the first 256 chars)
         for c in range(256):
@@ -1409,11 +1413,15 @@ class UnicodeTest(string_tests.CommonTest,
                 self.assertEqual(str(u.encode(encoding),encoding), u)
 
         # Roundtrip safety for non-BMP (just a few chars)
-        u = '\U00010001\U00020002\U00030003\U00040004\U00050005'
-        for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
-                         'raw_unicode_escape',
-                         'unicode_escape', 'unicode_internal'):
-            self.assertEqual(str(u.encode(encoding),encoding), u)
+        with warnings.catch_warnings():
+            # unicode-internal has been deprecated
+            warnings.simplefilter("ignore", DeprecationWarning)
+
+            u = '\U00010001\U00020002\U00030003\U00040004\U00050005'
+            for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
+                             'raw_unicode_escape',
+                             'unicode_escape', 'unicode_internal'):
+                self.assertEqual(str(u.encode(encoding),encoding), u)
 
         # UTF-8 must be roundtrip safe for all code points
         # (except surrogates, which are forbidden).