gh-124452: Fix header mismatches when folding/unfolding with email message

Lib/email/_policybase.py

@@ -302,12 +302,12 @@ def header_source_parse(self, sourcelines):
         """+
         The name is parsed as everything up to the ':' and returned unmodified.
         The value is determined by stripping leading whitespace off the
-        remainder of the first line, joining all subsequent lines together, and
+        remainder of the first line joined with all subsequent lines, and
         stripping any trailing carriage return or linefeed characters.
 
         """
         name, value = sourcelines[0].split(':', 1)
-        value = value.lstrip(' \t') + ''.join(sourcelines[1:])
+        value = ''.join((value, *sourcelines[1:])).lstrip(' \t\r\n')
         return (name, value.rstrip('\r\n'))
 
     def header_store_parse(self, name, value):

Lib/email/policy.py

@@ -119,13 +119,13 @@ def header_source_parse(self, sourcelines):
         """+
         The name is parsed as everything up to the ':' and returned unmodified.
         The value is determined by stripping leading whitespace off the
-        remainder of the first line, joining all subsequent lines together, and
+        remainder of the first line joined with all subsequent lines, and
         stripping any trailing carriage return or linefeed characters.  (This
         is the same as Compat32).
 
         """
         name, value = sourcelines[0].split(':', 1)
-        value = value.lstrip(' \t') + ''.join(sourcelines[1:])
+        value = ''.join((value, *sourcelines[1:])).lstrip(' \t\r\n')
         return (name, value.rstrip('\r\n'))
 
     def header_store_parse(self, name, value):

Lib/test/test_email/test_message.py

@@ -1,6 +1,6 @@
-import unittest
 import textwrap
-from email import policy, message_from_string
+import unittest
+from email import message_from_bytes, message_from_string, policy
 from email.message import EmailMessage, MIMEPart
 from test.test_email import TestEmailBase, parameterize
 
@@ -958,6 +958,52 @@ def test_folding_with_utf8_encoding_8(self):
                          b'123456789-123456789\n 123456789 Hello '
                          b'=?utf-8?q?W=C3=B6rld!?= 123456789 123456789\n\n')
 
+    def test_folding_with_short_nospace_1(self):
+        # bpo-36520
+        #
+        # Fold a line that contains a long whitespace after
+        # the fold point.
+
+        m = EmailMessage(policy.default)
+        m['Message-ID'] = '123456789' * 3
+        parsed_msg = message_from_bytes(m.as_bytes(), policy=policy.default)
+        self.assertEqual(parsed_msg['Message-ID'], m['Message-ID'])
+
+    def test_folding_with_long_nospace_default_policy_1(self):
+        # Fixed: https://github.com/python/cpython/issues/124452
+        #
+        # When the value is too long, it should be converted back
+        # to its original form without any modifications.
+
+        m = EmailMessage(policy.default)
+        message = '123456789' * 10
+        m['Message-ID'] = message
+        self.assertEqual(m.as_bytes(),
+                         f'Message-ID:\n {message}\n\n'.encode())
+        parsed_msg = message_from_bytes(m.as_bytes(), policy=policy.default)
+        self.assertEqual(parsed_msg['Message-ID'], m['Message-ID'])
+
+    def test_folding_with_long_nospace_compat32_policy_1(self):
+        m = EmailMessage(policy.compat32)
+        message = '123456789' * 10
+        m['Message-ID'] = message
+        parsed_msg = message_from_bytes(m.as_bytes(), policy=policy.default)
+        self.assertEqual(parsed_msg['Message-ID'], m['Message-ID'])
+
+    def test_folding_with_long_nospace_smtp_policy_1(self):
+        m = EmailMessage(policy.SMTP)
+        message = '123456789' * 10
+        m['Message-ID'] = message
+        parsed_msg = message_from_bytes(m.as_bytes(), policy=policy.default)
+        self.assertEqual(parsed_msg['Message-ID'], m['Message-ID'])
+
+    def test_folding_with_long_nospace_http_policy_1(self):
+        m = EmailMessage(policy.HTTP)
+        message = '123456789' * 10
+        m['Message-ID'] = message
+        parsed_msg = message_from_bytes(m.as_bytes(), policy=policy.default)
+        self.assertEqual(parsed_msg['Message-ID'], m['Message-ID'])
+
     def test_get_body_malformed(self):
         """test for bpo-42892"""
         msg = textwrap.dedent("""\

Misc/NEWS.d/next/Library/2024-10-24-10-49-47.gh-issue-124452.eqTRgx.rst

@@ -0,0 +1,4 @@
+Fix an issue in :meth:`email.policy.EmailPolicy.header_source_parse` and
+:meth:`email.policy.Compat32.header_source_parse` that introduced spurious
+leading whitespaces into header values when the header includes a newline
+character after the header name delimiter (``:``) and before the value.