Merge branch 'main' into virtual-iterators

Author: markshannon

.github/workflows/mypy.yml

@@ -11,6 +11,7 @@ on:
       - "Lib/_colorize.py"
       - "Lib/_pyrepl/**"
       - "Lib/test/libregrtest/**"
+      - "Lib/tomllib/**"
       - "Misc/mypy/**"
       - "Tools/build/generate_sbom.py"
       - "Tools/cases_generator/**"
@@ -44,6 +45,7 @@ jobs:
         target: [
           "Lib/_pyrepl",
           "Lib/test/libregrtest",
+          "Lib/tomllib",
           "Tools/build",
           "Tools/cases_generator",
           "Tools/clinic",

.gitignore

@@ -143,6 +143,7 @@ Tools/unicode/data/
 /profile-clean-stamp
 /profile-run-stamp
 /profile-bolt-stamp
+/profile-gen-stamp
 /pybuilddir.txt
 /pyconfig.h
 /python-config

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+      :func:`codecs.open` has been superseded by :func:`open`.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.
@@ -1642,6 +1646,13 @@ Deprecated
   Deprecate :meth:`symtable.Class.get_methods` due to the lack of interest.
   (Contributed by Bénédikt Tran in :gh:`119698`.)
 
+* :mod:`tkinter`:
+  The :class:`!tkinter.Variable` methods :meth:`!trace_variable`,
+  :meth:`!trace_vdelete` and :meth:`!trace_vinfo` are now deprecated.
+  Use :meth:`!trace_add`, :meth:`!trace_remove` and :meth:`!trace_info`
+  instead.
+  (Contributed by Serhiy Storchaka in :gh:`120220`.)
+
 * :mod:`urllib.parse`:
   Accepting objects with false values (like ``0`` and ``[]``) except empty
   strings, byte-like objects and ``None`` in :mod:`urllib.parse` functions

Grammar/python.gram

@@ -79,7 +79,7 @@ _PyPegen_parse(Parser *p)
 # ~
 #   Commit to the current alternative, even if it fails to parse.
 # &&e
-#   Eager parse e. The parser will not backtrack and will immediately 
+#   Eager parse e. The parser will not backtrack and will immediately
 #   fail with SyntaxError if e cannot be parsed.
 #
 
@@ -659,7 +659,7 @@ type_alias[stmt_ty]:
 # Type parameter declaration
 # --------------------------
 
-type_params[asdl_type_param_seq*]: 
+type_params[asdl_type_param_seq*]:
     | invalid_type_params
     | '[' t=type_param_seq ']' {
         CHECK_VERSION(asdl_type_param_seq *, 12, "Type parameter lists are", t) }
@@ -1339,13 +1339,13 @@ invalid_group:
 invalid_import:
     | a='import' ','.dotted_name+ 'from' dotted_name {
         RAISE_SYNTAX_ERROR_STARTING_FROM(a, "Did you mean to use 'from ... import ...' instead?") }
-    | 'import' token=NEWLINE { 
+    | 'import' token=NEWLINE {
         RAISE_SYNTAX_ERROR_STARTING_FROM(token, "Expected one or more names after 'import'") }
 
 invalid_import_from_targets:
     | import_from_as_names ',' NEWLINE {
         RAISE_SYNTAX_ERROR("trailing comma not allowed without surrounding parentheses") }
-    | token=NEWLINE { 
+    | token=NEWLINE {
         RAISE_SYNTAX_ERROR_STARTING_FROM(token, "Expected one or more names after 'import'") }
 
 invalid_with_stmt:
@@ -1484,5 +1484,5 @@ invalid_factor:
 invalid_type_params:
     | '[' token=']' {
         RAISE_SYNTAX_ERROR_STARTING_FROM(
-            token, 
+            token,
             "Type parameter list cannot be empty")}

InternalDocs/garbage_collector.md

@@ -622,7 +622,7 @@ used as follows.  If the buffer has reached the maximum size, new object
 pointers found while following references are pushed to the stack, rather than
 put in the buffer.  When dequeuing objects from the buffer, we will "prime" the
 buffer if the current length drops below the low threshold.  Priming means
-popping objects from the stack and enqueing them into the buffer.  While
+popping objects from the stack and enqueuing them into the buffer.  While
 priming, we will fill it only until the high threshold is reached.
 
 To measure the effectiveness of the buffer, some benchmark programs were run

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)