python: Ensure that we pass utf-8 encoded string to libnotmuch

If we use unicode objects, libnotmuch would not cope with null bytes in
the byte array, so we need to make sure they are nicely formatted as
utf-8.

Introduce a helper function _str which does this throughout the code.

Patch slightly modified by Sebastian Spaeth.

Signed-off-by: Sebastian Spaeth <Sebastian@SSpaeth.de>

bindings/python/notmuch/database.py

@@ -19,12 +19,11 @@ Copyright 2010 Sebastian Spaeth <Sebastian@SSpaeth.de>'
 
 import os
 from ctypes import c_int, c_char_p, c_void_p, c_uint, c_long, byref
-from notmuch.globals import nmlib, STATUS, NotmuchError, Enum
+from notmuch.globals import nmlib, STATUS, NotmuchError, Enum, _str
 from notmuch.thread import Threads
 from notmuch.message import Messages, Message
 from notmuch.tag import Tags
 
-
 class Database(object):
     """Represents a notmuch database (wraps notmuch_database_t)
 
@@ -101,7 +100,6 @@ class Database(object):
                 Database._std_db_path = self._get_user_default_db()
             path = Database._std_db_path
 
-        assert isinstance(path, basestring), 'Path must be a string or None.'
         if create == False:
             self.open(path, mode)
         else:
@@ -132,7 +130,7 @@ class Database(object):
             raise NotmuchError(message="Cannot create db, this Database() "
                                        "already has an open one.")
 
-        res = Database._create(path, Database.MODE.READ_WRITE)
+        res = Database._create(_str(path), Database.MODE.READ_WRITE)
 
         if res is None:
             raise NotmuchError(
@@ -152,9 +150,7 @@ class Database(object):
         :exception: Raises :exc:`NotmuchError` in case
                     of any failure (after printing an error message on stderr).
         """
-        if isinstance(path, unicode):
+        res = Database._open(_str(path), mode)
-            path = path.encode('utf-8') 
-        res = Database._open(path, mode)
 
         if res is None:
             raise NotmuchError(
@@ -259,12 +255,10 @@ class Database(object):
             #we got a relative path, make it absolute
             abs_dirpath = os.path.abspath(os.path.join(self.get_path(), path))
 
-        if isinstance(path, unicode):
+        dir_p = Database._get_directory(self._db, _str(path))
-            path = path.encode('UTF-8')
-        dir_p = Database._get_directory(self._db, path)
 
         # return the Directory, init it with the absolute path
-        return Directory(abs_dirpath, dir_p, self)
+        return Directory(_str(abs_dirpath), dir_p, self)
 
     def add_message(self, filename, sync_maildir_flags=False):
         """Adds a new message to the database
@@ -321,7 +315,7 @@ class Database(object):
 
         msg_p = c_void_p()
         status = nmlib.notmuch_database_add_message(self._db,
-                                                  filename,
+                                                  _str(filename),
                                                   byref(msg_p))
 
         if not status in [STATUS.SUCCESS, STATUS.DUPLICATE_MESSAGE_ID]:
@@ -390,10 +384,8 @@ class Database(object):
         # Raise a NotmuchError if not initialized
         self._verify_initialized_db()
 
-        msg_p = Database._find_message(self._db, msgid)
+        msg_p = Database._find_message(self._db, _str(msgid))
-        if msg_p is None:
+        return msg_p and Message(msg_p, self) or None
-            return None
-        return Message(msg_p, self)
 
     def get_all_tags(self):
         """Returns :class:`Tags` with a list of all tags found in the database
@@ -535,11 +527,8 @@ class Query(object):
             raise NotmuchError(STATUS.NOT_INITIALIZED)
         # create reference to parent db to keep it alive
         self._db = db
-        if isinstance(querystr, unicode):
-            # xapian takes utf-8 encoded byte arrays
-            querystr = querystr.encode('utf-8')
         # create query, return None if too little mem available
-        query_p = Query._create(db.db_p, querystr)
+        query_p = Query._create(db.db_p, _str(querystr))
         if query_p is None:
             NotmuchError(STATUS.NULL_POINTER)
         self._query = query_p

bindings/python/notmuch/globals.py

@@ -98,3 +98,15 @@ class NotmuchError(Exception):
             return self.args[0]
         else:
             return STATUS.status2str(self.args[1])
+
+def _str(value):
+    """Ensure a nicely utf-8 encoded string to pass to libnotmuch
+
+    C++ code expects strings to be well formatted and
+    unicode strings to have no null bytes."""
+    if not isinstance(value, basestring):
+        raise TypeError("Expected str or unicode, got %s" % str(type(value)))
+    if isinstance(value, unicode):
+        return value.encode('UTF-8')
+    return value
+

bindings/python/notmuch/message.py

@@ -21,7 +21,7 @@ Copyright 2010 Sebastian Spaeth <Sebastian@SSpaeth.de>'
 
 from ctypes import c_char_p, c_void_p, c_long, c_uint, c_int
 from datetime import date
-from notmuch.globals import nmlib, STATUS, NotmuchError, Enum
+from notmuch.globals import nmlib, STATUS, NotmuchError, Enum, _str
 from notmuch.tag import Tags
 from notmuch.filename import Filenames
 import sys
@@ -505,7 +505,7 @@ class Message(object):
         if self._msg is None:
             raise NotmuchError(STATUS.NOT_INITIALIZED)
 
-        status = nmlib.notmuch_message_add_tag(self._msg, tag)
+        status = nmlib.notmuch_message_add_tag(self._msg, _str(tag))
 
         # bail out on failure
         if status != STATUS.SUCCESS:
@@ -549,7 +549,7 @@ class Message(object):
         if self._msg is None:
             raise NotmuchError(STATUS.NOT_INITIALIZED)
 
-        status = nmlib.notmuch_message_remove_tag(self._msg, tag)
+        status = nmlib.notmuch_message_remove_tag(self._msg, _str(tag))
         # bail out on error
         if status != STATUS.SUCCESS:
             raise NotmuchError(status)