Merge branch 'main' into ac-decimal/73487-pt2

Author: AA-Turner

Doc/library/decimal.rst

@@ -42,7 +42,7 @@ The :mod:`locale` module defines the following exception and functions:
    If *locale* is a pair, it is converted to a locale name using
    the locale aliasing engine.
    The language code has the same format as a :ref:`locale name <locale_name>`,
-   but without encoding and ``@``-modifier.
+   but without encoding.
    The language code and encoding can be ``None``.
 
    If *locale* is omitted or ``None``, the current setting for *category* is
@@ -58,6 +58,9 @@ The :mod:`locale` module defines the following exception and functions:
    specified in the :envvar:`LANG` environment variable).  If the locale is not
    changed thereafter, using multithreading should not cause problems.
 
+   .. versionchanged:: next
+      Support language codes with ``@``-modifiers.
+
 
 .. function:: localeconv()
 
@@ -366,11 +369,15 @@ The :mod:`locale` module defines the following exception and functions:
    values except :const:`LC_ALL`.  It defaults to :const:`LC_CTYPE`.
 
    The language code has the same format as a :ref:`locale name <locale_name>`,
-   but without encoding and ``@``-modifier.
+   but without encoding.
    The language code and encoding may be ``None`` if their values cannot be
    determined.
    The "C" locale is represented as ``(None, None)``.
 
+   .. versionchanged:: next
+      ``@``-modifier are no longer silently removed, but included in
+      the language code.
+
 
 .. function:: getpreferredencoding(do_setlocale=True)
 

Doc/library/locale.rst

@@ -34,7 +34,7 @@ To write a t-string, use a ``'t'`` prefix instead of an ``'f'``, like so:
    >>> pi = 3.14
    >>> t't-strings are new in Python {pi!s}!'
    Template(
-      strings=('t-strings are new in Python ', '.'),
+      strings=('t-strings are new in Python ', '!'),
       interpolations=(Interpolation(3.14, 'pi', 's', ''),)
    )
 

Doc/library/string.templatelib.rst

@@ -411,7 +411,7 @@ Here are some examples of typical usage of the :mod:`uuid` module::
    >>> import uuid
 
    >>> # make a UUID based on the host ID and current time
-   >>> uuid.uuid1()
+   >>> uuid.uuid1()  # doctest: +SKIP
    UUID('a8098c1a-f86e-11da-bd1a-00112444be1e')
 
    >>> # make a UUID using an MD5 hash of a namespace UUID and a name
@@ -449,15 +449,24 @@ Here are some examples of typical usage of the :mod:`uuid` module::
    >>> uuid.MAX
    UUID('ffffffff-ffff-ffff-ffff-ffffffffffff')
 
+   >>> # same as UUIDv1 but with fields reordered to improve DB locality
+   >>> uuid.uuid6()  # doctest: +SKIP
+   UUID('1f0799c0-98b9-62db-92c6-a0d365b91053')
+
    >>> # get UUIDv7 creation (local) time as a timestamp in milliseconds
    >>> u = uuid.uuid7()
    >>> u.time  # doctest: +SKIP
    1743936859822
+
    >>> # get UUIDv7 creation (local) time as a datetime object
    >>> import datetime as dt
    >>> dt.datetime.fromtimestamp(u.time / 1000)  # doctest: +SKIP
    datetime.datetime(...)
 
+   >>> # make a UUID with custom blocks
+   >>> uuid.uuid8(0x12345678, 0x9abcdef0, 0x11223344)
+   UUID('00001234-5678-8ef0-8000-000011223344')
+
 
 .. _uuid-cli-example:
 

Doc/library/uuid.rst

@@ -274,6 +274,15 @@ http.cookies
   (Contributed by Nick Burns and Senthil Kumaran in :gh:`92936`.)
 
 
+locale
+------
+
+* :func:`~locale.setlocale` now supports language codes with ``@``-modifiers.
+  ``@``-modifier are no longer silently removed in :func:`~locale.getlocale`,
+  but included in the language code.
+  (Contributed by Serhiy Storchaka in :gh:`137729`.)
+
+
 math
 ----
 

Doc/whatsnew/3.15.rst

@@ -271,11 +271,8 @@ def goahead(self, end):
                                 j -= len(suffix)
                                 break
                         self.handle_comment(rawdata[i+4:j])
-                    elif startswith("<![CDATA[", i):
-                        if self._support_cdata:
-                            self.unknown_decl(rawdata[i+3:])
-                        else:
-                            self.handle_comment(rawdata[i+1:])
+                    elif startswith("<![CDATA[", i) and self._support_cdata:
+                        self.unknown_decl(rawdata[i+3:])
                     elif rawdata[i:i+9].lower() == '<!doctype':
                         self.handle_decl(rawdata[i+2:])
                     elif startswith("<!", i):
@@ -350,15 +347,12 @@ def parse_html_declaration(self, i):
         if rawdata[i:i+4] == '<!--':
             # this case is actually already handled in goahead()
             return self.parse_comment(i)
-        elif rawdata[i:i+9] == '<![CDATA[':
-            if self._support_cdata:
-                j = rawdata.find(']]>', i+9)
-                if j < 0:
-                    return -1
-                self.unknown_decl(rawdata[i+3: j])
-                return j + 3
-            else:
-                return self.parse_bogus_comment(i)
+        elif rawdata[i:i+9] == '<![CDATA[' and self._support_cdata:
+            j = rawdata.find(']]>', i+9)
+            if j < 0:
+                return -1
+            self.unknown_decl(rawdata[i+3: j])
+            return j + 3
         elif rawdata[i:i+9].lower() == '<!doctype':
             # find the closing >
             gtpos = rawdata.find('>', i+9)

Lib/html/parser.py

@@ -297,7 +297,8 @@ def cache_from_source(path, debug_override=None, *, optimization=None):
         # Strip initial drive from a Windows path. We know we have an absolute
         # path here, so the second part of the check rules out a POSIX path that
         # happens to contain a colon at the second character.
-        if head[1] == ':' and head[0] not in path_separators:
+        # Slicing avoids issues with an empty (or short) `head`.
+        if head[1:2] == ':' and head[0:1] not in path_separators:
             head = head[2:]
 
         # Strip initial path separator from `head` to complete the conversion

Lib/importlib/_bootstrap_external.py

@@ -375,12 +375,14 @@ def _replace_encoding(code, encoding):
 def _append_modifier(code, modifier):
     if modifier == 'euro':
         if '.' not in code:
-            return code + '.ISO8859-15'
+            # Linux appears to require keeping the "@euro" modifier in place,
+            # even when using the ".ISO8859-15" encoding.
+            return code + '.ISO8859-15@euro'
         _, _, encoding = code.partition('.')
-        if encoding in ('ISO8859-15', 'UTF-8'):
+        if encoding == 'UTF-8':
             return code
         if encoding == 'ISO8859-1':
-            return _replace_encoding(code, 'ISO8859-15')
+            code = _replace_encoding(code, 'ISO8859-15')
     return code + '@' + modifier
 
 def normalize(localename):
@@ -485,13 +487,18 @@ def _parse_localename(localename):
         # Deal with locale modifiers
         code, modifier = code.split('@', 1)
         if modifier == 'euro' and '.' not in code:
-            # Assume Latin-9 for @euro locales. This is bogus,
-            # since some systems may use other encodings for these
-            # locales. Also, we ignore other modifiers.
-            return code, 'iso-8859-15'
+            # Assume ISO8859-15 for @euro locales. Do note that some systems
+            # may use other encodings for these locales, so this may not always
+            # be correct.
+            return code + '@euro', 'ISO8859-15'
+    else:
+        modifier = ''
 
     if '.' in code:
-        return tuple(code.split('.')[:2])
+        code, encoding = code.split('.')[:2]
+        if modifier:
+            code += '@' + modifier
+        return code, encoding
     elif code == 'C':
         return None, None
     elif code == 'UTF-8':
@@ -516,7 +523,14 @@ def _build_localename(localetuple):
         if encoding is None:
             return language
         else:
-            return language + '.' + encoding
+            if '@' in language:
+                language, modifier = language.split('@', 1)
+            else:
+                modifier = ''
+            localename = language + '.' + encoding
+            if modifier:
+                localename += '@' + modifier
+            return localename
     except (TypeError, ValueError):
         raise TypeError('Locale must be None, a string, or an iterable of '
                         'two strings -- language code, encoding.') from None
@@ -888,6 +902,12 @@ def getpreferredencoding(do_setlocale=True):
 # SS 2025-06-10:
 # Remove 'c.utf8' -> 'en_US.UTF-8' because 'en_US.UTF-8' does not exist
 # on all platforms.
+#
+# SS 2025-07-30:
+# Remove conflicts with GNU libc.
+#
+#    removed 'el_gr@euro'
+#    removed 'uz_uz@cyrillic'
 
 locale_alias = {
     'a3':                                   'az_AZ.KOI8-C',
@@ -1021,7 +1041,6 @@ def getpreferredencoding(do_setlocale=True):
     'el':                                   'el_GR.ISO8859-7',
     'el_cy':                                'el_CY.ISO8859-7',
     'el_gr':                                'el_GR.ISO8859-7',
-    'el_gr@euro':                           'el_GR.ISO8859-15',
     'en':                                   'en_US.ISO8859-1',
     'en_ag':                                'en_AG.UTF-8',
     'en_au':                                'en_AU.ISO8859-1',
@@ -1456,7 +1475,6 @@ def getpreferredencoding(do_setlocale=True):
     'ur_pk':                                'ur_PK.CP1256',
     'uz':                                   'uz_UZ.UTF-8',
     'uz_uz':                                'uz_UZ.UTF-8',
-    'uz_uz@cyrillic':                       'uz_UZ.UTF-8',
     've':                                   've_ZA.UTF-8',
     've_za':                                've_ZA.UTF-8',
     'vi':                                   'vi_VN.TCVN',

Lib/locale.py

@@ -791,7 +791,7 @@ def test_eof_in_cdata(self, content):
         self._run_check('<![CDATA[' + content,
                         [('unknown decl', 'CDATA[' + content)])
         self._run_check('<![CDATA[' + content,
-                        [('comment', '![CDATA[' + content)],
+                        [('comment', '[CDATA[' + content)],
                         collector=EventCollector(autocdata=True))
         self._run_check('<svg><text y="100"><![CDATA[' + content,
                         [('starttag', 'svg', []),

Lib/test/test_htmlparser.py

@@ -580,6 +580,18 @@ def test_cache_from_source_respects_pycache_prefix_relative(self):
                 self.util.cache_from_source(path, optimization=''),
                 os.path.normpath(expect))
 
+    @unittest.skipIf(sys.implementation.cache_tag is None,
+                     'requires sys.implementation.cache_tag to not be None')
+    def test_cache_from_source_in_root_with_pycache_prefix(self):
+        # Regression test for gh-82916
+        pycache_prefix = os.path.join(os.path.sep, 'tmp', 'bytecode')
+        path = 'qux.py'
+        expect = os.path.join(os.path.sep, 'tmp', 'bytecode',
+                              f'qux.{self.tag}.pyc')
+        with util.temporary_pycache_prefix(pycache_prefix):
+            with os_helper.change_cwd('/'):
+                self.assertEqual(self.util.cache_from_source(path), expect)
+
     @unittest.skipIf(sys.implementation.cache_tag is None,
                      'requires sys.implementation.cache_tag to not be None')
     def test_source_from_cache_inside_pycache_prefix(self):