Merge 'origin/main' into type-slot-ts-v2

Author: nascheme

Doc/deprecations/pending-removal-in-future.rst

@@ -47,6 +47,8 @@ although there is currently no date scheduled for their removal.
   :data:`calendar.FEBRUARY`.
   (Contributed by Prince Roshan in :gh:`103636`.)
 
+* :mod:`codecs`: use :func:`open` instead of :func:`codecs.open`. (:gh:`133038`)
+
 * :attr:`codeobject.co_lnotab`: use the :meth:`codeobject.co_lines` method
   instead.
 

Doc/library/codecs.rst

@@ -208,6 +208,10 @@ wider range of codecs when working with binary files:
    .. versionchanged:: 3.11
       The ``'U'`` mode has been removed.
 
+   .. deprecated:: next
+
+      :func:`codecs.open` has been superseded by :func:`open`.
+
 
 .. function:: EncodedFile(file, data_encoding, file_encoding=None, errors='strict')
 

Doc/whatsnew/3.14.rst

@@ -1597,6 +1597,10 @@ Deprecated
   as a single positional argument.
   (Contributed by Serhiy Storchaka in :gh:`109218`.)
 
+* :mod:`codecs`:
+  :func:`codecs.open` is now deprecated. Use :func:`open` instead.
+  (Contributed by Inada Naoki in :gh:`133036`.)
+
 * :mod:`functools`:
   Calling the Python implementation of :func:`functools.reduce` with *function*
   or *sequence* as keyword arguments is now deprecated.

Lib/_pyio.py

@@ -2056,8 +2056,7 @@ def __init__(self, buffer, encoding=None, errors=None, newline=None,
             raise ValueError("invalid encoding: %r" % encoding)
 
         if not codecs.lookup(encoding)._is_text_encoding:
-            msg = ("%r is not a text encoding; "
-                   "use codecs.open() to handle arbitrary codecs")
+            msg = "%r is not a text encoding"
             raise LookupError(msg % encoding)
 
         if errors is None:

Lib/codecs.py

@@ -884,7 +884,6 @@ def __reduce_ex__(self, proto):
 ### Shortcuts
 
 def open(filename, mode='r', encoding=None, errors='strict', buffering=-1):
-
     """ Open an encoded file using the given mode and return
         a wrapped version providing transparent encoding/decoding.
 
@@ -912,8 +911,11 @@ def open(filename, mode='r', encoding=None, errors='strict', buffering=-1):
         .encoding which allows querying the used encoding. This
         attribute is only available if an encoding was specified as
         parameter.
-
     """
+    import warnings
+    warnings.warn("codecs.open() is deprecated. Use open() instead.",
+                  DeprecationWarning, stacklevel=2)
+
     if encoding is not None and \
        'b' not in mode:
         # Force opening of the file in binary mode

Lib/test/test_codecs.py

@@ -7,6 +7,7 @@
 import unittest
 import encodings
 from unittest import mock
+import warnings
 
 from test import support
 from test.support import os_helper
@@ -20,13 +21,12 @@
 except ImportError:
     _testinternalcapi = None
 
-try:
-    import ctypes
-except ImportError:
-    ctypes = None
-    SIZEOF_WCHAR_T = -1
-else:
-    SIZEOF_WCHAR_T = ctypes.sizeof(ctypes.c_wchar)
+
+def codecs_open_no_warn(*args, **kwargs):
+    """Call codecs.open(*args, **kwargs) ignoring DeprecationWarning."""
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+        return codecs.open(*args, **kwargs)
 
 def coding_checker(self, coder):
     def check(input, expect):
@@ -35,13 +35,13 @@ def check(input, expect):
 
 # On small versions of Windows like Windows IoT or Windows Nano Server not all codepages are present
 def is_code_page_present(cp):
-    from ctypes import POINTER, WINFUNCTYPE, WinDLL
+    from ctypes import POINTER, WINFUNCTYPE, WinDLL, Structure
     from ctypes.wintypes import BOOL, BYTE, WCHAR, UINT, DWORD
 
     MAX_LEADBYTES = 12  # 5 ranges, 2 bytes ea., 0 term.
     MAX_DEFAULTCHAR = 2 # single or double byte
     MAX_PATH = 260
-    class CPINFOEXW(ctypes.Structure):
+    class CPINFOEXW(Structure):
         _fields_ = [("MaxCharSize", UINT),
                     ("DefaultChar", BYTE*MAX_DEFAULTCHAR),
                     ("LeadByte", BYTE*MAX_LEADBYTES),
@@ -719,19 +719,19 @@ def test_bug691291(self):
         self.addCleanup(os_helper.unlink, os_helper.TESTFN)
         with open(os_helper.TESTFN, 'wb') as fp:
             fp.write(s)
-        with codecs.open(os_helper.TESTFN, 'r',
+        with codecs_open_no_warn(os_helper.TESTFN, 'r',
                          encoding=self.encoding) as reader:
             self.assertEqual(reader.read(), s1)
 
     def test_invalid_modes(self):
         for mode in ('U', 'rU', 'r+U'):
             with self.assertRaises(ValueError) as cm:
-                codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
+                codecs_open_no_warn(os_helper.TESTFN, mode, encoding=self.encoding)
             self.assertIn('invalid mode', str(cm.exception))
 
         for mode in ('rt', 'wt', 'at', 'r+t'):
             with self.assertRaises(ValueError) as cm:
-                codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
+                codecs_open_no_warn(os_helper.TESTFN, mode, encoding=self.encoding)
             self.assertIn("can't have text and binary mode at once",
                           str(cm.exception))
 
@@ -1844,9 +1844,9 @@ def test_all(self):
     def test_open(self):
         self.addCleanup(os_helper.unlink, os_helper.TESTFN)
         for mode in ('w', 'r', 'r+', 'w+', 'a', 'a+'):
-            with self.subTest(mode), \
-                    codecs.open(os_helper.TESTFN, mode, 'ascii') as file:
-                self.assertIsInstance(file, codecs.StreamReaderWriter)
+            with self.subTest(mode), self.assertWarns(DeprecationWarning):
+                with codecs.open(os_helper.TESTFN, mode, 'ascii') as file:
+                    self.assertIsInstance(file, codecs.StreamReaderWriter)
 
     def test_undefined(self):
         self.assertRaises(UnicodeError, codecs.encode, 'abc', 'undefined')
@@ -1863,7 +1863,7 @@ def test_file_closes_if_lookup_error_raised(self):
         mock_open = mock.mock_open()
         with mock.patch('builtins.open', mock_open) as file:
             with self.assertRaises(LookupError):
-                codecs.open(os_helper.TESTFN, 'wt', 'invalid-encoding')
+                codecs_open_no_warn(os_helper.TESTFN, 'wt', 'invalid-encoding')
 
             file().close.assert_called()
 
@@ -2883,7 +2883,7 @@ def test_seek0(self):
         self.addCleanup(os_helper.unlink, os_helper.TESTFN)
         for encoding in tests:
             # Check if the BOM is written only once
-            with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+            with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
                 f.write(data)
                 f.write(data)
                 f.seek(0)
@@ -2892,7 +2892,7 @@ def test_seek0(self):
                 self.assertEqual(f.read(), data * 2)
 
             # Check that the BOM is written after a seek(0)
-            with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+            with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
                 f.write(data[0])
                 self.assertNotEqual(f.tell(), 0)
                 f.seek(0)
@@ -2901,7 +2901,7 @@ def test_seek0(self):
                 self.assertEqual(f.read(), data)
 
             # (StreamWriter) Check that the BOM is written after a seek(0)
-            with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+            with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
                 f.writer.write(data[0])
                 self.assertNotEqual(f.writer.tell(), 0)
                 f.writer.seek(0)
@@ -2911,7 +2911,7 @@ def test_seek0(self):
 
             # Check that the BOM is not written after a seek() at a position
             # different than the start
-            with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+            with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
                 f.write(data)
                 f.seek(f.tell())
                 f.write(data)
@@ -2920,7 +2920,7 @@ def test_seek0(self):
 
             # (StreamWriter) Check that the BOM is not written after a seek()
             # at a position different than the start
-            with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+            with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
                 f.writer.write(data)
                 f.writer.seek(f.writer.tell())
                 f.writer.write(data)

Lib/test/test_dict.py

@@ -266,6 +266,31 @@ def __next__(self):
 
         self.assertRaises(ValueError, {}.update, [(1, 2, 3)])
 
+    def test_update_type_error(self):
+        with self.assertRaises(TypeError) as cm:
+            {}.update([object() for _ in range(3)])
+
+        self.assertEqual(str(cm.exception), "object is not iterable")
+        self.assertEqual(
+            cm.exception.__notes__,
+            ['Cannot convert dictionary update sequence element #0 to a sequence'],
+        )
+
+        def badgen():
+            yield "key"
+            raise TypeError("oops")
+            yield "value"
+
+        with self.assertRaises(TypeError) as cm:
+            dict([badgen() for _ in range(3)])
+
+        self.assertEqual(str(cm.exception), "oops")
+        self.assertEqual(
+            cm.exception.__notes__,
+            ['Cannot convert dictionary update sequence element #0 to a sequence'],
+        )
+
+
     def test_fromkeys(self):
         self.assertEqual(dict.fromkeys('abc'), {'a':None, 'b':None, 'c':None})
         d = {}

Lib/test/test_generated_cases.py

@@ -419,7 +419,7 @@ def test_pep7_condition(self):
     def test_error_if_plain(self):
         input = """
         inst(OP, (--)) {
-            ERROR_IF(cond, label);
+            ERROR_IF(cond);
         }
     """
         output = """
@@ -432,7 +432,7 @@ def test_error_if_plain(self):
             next_instr += 1;
             INSTRUCTION_STATS(OP);
             if (cond) {
-                JUMP_TO_LABEL(label);
+                JUMP_TO_LABEL(error);
             }
             DISPATCH();
         }
@@ -442,7 +442,7 @@ def test_error_if_plain(self):
     def test_error_if_plain_with_comment(self):
         input = """
         inst(OP, (--)) {
-            ERROR_IF(cond, label);  // Comment is ok
+            ERROR_IF(cond);  // Comment is ok
         }
     """
         output = """
@@ -455,7 +455,7 @@ def test_error_if_plain_with_comment(self):
             next_instr += 1;
             INSTRUCTION_STATS(OP);
             if (cond) {
-                JUMP_TO_LABEL(label);
+                JUMP_TO_LABEL(error);
             }
             DISPATCH();
         }
@@ -467,7 +467,7 @@ def test_error_if_pop(self):
         inst(OP, (left, right -- res)) {
             SPAM(left, right);
             INPUTS_DEAD();
-            ERROR_IF(cond, label);
+            ERROR_IF(cond);
             res = 0;
         }
     """
@@ -487,7 +487,7 @@ def test_error_if_pop(self):
             left = stack_pointer[-2];
             SPAM(left, right);
             if (cond) {
-                JUMP_TO_LABEL(pop_2_label);
+                JUMP_TO_LABEL(pop_2_error);
             }
             res = 0;
             stack_pointer[-2] = res;
@@ -503,7 +503,7 @@ def test_error_if_pop_with_result(self):
         inst(OP, (left, right -- res)) {
             res = SPAM(left, right);
             INPUTS_DEAD();
-            ERROR_IF(cond, label);
+            ERROR_IF(cond);
         }
     """
         output = """
@@ -522,7 +522,7 @@ def test_error_if_pop_with_result(self):
             left = stack_pointer[-2];
             res = SPAM(left, right);
             if (cond) {
-                JUMP_TO_LABEL(pop_2_label);
+                JUMP_TO_LABEL(pop_2_error);
             }
             stack_pointer[-2] = res;
             stack_pointer += -1;
@@ -903,7 +903,7 @@ def test_array_error_if(self):
         inst(OP, (extra, values[oparg] --)) {
             DEAD(extra);
             DEAD(values);
-            ERROR_IF(oparg == 0, somewhere);
+            ERROR_IF(oparg == 0);
         }
     """
         output = """
@@ -922,7 +922,7 @@ def test_array_error_if(self):
             if (oparg == 0) {
                 stack_pointer += -1 - oparg;
                 assert(WITHIN_STACK_BOUNDS());
-                JUMP_TO_LABEL(somewhere);
+                JUMP_TO_LABEL(error);
             }
             stack_pointer += -1 - oparg;
             assert(WITHIN_STACK_BOUNDS());
@@ -1319,7 +1319,7 @@ def test_pop_on_error_peeks(self):
 
         op(THIRD, (j, k --)) {
             INPUTS_DEAD(); // Mark j and k as used
-            ERROR_IF(cond, error);
+            ERROR_IF(cond);
         }
 
         macro(TEST) = FIRST + SECOND + THIRD;
@@ -1369,7 +1369,7 @@ def test_push_then_error(self):
 
         op(SECOND, (a -- a, b)) {
             b = 1;
-            ERROR_IF(cond, error);
+            ERROR_IF(cond);
         }
 
         macro(TEST) = FIRST + SECOND;
@@ -1414,10 +1414,10 @@ def test_error_if_true(self):
 
         input = """
         inst(OP1, ( --)) {
-            ERROR_IF(true, here);
+            ERROR_IF(true);
         }
         inst(OP2, ( --)) {
-            ERROR_IF(1, there);
+            ERROR_IF(1);
         }
         """
         output = """
@@ -1429,7 +1429,7 @@ def test_error_if_true(self):
             frame->instr_ptr = next_instr;
             next_instr += 1;
             INSTRUCTION_STATS(OP1);
-            JUMP_TO_LABEL(here);
+            JUMP_TO_LABEL(error);
         }
 
         TARGET(OP2) {
@@ -1440,7 +1440,7 @@ def test_error_if_true(self):
             frame->instr_ptr = next_instr;
             next_instr += 1;
             INSTRUCTION_STATS(OP2);
-            JUMP_TO_LABEL(there);
+            JUMP_TO_LABEL(error);
         }
         """
         self.run_cases_test(input, output)
@@ -1716,7 +1716,7 @@ def test_no_escaping_calls_in_branching_macros(self):
 
         input = """
         inst(OP, ( -- )) {
-            ERROR_IF(escaping_call(), error);
+            ERROR_IF(escaping_call());
         }
         """
         with self.assertRaises(SyntaxError):

Lib/test/test_multibytecodec.py

@@ -314,7 +314,8 @@ def test_bug1728403(self):
                 f.write(b'\xa1')
             finally:
                 f.close()
-            f = codecs.open(TESTFN, encoding='cp949')
+            with self.assertWarns(DeprecationWarning):
+                f = codecs.open(TESTFN, encoding='cp949')
             try:
                 self.assertRaises(UnicodeDecodeError, f.read, 2)
             finally: