Merge branch '3.14' into backport-ac75110-3.14

Author: picnixz

Android/android.py

@@ -175,7 +175,7 @@ def unpack_deps(host, prefix_dir):
     os.chdir(prefix_dir)
     deps_url = "https://github.com/beeware/cpython-android-source-deps/releases/download"
     for name_ver in ["bzip2-1.0.8-3", "libffi-3.4.4-3", "openssl-3.0.15-4",
-                     "sqlite-3.49.1-0", "xz-5.4.6-1"]:
+                     "sqlite-3.49.1-0", "xz-5.4.6-1", "zstd-1.5.7-1"]:
         filename = f"{name_ver}-{host}.tar.gz"
         download(f"{deps_url}/{name_ver}/{filename}")
         shutil.unpack_archive(filename)

Doc/c-api/exceptions.rst

@@ -233,75 +233,6 @@
 # Temporary undocumented names.
 # In future this list must be empty.
 nitpick_ignore += [
-    # C API: Standard Python exception classes
-    ('c:data', 'PyExc_ArithmeticError'),
-    ('c:data', 'PyExc_AssertionError'),
-    ('c:data', 'PyExc_AttributeError'),
-    ('c:data', 'PyExc_BaseException'),
-    ('c:data', 'PyExc_BaseExceptionGroup'),
-    ('c:data', 'PyExc_BlockingIOError'),
-    ('c:data', 'PyExc_BrokenPipeError'),
-    ('c:data', 'PyExc_BufferError'),
-    ('c:data', 'PyExc_ChildProcessError'),
-    ('c:data', 'PyExc_ConnectionAbortedError'),
-    ('c:data', 'PyExc_ConnectionError'),
-    ('c:data', 'PyExc_ConnectionRefusedError'),
-    ('c:data', 'PyExc_ConnectionResetError'),
-    ('c:data', 'PyExc_EOFError'),
-    ('c:data', 'PyExc_Exception'),
-    ('c:data', 'PyExc_FileExistsError'),
-    ('c:data', 'PyExc_FileNotFoundError'),
-    ('c:data', 'PyExc_FloatingPointError'),
-    ('c:data', 'PyExc_GeneratorExit'),
-    ('c:data', 'PyExc_ImportError'),
-    ('c:data', 'PyExc_IndentationError'),
-    ('c:data', 'PyExc_IndexError'),
-    ('c:data', 'PyExc_InterruptedError'),
-    ('c:data', 'PyExc_IsADirectoryError'),
-    ('c:data', 'PyExc_KeyboardInterrupt'),
-    ('c:data', 'PyExc_KeyError'),
-    ('c:data', 'PyExc_LookupError'),
-    ('c:data', 'PyExc_MemoryError'),
-    ('c:data', 'PyExc_ModuleNotFoundError'),
-    ('c:data', 'PyExc_NameError'),
-    ('c:data', 'PyExc_NotADirectoryError'),
-    ('c:data', 'PyExc_NotImplementedError'),
-    ('c:data', 'PyExc_OSError'),
-    ('c:data', 'PyExc_OverflowError'),
-    ('c:data', 'PyExc_PermissionError'),
-    ('c:data', 'PyExc_ProcessLookupError'),
-    ('c:data', 'PyExc_PythonFinalizationError'),
-    ('c:data', 'PyExc_RecursionError'),
-    ('c:data', 'PyExc_ReferenceError'),
-    ('c:data', 'PyExc_RuntimeError'),
-    ('c:data', 'PyExc_StopAsyncIteration'),
-    ('c:data', 'PyExc_StopIteration'),
-    ('c:data', 'PyExc_SyntaxError'),
-    ('c:data', 'PyExc_SystemError'),
-    ('c:data', 'PyExc_SystemExit'),
-    ('c:data', 'PyExc_TabError'),
-    ('c:data', 'PyExc_TimeoutError'),
-    ('c:data', 'PyExc_TypeError'),
-    ('c:data', 'PyExc_UnboundLocalError'),
-    ('c:data', 'PyExc_UnicodeDecodeError'),
-    ('c:data', 'PyExc_UnicodeEncodeError'),
-    ('c:data', 'PyExc_UnicodeError'),
-    ('c:data', 'PyExc_UnicodeTranslateError'),
-    ('c:data', 'PyExc_ValueError'),
-    ('c:data', 'PyExc_ZeroDivisionError'),
-    # C API: Standard Python warning classes
-    ('c:data', 'PyExc_BytesWarning'),
-    ('c:data', 'PyExc_DeprecationWarning'),
-    ('c:data', 'PyExc_EncodingWarning'),
-    ('c:data', 'PyExc_FutureWarning'),
-    ('c:data', 'PyExc_ImportWarning'),
-    ('c:data', 'PyExc_PendingDeprecationWarning'),
-    ('c:data', 'PyExc_ResourceWarning'),
-    ('c:data', 'PyExc_RuntimeWarning'),
-    ('c:data', 'PyExc_SyntaxWarning'),
-    ('c:data', 'PyExc_UnicodeWarning'),
-    ('c:data', 'PyExc_UserWarning'),
-    ('c:data', 'PyExc_Warning'),
     # Undocumented public C macros
     ('c:macro', 'Py_BUILD_ASSERT'),
     ('c:macro', 'Py_BUILD_ASSERT_EXPR'),

Doc/conf.py

@@ -1280,6 +1280,16 @@ Glossary
       and ending with double underscores.  Special methods are documented in
       :ref:`specialnames`.
 
+   standard library
+      The collection of :term:`packages <package>`, :term:`modules <module>`
+      and :term:`extension modules <extension module>` distributed as a part
+      of the official Python interpreter package.  The exact membership of the
+      collection may vary based on platform, available system libraries, or
+      other criteria.  Documentation can be found at :ref:`library-index`.
+
+      See also :data:`sys.stdlib_module_names` for a list of all possible
+      standard library module names.
+
    statement
       A statement is part of a suite (a "block" of code).  A statement is either
       an :term:`expression` or one of several constructs with a keyword, such
@@ -1290,6 +1300,9 @@ Glossary
       issues such as incorrect types. See also :term:`type hints <type hint>`
       and the :mod:`typing` module.
 
+   stdlib
+      An abbreviation of :term:`standard library`.
+
    strong reference
       In Python's C API, a strong reference is a reference to an object
       which is owned by the code holding the reference.  The strong

Doc/data/python3.14.abi

@@ -4140,6 +4140,42 @@ The script, when run, prints something like:
     2025-07-02 13:54:47,234 DEBUG     fool me ...
     2025-07-02 13:54:47,234 DEBUG     can't get fooled again
 
+If, on the other hand, you are concerned about `log injection
+<https://owasp.org/www-community/attacks/Log_Injection>`_, you can use a
+formatter which escapes newlines, as per the following example:
+
+.. code-block:: python
+
+    import logging
+
+    logger = logging.getLogger(__name__)
+
+    class EscapingFormatter(logging.Formatter):
+        def format(self, record):
+            s = super().format(record)
+            return s.replace('\n', r'\n')
+
+    if __name__ == '__main__':
+        h = logging.StreamHandler()
+        h.setFormatter(EscapingFormatter('%(asctime)s %(levelname)-9s %(message)s'))
+        logging.basicConfig(level=logging.DEBUG, handlers = [h])
+        logger.debug('Single line')
+        logger.debug('Multiple lines:\nfool me once ...')
+        logger.debug('Another single line')
+        logger.debug('Multiple lines:\n%s', 'fool me ...\ncan\'t get fooled again')
+
+You can, of course, use whatever escaping scheme makes the most sense for you.
+The script, when run, should produce output like this:
+
+.. code-block:: text
+
+    2025-07-09 06:47:33,783 DEBUG     Single line
+    2025-07-09 06:47:33,783 DEBUG     Multiple lines:\nfool me once ...
+    2025-07-09 06:47:33,783 DEBUG     Another single line
+    2025-07-09 06:47:33,783 DEBUG     Multiple lines:\nfool me ...\ncan't get fooled again
+
+Escaping behaviour can't be the stdlib default , as it would break backwards
+compatibility.
 
 .. patterns-to-avoid:
 

Doc/glossary.rst

@@ -243,8 +243,8 @@ wider range of codecs when working with binary files:
 .. function:: iterencode(iterator, encoding, errors='strict', **kwargs)
 
    Uses an incremental encoder to iteratively encode the input provided by
-   *iterator*. This function is a :term:`generator`.
-   The *errors* argument (as well as any
+   *iterator*. *iterator* must yield :class:`str` objects.
+   This function is a :term:`generator`. The *errors* argument (as well as any
    other keyword argument) is passed through to the incremental encoder.
 
    This function requires that the codec accept text :class:`str` objects
@@ -255,8 +255,8 @@ wider range of codecs when working with binary files:
 .. function:: iterdecode(iterator, encoding, errors='strict', **kwargs)
 
    Uses an incremental decoder to iteratively decode the input provided by
-   *iterator*. This function is a :term:`generator`.
-   The *errors* argument (as well as any
+   *iterator*. *iterator* must yield :class:`bytes` objects.
+   This function is a :term:`generator`. The *errors* argument (as well as any
    other keyword argument) is passed through to the incremental decoder.
 
    This function requires that the codec accept :class:`bytes` objects
@@ -265,6 +265,20 @@ wider range of codecs when working with binary files:
    :func:`iterencode`.
 
 
+.. function:: readbuffer_encode(buffer, errors=None, /)
+
+   Return a :class:`tuple` containing the raw bytes of *buffer*, a
+   :ref:`buffer-compatible object <bufferobjects>` or :class:`str`
+   (encoded to UTF-8 before processing), and their length in bytes.
+
+   The *errors* argument is ignored.
+
+   .. code-block:: pycon
+
+      >>> codecs.readbuffer_encode(b"Zito")
+      (b'Zito', 4)
+
+
 The module also provides the following constants which are useful for reading
 and writing to platform dependent files:
 
@@ -1381,7 +1395,11 @@ encodings.
 |                    |         | It is used in the Python  |
 |                    |         | pickle protocol.          |
 +--------------------+---------+---------------------------+
-| undefined          |         | Raise an exception for    |
+| undefined          |         | This Codec should only    |
+|                    |         | be used for testing       |
+|                    |         | purposes.                 |
+|                    |         |                           |
+|                    |         | Raise an exception for    |
 |                    |         | all conversions, even     |
 |                    |         | empty strings. The error  |
 |                    |         | handler is ignored.       |
@@ -1484,6 +1502,66 @@ mapping. It is not supported by :meth:`str.encode` (which only produces
    Restoration of the ``rot13`` alias.
 
 
+:mod:`encodings` --- Encodings package
+--------------------------------------
+
+.. module:: encodings
+   :synopsis: Encodings package
+
+This module implements the following functions:
+
+.. function:: normalize_encoding(encoding)
+
+   Normalize encoding name *encoding*.
+
+   Normalization works as follows: all non-alphanumeric characters except the
+   dot used for Python package names are collapsed and replaced with a single
+   underscore, leading and trailing underscores are removed.
+   For example, ``'  -;#'`` becomes ``'_'``.
+
+   Note that *encoding* should be ASCII only.
+
+
+.. note::
+   The following functions should not be used directly, except for testing
+   purposes; :func:`codecs.lookup` should be used instead.
+
+
+.. function:: search_function(encoding)
+
+   Search for the codec module corresponding to the given encoding name
+   *encoding*.
+
+   This function first normalizes the *encoding* using
+   :func:`normalize_encoding`, then looks for a corresponding alias.
+   It attempts to import a codec module from the encodings package using either
+   the alias or the normalized name. If the module is found and defines a valid
+   ``getregentry()`` function that returns a :class:`codecs.CodecInfo` object,
+   the codec is cached and returned.
+
+   If the codec module defines a ``getaliases()`` function any returned aliases
+   are registered for future use.
+
+
+.. function:: win32_code_page_search_function(encoding)
+
+   Search for a Windows code page encoding *encoding* of the form ``cpXXXX``.
+
+   If the code page is valid and supported, return a :class:`codecs.CodecInfo`
+   object for it.
+
+   .. availability:: Windows.
+
+   .. versionadded:: 3.14
+
+
+This module implements the following exception:
+
+.. exception:: CodecRegistryError
+
+   Raised when a codec is invalid or incompatible.
+
+
 :mod:`encodings.idna` --- Internationalized Domain Names in Applications
 ------------------------------------------------------------------------
 

Doc/howto/logging-cookbook.rst

@@ -48,8 +48,8 @@ methods.
 FeedParser API
 ^^^^^^^^^^^^^^
 
-The :class:`BytesFeedParser`, imported from the :mod:`email.feedparser` module,
-provides an API that is conducive to incremental parsing of email messages,
+The :class:`BytesFeedParser`, imported from the :mod:`email.parser.FeedParser`
+module, provides an API that is conducive to incremental parsing of email messages,
 such as would be necessary when reading the text of an email message from a
 source that can block (such as a socket).  The :class:`BytesFeedParser` can of
 course be used to parse an email message fully contained in a :term:`bytes-like
@@ -116,7 +116,7 @@ Here is the API for the :class:`BytesFeedParser`:
    Works like :class:`BytesFeedParser` except that the input to the
    :meth:`~BytesFeedParser.feed` method must be a string.  This is of limited
    utility, since the only way for such a message to be valid is for it to
-   contain only ASCII text or, if :attr:`~email.policy.Policy.utf8` is
+   contain only ASCII text or, if :attr:`~email.policy.EmailPolicy.utf8` is
    ``True``, no binary attachments.
 
    .. versionchanged:: 3.3 Added the *policy* keyword.
@@ -155,11 +155,11 @@ message body, instead setting the payload to the raw body.
 
       Read all the data from the binary file-like object *fp*, parse the
       resulting bytes, and return the message object.  *fp* must support
-      both the :meth:`~io.IOBase.readline` and the :meth:`~io.IOBase.read`
+      both the :meth:`~io.IOBase.readline` and the :meth:`~io.TextIOBase.read`
       methods.
 
       The bytes contained in *fp* must be formatted as a block of :rfc:`5322`
-      (or, if :attr:`~email.policy.Policy.utf8` is ``True``, :rfc:`6532`)
+      (or, if :attr:`~email.policy.EmailPolicy.utf8` is ``True``, :rfc:`6532`)
       style headers and header continuation lines, optionally preceded by an
       envelope header.  The header block is terminated either by the end of the
       data or by a blank line.  Following the header block is the body of the

Doc/library/codecs.rst

@@ -204,18 +204,24 @@ The following exceptions are the exceptions that are usually raised.
    assignment fails.  (When an object does not support attribute references or
    attribute assignments at all, :exc:`TypeError` is raised.)
 
-   The :attr:`name` and :attr:`obj` attributes can be set using keyword-only
-   arguments to the constructor. When set they represent the name of the attribute
-   that was attempted to be accessed and the object that was accessed for said
-   attribute, respectively.
+   The optional *name* and *obj* keyword-only arguments
+   set the corresponding attributes:
+
+   .. attribute:: name
+
+      The name of the attribute that was attempted to be accessed.
+
+   .. attribute:: obj
+
+      The object that was accessed for the named attribute.
 
    .. versionchanged:: 3.10
       Added the :attr:`name` and :attr:`obj` attributes.
 
 .. exception:: EOFError
 
    Raised when the :func:`input` function hits an end-of-file condition (EOF)
-   without reading any data. (N.B.: the :meth:`io.IOBase.read` and
+   without reading any data. (Note: the :meth:`!io.IOBase.read` and
    :meth:`io.IOBase.readline` methods return an empty string when they hit EOF.)
 
 
@@ -312,9 +318,11 @@ The following exceptions are the exceptions that are usually raised.
    unqualified names.  The associated value is an error message that includes the
    name that could not be found.
 
-   The :attr:`name` attribute can be set using a keyword-only argument to the
-   constructor. When set it represent the name of the variable that was attempted
-   to be accessed.
+   The optional *name* keyword-only argument sets the attribute:
+
+   .. attribute:: name
+
+      The name of the variable that was attempted to be accessed.
 
    .. versionchanged:: 3.10
       Added the :attr:`name` attribute.
@@ -382,7 +390,7 @@ The following exceptions are the exceptions that are usually raised.
 
       The corresponding error message, as provided by
       the operating system.  It is formatted by the C
-      functions :c:func:`perror` under POSIX, and :c:func:`FormatMessage`
+      functions :c:func:`!perror` under POSIX, and :c:func:`!FormatMessage`
       under Windows.
 
    .. attribute:: filename
@@ -398,7 +406,7 @@ The following exceptions are the exceptions that are usually raised.
    .. versionchanged:: 3.3
       :exc:`EnvironmentError`, :exc:`IOError`, :exc:`WindowsError`,
       :exc:`socket.error`, :exc:`select.error` and
-      :exc:`mmap.error` have been merged into :exc:`OSError`, and the
+      :exc:`!mmap.error` have been merged into :exc:`OSError`, and the
       constructor may return a subclass.
 
    .. versionchanged:: 3.4
@@ -590,7 +598,7 @@ The following exceptions are the exceptions that are usually raised.
    handled, the Python interpreter exits; no stack traceback is printed.  The
    constructor accepts the same optional argument passed to :func:`sys.exit`.
    If the value is an integer, it specifies the system exit status (passed to
-   C's :c:func:`exit` function); if it is ``None``, the exit status is zero; if
+   C's :c:func:`!exit` function); if it is ``None``, the exit status is zero; if
    it has another type (such as a string), the object's value is printed and
    the exit status is one.
 

Doc/library/email.parser.rst

@@ -298,9 +298,10 @@ the :mod:`glob` module.)
    device than *path*, or whether :file:`{path}/..` and *path* point to the same
    i-node on the same device --- this should detect mount points for all Unix
    and POSIX variants.  It is not able to reliably detect bind mounts on the
-   same filesystem.  On Windows, a drive letter root and a share UNC are
-   always mount points, and for any other path ``GetVolumePathName`` is called
-   to see if it is different from the input path.
+   same filesystem. On Linux systems, it will always return ``True`` for btrfs
+   subvolumes, even if they aren't mount points. On Windows, a drive letter root
+   and a share UNC are always mount points, and for any other path
+   ``GetVolumePathName`` is called to see if it is different from the input path.
 
    .. versionchanged:: 3.4
       Added support for detecting non-root mount points on Windows.