Merge branch 'main' into fix-exeptions-append-after-cancel-async-stagger

Author: graingert

.github/workflows/reusable-docs.yml

@@ -99,7 +99,7 @@ jobs:
   # Run "doctest" on HEAD as new syntax doesn't exist in the latest stable release
   doctest:
     name: 'Doctest'
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     timeout-minutes: 60
     steps:
     - uses: actions/checkout@v4

Doc/library/email.policy.rst

@@ -267,7 +267,7 @@ added matters.  To illustrate::
 
       Handle a *defect* found on *obj*.  When the email package calls this
       method, *defect* will always be a subclass of
-      :class:`~email.errors.Defect`.
+      :class:`~email.errors.MessageDefect`.
 
       The default implementation checks the :attr:`raise_on_defect` flag.  If
       it is ``True``, *defect* is raised as an exception.  If it is ``False``
@@ -277,7 +277,7 @@ added matters.  To illustrate::
    .. method:: register_defect(obj, defect)
 
       Register a *defect* on *obj*.  In the email package, *defect* will always
-      be a subclass of :class:`~email.errors.Defect`.
+      be a subclass of :class:`~email.errors.MessageDefect`.
 
       The default implementation calls the ``append`` method of the ``defects``
       attribute of *obj*.  When the email package calls :attr:`handle_defect`,

Doc/tools/.nitignore

@@ -23,7 +23,6 @@ Doc/library/email.charset.rst
 Doc/library/email.compat32-message.rst
 Doc/library/email.errors.rst
 Doc/library/email.parser.rst
-Doc/library/email.policy.rst
 Doc/library/exceptions.rst
 Doc/library/functools.rst
 Doc/library/http.cookiejar.rst

Include/cpython/unicodeobject.h

@@ -109,7 +109,7 @@ typedef struct {
                3: Interned, Immortal, and Static
            This categorization allows the runtime to determine the right
            cleanup mechanism at runtime shutdown. */
-        unsigned int interned:2;
+        uint16_t interned;
         /* Character size:
 
            - PyUnicode_1BYTE_KIND (1):
@@ -132,21 +132,23 @@ typedef struct {
              * all characters are in the range U+0000-U+10FFFF
              * at least one character is in the range U+10000-U+10FFFF
          */
-        unsigned int kind:3;
+        unsigned short kind:3;
         /* Compact is with respect to the allocation scheme. Compact unicode
            objects only require one memory block while non-compact objects use
            one block for the PyUnicodeObject struct and another for its data
            buffer. */
-        unsigned int compact:1;
+        unsigned short compact:1;
         /* The string only contains characters in the range U+0000-U+007F (ASCII)
            and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
            set, use the PyASCIIObject structure. */
-        unsigned int ascii:1;
+        unsigned short ascii:1;
         /* The object is statically allocated. */
-        unsigned int statically_allocated:1;
+        unsigned short statically_allocated:1;
         /* Padding to ensure that PyUnicode_DATA() is always aligned to
-           4 bytes (see issue #19537 on m68k). */
-        unsigned int :24;
+           4 bytes (see issue #19537 on m68k) and we use unsigned short to avoid
+           the extra four bytes on 32-bit Windows. This is restricted features
+           for specific compilers including GCC, MSVC, Clang and IBM's XL compiler. */
+        unsigned short :10;
     } state;
 } PyASCIIObject;
 
@@ -195,7 +197,11 @@ typedef struct {
 
 /* Use only if you know it's a string */
 static inline unsigned int PyUnicode_CHECK_INTERNED(PyObject *op) {
+#ifdef Py_GIL_DISABLED
+    return _Py_atomic_load_uint16_relaxed(&_PyASCIIObject_CAST(op)->state.interned);
+#else
     return _PyASCIIObject_CAST(op)->state.interned;
+#endif
 }
 #define PyUnicode_CHECK_INTERNED(op) PyUnicode_CHECK_INTERNED(_PyObject_CAST(op))
 

Lib/email/message.py

@@ -286,8 +286,12 @@ def get_payload(self, i=None, decode=False):
         if i is not None and not isinstance(self._payload, list):
             raise TypeError('Expected list, got %s' % type(self._payload))
         payload = self._payload
-        # cte might be a Header, so for now stringify it.
-        cte = str(self.get('content-transfer-encoding', '')).lower()
+        cte = self.get('content-transfer-encoding', '')
+        if hasattr(cte, 'cte'):
+            cte = cte.cte
+        else:
+            # cte might be a Header, so for now stringify it.
+            cte = str(cte).strip().lower()
         # payload may be bytes here.
         if not decode:
             if isinstance(payload, str) and utils._has_surrogates(payload):

Lib/test/test_email/test_email.py

@@ -810,6 +810,16 @@ def test_unicode_body_defaults_to_utf8_encoding(self):
             w4kgdGVzdGFiYwo=
             """))
 
+    def test_string_payload_with_base64_cte(self):
+        msg = email.message_from_string(textwrap.dedent("""\
+        Content-Transfer-Encoding: base64
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg['content-transfer-encoding'].defects, [])
+
+
 
 # Test the email.encoders module
 class TestEncoders(unittest.TestCase):
@@ -2352,6 +2362,40 @@ def test_missing_header_body_separator(self):
         self.assertDefectsEqual(msg.defects,
                                 [errors.MissingHeaderBodySeparatorDefect])
 
+    def test_string_payload_with_extra_space_after_cte(self):
+        # https://github.com/python/cpython/issues/98188
+        cte = "base64 "
+        msg = email.message_from_string(textwrap.dedent(f"""\
+        Content-Transfer-Encoding: {cte}
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg['content-transfer-encoding'].defects, [])
+
+    def test_string_payload_with_extra_text_after_cte(self):
+        msg = email.message_from_string(textwrap.dedent("""\
+        Content-Transfer-Encoding: base64 some text
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.default)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        cte = msg['content-transfer-encoding']
+        self.assertDefectsEqual(cte.defects, [email.errors.InvalidHeaderDefect])
+
+    def test_string_payload_with_extra_space_after_cte_compat32(self):
+        cte = "base64 "
+        msg = email.message_from_string(textwrap.dedent(f"""\
+        Content-Transfer-Encoding: {cte}
+
+        SGVsbG8uIFRlc3Rpbmc=
+        """), policy=email.policy.compat32)
+        pasted_cte = msg['content-transfer-encoding']
+        self.assertEqual(pasted_cte, cte)
+        self.assertEqual(msg.get_payload(decode=True), b"Hello. Testing")
+        self.assertDefectsEqual(msg.defects, [])
+
+
 
 # Test RFC 2047 header encoding and decoding
 class TestRFC2047(TestEmailBase):

Lib/test/test_email/test_headerregistry.py

@@ -837,6 +837,11 @@ def cte_as_value(self,
             '7bit',
             [errors.InvalidHeaderDefect]),
 
+        'extra_space_after_cte': (
+            'base64 ',
+            'base64',
+            []),
+
     }
 
 

Misc/ACKS

@@ -1129,6 +1129,7 @@ Gregor Lingl
 Everett Lipman
 Mirko Liss
 Alexander Liu
+Hui Liu
 Yuan Liu
 Nick Lockwood
 Stephanie Lockwood

Misc/NEWS.d/next/Core_and_Builtins/2024-12-24-01-40-12.gh-issue-128137.gsTwr_.rst

@@ -0,0 +1,2 @@
+Update :c:type:`PyASCIIObject` layout to handle interned field with the
+atomic operation. Patch by Donghee Na.

Misc/NEWS.d/next/Library/2024-12-03-14-45-16.gh-issue-98188.GX9i2b.rst

@@ -0,0 +1,3 @@
+Fix an issue in :meth:`email.message.Message.get_payload` where data
+cannot be decoded if the Content Transfer Encoding mechanism contains
+trailing whitespaces or additional junk text. Patch by Hui Liu.