[3.14] gh-148518 fix index error in local part attribute (GH-148522) (#149200)

As part of fixing bpo-27931 code was introduced to get_bare_quoted_string
that added an empty Terminal if the quoted string was empty.  This isn't
the best answer in terms of the parse tree; we really want the token
list to be empty in that case.  But having it be empty resulted in
local_part raising the index error.  We find that same problem if we
try to parse an address consisting of a single dquote.  By fixing
local_part to not raise on an empty token list, we can have the
bare_quoted_string code correctly return an empty token list for
the empty string cases (two dquotes or a single dquote as the
entire addrespec, at the end of a line).
(cherry picked from commit bdbb55c403d2ab6b4b0a3e994d21b623fee4a544)

Co-authored-by: R. David Murray <rdmurray@bitdance.com>

diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
index 35e71e04c49358673e08f0a3beca1857cdbc20e5..1367e34195bfdd923ca2459d9c991997d662ebfa 100644 (file)
--- a/Lib/email/_header_value_parser.py
+++ b/Lib/email/_header_value_parser.py
@@ -639,11 +639,11 @@ class LocalPart(TokenList):
         for tok in self[0] + [DOT]:
             if tok.token_type == 'cfws':
                 continue
-            if (last_is_tl and tok.token_type == 'dot' and
+            if (last_is_tl and tok.token_type == 'dot' and last and
                     last[-1].token_type == 'cfws'):
                 res[-1] = TokenList(last[:-1])
             is_tl = isinstance(tok, TokenList)
-            if (is_tl and last.token_type == 'dot' and
+            if (is_tl and last.token_type == 'dot' and tok and
                     tok[0].token_type == 'cfws'):
                 res.append(TokenList(tok[1:]))
             else:
@@ -1245,8 +1245,7 @@ def get_bare_quoted_string(value):
     bare_quoted_string = BareQuotedString()
     value = value[1:]
     if value and value[0] == '"':
-        token, value = get_qcontent(value)
-        bare_quoted_string.append(token)
+        return bare_quoted_string, value[1:]
     while value and value[0] != '"':
         if value[0] in WSP:
             token, value = get_fws(value)

diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index 52be7bdbb129b97ccb2b57eb31617b8b1a94d987..d0643be2ce0de8016404469c7753561bd4bff47e 100644 (file)
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -1262,12 +1262,12 @@ class TestAddressHeader(TestHeaderBase):
              'example.com',
              None),
 
-        }
-
         # XXX: Need many more examples, and in particular some with names in
         # trailing comments, which aren't currently handled.  comments in
         # general are not handled yet.
 
+        }
+
     def example_as_address(self, source, defects, decoded, display_name,
                            addr_spec, username, domain, comment):
         h = self.make_header('sender', source)
@@ -1285,6 +1285,43 @@ class TestAddressHeader(TestHeaderBase):
         # XXX: we have no comment support yet.
         #self.assertEqual(a.comment, comment)
 
+    example_broken_header_params = {
+
+        'just_dquote':
+            ('"',
+             [errors.InvalidHeaderDefect]*2,
+             '<>',
+             '',
+             '<>',
+             '',
+             '',
+            ),
+
+        }
+
+    def example_broken_header_as_address(
+            self,
+            source,
+            defects,
+            decoded,
+            display_name,
+            addr_spec,
+            username,
+            domain,
+        ):
+        h = self.make_header('sender', source)
+        self.assertEqual(h, decoded)
+        self.assertDefectsEqual(h.defects, defects)
+        a = h.address
+        self.assertEqual(str(a), decoded)
+        self.assertEqual(len(h.groups), 1)
+        self.assertEqual([a], list(h.groups[0].addresses))
+        self.assertEqual([a], list(h.addresses))
+        self.assertEqual(a.display_name, display_name)
+        self.assertEqual(a.addr_spec, addr_spec)
+        self.assertEqual(a.username, username)
+        self.assertEqual(a.domain, domain)
+
     def example_as_group(self, source, defects, decoded, display_name,
                          addr_spec, username, domain, comment):
         source = 'foo: {};'.format(source)

diff --git a/Misc/NEWS.d/next/Library/2026-04-13-15-59-44.gh-issue-148518.RQdvsu.rst b/Misc/NEWS.d/next/Library/2026-04-13-15-59-44.gh-issue-148518.RQdvsu.rst
new file mode 100644 (file)
index 0000000..994e4ad
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2026-04-13-15-59-44.gh-issue-148518.RQdvsu.rst
@@ -0,0 +1,4 @@
+If an email containing an address header that ended in an open double quote
+was parsed with a non-``compat32`` policy, accessing the ``username`` attribute
+of the mailbox accessed through that header object would result in an
+``IndexError``. It now correctly returns an empty string as the result.