Merge #14291: if a header has non-ascii unicode, default to CTE using utf-8

bitdancer · bitdancer · commit e2922835b0d4 · 2012-03-14T03:03:27.000-04:00
In Python2, if a unicode string was assigned as the value of a header,
email would automatically CTE encode it using the UTF8 charset.
This capability was lost in the Python3 translation, and this patch
restores it.

Patch by Ali Ikinci, assisted by R. David Murray.

I also added a fix for the mailbox test that was depending (with a comment
that it was a bad idea to so depend) on non-ASCII causing message_from_string
to raise an error.  It now uses support.patch to induce an error during
message serialization.
diff --git a/Lib/email/header.py b/Lib/email/header.py
@@ -283,7 +283,12 @@ def append(self, s, charset=None, errors='strict'):
         # character set, otherwise an early error is thrown.
         output_charset = charset.output_codec or 'us-ascii'
         if output_charset != _charset.UNKNOWN8BIT:
-            s.encode(output_charset, errors)
+            try:
+                s.encode(output_charset, errors)
+            except UnicodeEncodeError:
+                if output_charset!='us-ascii':
+                    raise
+                charset = UTF8
         self._chunks.append((s, charset))
 
     def encode(self, splitchars=';, \t', maxlinelen=None, linesep='\n'):
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
@@ -604,6 +604,19 @@ def test_embeded_header_via_string_rejected(self):
         msg['Dummy'] = 'dummy\nX-Injected-Header: test'
         self.assertRaises(errors.HeaderParseError, msg.as_string)
 
+    def test_unicode_header_defaults_to_utf8_encoding(self):
+        # Issue 14291
+        m = MIMEText('abc\n')
+        m['Subject'] = 'É test'
+        self.assertEqual(str(m),textwrap.dedent("""\
+            Content-Type: text/plain; charset="us-ascii"
+            MIME-Version: 1.0
+            Content-Transfer-Encoding: 7bit
+            Subject: =?utf-8?q?=C3=89_test?=
+
+            abc
+            """))
+
 # Test the email.encoders module
 class TestEncoders(unittest.TestCase):
 
@@ -1045,9 +1058,13 @@ def test_long_8bit_header_no_charset(self):
                          'f\xfcr Offshore-Windkraftprojekte '
                          '<a-very-long-address@example.com>')
         msg['Reply-To'] = header_string
-        self.assertRaises(UnicodeEncodeError, msg.as_string)
+        eq(msg.as_string(maxheaderlen=78), """\
+Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?=
+ =?utf-8?q?hore-Windkraftprojekte_=3Ca-very-long-address=40example=2Ecom=3E?=
+
+""")
         msg = Message()
-        msg['Reply-To'] = Header(header_string, 'utf-8',
+        msg['Reply-To'] = Header(header_string,
                                  header_name='Reply-To')
         eq(msg.as_string(maxheaderlen=78), """\
 Reply-To: =?utf-8?q?Britische_Regierung_gibt_gr=C3=BCnes_Licht_f=C3=BCr_Offs?=
diff --git a/Lib/test/test_mailbox.py b/Lib/test/test_mailbox.py
@@ -111,10 +111,10 @@ def test_add_nonascii_string_header_raises(self):
         self.assertMailboxEmpty()
 
     def test_add_that_raises_leaves_mailbox_empty(self):
-        # XXX This test will start failing when Message learns to handle
-        # non-ASCII string headers, and a different internal failure will
-        # need to be found or manufactured.
-        with self.assertRaises(ValueError):
+        def raiser(*args, **kw):
+            raise Exception("a fake error")
+        support.patch(self, email.generator.BytesGenerator, 'flatten', raiser)
+        with self.assertRaises(Exception):
             self._box.add(email.message_from_string("From: Alphöso"))
         self.assertEqual(len(self._box), 0)
         self._box.close()
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -470,6 +470,7 @@ Gerhard Häring
 Fredrik Håård
 Catalin Iacob
 Mihai Ibanescu
+Ali Ikinci
 Lars Immisch
 Bobby Impollonia
 Meador Inge
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -24,6 +24,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #14291: Email now defaults to utf-8 for non-ASCII unicode headers
+  instead of raising an error.  This fixes a regression relative to 2.7.
+
 - Issue #989712: Support using Tk without a mainloop.
 
 - Issue #5219: Prevent event handler cascade in IDLE.
