From 25a0aea875fd0d67238beed1237f7239474673ec Mon Sep 17 00:00:00 2001
From: Kali Kaneko <kali@leap.se>
Date: Fri, 27 Dec 2013 02:06:44 -0400
Subject: First stage of the storage schema rewrite.

* Separates between flags, docs, body and attachment docs.

* Implement IMessageCopier interface: move and have fun!
  This little change is known to push forward our beloved architect
  emotional rollercoster.

* Message deduplication.

* It also fixes a hidden bug that was rendering the multipart mime
  interface useless
  (yes, the "True" parameter in the parsestr method).

* Does not handle well nested attachs, includes dirty workaround that
  flattens them.

* Includes chiiph's patch for rc2:

 * return deferred from addMessage
 * convert StringIO types to string
 * remove unneeded yields from the chain of deferreds in fetcher
---
 src/leap/mail/imap/parser.py | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

(limited to 'src/leap/mail/imap/parser.py')

diff --git a/src/leap/mail/imap/parser.py b/src/leap/mail/imap/parser.py
index 1ae19c0..306dcf0 100644
--- a/src/leap/mail/imap/parser.py
+++ b/src/leap/mail/imap/parser.py
@@ -19,10 +19,14 @@ Mail parser mixins.
 """
 import cStringIO
 import StringIO
+import hashlib
 import re
 
+from email.message import Message
 from email.parser import Parser
 
+from leap.common.check import leap_assert_type
+
 
 class MailParser(object):
     """
@@ -34,16 +38,30 @@ class MailParser(object):
         """
         self._parser = Parser()
 
-    def _get_parsed_msg(self, raw):
+    def _get_parsed_msg(self, raw, headersonly=False):
         """
         Return a parsed Message.
 
         :param raw: the raw string to parse
         :type raw: basestring, or StringIO object
+
+        :param headersonly: True for parsing only the headers.
+        :type headersonly: bool
         """
-        msg = self._get_parser_fun(raw)(raw, True)
+        msg = self._get_parser_fun(raw)(raw, headersonly=headersonly)
         return msg
 
+    def _get_hash(self, msg):
+        """
+        Returns a hash of the string representation of the raw message,
+        suitable for indexing the inmutable pieces.
+
+        :param msg: a Message object
+        :type msg: Message
+        """
+        leap_assert_type(msg, Message)
+        return hashlib.sha256(msg.as_string()).hexdigest()
+
     def _get_parser_fun(self, o):
         """
         Retunn the proper parser function for an object.
@@ -67,6 +85,8 @@ class MailParser(object):
         :param o: object
         :type o: object
         """
+        # XXX Maybe we don't need no more, we're using
+        # msg.as_string()
         if isinstance(o, (cStringIO.OutputType, StringIO.StringIO)):
             return o.getvalue()
         else:
-- 
cgit v1.2.3