Merge branch 'main' into minidom

Author: auvipy

.github/CODEOWNERS

@@ -586,10 +586,10 @@ Lib/test/test_string/test_templatelib.py  @lysnikolaou @AA-Turner
 **/*sysconfig*                @FFY00
 
 # SQLite 3
-Doc/library/sqlite3.rst       @berkerpeksag @erlend-aasland
-Lib/sqlite3/                  @berkerpeksag @erlend-aasland
-Lib/test/test_sqlite3/        @berkerpeksag @erlend-aasland
-Modules/_sqlite/              @berkerpeksag @erlend-aasland
+Doc/library/sqlite3.rst       @erlend-aasland
+Lib/sqlite3/                  @erlend-aasland
+Lib/test/test_sqlite3/        @erlend-aasland
+Modules/_sqlite/              @erlend-aasland
 
 # Subprocess
 Lib/subprocess.py             @gpshead
@@ -622,9 +622,6 @@ Modules/_typesmodule.c        @AA-Turner
 Lib/unittest/mock.py             @cjw296
 Lib/test/test_unittest/testmock/ @cjw296
 
-# Urllib
-**/*robotparser*              @berkerpeksag
-
 # Venv
 **/*venv*                     @vsajip @FFY00
 

.github/workflows/mypy.yml

@@ -69,12 +69,11 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
         with:
           persist-credentials: false
-      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0
         with:
           python-version: "3.15"
-          allow-prereleases: true
-          cache: pip
-          cache-dependency-path: Tools/requirements-dev.txt
-      - run: pip install -r Tools/requirements-dev.txt
+          activate-environment: true
+          cache-dependency-glob: Tools/requirements-dev.txt
+      - run: uv pip install -r Tools/requirements-dev.txt
       - run: python3 Misc/mypy/make_symlinks.py --symlink
-      - run: mypy --config-file ${{ matrix.target }}/mypy.ini
+      - run: mypy --num-workers 4 --config-file ${{ matrix.target }}/mypy.ini

.github/workflows/posix-deps-apt.sh

@@ -27,7 +27,7 @@ apt-get -yq --no-install-recommends install \
     zlib1g-dev
 
 # Workaround missing libmpdec-dev on ubuntu 24.04 by building mpdecimal
-# from source. ppa:ondrej/php (launchpad.net) are unreliable 
+# from source. ppa:ondrej/php (launchpad.net) are unreliable
 # (https://status.canonical.com) so fetch the tarball directly
 # from the upstream host.
 # https://www.bytereef.org/mpdecimal/

.github/workflows/reusable-macos.yml

@@ -38,9 +38,8 @@ jobs:
       run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV"
     - name: Install Homebrew dependencies
       run: |
-        brew install pkg-config openssl@3.5 xz gdbm tcl-tk@9 make
-        # Because alternate versions are not symlinked into place by default:
-        brew link --overwrite tcl-tk@9
+        brew bundle --file=Misc/Brewfile
+        brew install make
     - name: Configure CPython
       run: |
         MACOSX_DEPLOYMENT_TARGET=10.15 \

Doc/c-api/sentinel.rst

@@ -14,8 +14,20 @@ Sentinel objects
 
 .. c:function:: int PySentinel_Check(PyObject *o)
 
-   Return true if *o* is a :class:`sentinel` object.  The :class:`sentinel` type
-   does not allow subclasses, so this check is exact.
+   Return true if *o* is a :class:`sentinel` object or a subtype.
+   The :class:`sentinel` type does not currently allow subclasses,
+   so this check is exact.
+   Future Python versions may choose to allow subtyping.
+   This function always succeeds.
+
+   .. versionadded:: 3.15
+
+.. c:function:: int PySentinel_CheckExact(PyObject *o)
+
+   Return true if *o* is a :class:`sentinel` object, but not a subtype.
+   The :class:`sentinel` type does not currently allow subclasses.
+   Future Python versions may choose to allow subtyping.
+   This function always succeeds.
 
    .. versionadded:: 3.15
 

Doc/c-api/stable.rst

@@ -114,7 +114,7 @@ versions of Python.
 
 All functions in Stable ABI are present as functions in Python's shared
 library, not solely as macros.
-This makes them usable are usable from languages that don't use the C
+This makes them usable in languages that don't use the C
 preprocessor, including Python's :py:mod:`ctypes`.
 
 

Doc/deprecations/pending-removal-in-3.16.rst

@@ -89,7 +89,7 @@ Pending removal in Python 3.16
 
 * :mod:`sys`:
 
-  * The :func:`~sys._enablelegacywindowsfsencoding` function
+  * The :func:`!_enablelegacywindowsfsencoding` function
     has been deprecated since Python 3.13.
     Use the :envvar:`PYTHONLEGACYWINDOWSFSENCODING` environment variable instead.
 
@@ -101,5 +101,5 @@ Pending removal in Python 3.16
 
 * :mod:`tarfile`:
 
-  * The undocumented and unused :attr:`!TarFile.tarfile` attribute
+  * The undocumented and unused :attr:`!TarInfo.tarfile` attribute
     has been deprecated since Python 3.13.

Doc/library/array.rst

@@ -12,7 +12,7 @@ This module defines an object type which can compactly represent an array of
 basic values: characters, integers, floating-point numbers, complex numbers.  Arrays are mutable :term:`sequence`
 types and behave very much like lists, except that the type of objects stored in
 them is constrained.  The type is specified at object creation time by using a
-:dfn:`type code`, which is a single character.  The following type codes are
+:dfn:`type code`.  The following type codes are
 defined:
 
 +-----------+--------------------+-------------------+-----------------------+-------+
@@ -91,7 +91,7 @@ Notes:
 .. seealso::
 
    The :ref:`ctypes <ctypes-fundamental-data-types>` and
-   :ref:`struct <format-characters>` modules,
+   :ref:`struct <type-codes>` modules,
    as well as third-party modules like `numpy <https://numpy.org/doc/stable/reference/arrays.interface.html#object.__array_interface__>`__,
    use similar -- but slightly different -- type codes.
 

Doc/library/base64.rst

@@ -16,8 +16,10 @@
 This module provides functions for encoding binary data to printable
 ASCII characters and decoding such encodings back to binary data.
 This includes the :ref:`encodings specified in <base64-rfc-4648>`
-:rfc:`4648` (Base64, Base32 and Base16)
-and the non-standard :ref:`Base85 encodings <base64-base-85>`.
+:rfc:`4648` (Base64, Base32 and Base16), the :ref:`Base85 encoding
+<base64-base-85>` specified in `PDF 2.0
+<https://pdfa.org/resource/iso-32000-2/>`_, and non-standard variants
+of Base85 used elsewhere.
 
 There are two interfaces provided by this module.  The modern interface
 supports encoding :term:`bytes-like objects <bytes-like object>` to ASCII
@@ -284,19 +286,28 @@ POST request.
 Base85 Encodings
 -----------------
 
-Base85 encoding is not formally specified but rather a de facto standard,
-thus different systems perform the encoding differently.
+Base85 encoding is a family of algorithms which represent four bytes
+using five ASCII characters.  Originally implemented in the Unix
+``btoa(1)`` utility, a version of it was later adopted by Adobe in the
+PostScript language and is standardized in PDF 2.0 (ISO 32000-2).
+This version, in both its ``btoa`` and PDF variants, is implemented by
+:func:`a85encode`.
 
-The :func:`a85encode` and :func:`b85encode` functions in this module are two implementations of
-the de facto standard. You should call the function with the Base85
-implementation used by the software you intend to work with.
+A separate version, using a different output character set, was
+defined as an April Fool's joke in :rfc:`1924` but is now used by Git
+and other software.  This version is implemented by :func:`b85encode`.
 
-The two functions present in this module differ in how they handle the following:
+Finally, a third version, using yet another output character set
+designed for safe inclusion in programming language strings, is
+defined by ZeroMQ and implemented here by :func:`z85encode`.
 
-* Whether to include enclosing ``<~`` and ``~>`` markers
-* Whether to include newline characters
-* The set of ASCII characters used for encoding
-* Handling of null bytes
+The functions present in this module differ in how they handle the following:
+
+* Whether to include and expect enclosing ``<~`` and ``~>`` markers.
+* Whether to fold the input into multiple lines.
+* The set of ASCII characters used for encoding.
+* Compact encodings of sequences of spaces and null bytes.
+* The encoding of zero-padding bytes applied to the input.
 
 Refer to the documentation of the individual functions for more information.
 
@@ -307,18 +318,22 @@ Refer to the documentation of the individual functions for more information.
 
    *foldspaces* is an optional flag that uses the special short sequence 'y'
    instead of 4 consecutive spaces (ASCII 0x20) as supported by 'btoa'. This
-   feature is not supported by the "standard" Ascii85 encoding.
+   feature is not supported by the standard encoding used in PDF.
 
    If *wrapcol* is non-zero, insert a newline (``b'\n'``) character
    after at most every *wrapcol* characters.
    If *wrapcol* is zero (default), do not insert any newlines.
 
-   If *pad* is true, the input is padded with ``b'\0'`` so its length is a
-   multiple of 4 bytes before encoding.
-   Note that the ``btoa`` implementation always pads.
+   *pad* controls whether zero-padding applied to the end of the input
+   is fully retained in the output encoding, as done by ``btoa``,
+   producing an exact multiple of 5 bytes of output. This is not part
+   of the standard encoding used in PDF, as it does not preserve the
+   length of the data.
 
-   *adobe* controls whether the encoded byte sequence is framed with ``<~``
-   and ``~>``, which is used by the Adobe implementation.
+   *adobe* controls whether the encoded byte sequence is framed with
+   ``<~`` and ``~>``, as in a PostScript base-85 string literal.  Note
+   that while ASCII85Decode streams in PDF documents *must* be
+   terminated with ``~>``, they *must not* use a leading ``<~``.
 
    .. versionadded:: 3.4
 
@@ -330,10 +345,12 @@ Refer to the documentation of the individual functions for more information.
 
    *foldspaces* is a flag that specifies whether the 'y' short sequence
    should be accepted as shorthand for 4 consecutive spaces (ASCII 0x20).
-   This feature is not supported by the "standard" Ascii85 encoding.
+   This feature is not supported by the standard Ascii85 encoding used in
+   PDF and PostScript.
 
-   *adobe* controls whether the input sequence is in Adobe Ascii85 format
-   (i.e. is framed with <~ and ~>).
+   *adobe* controls whether the ``<~`` and ``~>`` markers are
+   present. While the leading ``<~`` is not required, the input must
+   end with ``~>``, or a :exc:`ValueError` is raised.
 
    *ignorechars* should be a :term:`bytes-like object` containing characters
    to ignore from the input.
@@ -356,8 +373,11 @@ Refer to the documentation of the individual functions for more information.
    Encode the :term:`bytes-like object` *b* using base85 (as used in e.g.
    git-style binary diffs) and return the encoded :class:`bytes`.
 
-   If *pad* is true, the input is padded with ``b'\0'`` so its length is a
-   multiple of 4 bytes before encoding.
+   The input is padded with ``b'\0'`` so its length is a multiple of 4
+   bytes before encoding.  If *pad* is true, all the resulting
+   characters are retained in the output, which will always be a
+   multiple of 5 bytes, and thus the length of the data may not be
+   preserved on decoding.
 
    If *wrapcol* is non-zero, insert a newline (``b'\n'``) character
    after at most every *wrapcol* characters.
@@ -372,8 +392,7 @@ Refer to the documentation of the individual functions for more information.
 .. function:: b85decode(b, *, ignorechars=b'', canonical=False)
 
    Decode the base85-encoded :term:`bytes-like object` or ASCII string *b* and
-   return the decoded :class:`bytes`.  Padding is implicitly removed, if
-   necessary.
+   return the decoded :class:`bytes`.
 
    *ignorechars* should be a :term:`bytes-like object` containing characters
    to ignore from the input.
@@ -392,11 +411,12 @@ Refer to the documentation of the individual functions for more information.
 .. function:: z85encode(s, pad=False, *, wrapcol=0)
 
    Encode the :term:`bytes-like object` *s* using Z85 (as used in ZeroMQ)
-   and return the encoded :class:`bytes`.  See `Z85  specification
-   <https://rfc.zeromq.org/spec/32/>`_ for more information.
+   and return the encoded :class:`bytes`.
 
-   If *pad* is true, the input is padded with ``b'\0'`` so its length is a
-   multiple of 4 bytes before encoding.
+   The input is padded with ``b'\0'`` so its length is a multiple of 4
+   bytes before encoding.  If *pad* is true, all the resulting
+   characters are retained in the output, which will always be a
+   multiple of 5 bytes, as required by the ZeroMQ standard.
 
    If *wrapcol* is non-zero, insert a newline (``b'\n'``) character
    after at most every *wrapcol* characters.
@@ -414,8 +434,7 @@ Refer to the documentation of the individual functions for more information.
 .. function:: z85decode(s, *, ignorechars=b'', canonical=False)
 
    Decode the Z85-encoded :term:`bytes-like object` or ASCII string *s* and
-   return the decoded :class:`bytes`.  See `Z85  specification
-   <https://rfc.zeromq.org/spec/32/>`_ for more information.
+   return the decoded :class:`bytes`.
 
    *ignorechars* should be a :term:`bytes-like object` containing characters
    to ignore from the input.
@@ -499,3 +518,11 @@ recommended to review the security section for any code deployed to production.
       Section 5.2, "Base64 Content-Transfer-Encoding," provides the definition of the
       base64 encoding.
 
+   `ISO 32000-2 Portable document format - Part 2: PDF 2.0 <https://pdfa.org/resource/iso-32000-2/>`_
+      Section 7.4.3, "ASCII85Decode Filter," provides the definition
+      of the Ascii85 encoding used in PDF and PostScript, including
+      the output character set and the details of data length preservation
+      using zero-padding and partial output groups.
+
+   `ZeroMQ RFC 32/Z85 <https://rfc.zeromq.org/spec/32/>`_
+      The "Formal Specification" section provides the character set used in Z85.

Doc/library/binascii.rst

@@ -133,8 +133,11 @@ The :mod:`!binascii` module defines the following functions:
    should be accepted as shorthand for 4 consecutive spaces (ASCII 0x20).
    This feature is not supported by the "standard" Ascii85 encoding.
 
-   *adobe* controls whether the input sequence is in Adobe Ascii85 format
-   (i.e. is framed with <~ and ~>).
+   *adobe* controls whether the encoded byte sequence is framed with
+   ``<~`` and ``~>``, as in a PostScript base-85 string literal.  If
+   *adobe* is true, a leading ``<~`` is optionally accepted, while a
+   trailing ``~>`` is *required*, and :exc:`binascii.Error` is raised
+   if it is not found.
 
    *ignorechars* should be a :term:`bytes-like object` containing characters
    to ignore from the input.
@@ -164,12 +167,16 @@ The :mod:`!binascii` module defines the following functions:
    after at most every *wrapcol* characters.
    If *wrapcol* is zero (default), do not insert any newlines.
 
-   If *pad* is true, the input is padded with ``b'\0'`` so its length is a
-   multiple of 4 bytes before encoding.
-   Note that the ``btoa`` implementation always pads.
+   If *pad* is true, the zero-padding applied to the end of the input
+   is fully retained in the output encoding, as done by ``btoa``,
+   producing an exact multiple of 5 bytes of output. This is not part
+   of the standard encoding used in PDF, as it does not preserve the
+   length of the data.
 
-   *adobe* controls whether the encoded byte sequence is framed with ``<~``
-   and ``~>``, which is used by the Adobe implementation.
+   *adobe* controls whether the encoded byte sequence is framed with
+   ``<~`` and ``~>``, as in a PostScript base-85 string literal.  Note
+   that while ASCII85Decode streams in PDF documents *must* be
+   terminated with ``~>``, they *must not* use a leading ``<~``.
 
    .. versionadded:: 3.15
 
@@ -213,8 +220,10 @@ The :mod:`!binascii` module defines the following functions:
    after at most every *wrapcol* characters.
    If *wrapcol* is zero (default), do not insert any newlines.
 
-   If *pad* is true, the input is padded with ``b'\0'`` so its length is a
-   multiple of 4 bytes before encoding.
+   If *pad* is true, the zero-padding applied to the end of the input
+   is retained in the output, which will always be a multiple of 5
+   bytes, and thus the length of the data may not be preserved on
+   decoding.
 
    .. versionadded:: 3.15