Handle RFC 2047 encoded headers

mbox2web

@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 
+import email.header
 import email.parser
 import hashlib
 import html
@@ -32,18 +33,39 @@ def get_message_id(msg):
     match = re.search(r'<(.*?)>', msg["Message-ID"])
     return match.group(1)
 
+
 def encode_message_id(msgid):
     encmsgid = re.sub('[^!"$(-.0-9:=@-z|~]', lambda x: "{%02x}" % (ord(x.group(0))), msgid)
     return encmsgid
 
+
+def decode_rfc2047(s):
+    if s is None:
+        return None
+    r = ""
+    for chunk in email.header.decode_header(s):
+        if chunk[1]:
+            try:
+                r += chunk[0].decode(chunk[1])
+            except LookupError:
+                r += chunk[0].decode("windows-1252")
+            except UnicodeDecodeError:
+                r += chunk[0].decode("windows-1252")
+        elif type(chunk[0]) == bytes:
+            r += chunk[0].decode('us-ascii')
+        else:
+            r += chunk[0]
+    return r
+
+
 def render_message(msg):
     msgtmpl = jenv.get_template("message2.html")
     bodyhtml = render_body(msg)
     context = {
         "msg": msg,
         "message_id": msg["Message-Id"],
-        "subject": msg["Subject"],
-        "from": msg["From"],
+        "subject": decode_rfc2047(msg["Subject"]),
+        "from": decode_rfc2047(msg["From"]),
         "date": msg["Date"],
         "bodyhtml": bodyhtml,
     }
@@ -338,8 +360,8 @@ def archive(msg):
         context = {
             "list": "LUGA",
             "message_id": mid,
-            "subject": msg["Subject"],
-            "from": msg["From"],
+            "subject": decode_rfc2047(msg["Subject"]),
+            "from": decode_rfc2047(msg["From"]),
             "date": msg["Date"],
             "bodyhtml": bodyhtml,
         }