Update Python 3 to 3.13.12

commit_hash:71d3efea437a769b2b7910d196120bb02587046e

5 files changed, 78 insertions, 7 deletions

diff --git a/contrib/tools/python3/Lib/email/_encoded_words.py b/contrib/tools/python3/Lib/email/_encoded_words.py
index 6795a606de0..05a34a4c105 100644
--- a/contrib/tools/python3/Lib/email/_encoded_words.py
+++ b/contrib/tools/python3/Lib/email/_encoded_words.py
@@ -219,7 +219,7 @@ def encode(string, charset='utf-8', encoding=None, lang=''):
 
     """
     if charset == 'unknown-8bit':
-        bstring = string.encode('ascii', 'surrogateescape')
+        bstring = string.encode('utf-8', 'surrogateescape')
     else:
         bstring = string.encode(charset)
     if encoding is None:
diff --git a/contrib/tools/python3/Lib/email/_header_value_parser.py b/contrib/tools/python3/Lib/email/_header_value_parser.py
index 91243378dc0..51727688c05 100644
--- a/contrib/tools/python3/Lib/email/_header_value_parser.py
+++ b/contrib/tools/python3/Lib/email/_header_value_parser.py
@@ -101,6 +101,12 @@ def make_quoted_pairs(value):
     return str(value).replace('\\', '\\\\').replace('"', '\\"')
 
 
+def make_parenthesis_pairs(value):
+    """Escape parenthesis and backslash for use within a comment."""
+    return str(value).replace('\\', '\\\\') \
+        .replace('(', '\\(').replace(')', '\\)')
+
+
 def quote_string(value):
     escaped = make_quoted_pairs(value)
     return f'"{escaped}"'
@@ -874,6 +880,12 @@ class MessageID(MsgID):
 class InvalidMessageID(MessageID):
     token_type = 'invalid-message-id'
 
+class MessageIDList(TokenList):
+    token_type = 'message-id-list'
+
+    @property
+    def message_ids(self):
+        return [x for x in self if x.token_type=='msg-id']
 
 class Header(TokenList):
     token_type = 'header'
@@ -933,7 +945,7 @@ class WhiteSpaceTerminal(Terminal):
         return ' '
 
     def startswith_fws(self):
-        return True
+        return self and self[0] in WSP
 
 
 class ValueTerminal(Terminal):
@@ -2171,6 +2183,32 @@ def parse_message_id(value):
 
     return message_id
 
+def parse_message_ids(value):
+    """in-reply-to     =   "In-Reply-To:" 1*msg-id CRLF
+       references      =   "References:" 1*msg-id CRLF
+    """
+    message_id_list = MessageIDList()
+    while value:
+        if value[0] == ',':
+            # message id list separated with commas - this is invalid,
+            # but happens rather frequently in the wild
+            message_id_list.defects.append(
+                errors.InvalidHeaderDefect("comma in msg-id list"))
+            message_id_list.append(
+                WhiteSpaceTerminal(' ', 'invalid-comma-replacement'))
+            value = value[1:]
+            continue
+        try:
+            token, value = get_msg_id(value)
+            message_id_list.append(token)
+        except errors.HeaderParseError as ex:
+            token = get_unstructured(value)
+            message_id_list.append(InvalidMessageID(token))
+            message_id_list.defects.append(
+                errors.InvalidHeaderDefect("Invalid msg-id: {!r}".format(ex)))
+            break
+    return message_id_list
+
 #
 # XXX: As I begin to add additional header parsers, I'm realizing we probably
 # have two level of parser routines: the get_XXX methods that get a token in
@@ -2788,6 +2826,9 @@ def _steal_trailing_WSP_if_exists(lines):
     if lines and lines[-1] and lines[-1][-1] in WSP:
         wsp = lines[-1][-1]
         lines[-1] = lines[-1][:-1]
+        # gh-142006: if the line is now empty, remove it entirely.
+        if not lines[-1]:
+            lines.pop()
     return wsp
 
 def _refold_parse_tree(parse_tree, *, policy):
@@ -2924,6 +2965,13 @@ def _refold_parse_tree(parse_tree, *, policy):
                     [ValueTerminal(make_quoted_pairs(p), 'ptext')
                      for p in newparts] +
                     [ValueTerminal('"', 'ptext')])
+            if part.token_type == 'comment':
+                newparts = (
+                    [ValueTerminal('(', 'ptext')] +
+                    [ValueTerminal(make_parenthesis_pairs(p), 'ptext')
+                     if p.token_type == 'ptext' else p
+                     for p in newparts] +
+                    [ValueTerminal(')', 'ptext')])
             if not part.as_ew_allowed:
                 wrap_as_ew_blocked += 1
                 newparts.append(end_ew_not_allowed)
diff --git a/contrib/tools/python3/Lib/email/feedparser.py b/contrib/tools/python3/Lib/email/feedparser.py
index bc773f38030..8e60f1d1181 100644
--- a/contrib/tools/python3/Lib/email/feedparser.py
+++ b/contrib/tools/python3/Lib/email/feedparser.py
@@ -504,10 +504,9 @@ class FeedParser:
                     self._input.unreadline(line)
                     return
                 else:
-                    # Weirdly placed unix-from line.  Note this as a defect
-                    # and ignore it.
+                    # Weirdly placed unix-from line.
                     defect = errors.MisplacedEnvelopeHeaderDefect(line)
-                    self._cur.defects.append(defect)
+                    self.policy.handle_defect(self._cur, defect)
                     continue
             # Split the line on the colon separating field name from value.
             # There will always be a colon, because if there wasn't the part of
@@ -519,7 +518,7 @@ class FeedParser:
             # message. Track the error but keep going.
             if i == 0:
                 defect = errors.InvalidHeaderDefect("Missing header name.")
-                self._cur.defects.append(defect)
+                self.policy.handle_defect(self._cur, defect)
                 continue
 
             assert i>0, "_parse_headers fed line with no : and no leading WS"
diff --git a/contrib/tools/python3/Lib/email/generator.py b/contrib/tools/python3/Lib/email/generator.py
index ce94f5c56fe..a03eb1fbbc9 100644
--- a/contrib/tools/python3/Lib/email/generator.py
+++ b/contrib/tools/python3/Lib/email/generator.py
@@ -22,6 +22,7 @@ NL = '\n'  # XXX: no longer used by the code below.
 NLCRE = re.compile(r'\r\n|\r|\n')
 fcre = re.compile(r'^From ', re.MULTILINE)
 NEWLINE_WITHOUT_FWSP = re.compile(r'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
+NEWLINE_WITHOUT_FWSP_BYTES = re.compile(br'\r\n[^ \t]|\r[^ \n\t]|\n[^ \t]')
 
 
 class Generator:
@@ -429,7 +430,16 @@ class BytesGenerator(Generator):
         # This is almost the same as the string version, except for handling
         # strings with 8bit bytes.
         for h, v in msg.raw_items():
-            self._fp.write(self.policy.fold_binary(h, v))
+            folded = self.policy.fold_binary(h, v)
+            if self.policy.verify_generated_headers:
+                linesep = self.policy.linesep.encode()
+                if not folded.endswith(linesep):
+                    raise HeaderWriteError(
+                        f'folded header does not end with {linesep!r}: {folded!r}')
+                if NEWLINE_WITHOUT_FWSP_BYTES.search(folded.removesuffix(linesep)):
+                    raise HeaderWriteError(
+                        f'folded header contains newline: {folded!r}')
+            self._fp.write(folded)
         # A blank line always separates headers from body
         self.write(self._NL)
 
diff --git a/contrib/tools/python3/Lib/email/headerregistry.py b/contrib/tools/python3/Lib/email/headerregistry.py
index 543141dc427..0e8698efc0b 100644
--- a/contrib/tools/python3/Lib/email/headerregistry.py
+++ b/contrib/tools/python3/Lib/email/headerregistry.py
@@ -534,6 +534,18 @@ class MessageIDHeader:
         kwds['defects'].extend(parse_tree.all_defects)
 
 
+class ReferencesHeader:
+
+    max_count = 1
+    value_parser = staticmethod(parser.parse_message_ids)
+
+    @classmethod
+    def parse(cls, value, kwds):
+        kwds['parse_tree'] = parse_tree = cls.value_parser(value)
+        kwds['decoded'] = str(parse_tree)
+        kwds['defects'].extend(parse_tree.all_defects)
+
+
 # The header factory #
 
 _default_header_map = {
@@ -557,6 +569,8 @@ _default_header_map = {
     'content-disposition':          ContentDispositionHeader,
     'content-transfer-encoding':    ContentTransferEncodingHeader,
     'message-id':                   MessageIDHeader,
+    'in-reply-to':                  ReferencesHeader,
+    'references':                   ReferencesHeader,
     }
 
 class HeaderRegistry: