Decode headers into utf-8 from QP

Since we aren't planning on sending any of this as actual emails,
convert EVERYTHING into utf-8 before writing messages, including
QP-escaped 7-bit headers.

Signed-off-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>

1 files changed, 12 insertions, 1 deletions

diff --git a/b4/__init__.py b/b4/__init__.py
index 41f8dbc..acb3125 100644
--- a/b4/__init__.py
+++ b/b4/__init__.py
@@ -693,7 +693,18 @@ class LoreMessage:
 
     @staticmethod
     def clean_header(hdrval):
-        new_hdrval = re.sub(r'\n?\s+', ' ', str(hdrval))
+        decoded = ''
+        for hstr, hcs in email.header.decode_header(hdrval):
+            if hcs is None:
+                hcs = 'utf-8'
+            try:
+                decoded += hstr.decode(hcs)
+            except LookupError:
+                # Try as utf-u
+                decoded += hstr.decode('utf-8', errors='replace')
+            except (UnicodeDecodeError, AttributeError):
+                decoded += hstr
+        new_hdrval = re.sub(r'\n?\s+', ' ', decoded)
         return new_hdrval.strip()
 
     @staticmethod