launchpad-reviewers team mailing list archive

[Colin Watson <cjwatson@xxxxxxxxxxxxx>]

Colin Watson has proposed merging ~cjwatson/launchpad:py3-escape-nonascii-uniquely into launchpad:master.

Commit message:
Make escape_nonascii_uniquely require bytes

Requested reviews:
  Launchpad code reviewers (launchpad-reviewers)

For more details, see:
https://code.launchpad.net/~cjwatson/launchpad/+git/launchpad/+merge/398918

This is only used by MailingListAPIView.holdMessage, which operates on bytes.
-- 
Your team Launchpad code reviewers is requested to review the proposed merge of ~cjwatson/launchpad:py3-escape-nonascii-uniquely into launchpad:master.

diff --git a/lib/lp/registry/xmlrpc/mailinglist.py b/lib/lp/registry/xmlrpc/mailinglist.py
index 6467dd5..d22dfc2 100644
--- a/lib/lp/registry/xmlrpc/mailinglist.py
+++ b/lib/lp/registry/xmlrpc/mailinglist.py
@@ -239,8 +239,8 @@ class MailingListAPIView(LaunchpadXMLRPCView):
 
     def holdMessage(self, team_name, bytes):
         """See `IMailingListAPIView`."""
-        # For testing purposes, accept both strings and Binary instances.  In
-        # production, bytes will always be a Binary so that unencoded
+        # For testing purposes, accept both byte strings and Binary instances.
+        # In production, bytes will always be a Binary so that unencoded
         # non-ascii characters in the message can be safely passed across
         # XMLRPC. For most tests though it's much more convenient to just
         # pass 8-bit strings.
@@ -250,7 +250,7 @@ class MailingListAPIView(LaunchpadXMLRPCView):
         # Although it is illegal for an email header to have unencoded
         # non-ascii characters, it is better to let the list owner
         # process the message than to cause an oops.
-        header_body_separator = re.compile('\r\n\r\n|\r\r|\n\n')
+        header_body_separator = re.compile(br'\r\n\r\n|\r\r|\n\n')
         match = header_body_separator.search(bytes)
         header = bytes[:match.start()]
         header = escape_nonascii_uniquely(header)
diff --git a/lib/lp/services/encoding.py b/lib/lp/services/encoding.py
index 29a0d3f..3c1728b 100644
--- a/lib/lp/services/encoding.py
+++ b/lib/lp/services/encoding.py
@@ -171,25 +171,27 @@ def escape_nonascii_uniquely(bogus_string):
     all the nonascii characters have been replaced with the same ascii
     character.
 
-    >>> print(len('\xa9'), len('\\xa9'))
+    >>> print(len(b'\xa9'), len(b'\\xa9'))
     1 4
-    >>> print(escape_nonascii_uniquely('hello \xa9'))
+    >>> print(six.ensure_str(escape_nonascii_uniquely(b'hello \xa9')))
     hello \xa9
 
     This string only has ascii characters, so escape_nonascii_uniquely()
     actually has no effect.
 
-    >>> print(escape_nonascii_uniquely('hello \\xa9'))
+    >>> print(six.ensure_str(escape_nonascii_uniquely(b'hello \\xa9')))
     hello \xa9
+
+    :type bogus_string: bytes
     """
-    nonascii_regex = re.compile(r'[\200-\377]')
+    nonascii_regex = re.compile(br'[\200-\377]')
 
     # By encoding the invalid ascii with a backslash, x, and then the
     # hex value, it makes it easy to decode it by pasting into a python
     # interpreter. quopri() is not used, since that could caused the
     # decoding of an email to fail.
     def quote(match):
-        return '\\x%x' % ord(match.group(0))
+        return b'\\x%x' % ord(match.group(0))
 
     return nonascii_regex.sub(quote, bogus_string)