[parser] Handle patches with no content charset defined

If we don't have an incoming charset defined, assume utf-8.

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>

2 files changed, 19 insertions, 2 deletions

diff --git a/apps/patchwork/bin/parsemail.py b/apps/patchwork/bin/parsemail.py
index 9aaaa9d..772728e 100755
--- a/apps/patchwork/bin/parsemail.py
+++ b/apps/patchwork/bin/parsemail.py
@@ -138,10 +138,16 @@ def find_content(project, mail):
             continue
 
         payload = part.get_payload(decode=True)
-        if not isinstance(payload, unicode):
-            payload = unicode(payload, part.get_content_charset())
+        charset = part.get_content_charset()
         subtype = part.get_content_subtype()
 
+        # if we don't have a charset, assume utf-8
+        if charset is None:
+            charset = 'utf-8'
+
+        if not isinstance(payload, unicode):
+            payload = unicode(payload, charset)
+
         if subtype in ['x-patch', 'x-diff']:
             patchbuf = payload
 
diff --git a/apps/patchwork/tests/patchparser.py b/apps/patchwork/tests/patchparser.py
index e508dc0..3518432 100644
--- a/apps/patchwork/tests/patchparser.py
+++ b/apps/patchwork/tests/patchparser.py
@@ -83,6 +83,17 @@ class UTF8InlinePatchTest(InlinePatchTest):
                              content_encoding = self.patch_encoding)
         (self.patch, self.comment) = find_content(self.project, email)
 
+class NoCharsetInlinePatchTest(InlinePatchTest):
+    """ Test mails with no content-type or content-encoding header """
+    patch_filename = '0001-add-line.patch'
+
+    def setUp(self):
+        self.orig_patch = read_patch(self.patch_filename)
+        email = create_email(self.test_comment + '\n' + self.orig_patch)
+        del email['Content-Type']
+        del email['Content-Transfer-Encoding']
+        (self.patch, self.comment) = find_content(self.project, email)
+
 class SignatureCommentTest(InlinePatchTest):
     patch_filename = '0001-add-line.patch'
     test_comment = 'Test comment\nmore comment'