Merge branch 'python:main' into patch-1

Author: jonathandung

Doc/c-api/import.rst

@@ -372,8 +372,10 @@ Importing Modules
 
    Sets the current lazy imports filter. The *filter* should be a callable that
    will receive ``(importing_module_name, imported_module_name, [fromlist])``
-   when an import can potentially be lazy and that must return ``True`` if
-   the import should be lazy and ``False`` otherwise.
+   when an import can potentially be lazy. The ``imported_module_name`` value
+   is the resolved module name, so ``lazy from .spam import eggs`` passes
+   ``package.spam``. The callable must return ``True`` if the import should be
+   lazy and ``False`` otherwise.
 
    Return ``0`` on success and ``-1`` with an exception set otherwise.
 

Doc/library/base64.rst

@@ -85,8 +85,11 @@ POST request.
 
    If *padded* is true, the last group of 4 base 64 alphabet characters must
    be padded with the '=' character.
-   If *padded* is false, the '=' character is treated as other non-alphabet
-   characters (depending on the value of *validate* and *ignorechars*).
+   If *padded* is false, padding is neither required nor recognized:
+   the '=' character is not treated as padding but as a non-alphabet
+   character, which means it is silently discarded when *validate* is false,
+   or causes an :exc:`~binascii.Error` when *validate* is true unless
+   b'=' is included in *ignorechars*.
 
    A :exc:`binascii.Error` exception is raised
    if *s* is incorrectly padded.
@@ -194,8 +197,10 @@ POST request.
 
    If *padded* is true, the last group of 8 base 32 alphabet characters must
    be padded with the '=' character.
-   If *padded* is false, the '=' character is treated as other non-alphabet
-   characters (depending on the value of *ignorechars*).
+   If *padded* is false, padding is neither required nor recognized:
+   the '=' character is not treated as padding but as a non-alphabet
+   character, which means it raises an :exc:`~binascii.Error` unless
+   b'=' is included in *ignorechars*.
 
    *ignorechars* should be a :term:`bytes-like object` containing characters
    to ignore from the input.

Doc/library/binascii.rst

@@ -59,8 +59,11 @@ The :mod:`!binascii` module defines the following functions:
 
    If *padded* is true, the last group of 4 base 64 alphabet characters must
    be padded with the '=' character.
-   If *padded* is false, the '=' character is treated as other non-alphabet
-   characters (depending on the value of *strict_mode* and *ignorechars*).
+   If *padded* is false, padding is neither required nor recognized:
+   the '=' character is not treated as padding but as a non-alphabet
+   character, which means it is silently discarded when *strict_mode* is false,
+   or causes an :exc:`~binascii.Error` when *strict_mode* is true unless
+   b'=' is included in *ignorechars*.
 
    If *ignorechars* is specified, it should be a :term:`bytes-like object`
    containing characters to ignore from the input when *strict_mode* is true.

Doc/library/pkgutil.rst

@@ -151,24 +151,48 @@ support.
    :meth:`get_data <importlib.abc.ResourceLoader.get_data>` API.  The
    *package* argument should be the name of a package, in standard module format
    (``foo.bar``).  The *resource* argument should be in the form of a relative
-   filename, using ``/`` as the path separator.  The parent directory name
-   ``..`` is not allowed, and nor is a rooted name (starting with a ``/``).
+   filename, using ``/`` as the path separator.
 
    The function returns a binary string that is the contents of the specified
    resource.
 
+   This function uses the :term:`loader` method
+   :func:`~importlib.abc.FileLoader.get_data`
+   to support modules installed in the filesystem, but also in zip files,
+   databases, or elsewhere.
+
    For packages located in the filesystem, which have already been imported,
    this is the rough equivalent of::
 
       d = os.path.dirname(sys.modules[package].__file__)
       data = open(os.path.join(d, resource), 'rb').read()
 
+   Like the :func:`open` function, :func:`!get_data` can follow parent
+   directories (``../``) and absolute paths (starting with ``/`` or ``C:/``,
+   for example).
+   It can open compilation/installation artifacts like ``.py`` and ``.pyc``
+   files or files with :func:`reserved filenames <os.path.isreserved>`.
+   To be compatible with non-filesystem loaders, avoid using these features.
+
+   .. warning::
+
+      This function is intended for trusted input.
+      It does not verify that *resource* "belongs" to *package*.
+
+   If you use a user-provided *resource* path, consider verifying it.
+   For example, require an alphanumeric filename with a known extension, or
+   install and check a list of known resources.
+
    If the package cannot be located or loaded, or it uses a :term:`loader`
    which does not support :meth:`get_data <importlib.abc.ResourceLoader.get_data>`,
    then ``None`` is returned.  In particular, the :term:`loader` for
    :term:`namespace packages <namespace package>` does not support
    :meth:`get_data <importlib.abc.ResourceLoader.get_data>`.
 
+   .. seealso::
+
+      The :mod:`importlib.resources` module provides structured access to
+      module resources.
 
 .. function:: resolve_name(name)
 

Doc/library/pprint.rst

@@ -31,7 +31,8 @@ Functions
 ---------
 
 .. function:: pp(object, stream=None, indent=1, width=80, depth=None, *, \
-                     compact=False, sort_dicts=False, underscore_numbers=False)
+                 compact=False, expand=False, sort_dicts=False, \
+                 underscore_numbers=False)
 
    Prints the formatted representation of *object*, followed by a newline.
    This function may be used in the interactive interpreter
@@ -69,6 +70,13 @@ Functions
       each item of a sequence will be formatted on a separate line,
       otherwise as many items as will fit within the *width*
       will be formatted on each output line.
+      Incompatible with *expand*.
+
+   :param bool expand:
+      If ``True``,
+      opening parentheses and brackets will be followed by a newline and the
+      following content will be indented by one level, similar to
+      pretty-printed JSON. Incompatible with *compact*.
 
    :param bool sort_dicts:
       If ``True``, dictionaries will be formatted with
@@ -95,18 +103,20 @@ Functions
 
 
 .. function:: pprint(object, stream=None, indent=1, width=80, depth=None, *, \
-                     compact=False, sort_dicts=True, underscore_numbers=False)
+                     compact=False, expand=False, sort_dicts=True, \
+                     underscore_numbers=False)
 
    Alias for :func:`~pprint.pp` with *sort_dicts* set to ``True`` by default,
    which would automatically sort the dictionaries' keys,
    you might want to use :func:`~pprint.pp` instead where it is ``False`` by default.
 
 
 .. function:: pformat(object, indent=1, width=80, depth=None, *, \
-                      compact=False, sort_dicts=True, underscore_numbers=False)
+                      compact=False, expand=False, sort_dicts=True, \
+                      underscore_numbers=False)
 
    Return the formatted representation of *object* as a string.  *indent*,
-   *width*, *depth*, *compact*, *sort_dicts* and *underscore_numbers* are
+   *width*, *depth*, *compact*, *expand*, *sort_dicts* and *underscore_numbers* are
    passed to the :class:`PrettyPrinter` constructor as formatting parameters
    and their meanings are as described in the documentation above.
 
@@ -150,7 +160,8 @@ PrettyPrinter Objects
 .. index:: single: ...; placeholder
 
 .. class:: PrettyPrinter(indent=1, width=80, depth=None, stream=None, *, \
-                         compact=False, sort_dicts=True, underscore_numbers=False)
+                         compact=False, expand=False, sort_dicts=True, \
+                         underscore_numbers=False)
 
    Construct a :class:`PrettyPrinter` instance.
 
@@ -174,6 +185,22 @@ PrettyPrinter Objects
      'knights', 'ni'],
     'spam', 'eggs', 'lumberjack', 'knights',
     'ni']
+   >>> pp = pprint.PrettyPrinter(width=41, expand=True, indent=3)
+   >>> pp.pprint(stuff)
+   [
+      [
+         'spam',
+         'eggs',
+         'lumberjack',
+         'knights',
+         'ni',
+      ],
+      'spam',
+      'eggs',
+      'lumberjack',
+      'knights',
+      'ni',
+   ]
    >>> tup = ('spam', ('eggs', ('lumberjack', ('knights', ('ni', ('dead',
    ... ('parrot', ('fresh fruit',))))))))
    >>> pp = pprint.PrettyPrinter(depth=6)
@@ -193,6 +220,9 @@ PrettyPrinter Objects
    .. versionchanged:: 3.11
       No longer attempts to write to :data:`!sys.stdout` if it is ``None``.
 
+   .. versionchanged:: next
+      Added the *expand* parameter.
+
 
 :class:`PrettyPrinter` instances have the following methods:
 
@@ -415,3 +445,72 @@ cannot be split, the specified width will be exceeded::
     'requires_python': None,
     'summary': 'A sample Python project',
     'version': '1.2.0'}
+
+Lastly, we can format like pretty-printed JSON with the *expand* parameter.
+Best results are achieved with a higher *indent* value::
+
+   >>> pprint.pp(project_info, indent=4, expand=True)
+   {
+      'author': 'The Python Packaging Authority',
+      'author_email': 'pypa-dev@googlegroups.com',
+      'bugtrack_url': None,
+      'classifiers': [
+         'Development Status :: 3 - Alpha',
+         'Intended Audience :: Developers',
+         'License :: OSI Approved :: MIT License',
+         'Programming Language :: Python :: 2',
+         'Programming Language :: Python :: 2.6',
+         'Programming Language :: Python :: 2.7',
+         'Programming Language :: Python :: 3',
+         'Programming Language :: Python :: 3.2',
+         'Programming Language :: Python :: 3.3',
+         'Programming Language :: Python :: 3.4',
+         'Topic :: Software Development :: Build Tools',
+      ],
+      'description': 'A sample Python project\n'
+      '=======================\n'
+      '\n'
+      'This is the description file for the project.\n'
+      '\n'
+      'The file should use UTF-8 encoding and be written using ReStructured '
+      'Text. It\n'
+      'will be used to generate the project webpage on PyPI, and should be '
+      'written for\n'
+      'that purpose.\n'
+      '\n'
+      'Typical contents for this file would include an overview of the project, '
+      'basic\n'
+      'usage examples, etc. Generally, including the project changelog in here '
+      'is not\n'
+      'a good idea, although a simple "What\'s New" section for the most recent '
+      'version\n'
+      'may be appropriate.',
+      'description_content_type': None,
+      'docs_url': None,
+      'download_url': 'UNKNOWN',
+      'downloads': {'last_day': -1, 'last_month': -1, 'last_week': -1},
+      'dynamic': None,
+      'home_page': 'https://github.com/pypa/sampleproject',
+      'keywords': 'sample setuptools development',
+      'license': 'MIT',
+      'license_expression': None,
+      'license_files': None,
+      'maintainer': None,
+      'maintainer_email': None,
+      'name': 'sampleproject',
+      'package_url': 'https://pypi.org/project/sampleproject/',
+      'platform': 'UNKNOWN',
+      'project_url': 'https://pypi.org/project/sampleproject/',
+      'project_urls': {
+         'Download': 'UNKNOWN',
+         'Homepage': 'https://github.com/pypa/sampleproject',
+      },
+      'provides_extra': None,
+      'release_url': 'https://pypi.org/project/sampleproject/1.2.0/',
+      'requires_dist': None,
+      'requires_python': None,
+      'summary': 'A sample Python project',
+      'version': '1.2.0',
+      'yanked': False,
+      'yanked_reason': None,
+   }

Doc/library/sys.rst

@@ -1788,7 +1788,9 @@ always available. Unless explicitly noted otherwise, all variables are read-only
    Where:
 
    * *importing_module* is the name of the module doing the import
-   * *imported_module* is the name of the module being imported
+   * *imported_module* is the resolved name of the module being imported
+     (for example, ``lazy from .spam import eggs`` passes
+     ``package.spam``)
    * *fromlist* is the tuple of names being imported (for ``from ... import``
      statements), or ``None`` for regular imports
 

Doc/whatsnew/3.15.rst

@@ -1507,6 +1507,16 @@ platform
   (Contributed by Alexey Makridenko in :gh:`133604`.)
 
 
+pprint
+------
+
+* Add an *expand* keyword argument for :func:`pprint.pprint`,
+  :func:`pprint.pformat`, :func:`pprint.pp`. If true, the output will be
+  formatted similar to pretty-printed :func:`json.dumps` when
+  *indent* is supplied.
+  (Contributed by Stefan Todoran and Semyon Moroz in :gh:`112632`.)
+
+
 sre_*
 -----
 

Include/cpython/object.h

@@ -495,3 +495,82 @@ PyAPI_FUNC(void) PyUnstable_EnableTryIncRef(PyObject *);
 PyAPI_FUNC(int) PyUnstable_Object_IsUniquelyReferenced(PyObject *);
 
 PyAPI_FUNC(int) PyUnstable_SetImmortal(PyObject *op);
+
+#if defined(Py_GIL_DISABLED)
+PyAPI_FUNC(uintptr_t) _Py_GetThreadLocal_Addr(void);
+
+static inline uintptr_t
+_Py_ThreadId(void)
+{
+    uintptr_t tid;
+#if defined(_MSC_VER) && defined(_M_X64)
+    tid = __readgsqword(48);
+#elif defined(_MSC_VER) && defined(_M_IX86)
+    tid = __readfsdword(24);
+#elif defined(_MSC_VER) && defined(_M_ARM64)
+    tid = __getReg(18);
+#elif defined(__MINGW32__) && defined(_M_X64)
+    tid = __readgsqword(48);
+#elif defined(__MINGW32__) && defined(_M_IX86)
+    tid = __readfsdword(24);
+#elif defined(__MINGW32__) && defined(_M_ARM64)
+    tid = __getReg(18);
+#elif defined(__i386__)
+    __asm__("{movl %%gs:0, %0|mov %0, dword ptr gs:[0]}" : "=r" (tid));  // 32-bit always uses GS
+#elif defined(__MACH__) && defined(__x86_64__)
+    __asm__("{movq %%gs:0, %0|mov %0, qword ptr gs:[0]}" : "=r" (tid));  // x86_64 macOSX uses GS
+#elif defined(__x86_64__)
+    __asm__("{movq %%fs:0, %0|mov %0, qword ptr fs:[0]}" : "=r" (tid));  // x86_64 Linux, BSD uses FS
+#elif defined(__arm__) && __ARM_ARCH >= 7
+    __asm__ ("mrc p15, 0, %0, c13, c0, 3\nbic %0, %0, #3" : "=r" (tid));
+#elif defined(__aarch64__) && defined(__APPLE__)
+    __asm__ ("mrs %0, tpidrro_el0" : "=r" (tid));
+#elif defined(__aarch64__)
+    __asm__ ("mrs %0, tpidr_el0" : "=r" (tid));
+#elif defined(__powerpc64__)
+    #if defined(__clang__) && _Py__has_builtin(__builtin_thread_pointer)
+    tid = (uintptr_t)__builtin_thread_pointer();
+    #else
+    // r13 is reserved for use as system thread ID by the Power 64-bit ABI.
+    register uintptr_t tp __asm__ ("r13");
+    __asm__("" : "=r" (tp));
+    tid = tp;
+    #endif
+#elif defined(__powerpc__)
+    #if defined(__clang__) && _Py__has_builtin(__builtin_thread_pointer)
+    tid = (uintptr_t)__builtin_thread_pointer();
+    #else
+    // r2 is reserved for use as system thread ID by the Power 32-bit ABI.
+    register uintptr_t tp __asm__ ("r2");
+    __asm__ ("" : "=r" (tp));
+    tid = tp;
+    #endif
+#elif defined(__s390__) && defined(__GNUC__)
+    // Both GCC and Clang have supported __builtin_thread_pointer
+    // for s390 from long time ago.
+    tid = (uintptr_t)__builtin_thread_pointer();
+#elif defined(__riscv)
+    #if defined(__clang__) && _Py__has_builtin(__builtin_thread_pointer)
+    tid = (uintptr_t)__builtin_thread_pointer();
+    #else
+    // tp is Thread Pointer provided by the RISC-V ABI.
+    __asm__ ("mv %0, tp" : "=r" (tid));
+    #endif
+#else
+    // Fallback to a portable implementation if we do not have a faster
+    // platform-specific implementation.
+    tid = _Py_GetThreadLocal_Addr();
+#endif
+  return tid;
+}
+
+static inline Py_ALWAYS_INLINE int
+_Py_IsOwnedByCurrentThread(PyObject *ob)
+{
+#ifdef _Py_THREAD_SANITIZER
+    return _Py_atomic_load_uintptr_relaxed(&ob->ob_tid) == _Py_ThreadId();
+#else
+    return ob->ob_tid == _Py_ThreadId();
+#endif
+}
+#endif

Include/internal/pycore_crossinterp.h

@@ -265,6 +265,12 @@ typedef struct {
         // heap types
         PyObject *PyExc_NotShareableError;
     } exceptions;
+
+    // Cached references to pickle.dumps/loads (per-interpreter).
+    struct {
+        PyObject *dumps;
+        PyObject *loads;
+    } pickle;
 } _PyXI_state_t;
 
 #define _PyXI_GET_GLOBAL_STATE(interp) (&(interp)->runtime->xi)