RustPython · youknowone · Aug 22, 2026 · Aug 20, 2026 · Aug 20, 2026 · Aug 20, 2026
diff --git a/Lib/_pydatetime.py b/Lib/_pydatetime.py
@@ -55,7 +55,7 @@ def _days_before_year(year):
 
 def _days_in_month(year, month):
     "year, month -> number of days in that month in that year."
-    assert 1 <= month <= 12, month
+    assert 1 <= month <= 12, f"month must be in 1..12, not {month}"
     if month == 2 and _is_leap(year):
         return 29
     return _DAYS_IN_MONTH[month]
@@ -272,12 +272,12 @@ def _wrap_strftime(object, format, timetuple):
                     newformat.append(Zreplace)
                 # Note that datetime(1000, 1, 1).strftime('%G') == '1000' so
                 # year 1000 for %G can go on the fast path.
-                elif ((ch in 'YG' or ch in 'FC') and
-                        object.year < 1000 and _need_normalize_century()):
+                elif (ch in 'YGFC' and timetuple[0] < 1000 and
+                        _need_normalize_century()):
                     if ch == 'G':
                         year = int(_time.strftime("%G", timetuple))
                     else:
-                        year = object.year
+                        year = timetuple[0]
                     if ch == 'C':
                         push('{:02}'.format(year // 100))
                     else:
@@ -358,7 +358,8 @@ def _find_isoformat_datetime_separator(dtstr):
 def _parse_isoformat_date(dtstr):
     # It is assumed that this is an ASCII-only string of lengths 7, 8 or 10,
     # see the comment on Modules/_datetimemodule.c:_find_isoformat_datetime_separator
-    assert len(dtstr) in (7, 8, 10)
+    if len(dtstr) not in (7, 8, 10):
+        raise ValueError("Invalid isoformat string")
     year = int(dtstr[0:4])
     has_sep = dtstr[4] == '-'
 
@@ -1947,7 +1948,7 @@ def fromisoformat(cls, date_string):
                 if became_next_day:
                     year, month, day = date_components
                     # Only wrap day/month when it was previously valid
-                    if month <= 12 and day <= (days_in_month := _days_in_month(year, month)):
+                    if 1 <= month <= 12 and day <= (days_in_month := _days_in_month(year, month)):
                         # Calculate midnight of the next day
                         day += 1
                         if day > days_in_month:

diff --git a/Lib/_pyio.py b/Lib/_pyio.py
@@ -1904,7 +1904,7 @@ def truncate(self, pos=None):
         """Truncate size to pos, where pos is an int."""
         self._unsupported("truncate")
 
-    def readline(self):
+    def readline(self, size=-1, /):
         """Read until newline or EOF.
 
         Returns an empty string if EOF is hit immediately.

diff --git a/Lib/argparse.py b/Lib/argparse.py
@@ -1829,6 +1829,9 @@ def _prog_name(prog=None):
     if modspec is None:
         # simple script
         return _os.path.basename(arg0)
+    if modspec.name != '__main__' and arg0 != modspec.origin:
+        # named module executed as main without altering sys.argv[0]
+        return _os.path.basename(arg0)
     py = _os.path.basename(_sys.executable)
     if modspec.name != '__main__':
         # imported module or package

diff --git a/Lib/base64.py b/Lib/base64.py
@@ -1,4 +1,4 @@
-"""Base16, Base32, Base64 (RFC 3548), Base85 and Ascii85 data encodings"""
+"""Base16, Base32, Base64 (RFC 4648), Base85 and Ascii85 data encodings"""
 
 # Modified 04-Oct-1995 by Jack Jansen to use binascii module
 # Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support
@@ -147,7 +147,7 @@ def urlsafe_b64decode(s):
 characters present in the input.
 '''
 _B32_DECODE_MAP01_DOCSTRING = '''
-RFC 3548 allows for optional mapping of the digit 0 (zero) to the
+RFC 4648 allows for optional mapping of the digit 0 (zero) to the
 letter O (oh), and for optional mapping of the digit 1 (one) to
 either the letter I (eye) or letter L (el).  The optional argument
 map01 when not None, specifies which letter the digit 1 should be
@@ -261,7 +261,7 @@ def b32hexdecode(s, casefold=False):
                                                     extra_args='')
 
 
-# RFC 3548, Base 16 Alphabet specifies uppercase, but hexlify() returns
+# RFC 4648, Base 16 Alphabet specifies uppercase, but hexlify() returns
 # lowercase.  The RFC also recommends against accepting input case
 # insensitively.
 def b16encode(s):

diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py
@@ -553,6 +553,9 @@ class Counter(dict):
     or multiset.  Elements are stored as dictionary keys and their counts
     are stored as dictionary values.
 
+    When constructed from a Mapping or Counter, the original object's
+    values will be used as the initial counts.
+
     >>> c = Counter('abcdeabcdabcaba')  # count elements from a string
 
     >>> c.most_common(3)                # three most common elements

diff --git a/Lib/configparser.py b/Lib/configparser.py
@@ -992,7 +992,9 @@ def _write_section(self, fp, section_name, section_items, delimiter, unnamed=Fal
             value = self._interpolation.before_write(self, section_name, key,
                                                      value)
             if value is not None or not self._allow_no_value:
-                value = delimiter + str(value).replace('\n', '\n\t')
+                # Convert all possible line-endings into '\n\t'
+                value = (delimiter + str(value).replace('\r\n', '\n')
+                         .replace('\r', '\n').replace('\n', '\n\t'))
             else:
                 value = ""
             fp.write("{}{}\n".format(key, value))

diff --git a/Lib/csv.py b/Lib/csv.py
@@ -243,8 +243,14 @@ def __init__(self):
     def sniff(self, sample, delimiters=None):
         """
         Returns a dialect (or None) corresponding to the sample
+
+        If several delimiters fit the sample equally well, the
+        delimiters listed in the preferred attribute are preferred, in
+        that order, no matter how many times each of them occurs.
         """
 
+        sample = sample.replace('\r\n', '\n').replace('\r', '\n')
+
         quotechar, doublequote, delimiter, skipinitialspace = \
                    self._guess_quote_and_delimiter(sample, delimiters)
         if not delimiter:
@@ -282,12 +288,16 @@ def _guess_quote_and_delimiter(self, data, delimiters):
         """
         import re
 
+        # The body of a quoted field ends at the first quote which is
+        # not doubled, as it does for a reader.  A lazy ".*?" scans to
+        # the end of the sample instead, from every start: quadratically.
+        body = r'(?:(?P=quote){2}|(?!(?P=quote)).)*+'
         matches = []
-        for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?",
-                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)',   #  ".*?",
-                      r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)',   # ,".*?"
-                      r'(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'):                            #  ".*?" (no delim, no space)
-            regexp = re.compile(restr, re.DOTALL | re.MULTILINE)
+        for restr in (r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\'])%s(?P=quote)(?P=delim)',   # ,"...",
+                      r'(?:^|\n)(?P<quote>["\'])%s(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)',     #  "...",
+                      r'(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\'])%s(?P=quote)(?:$|\n)',  # ,"..."
+                      r'(?:^|\n)(?P<quote>["\'])%s(?P=quote)(?:$|\n)'):                           #  "..." (no delim, no space)
+            regexp = re.compile(restr % body, re.DOTALL | re.MULTILINE)
             matches = regexp.findall(data)
             if matches:
                 break
@@ -330,18 +340,22 @@ def _guess_quote_and_delimiter(self, data, delimiters):
             delim = ''
             skipinitialspace = 0
 
-        # if we see an extra quote between delimiters, we've got a
-        # double quoted format
-        dq_regexp = re.compile(
-                               r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \
-                               {'delim':re.escape(delim), 'quote':quotechar}, re.MULTILINE)
-
-
-
-        if dq_regexp.search(data):
-            doublequote = True
-        else:
-            doublequote = False
+        # A doubled quote character inside a quoted field means
+        # a double quoted format.  Match whole fields, so that a match
+        # cannot slide across field boundaries.
+        doublequote = False
+        if delim:
+            dq_regexp = re.compile(
+                    r"(?:(?<=%(delim)s)|^)%(space)s%(quote)s"     # ,"
+                    r"((?:%(quote)s%(quote)s|[^%(quote)s]++)*+)"  # the body
+                    r"%(quote)s(?:%(delim)s|$)"                   # ",
+                    % {'delim': re.escape(delim), 'quote': quotechar,
+                       # Skipping spaces after a space rescans them.
+                       'space': ' *+' if delim != ' ' else ''},
+                    re.MULTILINE)
+            dquotechar = quotechar * 2
+            doublequote = any(dquotechar in m[1]
+                              for m in dq_regexp.finditer(data))
 
         return (quotechar, doublequote, delim, skipinitialspace)
 

diff --git a/Lib/dataclasses.py b/Lib/dataclasses.py
@@ -1247,6 +1247,7 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen,
 # classes with slots.  These could be slightly more performant if we generated
 # the code instead of iterating over fields.  But that can be a project for
 # another day, if performance becomes an issue.
+
 def _dataclass_getstate(self):
     return [getattr(self, f.name) for f in fields(self)]
 

diff --git a/Lib/difflib.py b/Lib/difflib.py
@@ -1977,6 +1977,8 @@ def make_table(self,fromlines,tolines,fromdesc='',todesc='',context=False,
 
         # change tabs to spaces before it gets more difficult after we insert
         # markup
+        # it also removes trailing newlines, causing some diffs to be missed
+        # see: gh-71896
         fromlines,tolines = self._tab_newline_replace(fromlines,tolines)
 
         # create diffs iterator which generates side by side from/to data

diff --git a/Lib/glob.py b/Lib/glob.py
@@ -34,8 +34,8 @@ def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
     If `dir_fd` is not None, it should be a file descriptor referring to a
     directory, and paths will then be relative to that directory.
 
-    If `include_hidden` is true, the patterns '*', '?', '**'  will match
-    hidden directories.
+    If `include_hidden` is true, wildcards can match path segments beginning
+    with a dot ('.').
 
     If `recursive` is true, the pattern '**' will match any files and
     zero or more directories and subdirectories.
@@ -64,8 +64,8 @@ def iglob(pathname, *, root_dir=None, dir_fd=None, recursive=False,
     If `dir_fd` is not None, it should be a file descriptor referring to a
     directory, and paths will then be relative to that directory.
 
-    If `include_hidden` is true, the patterns '*', '?', '**'  will match
-    hidden directories.
+    If `include_hidden` is true, wildcards can match path segments beginning
+    with a dot ('.').
 
     If `recursive` is true, the pattern '**' will match any files and
     zero or more directories and subdirectories.

diff --git a/Lib/inspect.py b/Lib/inspect.py
@@ -196,18 +196,18 @@ def ispackage(object):
 def ismethoddescriptor(object):
     """Return true if the object is a method descriptor.
 
-    But not if ismethod() or isclass() or isfunction() are true.
+    But not if ismethod(), isclass() or isfunction() is true.
 
-    This is new in Python 2.2, and, for example, is true of int.__add__.
-    An object passing this test has a __get__ attribute, but not a
-    __set__ attribute or a __delete__ attribute. Beyond that, the set
-    of attributes varies; __name__ is usually sensible, and __doc__
-    often is.
+    An object passing this test (for example, int.__add__) has a __get__
+    attribute, but not a __set__ attribute or a __delete__ attribute.
+    Beyond that, the set of attributes varies; __name__ is usually
+    sensible, and __doc__ often is.
 
     Methods implemented via descriptors that also pass one of the other
-    tests return false from the ismethoddescriptor() test, simply because
-    the other tests promise more -- you can, e.g., count on having the
-    __func__ attribute (etc) when an object passes ismethod()."""
+    tests (ismethod(), isclass(), isfunction()) make this function return
+    false, simply because those other tests promise more -- you can, for
+    example, count on having the __func__ attribute when an object passes
+    ismethod()."""
     if isclass(object) or ismethod(object) or isfunction(object):
         # mutual exclusion
         return False
@@ -219,8 +219,13 @@ def ismethoddescriptor(object):
 def isdatadescriptor(object):
     """Return true if the object is a data descriptor.
 
+    But not if ismethod(), isclass() or isfunction() is true.
+
     Data descriptors have a __set__ or a __delete__ attribute.  Examples are
-    properties (defined in Python) and getsets and members (defined in C).
+    properties, getsets, and members.  For the latter two (defined only in C
+    extension modules) more specific tests are available as well:
+    isgetsetdescriptor() and ismemberdescriptor(), respectively.
+
     Typically, data descriptors will also have __name__ and __doc__ attributes
     (properties, getsets, and members have both of these attributes), but this
     is not guaranteed."""
@@ -2712,6 +2717,10 @@ def __init__(self, name, kind, *, default=_empty, annotation=_empty):
                 raise ValueError(msg)
             self._kind = _POSITIONAL_ONLY
             name = 'implicit{}'.format(name[1:])
+        elif name == '.format':
+            # gh-151665: Hidden parameter of compiler-generated annotation and type
+            # alias/typevar evaluators. Show it as "format".
+            name = 'format'
 
         # It's possible for C functions to have a positional-only parameter
         # where the name is a keyword, so for compatibility we'll allow it.

diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py
@@ -111,7 +111,7 @@ def py_scanstring(s, end, strict=True,
             if strict:
                 #msg = "Invalid control character %r at" % (terminator,)
                 msg = "Invalid control character {0!r} at".format(terminator)
-                raise JSONDecodeError(msg, s, end)
+                raise JSONDecodeError(msg, s, end - 1)
             else:
                 _append(terminator)
                 continue

diff --git a/Lib/locale.py b/Lib/locale.py
@@ -545,12 +545,6 @@ def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):
 
     """
 
-    import warnings
-    warnings._deprecated(
-        "locale.getdefaultlocale",
-        "{name!r} is deprecated and slated for removal in Python {remove}. "
-        "Use setlocale(), getencoding() and getlocale() instead.",
-        remove=(3, 15))
     return _getdefaultlocale(envvars)
 
 

diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py
@@ -244,7 +244,7 @@ def read(self, filename, strict=True):
         list of standard types, else to the list of non-standard
         types.
         """
-        with open(filename, encoding='utf-8') as fp:
+        with open(filename, encoding='utf-8', errors='surrogateescape') as fp:
             self.readfp(fp, strict)
 
     def readfp(self, fp, strict=True):
@@ -435,7 +435,7 @@ def init(files=None):
 
 def read_mime_types(file):
     try:
-        f = open(file, encoding='utf-8')
+        f = open(file, encoding='utf-8', errors='surrogateescape')
     except OSError:
         return None
     with f:

diff --git a/Lib/ntpath.py b/Lib/ntpath.py
@@ -345,7 +345,7 @@ def _isreservedname(name):
 def expanduser(path):
     """Expand ~ and ~user constructs.
 
-    If user or $HOME is unknown, do nothing."""
+    If user or home directory is unknown, do nothing."""
     path = os.fspath(path)
     if isinstance(path, bytes):
         seps = b'\\/'

diff --git a/Lib/pydoc.py b/Lib/pydoc.py
@@ -1876,6 +1876,7 @@ class Helper:
         'async': ('async', ''),
         'await': ('await', ''),
         'break': ('break', 'while for'),
+        'case': 'match',
         'class': ('class', 'CLASSES SPECIALMETHODS'),
         'continue': ('continue', 'while for'),
         'def': ('function', ''),
@@ -1887,11 +1888,12 @@ class Helper:
         'for': ('for', 'break continue while'),
         'from': 'import',
         'global': ('global', 'nonlocal NAMESPACES'),
-        'if': ('if', 'TRUTHVALUE'),
+        'if': ('if', 'TRUTHVALUE match'),
         'import': ('import', 'MODULES'),
         'in': ('in', 'SEQUENCEMETHODS'),
         'is': 'COMPARISON',
         'lambda': ('lambda', 'FUNCTIONS'),
+        'match': ('match', 'if'),
         'nonlocal': ('nonlocal', 'global NAMESPACES'),
         'not': 'BOOLEAN',
         'or': 'BOOLEAN',

diff --git a/Lib/pydoc_data/module_docs.py b/Lib/pydoc_data/module_docs.py
@@ -1,4 +1,4 @@
-# Autogenerated by Sphinx on Wed Jun 10 13:03:46 2026
+# Autogenerated by Sphinx on Wed Aug  5 13:29:41 2026
 # as part of the release process.
 
 module_docs = {
@@ -251,6 +251,7 @@
     'tkinter': 'tkinter#module-tkinter',
     'tkinter.colorchooser': 'tkinter.colorchooser#module-tkinter.colorchooser',
     'tkinter.commondialog': 'dialog#module-tkinter.commondialog',
+    'tkinter.dialog': 'dialog#module-tkinter.dialog',
     'tkinter.dnd': 'tkinter.dnd#module-tkinter.dnd',
     'tkinter.filedialog': 'dialog#module-tkinter.filedialog',
     'tkinter.font': 'tkinter.font#module-tkinter.font',