#9286: Fix the rfc822 parser to preserve whitespace in address local part.

bitdancer · bitdancer · commit 63563cdf9d3a · 2010-12-18T18:25:38.000Z
Such addresses are not RFC compliant except under the 'obsolete syntax'
rules, but before this fix the whitespace was dropped from the input,
concatenating the pieces.  That breaks one of the principles of the
email package, that of preserving the input as much as possible.
It also denies the application program the opportunity to apply its
own heuristics to interpretation of such non-compliant addresses.

It is possible users of the email package were depending on the local
part always being a single token, so this fix will not be backported.
diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py
@@ -199,14 +199,18 @@ def __init__(self, field):
         self.commentlist = []
 
     def gotonext(self):
-        """Parse up to the start of the next address."""
+        """Skip white space and extract comments."""
+        wslist = []
         while self.pos < len(self.field):
             if self.field[self.pos] in self.LWS + '\n\r':
+                if self.field[self.pos] not in '\n\r':
+                    wslist.append(self.field[self.pos])
                 self.pos += 1
             elif self.field[self.pos] == '(':
                 self.commentlist.append(self.getcomment())
             else:
                 break
+        return EMPTYSTRING.join(wslist)
 
     def getaddrlist(self):
         """Parse all addresses.
@@ -319,16 +323,24 @@ def getaddrspec(self):
 
         self.gotonext()
         while self.pos < len(self.field):
+            preserve_ws = True
             if self.field[self.pos] == '.':
+                if aslist and not aslist[-1].strip():
+                    aslist.pop()
                 aslist.append('.')
                 self.pos += 1
+                preserve_ws = False
             elif self.field[self.pos] == '"':
                 aslist.append('"%s"' % quote(self.getquote()))
             elif self.field[self.pos] in self.atomends:
+                if aslist and not aslist[-1].strip():
+                    aslist.pop()
                 break
             else:
                 aslist.append(self.getatom())
-            self.gotonext()
+            ws = self.gotonext()
+            if preserve_ws and ws:
+                aslist.append(ws)
 
         if self.pos >= len(self.field) or self.field[self.pos] != '@':
             return EMPTYSTRING.join(aslist)
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
@@ -2342,6 +2342,24 @@ def test_parseaddr_preserves_quoted_pairs_in_addresses(self):
         eq(utils.parseaddr('"\\\\"example\\\\" example"@example.com'),
           ('', '"\\\\"example\\\\" example"@example.com'))
 
+    def test_parseaddr_preserves_spaces_in_local_part(self):
+        # issue 9286.  A normal RFC5322 local part should not contain any
+        # folding white space, but legacy local parts can (they are a sequence
+        # of atoms, not dotatoms).  On the other hand we strip whitespace from
+        # before the @ and around dots, on the assumption that the whitespace
+        # around the punctuation is a mistake in what would otherwise be
+        # an RFC5322 local part.  Leading whitespace is, usual, stripped as well.
+        self.assertEqual(('', "merwok wok@xample.com"),
+            utils.parseaddr("merwok wok@xample.com"))
+        self.assertEqual(('', "merwok  wok@xample.com"),
+            utils.parseaddr("merwok  wok@xample.com"))
+        self.assertEqual(('', "merwok  wok@xample.com"),
+            utils.parseaddr(" merwok  wok  @xample.com"))
+        self.assertEqual(('', 'merwok"wok"  wok@xample.com'),
+            utils.parseaddr('merwok"wok"  wok@xample.com'))
+        self.assertEqual(('', 'merwok.wok.wok@xample.com'),
+            utils.parseaddr('merwok. wok .  wok@xample.com'))
+
     def test_multiline_from_comment(self):
         x = """\
 Foo
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -23,6 +23,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #9286: email.utils.parseaddr no longer concatenates blank-separated
+  words in the local part of email addresses, thereby preserving the input.
+
 - Issue #6791: Limit header line length (to 65535 bytes) in http.client
   and http.server, to avoid denial of services from the other party.
 
