Fix for email.generator.Generator with whitespace between encoded words.

email.generator.Generator currently does not handle whitespace between
encoded words correctly when the encoded words span multiple lines.  The
current generator will create an encoded word for each line.  If the end
of the line happens to correspond with the end real word in the
plaintext, the generator will place an unencoded space at the start of
the subsequent lines to represent the whitespace between the plaintext
words.

A compliant decoder will strip all the whitespace from between two
encoded words which leads to missing spaces in the round-tripped
output.

The fix for this is to make sure that whitespace between two encoded
words ends up inside of one or the other of the encoded words.  This
fix places the space inside of the second encoded word.

Test case from #92081

Author: abadger

Lib/email/_header_value_parser.py

@@ -2766,10 +2766,11 @@ def _refold_parse_tree(parse_tree, *, policy):
     # max_line_length 0/None means no limit, ie: infinitely long.
     maxlen = policy.max_line_length or sys.maxsize
     encoding = 'utf-8' if policy.utf8 else 'us-ascii'
-    lines = ['']
-    last_ew = None
+    lines = ['']  # Folded lines to be output
+    last_ew = None  # Points to the last encoded character if there's an ew on
+                    # the line
     wrap_as_ew_blocked = 0
-    want_encoding = False
+    want_encoding = False  # True if we need to encode this part
     end_ew_not_allowed = Terminal('', 'wrap_as_ew_blocked')
     parts = list(parse_tree)
     while parts:
@@ -2793,10 +2794,12 @@ def _refold_parse_tree(parse_tree, *, policy):
                 # 'charset' property on the policy.
                 charset = 'utf-8'
             want_encoding = True
+
         if part.token_type == 'mime-parameters':
             # Mime parameter folding (using RFC2231) is extra special.
             _fold_mime_parameters(part, lines, maxlen, encoding)
             continue
+
         if want_encoding and not wrap_as_ew_blocked:
             if not part.as_ew_allowed:
                 want_encoding = False
@@ -2826,6 +2829,7 @@ def _refold_parse_tree(parse_tree, *, policy):
                                       part.ew_combine_allowed, charset)
             want_encoding = False
             continue
+
         if len(tstr) <= maxlen - len(lines[-1]):
             lines[-1] += tstr
             continue
@@ -2860,6 +2864,7 @@ def _refold_parse_tree(parse_tree, *, policy):
         else:
             # We can't fold it onto the next line either...
             lines[-1] += tstr
+
     return policy.linesep.join(lines) + policy.linesep
 
 def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset):
@@ -2877,14 +2882,15 @@ def _fold_as_ew(to_encode, lines, maxlen, last_ew, ew_combine_allowed, charset):
         to_encode = str(
             get_unstructured(lines[-1][last_ew:] + to_encode))
         lines[-1] = lines[-1][:last_ew]
-    if to_encode[0] in WSP:
+    elif to_encode[0] in WSP:
         # We're joining this to non-encoded text, so don't encode
         # the leading blank.
         leading_wsp = to_encode[0]
         to_encode = to_encode[1:]
         if (len(lines[-1]) == maxlen):
             lines.append(_steal_trailing_WSP_if_exists(lines))
         lines[-1] += leading_wsp
+
     trailing_wsp = ''
     if to_encode[-1] in WSP:
         # Likewise for the trailing space.

Lib/test/test_email/test_generator.py

@@ -232,6 +232,19 @@ class TestBytesGenerator(TestGeneratorBase, TestEmailBase):
     ioclass = io.BytesIO
     typ = lambda self, x: x.encode('ascii')
 
+    def test_defaults_handle_spaces_between_encoded_words_when_wrapped(self):
+        source = ("Уведомление о принятии в работу обращения для"
+                  " подключения услуги")
+        expected = ('Subject: =?utf-8?b?0KPQstC10LTQvtC80LvQtdC90LjQtSDQviDQv9GA0LjQvdGP0YLQuNC4?=\n'
+                    ' =?utf-8?b?INCyINGA0LDQsdC+0YLRgyDQvtCx0YDQsNGJ0LXQvdC40Y8g0LTQu9GPINC/0L4=?=\n'
+                    ' =?utf-8?b?0LTQutC70Y7Rh9C10L3QuNGPINGD0YHQu9GD0LPQuA==?=\n\n').encode('ascii')
+        msg = EmailMessage()
+        msg['Subject'] = source
+        s = io.BytesIO()
+        g = BytesGenerator(s)
+        g.flatten(msg)
+        self.assertEqual(s.getvalue(), expected)
+
     def test_cte_type_7bit_handles_unknown_8bit(self):
         source = ("Subject: Maintenant je vous présente mon "
                  "collègue\n\n").encode('utf-8')