Merge pull request #4497 from minrk/datetime-session

don't automatically unpack datetime objects in the message spec

only unpack in headers
move handling of datetime objects in content and metadata to application-level code
minor fix to ISO8601 re (closes  #4493)

IPython/kernel/zmq/session.py

@@ -1,846 +1,848
 """Session object for building, serializing, sending, and receiving messages in
 IPython. The Session object supports serialization, HMAC signatures, and
 metadata on messages.
 
 Also defined here are utilities for working with Sessions:
 * A SessionFactory to be used as a base class for configurables that work with
 Sessions.
 * A Message object for convenience that allows attribute-access to the msg dict.
 
 Authors:
 
 * Min RK
 * Brian Granger
 * Fernando Perez
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import hashlib
 import hmac
 import logging
 import os
 import pprint
 import random
 import uuid
 from datetime import datetime
 
 try:
     import cPickle
     pickle = cPickle
 except:
     cPickle = None
     import pickle
 
 import zmq
 from zmq.utils import jsonapi
 from zmq.eventloop.ioloop import IOLoop
 from zmq.eventloop.zmqstream import ZMQStream
 
 from IPython.config.configurable import Configurable, LoggingConfigurable
 from IPython.utils import io
 from IPython.utils.importstring import import_item
 from IPython.utils.jsonutil import extract_dates, squash_dates, date_default
 from IPython.utils.py3compat import (str_to_bytes, str_to_unicode, unicode_type,
                                      iteritems)
 from IPython.utils.traitlets import (CBytes, Unicode, Bool, Any, Instance, Set,
                                         DottedObjectName, CUnicode, Dict, Integer,
                                         TraitError,
 )
 from IPython.kernel.zmq.serialize import MAX_ITEMS, MAX_BYTES
 
 #-----------------------------------------------------------------------------
 # utility functions
 #-----------------------------------------------------------------------------
 
 def squash_unicode(obj):
     """coerce unicode back to bytestrings."""
     if isinstance(obj,dict):
         for key in obj.keys():
             obj[key] = squash_unicode(obj[key])
             if isinstance(key, unicode_type):
                 obj[squash_unicode(key)] = obj.pop(key)
     elif isinstance(obj, list):
         for i,v in enumerate(obj):
             obj[i] = squash_unicode(v)
     elif isinstance(obj, unicode_type):
         obj = obj.encode('utf8')
     return obj
 
 #-----------------------------------------------------------------------------
 # globals and defaults
 #-----------------------------------------------------------------------------
 
 # ISO8601-ify datetime objects
 json_packer = lambda obj: jsonapi.dumps(obj, default=date_default)
-json_unpacker = lambda s: extract_dates(jsonapi.loads(s))
+json_unpacker = lambda s: jsonapi.loads(s)
 
-pickle_packer = lambda o: pickle.dumps(o,-1)
+pickle_packer = lambda o: pickle.dumps(squash_dates(o),-1)
 pickle_unpacker = pickle.loads
 
 default_packer = json_packer
 default_unpacker = json_unpacker
 
 DELIM = b"<IDS|MSG>"
 # singleton dummy tracker, which will always report as done
 DONE = zmq.MessageTracker()
 
 #-----------------------------------------------------------------------------
 # Mixin tools for apps that use Sessions
 #-----------------------------------------------------------------------------
 
 session_aliases = dict(
     ident = 'Session.session',
     user = 'Session.username',
     keyfile = 'Session.keyfile',
 )
 
 session_flags  = {
     'secure' : ({'Session' : { 'key' : str_to_bytes(str(uuid.uuid4())),
                             'keyfile' : '' }},
         """Use HMAC digests for authentication of messages.
         Setting this flag will generate a new UUID to use as the HMAC key.
         """),
     'no-secure' : ({'Session' : { 'key' : b'', 'keyfile' : '' }},
         """Don't authenticate messages."""),
 }
 
 def default_secure(cfg):
     """Set the default behavior for a config environment to be secure.
     
     If Session.key/keyfile have not been set, set Session.key to
     a new random UUID.
     """
     
     if 'Session' in cfg:
         if 'key' in cfg.Session or 'keyfile' in cfg.Session:
             return
     # key/keyfile not specified, generate new UUID:
     cfg.Session.key = str_to_bytes(str(uuid.uuid4()))
 
 
 #-----------------------------------------------------------------------------
 # Classes
 #-----------------------------------------------------------------------------
 
 class SessionFactory(LoggingConfigurable):
     """The Base class for configurables that have a Session, Context, logger,
     and IOLoop.
     """
 
     logname = Unicode('')
     def _logname_changed(self, name, old, new):
         self.log = logging.getLogger(new)
 
     # not configurable:
     context = Instance('zmq.Context')
     def _context_default(self):
         return zmq.Context.instance()
 
     session = Instance('IPython.kernel.zmq.session.Session')
 
     loop = Instance('zmq.eventloop.ioloop.IOLoop', allow_none=False)
     def _loop_default(self):
         return IOLoop.instance()
 
     def __init__(self, **kwargs):
         super(SessionFactory, self).__init__(**kwargs)
 
         if self.session is None:
             # construct the session
             self.session = Session(**kwargs)
 
 
 class Message(object):
     """A simple message object that maps dict keys to attributes.
 
     A Message can be created from a dict and a dict from a Message instance
     simply by calling dict(msg_obj)."""
 
     def __init__(self, msg_dict):
         dct = self.__dict__
         for k, v in iteritems(dict(msg_dict)):
             if isinstance(v, dict):
                 v = Message(v)
             dct[k] = v
 
     # Having this iterator lets dict(msg_obj) work out of the box.
     def __iter__(self):
         return iter(iteritems(self.__dict__))
 
     def __repr__(self):
         return repr(self.__dict__)
 
     def __str__(self):
         return pprint.pformat(self.__dict__)
 
     def __contains__(self, k):
         return k in self.__dict__
 
     def __getitem__(self, k):
         return self.__dict__[k]
 
 
 def msg_header(msg_id, msg_type, username, session):
     date = datetime.now()
     return locals()
 
 def extract_header(msg_or_header):
     """Given a message or header, return the header."""
     if not msg_or_header:
         return {}
     try:
         # See if msg_or_header is the entire message.
         h = msg_or_header['header']
     except KeyError:
         try:
             # See if msg_or_header is just the header
             h = msg_or_header['msg_id']
         except KeyError:
             raise
         else:
             h = msg_or_header
     if not isinstance(h, dict):
         h = dict(h)
     return h
 
 class Session(Configurable):
     """Object for handling serialization and sending of messages.
 
     The Session object handles building messages and sending them
     with ZMQ sockets or ZMQStream objects.  Objects can communicate with each
     other over the network via Session objects, and only need to work with the
     dict-based IPython message spec. The Session will handle
     serialization/deserialization, security, and metadata.
 
     Sessions support configurable serialiization via packer/unpacker traits,
     and signing with HMAC digests via the key/keyfile traits.
 
     Parameters
     ----------
 
     debug : bool
         whether to trigger extra debugging statements
     packer/unpacker : str : 'json', 'pickle' or import_string
         importstrings for methods to serialize message parts.  If just
         'json' or 'pickle', predefined JSON and pickle packers will be used.
         Otherwise, the entire importstring must be used.
 
         The functions must accept at least valid JSON input, and output *bytes*.
 
         For example, to use msgpack:
         packer = 'msgpack.packb', unpacker='msgpack.unpackb'
     pack/unpack : callables
         You can also set the pack/unpack callables for serialization directly.
     session : bytes
         the ID of this Session object.  The default is to generate a new UUID.
     username : unicode
         username added to message headers.  The default is to ask the OS.
     key : bytes
         The key used to initialize an HMAC signature.  If unset, messages
         will not be signed or checked.
     keyfile : filepath
         The file containing a key.  If this is set, `key` will be initialized
         to the contents of the file.
 
     """
 
     debug=Bool(False, config=True, help="""Debug output in the Session""")
 
     packer = DottedObjectName('json',config=True,
             help="""The name of the packer for serializing messages.
             Should be one of 'json', 'pickle', or an import name
             for a custom callable serializer.""")
     def _packer_changed(self, name, old, new):
         if new.lower() == 'json':
             self.pack = json_packer
             self.unpack = json_unpacker
             self.unpacker = new
         elif new.lower() == 'pickle':
             self.pack = pickle_packer
             self.unpack = pickle_unpacker
             self.unpacker = new
         else:
             self.pack = import_item(str(new))
 
     unpacker = DottedObjectName('json', config=True,
         help="""The name of the unpacker for unserializing messages.
         Only used with custom functions for `packer`.""")
     def _unpacker_changed(self, name, old, new):
         if new.lower() == 'json':
             self.pack = json_packer
             self.unpack = json_unpacker
             self.packer = new
         elif new.lower() == 'pickle':
             self.pack = pickle_packer
             self.unpack = pickle_unpacker
             self.packer = new
         else:
             self.unpack = import_item(str(new))
 
     session = CUnicode(u'', config=True,
         help="""The UUID identifying this session.""")
     def _session_default(self):
         u = unicode_type(uuid.uuid4())
         self.bsession = u.encode('ascii')
         return u
 
     def _session_changed(self, name, old, new):
         self.bsession = self.session.encode('ascii')
 
     # bsession is the session as bytes
     bsession = CBytes(b'')
 
     username = Unicode(str_to_unicode(os.environ.get('USER', 'username')),
         help="""Username for the Session. Default is your system username.""",
         config=True)
 
     metadata = Dict({}, config=True,
         help="""Metadata dictionary, which serves as the default top-level metadata dict for each message.""")
 
     # message signature related traits:
     
     key = CBytes(b'', config=True,
         help="""execution key, for extra authentication.""")
     def _key_changed(self, name, old, new):
         if new:
             self.auth = hmac.HMAC(new, digestmod=self.digest_mod)
         else:
             self.auth = None
     
     signature_scheme = Unicode('hmac-sha256', config=True,
         help="""The digest scheme used to construct the message signatures.
         Must have the form 'hmac-HASH'.""")
     def _signature_scheme_changed(self, name, old, new):
         if not new.startswith('hmac-'):
             raise TraitError("signature_scheme must start with 'hmac-', got %r" % new)
         hash_name = new.split('-', 1)[1]
         try:
             self.digest_mod = getattr(hashlib, hash_name)
         except AttributeError:
             raise TraitError("hashlib has no such attribute: %s" % hash_name)
     
     digest_mod = Any()
     def _digest_mod_default(self):
         return hashlib.sha256
     
     auth = Instance(hmac.HMAC)
     
     digest_history = Set()
     digest_history_size = Integer(2**16, config=True,
         help="""The maximum number of digests to remember.
         
         The digest history will be culled when it exceeds this value.
         """
     )
 
     keyfile = Unicode('', config=True,
         help="""path to file containing execution key.""")
     def _keyfile_changed(self, name, old, new):
         with open(new, 'rb') as f:
             self.key = f.read().strip()
 
     # for protecting against sends from forks
     pid = Integer()
     
     # serialization traits:
     
     pack = Any(default_packer) # the actual packer function
     def _pack_changed(self, name, old, new):
         if not callable(new):
             raise TypeError("packer must be callable, not %s"%type(new))
 
     unpack = Any(default_unpacker) # the actual packer function
     def _unpack_changed(self, name, old, new):
         # unpacker is not checked - it is assumed to be
         if not callable(new):
             raise TypeError("unpacker must be callable, not %s"%type(new))
     
     # thresholds:
     copy_threshold = Integer(2**16, config=True,
         help="Threshold (in bytes) beyond which a buffer should be sent without copying.")
     buffer_threshold = Integer(MAX_BYTES, config=True,
         help="Threshold (in bytes) beyond which an object's buffer should be extracted to avoid pickling.")
     item_threshold = Integer(MAX_ITEMS, config=True,
         help="""The maximum number of items for a container to be introspected for custom serialization.
         Containers larger than this are pickled outright.
         """
     )
 
     
     def __init__(self, **kwargs):
         """create a Session object
 
         Parameters
         ----------
 
         debug : bool
             whether to trigger extra debugging statements
         packer/unpacker : str : 'json', 'pickle' or import_string
             importstrings for methods to serialize message parts.  If just
             'json' or 'pickle', predefined JSON and pickle packers will be used.
             Otherwise, the entire importstring must be used.
 
             The functions must accept at least valid JSON input, and output
             *bytes*.
 
             For example, to use msgpack:
             packer = 'msgpack.packb', unpacker='msgpack.unpackb'
         pack/unpack : callables
             You can also set the pack/unpack callables for serialization
             directly.
         session : unicode (must be ascii)
             the ID of this Session object.  The default is to generate a new
             UUID.
         bsession : bytes
             The session as bytes
         username : unicode
             username added to message headers.  The default is to ask the OS.
         key : bytes
             The key used to initialize an HMAC signature.  If unset, messages
             will not be signed or checked.
         signature_scheme : str
             The message digest scheme. Currently must be of the form 'hmac-HASH',
             where 'HASH' is a hashing function available in Python's hashlib.
             The default is 'hmac-sha256'.
             This is ignored if 'key' is empty.
         keyfile : filepath
             The file containing a key.  If this is set, `key` will be
             initialized to the contents of the file.
         """
         super(Session, self).__init__(**kwargs)
         self._check_packers()
         self.none = self.pack({})
         # ensure self._session_default() if necessary, so bsession is defined:
         self.session
         self.pid = os.getpid()
 
     @property
     def msg_id(self):
         """always return new uuid"""
         return str(uuid.uuid4())
 
     def _check_packers(self):
-        """check packers for binary data and datetime support."""
+        """check packers for datetime support."""
         pack = self.pack
         unpack = self.unpack
 
         # check simple serialization
         msg = dict(a=[1,'hi'])
         try:
             packed = pack(msg)
         except Exception as e:
             msg = "packer '{packer}' could not serialize a simple message: {e}{jsonmsg}"
             if self.packer == 'json':
                 jsonmsg = "\nzmq.utils.jsonapi.jsonmod = %s" % jsonapi.jsonmod
             else:
                 jsonmsg = ""
             raise ValueError(
                 msg.format(packer=self.packer, e=e, jsonmsg=jsonmsg)
             )
 
         # ensure packed message is bytes
         if not isinstance(packed, bytes):
             raise ValueError("message packed to %r, but bytes are required"%type(packed))
 
         # check that unpack is pack's inverse
         try:
             unpacked = unpack(packed)
             assert unpacked == msg
         except Exception as e:
             msg = "unpacker '{unpacker}' could not handle output from packer '{packer}': {e}{jsonmsg}"
             if self.packer == 'json':
                 jsonmsg = "\nzmq.utils.jsonapi.jsonmod = %s" % jsonapi.jsonmod
             else:
                 jsonmsg = ""
             raise ValueError(
                 msg.format(packer=self.packer, unpacker=self.unpacker, e=e, jsonmsg=jsonmsg)
             )
 
         # check datetime support
         msg = dict(t=datetime.now())
         try:
             unpacked = unpack(pack(msg))
+            if isinstance(unpacked['t'], datetime):
+                raise ValueError("Shouldn't deserialize to datetime")
         except Exception:
             self.pack = lambda o: pack(squash_dates(o))
-            self.unpack = lambda s: extract_dates(unpack(s))
+            self.unpack = lambda s: unpack(s)
 
     def msg_header(self, msg_type):
         return msg_header(self.msg_id, msg_type, self.username, self.session)
 
     def msg(self, msg_type, content=None, parent=None, header=None, metadata=None):
         """Return the nested message dict.
 
         This format is different from what is sent over the wire. The
         serialize/unserialize methods converts this nested message dict to the wire
         format, which is a list of message parts.
         """
         msg = {}
         header = self.msg_header(msg_type) if header is None else header
         msg['header'] = header
         msg['msg_id'] = header['msg_id']
         msg['msg_type'] = header['msg_type']
         msg['parent_header'] = {} if parent is None else extract_header(parent)
         msg['content'] = {} if content is None else content
         msg['metadata'] = self.metadata.copy()
         if metadata is not None:
             msg['metadata'].update(metadata)
         return msg
 
     def sign(self, msg_list):
         """Sign a message with HMAC digest. If no auth, return b''.
 
         Parameters
         ----------
         msg_list : list
             The [p_header,p_parent,p_content] part of the message list.
         """
         if self.auth is None:
             return b''
         h = self.auth.copy()
         for m in msg_list:
             h.update(m)
         return str_to_bytes(h.hexdigest())
 
     def serialize(self, msg, ident=None):
         """Serialize the message components to bytes.
 
         This is roughly the inverse of unserialize. The serialize/unserialize
         methods work with full message lists, whereas pack/unpack work with
         the individual message parts in the message list.
 
         Parameters
         ----------
         msg : dict or Message
             The nexted message dict as returned by the self.msg method.
 
         Returns
         -------
         msg_list : list
             The list of bytes objects to be sent with the format:
             [ident1,ident2,...,DELIM,HMAC,p_header,p_parent,p_metadata,p_content,
              buffer1,buffer2,...]. In this list, the p_* entities are
             the packed or serialized versions, so if JSON is used, these
             are utf8 encoded JSON strings.
         """
         content = msg.get('content', {})
         if content is None:
             content = self.none
         elif isinstance(content, dict):
             content = self.pack(content)
         elif isinstance(content, bytes):
             # content is already packed, as in a relayed message
             pass
         elif isinstance(content, unicode_type):
             # should be bytes, but JSON often spits out unicode
             content = content.encode('utf8')
         else:
             raise TypeError("Content incorrect type: %s"%type(content))
 
         real_message = [self.pack(msg['header']),
                         self.pack(msg['parent_header']),
                         self.pack(msg['metadata']),
                         content,
         ]
 
         to_send = []
 
         if isinstance(ident, list):
             # accept list of idents
             to_send.extend(ident)
         elif ident is not None:
             to_send.append(ident)
         to_send.append(DELIM)
 
         signature = self.sign(real_message)
         to_send.append(signature)
 
         to_send.extend(real_message)
 
         return to_send
 
     def send(self, stream, msg_or_type, content=None, parent=None, ident=None,
              buffers=None, track=False, header=None, metadata=None):
         """Build and send a message via stream or socket.
 
         The message format used by this function internally is as follows:
 
         [ident1,ident2,...,DELIM,HMAC,p_header,p_parent,p_content,
          buffer1,buffer2,...]
 
         The serialize/unserialize methods convert the nested message dict into this
         format.
 
         Parameters
         ----------
 
         stream : zmq.Socket or ZMQStream
             The socket-like object used to send the data.
         msg_or_type : str or Message/dict
             Normally, msg_or_type will be a msg_type unless a message is being
             sent more than once. If a header is supplied, this can be set to
             None and the msg_type will be pulled from the header.
 
         content : dict or None
             The content of the message (ignored if msg_or_type is a message).
         header : dict or None
             The header dict for the message (ignored if msg_to_type is a message).
         parent : Message or dict or None
             The parent or parent header describing the parent of this message
             (ignored if msg_or_type is a message).
         ident : bytes or list of bytes
             The zmq.IDENTITY routing path.
         metadata : dict or None
             The metadata describing the message
         buffers : list or None
             The already-serialized buffers to be appended to the message.
         track : bool
             Whether to track.  Only for use with Sockets, because ZMQStream
             objects cannot track messages.
             
 
         Returns
         -------
         msg : dict
             The constructed message.
         """
         if not isinstance(stream, zmq.Socket):
             # ZMQStreams and dummy sockets do not support tracking.
             track = False
 
         if isinstance(msg_or_type, (Message, dict)):
             # We got a Message or message dict, not a msg_type so don't
             # build a new Message.
             msg = msg_or_type
         else:
             msg = self.msg(msg_or_type, content=content, parent=parent,
                            header=header, metadata=metadata)
         if not os.getpid() == self.pid:
             io.rprint("WARNING: attempted to send message from fork")
             io.rprint(msg)
             return
         buffers = [] if buffers is None else buffers
         to_send = self.serialize(msg, ident)
         to_send.extend(buffers)
         longest = max([ len(s) for s in to_send ])
         copy = (longest < self.copy_threshold)
         
         if buffers and track and not copy:
             # only really track when we are doing zero-copy buffers
             tracker = stream.send_multipart(to_send, copy=False, track=True)
         else:
             # use dummy tracker, which will be done immediately
             tracker = DONE
             stream.send_multipart(to_send, copy=copy)
 
         if self.debug:
             pprint.pprint(msg)
             pprint.pprint(to_send)
             pprint.pprint(buffers)
 
         msg['tracker'] = tracker
 
         return msg
 
     def send_raw(self, stream, msg_list, flags=0, copy=True, ident=None):
         """Send a raw message via ident path.
 
         This method is used to send a already serialized message.
 
         Parameters
         ----------
         stream : ZMQStream or Socket
             The ZMQ stream or socket to use for sending the message.
         msg_list : list
             The serialized list of messages to send. This only includes the
             [p_header,p_parent,p_metadata,p_content,buffer1,buffer2,...] portion of
             the message.
         ident : ident or list
             A single ident or a list of idents to use in sending.
         """
         to_send = []
         if isinstance(ident, bytes):
             ident = [ident]
         if ident is not None:
             to_send.extend(ident)
 
         to_send.append(DELIM)
         to_send.append(self.sign(msg_list))
         to_send.extend(msg_list)
         stream.send_multipart(msg_list, flags, copy=copy)
 
     def recv(self, socket, mode=zmq.NOBLOCK, content=True, copy=True):
         """Receive and unpack a message.
 
         Parameters
         ----------
         socket : ZMQStream or Socket
             The socket or stream to use in receiving.
 
         Returns
         -------
         [idents], msg
             [idents] is a list of idents and msg is a nested message dict of
             same format as self.msg returns.
         """
         if isinstance(socket, ZMQStream):
             socket = socket.socket
         try:
             msg_list = socket.recv_multipart(mode, copy=copy)
         except zmq.ZMQError as e:
             if e.errno == zmq.EAGAIN:
                 # We can convert EAGAIN to None as we know in this case
                 # recv_multipart won't return None.
                 return None,None
             else:
                 raise
         # split multipart message into identity list and message dict
         # invalid large messages can cause very expensive string comparisons
         idents, msg_list = self.feed_identities(msg_list, copy)
         try:
             return idents, self.unserialize(msg_list, content=content, copy=copy)
         except Exception as e:
             # TODO: handle it
             raise e
 
     def feed_identities(self, msg_list, copy=True):
         """Split the identities from the rest of the message.
 
         Feed until DELIM is reached, then return the prefix as idents and
         remainder as msg_list. This is easily broken by setting an IDENT to DELIM,
         but that would be silly.
 
         Parameters
         ----------
         msg_list : a list of Message or bytes objects
             The message to be split.
         copy : bool
             flag determining whether the arguments are bytes or Messages
 
         Returns
         -------
         (idents, msg_list) : two lists
             idents will always be a list of bytes, each of which is a ZMQ
             identity. msg_list will be a list of bytes or zmq.Messages of the
             form [HMAC,p_header,p_parent,p_content,buffer1,buffer2,...] and
             should be unpackable/unserializable via self.unserialize at this
             point.
         """
         if copy:
             idx = msg_list.index(DELIM)
             return msg_list[:idx], msg_list[idx+1:]
         else:
             failed = True
             for idx,m in enumerate(msg_list):
                 if m.bytes == DELIM:
                     failed = False
                     break
             if failed:
                 raise ValueError("DELIM not in msg_list")
             idents, msg_list = msg_list[:idx], msg_list[idx+1:]
             return [m.bytes for m in idents], msg_list
 
     def _add_digest(self, signature):
         """add a digest to history to protect against replay attacks"""
         if self.digest_history_size == 0:
             # no history, never add digests
             return
         
         self.digest_history.add(signature)
         if len(self.digest_history) > self.digest_history_size:
             # threshold reached, cull 10%
             self._cull_digest_history()
     
     def _cull_digest_history(self):
         """cull the digest history
         
         Removes a randomly selected 10% of the digest history
         """
         current = len(self.digest_history)
         n_to_cull = max(int(current // 10), current - self.digest_history_size)
         if n_to_cull >= current:
             self.digest_history = set()
             return
         to_cull = random.sample(self.digest_history, n_to_cull)
         self.digest_history.difference_update(to_cull)
     
     def unserialize(self, msg_list, content=True, copy=True):
         """Unserialize a msg_list to a nested message dict.
 
         This is roughly the inverse of serialize. The serialize/unserialize
         methods work with full message lists, whereas pack/unpack work with
         the individual message parts in the message list.
 
         Parameters:
         -----------
         msg_list : list of bytes or Message objects
             The list of message parts of the form [HMAC,p_header,p_parent,
             p_metadata,p_content,buffer1,buffer2,...].
         content : bool (True)
             Whether to unpack the content dict (True), or leave it packed
             (False).
         copy : bool (True)
             Whether to return the bytes (True), or the non-copying Message
             object in each place (False).
 
         Returns
         -------
         msg : dict
             The nested message dict with top-level keys [header, parent_header,
             content, buffers].
         """
         minlen = 5
         message = {}
         if not copy:
             for i in range(minlen):
                 msg_list[i] = msg_list[i].bytes
         if self.auth is not None:
             signature = msg_list[0]
             if not signature:
                 raise ValueError("Unsigned Message")
             if signature in self.digest_history:
                 raise ValueError("Duplicate Signature: %r" % signature)
             self._add_digest(signature)
             check = self.sign(msg_list[1:5])
             if not signature == check:
                 raise ValueError("Invalid Signature: %r" % signature)
         if not len(msg_list) >= minlen:
             raise TypeError("malformed message, must have at least %i elements"%minlen)
         header = self.unpack(msg_list[1])
-        message['header'] = header
+        message['header'] = extract_dates(header)
         message['msg_id'] = header['msg_id']
         message['msg_type'] = header['msg_type']
-        message['parent_header'] = self.unpack(msg_list[2])
+        message['parent_header'] = extract_dates(self.unpack(msg_list[2]))
         message['metadata'] = self.unpack(msg_list[3])
         if content:
             message['content'] = self.unpack(msg_list[4])
         else:
             message['content'] = msg_list[4]
 
         message['buffers'] = msg_list[5:]
         return message
 
 def test_msg2obj():
     am = dict(x=1)
     ao = Message(am)
     assert ao.x == am['x']
 
     am['y'] = dict(z=1)
     ao = Message(am)
     assert ao.y.z == am['y']['z']
 
     k1, k2 = 'y', 'z'
     assert ao[k1][k2] == am[k1][k2]
 
     am2 = dict(ao)
     assert am['x'] == am2['x']
     assert am['y']['z'] == am2['y']['z']
 

IPython/kernel/zmq/tests/test_session.py

@@ -1,271 +1,289
 """test building messages with streamsession"""
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-------------------------------------------------------------------------------
 
 #-------------------------------------------------------------------------------
 # Imports
 #-------------------------------------------------------------------------------
 
 import os
 import uuid
+from datetime import datetime
+
 import zmq
 
 from zmq.tests import BaseZMQTestCase
 from zmq.eventloop.zmqstream import ZMQStream
 
 from IPython.kernel.zmq import session as ss
 
+from IPython.testing.decorators import skipif, module_not_available
+from IPython.utils.py3compat import string_types
+from IPython.utils import jsonutil
+
 def _bad_packer(obj):
     raise TypeError("I don't work")
 
 def _bad_unpacker(bytes):
     raise TypeError("I don't work either")
 
 class SessionTestCase(BaseZMQTestCase):
 
     def setUp(self):
         BaseZMQTestCase.setUp(self)
         self.session = ss.Session()
 
 
 class TestSession(SessionTestCase):
 
     def test_msg(self):
         """message format"""
         msg = self.session.msg('execute')
         thekeys = set('header parent_header metadata content msg_type msg_id'.split())
         s = set(msg.keys())
         self.assertEqual(s, thekeys)
         self.assertTrue(isinstance(msg['content'],dict))
         self.assertTrue(isinstance(msg['metadata'],dict))
         self.assertTrue(isinstance(msg['header'],dict))
         self.assertTrue(isinstance(msg['parent_header'],dict))
         self.assertTrue(isinstance(msg['msg_id'],str))
         self.assertTrue(isinstance(msg['msg_type'],str))
         self.assertEqual(msg['header']['msg_type'], 'execute')
         self.assertEqual(msg['msg_type'], 'execute')
 
     def test_serialize(self):
         msg = self.session.msg('execute', content=dict(a=10, b=1.1))
         msg_list = self.session.serialize(msg, ident=b'foo')
         ident, msg_list = self.session.feed_identities(msg_list)
         new_msg = self.session.unserialize(msg_list)
         self.assertEqual(ident[0], b'foo')
         self.assertEqual(new_msg['msg_id'],msg['msg_id'])
         self.assertEqual(new_msg['msg_type'],msg['msg_type'])
         self.assertEqual(new_msg['header'],msg['header'])
         self.assertEqual(new_msg['content'],msg['content'])
         self.assertEqual(new_msg['parent_header'],msg['parent_header'])
         self.assertEqual(new_msg['metadata'],msg['metadata'])
         # ensure floats don't come out as Decimal:
         self.assertEqual(type(new_msg['content']['b']),type(new_msg['content']['b']))
 
     def test_send(self):
         ctx = zmq.Context.instance()
         A = ctx.socket(zmq.PAIR)
         B = ctx.socket(zmq.PAIR)
         A.bind("inproc://test")
         B.connect("inproc://test")
 
         msg = self.session.msg('execute', content=dict(a=10))
         self.session.send(A, msg, ident=b'foo', buffers=[b'bar'])
         
         ident, msg_list = self.session.feed_identities(B.recv_multipart())
         new_msg = self.session.unserialize(msg_list)
         self.assertEqual(ident[0], b'foo')
         self.assertEqual(new_msg['msg_id'],msg['msg_id'])
         self.assertEqual(new_msg['msg_type'],msg['msg_type'])
         self.assertEqual(new_msg['header'],msg['header'])
         self.assertEqual(new_msg['content'],msg['content'])
         self.assertEqual(new_msg['parent_header'],msg['parent_header'])
         self.assertEqual(new_msg['metadata'],msg['metadata'])
         self.assertEqual(new_msg['buffers'],[b'bar'])
 
         content = msg['content']
         header = msg['header']
         parent = msg['parent_header']
         metadata = msg['metadata']
         msg_type = header['msg_type']
         self.session.send(A, None, content=content, parent=parent,
             header=header, metadata=metadata, ident=b'foo', buffers=[b'bar'])
         ident, msg_list = self.session.feed_identities(B.recv_multipart())
         new_msg = self.session.unserialize(msg_list)
         self.assertEqual(ident[0], b'foo')
         self.assertEqual(new_msg['msg_id'],msg['msg_id'])
         self.assertEqual(new_msg['msg_type'],msg['msg_type'])
         self.assertEqual(new_msg['header'],msg['header'])
         self.assertEqual(new_msg['content'],msg['content'])
         self.assertEqual(new_msg['metadata'],msg['metadata'])
         self.assertEqual(new_msg['parent_header'],msg['parent_header'])
         self.assertEqual(new_msg['buffers'],[b'bar'])
 
         self.session.send(A, msg, ident=b'foo', buffers=[b'bar'])
         ident, new_msg = self.session.recv(B)
         self.assertEqual(ident[0], b'foo')
         self.assertEqual(new_msg['msg_id'],msg['msg_id'])
         self.assertEqual(new_msg['msg_type'],msg['msg_type'])
         self.assertEqual(new_msg['header'],msg['header'])
         self.assertEqual(new_msg['content'],msg['content'])
         self.assertEqual(new_msg['metadata'],msg['metadata'])
         self.assertEqual(new_msg['parent_header'],msg['parent_header'])
         self.assertEqual(new_msg['buffers'],[b'bar'])
 
         A.close()
         B.close()
         ctx.term()
 
     def test_args(self):
         """initialization arguments for Session"""
         s = self.session
         self.assertTrue(s.pack is ss.default_packer)
         self.assertTrue(s.unpack is ss.default_unpacker)
         self.assertEqual(s.username, os.environ.get('USER', u'username'))
 
         s = ss.Session()
         self.assertEqual(s.username, os.environ.get('USER', u'username'))
 
         self.assertRaises(TypeError, ss.Session, pack='hi')
         self.assertRaises(TypeError, ss.Session, unpack='hi')
         u = str(uuid.uuid4())
         s = ss.Session(username=u'carrot', session=u)
         self.assertEqual(s.session, u)
         self.assertEqual(s.username, u'carrot')
 
     def test_tracking(self):
         """test tracking messages"""
         a,b = self.create_bound_pair(zmq.PAIR, zmq.PAIR)
         s = self.session
         s.copy_threshold = 1
         stream = ZMQStream(a)
         msg = s.send(a, 'hello', track=False)
         self.assertTrue(msg['tracker'] is ss.DONE)
         msg = s.send(a, 'hello', track=True)
         self.assertTrue(isinstance(msg['tracker'], zmq.MessageTracker))
         M = zmq.Message(b'hi there', track=True)
         msg = s.send(a, 'hello', buffers=[M], track=True)
         t = msg['tracker']
         self.assertTrue(isinstance(t, zmq.MessageTracker))
         self.assertRaises(zmq.NotDone, t.wait, .1)
         del M
         t.wait(1) # this will raise
 
 
-    # def test_rekey(self):
-    #     """rekeying dict around json str keys"""
-    #     d = {'0': uuid.uuid4(), 0:uuid.uuid4()}
-    #     self.assertRaises(KeyError, ss.rekey, d)
-    #
-    #     d = {'0': uuid.uuid4(), 1:uuid.uuid4(), 'asdf':uuid.uuid4()}
-    #     d2 = {0:d['0'],1:d[1],'asdf':d['asdf']}
-    #     rd = ss.rekey(d)
-    #     self.assertEqual(d2,rd)
-    #
-    #     d = {'1.5':uuid.uuid4(),'1':uuid.uuid4()}
-    #     d2 = {1.5:d['1.5'],1:d['1']}
-    #     rd = ss.rekey(d)
-    #     self.assertEqual(d2,rd)
-    #
-    #     d = {'1.0':uuid.uuid4(),'1':uuid.uuid4()}
-    #     self.assertRaises(KeyError, ss.rekey, d)
-    #
     def test_unique_msg_ids(self):
         """test that messages receive unique ids"""
         ids = set()
         for i in range(2**12):
             h = self.session.msg_header('test')
             msg_id = h['msg_id']
             self.assertTrue(msg_id not in ids)
             ids.add(msg_id)
 
     def test_feed_identities(self):
         """scrub the front for zmq IDENTITIES"""
         theids = "engine client other".split()
         content = dict(code='whoda',stuff=object())
         themsg = self.session.msg('execute',content=content)
         pmsg = theids
 
     def test_session_id(self):
         session = ss.Session()
         # get bs before us
         bs = session.bsession
         us = session.session
         self.assertEqual(us.encode('ascii'), bs)
         session = ss.Session()
         # get us before bs
         us = session.session
         bs = session.bsession
         self.assertEqual(us.encode('ascii'), bs)
         # change propagates:
         session.session = 'something else'
         bs = session.bsession
         us = session.session
         self.assertEqual(us.encode('ascii'), bs)
         session = ss.Session(session='stuff')
         # get us before bs
         self.assertEqual(session.bsession, session.session.encode('ascii'))
         self.assertEqual(b'stuff', session.bsession)
 
     def test_zero_digest_history(self):
         session = ss.Session(digest_history_size=0)
         for i in range(11):
             session._add_digest(uuid.uuid4().bytes)
         self.assertEqual(len(session.digest_history), 0)
 
     def test_cull_digest_history(self):
         session = ss.Session(digest_history_size=100)
         for i in range(100):
             session._add_digest(uuid.uuid4().bytes)
         self.assertTrue(len(session.digest_history) == 100)
         session._add_digest(uuid.uuid4().bytes)
         self.assertTrue(len(session.digest_history) == 91)
         for i in range(9):
             session._add_digest(uuid.uuid4().bytes)
         self.assertTrue(len(session.digest_history) == 100)
         session._add_digest(uuid.uuid4().bytes)
         self.assertTrue(len(session.digest_history) == 91)
     
     def test_bad_pack(self):
         try:
             session = ss.Session(pack=_bad_packer)
         except ValueError as e:
             self.assertIn("could not serialize", str(e))
             self.assertIn("don't work", str(e))
         else:
             self.fail("Should have raised ValueError")
     
     def test_bad_unpack(self):
         try:
             session = ss.Session(unpack=_bad_unpacker)
         except ValueError as e:
             self.assertIn("could not handle output", str(e))
             self.assertIn("don't work either", str(e))
         else:
             self.fail("Should have raised ValueError")
     
     def test_bad_packer(self):
         try:
             session = ss.Session(packer=__name__ + '._bad_packer')
         except ValueError as e:
             self.assertIn("could not serialize", str(e))
             self.assertIn("don't work", str(e))
         else:
             self.fail("Should have raised ValueError")
     
     def test_bad_unpacker(self):
         try:
             session = ss.Session(unpacker=__name__ + '._bad_unpacker')
         except ValueError as e:
             self.assertIn("could not handle output", str(e))
             self.assertIn("don't work either", str(e))
         else:
             self.fail("Should have raised ValueError")
     
     def test_bad_roundtrip(self):
         with self.assertRaises(ValueError):
-            session=  ss.Session(unpack=lambda b: 5)
+            session = ss.Session(unpack=lambda b: 5)
+    
+    def _datetime_test(self, session):
+        content = dict(t=datetime.now())
+        metadata = dict(t=datetime.now())
+        p = session.msg('msg')
+        msg = session.msg('msg', content=content, metadata=metadata, parent=p['header'])
+        smsg = session.serialize(msg)
+        msg2 = session.unserialize(session.feed_identities(smsg)[1])
+        assert isinstance(msg2['header']['date'], datetime)
+        self.assertEqual(msg['header'], msg2['header'])
+        self.assertEqual(msg['parent_header'], msg2['parent_header'])
+        self.assertEqual(msg['parent_header'], msg2['parent_header'])
+        assert isinstance(msg['content']['t'], datetime)
+        assert isinstance(msg['metadata']['t'], datetime)
+        assert isinstance(msg2['content']['t'], string_types)
+        assert isinstance(msg2['metadata']['t'], string_types)
+        self.assertEqual(msg['content'], jsonutil.extract_dates(msg2['content']))
+        self.assertEqual(msg['content'], jsonutil.extract_dates(msg2['content']))
+    
+    def test_datetimes(self):
+        self._datetime_test(self.session)
+    
+    def test_datetimes_pickle(self):
+        session = ss.Session(packer='pickle')
+        self._datetime_test(session)
+    
+    @skipif(module_not_available('msgpack'))
+    def test_datetimes_msgpack(self):
+        session = ss.Session(packer='msgpack.packb', unpacker='msgpack.unpackb')
+        self._datetime_test(session)
     

IPython/parallel/client/client.py

@@ -1,1855 +1,1862
 """A semi-synchronous Client for the ZMQ cluster
 
 Authors:
 
 * MinRK
 """
 from __future__ import print_function
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 
 import os
 import json
 import sys
 from threading import Thread, Event
 import time
 import warnings
 from datetime import datetime
 from getpass import getpass
 from pprint import pprint
 
 pjoin = os.path.join
 
 import zmq
 # from zmq.eventloop import ioloop, zmqstream
 
 from IPython.config.configurable import MultipleInstanceError
 from IPython.core.application import BaseIPythonApplication
 from IPython.core.profiledir import ProfileDir, ProfileDirError
 
 from IPython.utils.capture import RichOutput
 from IPython.utils.coloransi import TermColors
-from IPython.utils.jsonutil import rekey
+from IPython.utils.jsonutil import rekey, extract_dates, parse_date
 from IPython.utils.localinterfaces import localhost, is_local_ip
 from IPython.utils.path import get_ipython_dir
 from IPython.utils.py3compat import cast_bytes, string_types, xrange, iteritems
 from IPython.utils.traitlets import (HasTraits, Integer, Instance, Unicode,
                                     Dict, List, Bool, Set, Any)
 from IPython.external.decorator import decorator
 from IPython.external.ssh import tunnel
 
 from IPython.parallel import Reference
 from IPython.parallel import error
 from IPython.parallel import util
 
 from IPython.kernel.zmq.session import Session, Message
 from IPython.kernel.zmq import serialize
 
 from .asyncresult import AsyncResult, AsyncHubResult
 from .view import DirectView, LoadBalancedView
 
 #--------------------------------------------------------------------------
 # Decorators for Client methods
 #--------------------------------------------------------------------------
 
 @decorator
 def spin_first(f, self, *args, **kwargs):
     """Call spin() to sync state prior to calling the method."""
     self.spin()
     return f(self, *args, **kwargs)
 
 
 #--------------------------------------------------------------------------
 # Classes
 #--------------------------------------------------------------------------
 
 
 class ExecuteReply(RichOutput):
     """wrapper for finished Execute results"""
     def __init__(self, msg_id, content, metadata):
         self.msg_id = msg_id
         self._content = content
         self.execution_count = content['execution_count']
         self.metadata = metadata
     
     # RichOutput overrides
     
     @property
     def source(self):
         pyout = self.metadata['pyout']
         if pyout:
             return pyout.get('source', '')
     
     @property
     def data(self):
         pyout = self.metadata['pyout']
         if pyout:
             return pyout.get('data', {})
     
     @property
     def _metadata(self):
         pyout = self.metadata['pyout']
         if pyout:
             return pyout.get('metadata', {})
     
     def display(self):
         from IPython.display import publish_display_data
         publish_display_data(self.source, self.data, self.metadata)
     
     def _repr_mime_(self, mime):
         if mime not in self.data:
             return
         data = self.data[mime]
         if mime in self._metadata:
             return data, self._metadata[mime]
         else:
             return data
     
     def __getitem__(self, key):
         return self.metadata[key]
     
     def __getattr__(self, key):
         if key not in self.metadata:
             raise AttributeError(key)
         return self.metadata[key]
     
     def __repr__(self):
         pyout = self.metadata['pyout'] or {'data':{}}
         text_out = pyout['data'].get('text/plain', '')
         if len(text_out) > 32:
             text_out = text_out[:29] + '...'
         
         return "<ExecuteReply[%i]: %s>" % (self.execution_count, text_out)
     
     def _repr_pretty_(self, p, cycle):
         pyout = self.metadata['pyout'] or {'data':{}}
         text_out = pyout['data'].get('text/plain', '')
         
         if not text_out:
             return
         
         try:
             ip = get_ipython()
         except NameError:
             colors = "NoColor"
         else:
             colors = ip.colors
         
         if colors == "NoColor":
             out = normal = ""
         else:
             out = TermColors.Red
             normal = TermColors.Normal
         
         if '\n' in text_out and not text_out.startswith('\n'):
             # add newline for multiline reprs
             text_out = '\n' + text_out
         
         p.text(
             out + u'Out[%i:%i]: ' % (
                 self.metadata['engine_id'], self.execution_count
             ) + normal + text_out
         )
 
 
 class Metadata(dict):
     """Subclass of dict for initializing metadata values.
 
     Attribute access works on keys.
 
     These objects have a strict set of keys - errors will raise if you try
     to add new keys.
     """
     def __init__(self, *args, **kwargs):
         dict.__init__(self)
         md = {'msg_id' : None,
               'submitted' : None,
               'started' : None,
               'completed' : None,
               'received' : None,
               'engine_uuid' : None,
               'engine_id' : None,
               'follow' : None,
               'after' : None,
               'status' : None,
 
               'pyin' : None,
               'pyout' : None,
               'pyerr' : None,
               'stdout' : '',
               'stderr' : '',
               'outputs' : [],
               'data': {},
               'outputs_ready' : False,
             }
         self.update(md)
         self.update(dict(*args, **kwargs))
 
     def __getattr__(self, key):
         """getattr aliased to getitem"""
         if key in self:
             return self[key]
         else:
             raise AttributeError(key)
 
     def __setattr__(self, key, value):
         """setattr aliased to setitem, with strict"""
         if key in self:
             self[key] = value
         else:
             raise AttributeError(key)
 
     def __setitem__(self, key, value):
         """strict static key enforcement"""
         if key in self:
             dict.__setitem__(self, key, value)
         else:
             raise KeyError(key)
 
 
 class Client(HasTraits):
     """A semi-synchronous client to the IPython ZMQ cluster
 
     Parameters
     ----------
 
     url_file : str/unicode; path to ipcontroller-client.json
         This JSON file should contain all the information needed to connect to a cluster,
         and is likely the only argument needed.
         Connection information for the Hub's registration.  If a json connector
         file is given, then likely no further configuration is necessary.
         [Default: use profile]
     profile : bytes
         The name of the Cluster profile to be used to find connector information.
         If run from an IPython application, the default profile will be the same
         as the running application, otherwise it will be 'default'.
     cluster_id : str
         String id to added to runtime files, to prevent name collisions when using
         multiple clusters with a single profile simultaneously.
         When set, will look for files named like: 'ipcontroller-<cluster_id>-client.json'
         Since this is text inserted into filenames, typical recommendations apply:
         Simple character strings are ideal, and spaces are not recommended (but
         should generally work)
     context : zmq.Context
         Pass an existing zmq.Context instance, otherwise the client will create its own.
     debug : bool
         flag for lots of message printing for debug purposes
     timeout : int/float
         time (in seconds) to wait for connection replies from the Hub
         [Default: 10]
 
     #-------------- session related args ----------------
 
     config : Config object
         If specified, this will be relayed to the Session for configuration
     username : str
         set username for the session object
 
     #-------------- ssh related args ----------------
     # These are args for configuring the ssh tunnel to be used
     # credentials are used to forward connections over ssh to the Controller
     # Note that the ip given in `addr` needs to be relative to sshserver
     # The most basic case is to leave addr as pointing to localhost (127.0.0.1),
     # and set sshserver as the same machine the Controller is on. However,
     # the only requirement is that sshserver is able to see the Controller
     # (i.e. is within the same trusted network).
 
     sshserver : str
         A string of the form passed to ssh, i.e. 'server.tld' or '[e-mail]:port'
         If keyfile or password is specified, and this is not, it will default to
         the ip given in addr.
     sshkey : str; path to ssh private key file
         This specifies a key to be used in ssh login, default None.
         Regular default ssh keys will be used without specifying this argument.
     password : str
         Your ssh password to sshserver. Note that if this is left None,
         you will be prompted for it if passwordless key based login is unavailable.
     paramiko : bool
         flag for whether to use paramiko instead of shell ssh for tunneling.
         [default: True on win32, False else]
 
 
     Attributes
     ----------
 
     ids : list of int engine IDs
         requesting the ids attribute always synchronizes
         the registration state. To request ids without synchronization,
         use semi-private _ids attributes.
 
     history : list of msg_ids
         a list of msg_ids, keeping track of all the execution
         messages you have submitted in order.
 
     outstanding : set of msg_ids
         a set of msg_ids that have been submitted, but whose
         results have not yet been received.
 
     results : dict
         a dict of all our results, keyed by msg_id
 
     block : bool
         determines default behavior when block not specified
         in execution methods
 
     Methods
     -------
 
     spin
         flushes incoming results and registration state changes
         control methods spin, and requesting `ids` also ensures up to date
 
     wait
         wait on one or more msg_ids
 
     execution methods
         apply
         legacy: execute, run
 
     data movement
         push, pull, scatter, gather
 
     query methods
         queue_status, get_result, purge, result_status
 
     control methods
         abort, shutdown
 
     """
 
 
     block = Bool(False)
     outstanding = Set()
     results = Instance('collections.defaultdict', (dict,))
     metadata = Instance('collections.defaultdict', (Metadata,))
     history = List()
     debug = Bool(False)
     _spin_thread = Any()
     _stop_spinning = Any()
 
     profile=Unicode()
     def _profile_default(self):
         if BaseIPythonApplication.initialized():
             # an IPython app *might* be running, try to get its profile
             try:
                 return BaseIPythonApplication.instance().profile
             except (AttributeError, MultipleInstanceError):
                 # could be a *different* subclass of config.Application,
                 # which would raise one of these two errors.
                 return u'default'
         else:
             return u'default'
 
 
     _outstanding_dict = Instance('collections.defaultdict', (set,))
     _ids = List()
     _connected=Bool(False)
     _ssh=Bool(False)
     _context = Instance('zmq.Context')
     _config = Dict()
     _engines=Instance(util.ReverseDict, (), {})
     # _hub_socket=Instance('zmq.Socket')
     _query_socket=Instance('zmq.Socket')
     _control_socket=Instance('zmq.Socket')
     _iopub_socket=Instance('zmq.Socket')
     _notification_socket=Instance('zmq.Socket')
     _mux_socket=Instance('zmq.Socket')
     _task_socket=Instance('zmq.Socket')
     _task_scheme=Unicode()
     _closed = False
     _ignored_control_replies=Integer(0)
     _ignored_hub_replies=Integer(0)
 
     def __new__(self, *args, **kw):
         # don't raise on positional args
         return HasTraits.__new__(self, **kw)
 
     def __init__(self, url_file=None, profile=None, profile_dir=None, ipython_dir=None,
             context=None, debug=False,
             sshserver=None, sshkey=None, password=None, paramiko=None,
             timeout=10, cluster_id=None, **extra_args
             ):
         if profile:
             super(Client, self).__init__(debug=debug, profile=profile)
         else:
             super(Client, self).__init__(debug=debug)
         if context is None:
             context = zmq.Context.instance()
         self._context = context
         self._stop_spinning = Event()
         
         if 'url_or_file' in extra_args:
             url_file = extra_args['url_or_file']
             warnings.warn("url_or_file arg no longer supported, use url_file", DeprecationWarning)
         
         if url_file and util.is_url(url_file):
             raise ValueError("single urls cannot be specified, url-files must be used.")
 
         self._setup_profile_dir(self.profile, profile_dir, ipython_dir)
         
         if self._cd is not None:
             if url_file is None:
                 if not cluster_id:
                     client_json = 'ipcontroller-client.json'
                 else:
                     client_json = 'ipcontroller-%s-client.json' % cluster_id
                 url_file = pjoin(self._cd.security_dir, client_json)
         if url_file is None:
             raise ValueError(
                 "I can't find enough information to connect to a hub!"
                 " Please specify at least one of url_file or profile."
             )
         
         with open(url_file) as f:
             cfg = json.load(f)
         
         self._task_scheme = cfg['task_scheme']
 
         # sync defaults from args, json:
         if sshserver:
             cfg['ssh'] = sshserver
 
         location = cfg.setdefault('location', None)
         
         proto,addr = cfg['interface'].split('://')
         addr = util.disambiguate_ip_address(addr, location)
         cfg['interface'] = "%s://%s" % (proto, addr)
         
         # turn interface,port into full urls:
         for key in ('control', 'task', 'mux', 'iopub', 'notification', 'registration'):
             cfg[key] = cfg['interface'] + ':%i' % cfg[key]
         
         url = cfg['registration']
         
         if location is not None and addr == localhost():
             # location specified, and connection is expected to be local
             if not is_local_ip(location) and not sshserver:
                 # load ssh from JSON *only* if the controller is not on
                 # this machine
                 sshserver=cfg['ssh']
             if not is_local_ip(location) and not sshserver:
                 # warn if no ssh specified, but SSH is probably needed
                 # This is only a warning, because the most likely cause
                 # is a local Controller on a laptop whose IP is dynamic
                 warnings.warn("""
             Controller appears to be listening on localhost, but not on this machine.
             If this is true, you should specify Client(...,sshserver='you@%s')
             or instruct your controller to listen on an external IP."""%location,
                 RuntimeWarning)
         elif not sshserver:
             # otherwise sync with cfg
             sshserver = cfg['ssh']
 
         self._config = cfg
 
         self._ssh = bool(sshserver or sshkey or password)
         if self._ssh and sshserver is None:
             # default to ssh via localhost
             sshserver = addr
         if self._ssh and password is None:
             if tunnel.try_passwordless_ssh(sshserver, sshkey, paramiko):
                 password=False
             else:
                 password = getpass("SSH Password for %s: "%sshserver)
         ssh_kwargs = dict(keyfile=sshkey, password=password, paramiko=paramiko)
 
         # configure and construct the session
         try:
             extra_args['packer'] = cfg['pack']
             extra_args['unpacker'] = cfg['unpack']
             extra_args['key'] = cast_bytes(cfg['key'])
             extra_args['signature_scheme'] = cfg['signature_scheme']
         except KeyError as exc:
             msg = '\n'.join([
                 "Connection file is invalid (missing '{}'), possibly from an old version of IPython.",
                 "If you are reusing connection files, remove them and start ipcontroller again."
             ])
             raise ValueError(msg.format(exc.message))
         
         self.session = Session(**extra_args)
 
         self._query_socket = self._context.socket(zmq.DEALER)
 
         if self._ssh:
             tunnel.tunnel_connection(self._query_socket, cfg['registration'], sshserver, **ssh_kwargs)
         else:
             self._query_socket.connect(cfg['registration'])
 
         self.session.debug = self.debug
 
         self._notification_handlers = {'registration_notification' : self._register_engine,
                                     'unregistration_notification' : self._unregister_engine,
                                     'shutdown_notification' : lambda msg: self.close(),
                                     }
         self._queue_handlers = {'execute_reply' : self._handle_execute_reply,
                                 'apply_reply' : self._handle_apply_reply}
         
         try:
             self._connect(sshserver, ssh_kwargs, timeout)
         except:
             self.close(linger=0)
             raise
         
         # last step: setup magics, if we are in IPython:
         
         try:
             ip = get_ipython()
         except NameError:
             return
         else:
             if 'px' not in ip.magics_manager.magics:
                 # in IPython but we are the first Client.
                 # activate a default view for parallel magics.
                 self.activate()
 
     def __del__(self):
         """cleanup sockets, but _not_ context."""
         self.close()
 
     def _setup_profile_dir(self, profile, profile_dir, ipython_dir):
         if ipython_dir is None:
             ipython_dir = get_ipython_dir()
         if profile_dir is not None:
             try:
                 self._cd = ProfileDir.find_profile_dir(profile_dir)
                 return
             except ProfileDirError:
                 pass
         elif profile is not None:
             try:
                 self._cd = ProfileDir.find_profile_dir_by_name(
                     ipython_dir, profile)
                 return
             except ProfileDirError:
                 pass
         self._cd = None
 
     def _update_engines(self, engines):
         """Update our engines dict and _ids from a dict of the form: {id:uuid}."""
         for k,v in iteritems(engines):
             eid = int(k)
             if eid not in self._engines:
                 self._ids.append(eid)
             self._engines[eid] = v
         self._ids = sorted(self._ids)
         if sorted(self._engines.keys()) != list(range(len(self._engines))) and \
                         self._task_scheme == 'pure' and self._task_socket:
             self._stop_scheduling_tasks()
 
     def _stop_scheduling_tasks(self):
         """Stop scheduling tasks because an engine has been unregistered
         from a pure ZMQ scheduler.
         """
         self._task_socket.close()
         self._task_socket = None
         msg = "An engine has been unregistered, and we are using pure " +\
               "ZMQ task scheduling.  Task farming will be disabled."
         if self.outstanding:
             msg += " If you were running tasks when this happened, " +\
                    "some `outstanding` msg_ids may never resolve."
         warnings.warn(msg, RuntimeWarning)
 
     def _build_targets(self, targets):
         """Turn valid target IDs or 'all' into two lists:
         (int_ids, uuids).
         """
         if not self._ids:
             # flush notification socket if no engines yet, just in case
             if not self.ids:
                 raise error.NoEnginesRegistered("Can't build targets without any engines")
 
         if targets is None:
             targets = self._ids
         elif isinstance(targets, string_types):
             if targets.lower() == 'all':
                 targets = self._ids
             else:
                 raise TypeError("%r not valid str target, must be 'all'"%(targets))
         elif isinstance(targets, int):
             if targets < 0:
                 targets = self.ids[targets]
             if targets not in self._ids:
                 raise IndexError("No such engine: %i"%targets)
             targets = [targets]
 
         if isinstance(targets, slice):
             indices = list(range(len(self._ids))[targets])
             ids = self.ids
             targets = [ ids[i] for i in indices ]
 
         if not isinstance(targets, (tuple, list, xrange)):
             raise TypeError("targets by int/slice/collection of ints only, not %s"%(type(targets)))
 
         return [cast_bytes(self._engines[t]) for t in targets], list(targets)
 
     def _connect(self, sshserver, ssh_kwargs, timeout):
         """setup all our socket connections to the cluster. This is called from
         __init__."""
 
         # Maybe allow reconnecting?
         if self._connected:
             return
         self._connected=True
 
         def connect_socket(s, url):
             if self._ssh:
                 return tunnel.tunnel_connection(s, url, sshserver, **ssh_kwargs)
             else:
                 return s.connect(url)
 
         self.session.send(self._query_socket, 'connection_request')
         # use Poller because zmq.select has wrong units in pyzmq 2.1.7
         poller = zmq.Poller()
         poller.register(self._query_socket, zmq.POLLIN)
         # poll expects milliseconds, timeout is seconds
         evts = poller.poll(timeout*1000)
         if not evts:
             raise error.TimeoutError("Hub connection request timed out")
         idents,msg = self.session.recv(self._query_socket,mode=0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         # self._config['registration'] = dict(content)
         cfg = self._config
         if content['status'] == 'ok':
             self._mux_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._mux_socket, cfg['mux'])
 
             self._task_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._task_socket, cfg['task'])
 
             self._notification_socket = self._context.socket(zmq.SUB)
             self._notification_socket.setsockopt(zmq.SUBSCRIBE, b'')
             connect_socket(self._notification_socket, cfg['notification'])
 
             self._control_socket = self._context.socket(zmq.DEALER)
             connect_socket(self._control_socket, cfg['control'])
 
             self._iopub_socket = self._context.socket(zmq.SUB)
             self._iopub_socket.setsockopt(zmq.SUBSCRIBE, b'')
             connect_socket(self._iopub_socket, cfg['iopub'])
 
             self._update_engines(dict(content['engines']))
         else:
             self._connected = False
             raise Exception("Failed to connect!")
 
     #--------------------------------------------------------------------------
     # handlers and callbacks for incoming messages
     #--------------------------------------------------------------------------
 
     def _unwrap_exception(self, content):
         """unwrap exception, and remap engine_id to int."""
         e = error.unwrap_exception(content)
         # print e.traceback
         if e.engine_info:
             e_uuid = e.engine_info['engine_uuid']
             eid = self._engines[e_uuid]
             e.engine_info['engine_id'] = eid
         return e
 
     def _extract_metadata(self, msg):
         header = msg['header']
         parent = msg['parent_header']
         msg_meta = msg['metadata']
         content = msg['content']
         md = {'msg_id' : parent['msg_id'],
               'received' : datetime.now(),
               'engine_uuid' : msg_meta.get('engine', None),
               'follow' : msg_meta.get('follow', []),
               'after' : msg_meta.get('after', []),
               'status' : content['status'],
             }
 
         if md['engine_uuid'] is not None:
             md['engine_id'] = self._engines.get(md['engine_uuid'], None)
 
         if 'date' in parent:
             md['submitted'] = parent['date']
         if 'started' in msg_meta:
-            md['started'] = msg_meta['started']
+            md['started'] = parse_date(msg_meta['started'])
         if 'date' in header:
             md['completed'] = header['date']
         return md
 
     def _register_engine(self, msg):
         """Register a new engine, and update our connection info."""
         content = msg['content']
         eid = content['id']
         d = {eid : content['uuid']}
         self._update_engines(d)
 
     def _unregister_engine(self, msg):
         """Unregister an engine that has died."""
         content = msg['content']
         eid = int(content['id'])
         if eid in self._ids:
             self._ids.remove(eid)
             uuid = self._engines.pop(eid)
 
             self._handle_stranded_msgs(eid, uuid)
 
         if self._task_socket and self._task_scheme == 'pure':
             self._stop_scheduling_tasks()
 
     def _handle_stranded_msgs(self, eid, uuid):
         """Handle messages known to be on an engine when the engine unregisters.
 
         It is possible that this will fire prematurely - that is, an engine will
         go down after completing a result, and the client will be notified
         of the unregistration and later receive the successful result.
         """
 
         outstanding = self._outstanding_dict[uuid]
 
         for msg_id in list(outstanding):
             if msg_id in self.results:
                 # we already
                 continue
             try:
                 raise error.EngineError("Engine %r died while running task %r"%(eid, msg_id))
             except:
                 content = error.wrap_exception()
             # build a fake message:
             msg = self.session.msg('apply_reply', content=content)
             msg['parent_header']['msg_id'] = msg_id
             msg['metadata']['engine'] = uuid
             self._handle_apply_reply(msg)
 
     def _handle_execute_reply(self, msg):
         """Save the reply to an execute_request into our results.
 
         execute messages are never actually used. apply is used instead.
         """
 
         parent = msg['parent_header']
         msg_id = parent['msg_id']
         if msg_id not in self.outstanding:
             if msg_id in self.history:
                 print("got stale result: %s"%msg_id)
             else:
                 print("got unknown result: %s"%msg_id)
         else:
             self.outstanding.remove(msg_id)
 
         content = msg['content']
         header = msg['header']
 
         # construct metadata:
         md = self.metadata[msg_id]
         md.update(self._extract_metadata(msg))
         # is this redundant?
         self.metadata[msg_id] = md
         
         e_outstanding = self._outstanding_dict[md['engine_uuid']]
         if msg_id in e_outstanding:
             e_outstanding.remove(msg_id)
 
         # construct result:
         if content['status'] == 'ok':
             self.results[msg_id] = ExecuteReply(msg_id, content, md)
         elif content['status'] == 'aborted':
             self.results[msg_id] = error.TaskAborted(msg_id)
         elif content['status'] == 'resubmitted':
             # TODO: handle resubmission
             pass
         else:
             self.results[msg_id] = self._unwrap_exception(content)
 
     def _handle_apply_reply(self, msg):
         """Save the reply to an apply_request into our results."""
         parent = msg['parent_header']
         msg_id = parent['msg_id']
         if msg_id not in self.outstanding:
             if msg_id in self.history:
                 print("got stale result: %s"%msg_id)
                 print(self.results[msg_id])
                 print(msg)
             else:
                 print("got unknown result: %s"%msg_id)
         else:
             self.outstanding.remove(msg_id)
         content = msg['content']
         header = msg['header']
 
         # construct metadata:
         md = self.metadata[msg_id]
         md.update(self._extract_metadata(msg))
         # is this redundant?
         self.metadata[msg_id] = md
 
         e_outstanding = self._outstanding_dict[md['engine_uuid']]
         if msg_id in e_outstanding:
             e_outstanding.remove(msg_id)
 
         # construct result:
         if content['status'] == 'ok':
             self.results[msg_id] = serialize.unserialize_object(msg['buffers'])[0]
         elif content['status'] == 'aborted':
             self.results[msg_id] = error.TaskAborted(msg_id)
         elif content['status'] == 'resubmitted':
             # TODO: handle resubmission
             pass
         else:
             self.results[msg_id] = self._unwrap_exception(content)
 
     def _flush_notifications(self):
         """Flush notifications of engine registrations waiting
         in ZMQ queue."""
         idents,msg = self.session.recv(self._notification_socket, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             msg_type = msg['header']['msg_type']
             handler = self._notification_handlers.get(msg_type, None)
             if handler is None:
                 raise Exception("Unhandled message type: %s" % msg_type)
             else:
                 handler(msg)
             idents,msg = self.session.recv(self._notification_socket, mode=zmq.NOBLOCK)
 
     def _flush_results(self, sock):
         """Flush task or queue results waiting in ZMQ queue."""
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             msg_type = msg['header']['msg_type']
             handler = self._queue_handlers.get(msg_type, None)
             if handler is None:
                 raise Exception("Unhandled message type: %s" % msg_type)
             else:
                 handler(msg)
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     def _flush_control(self, sock):
         """Flush replies from the control channel waiting
         in the ZMQ queue.
 
         Currently: ignore them."""
         if self._ignored_control_replies <= 0:
             return
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             self._ignored_control_replies -= 1
             if self.debug:
                 pprint(msg)
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     def _flush_ignored_control(self):
         """flush ignored control replies"""
         while self._ignored_control_replies > 0:
             self.session.recv(self._control_socket)
             self._ignored_control_replies -= 1
 
     def _flush_ignored_hub_replies(self):
         ident,msg = self.session.recv(self._query_socket, mode=zmq.NOBLOCK)
         while msg is not None:
             ident,msg = self.session.recv(self._query_socket, mode=zmq.NOBLOCK)
 
     def _flush_iopub(self, sock):
         """Flush replies from the iopub channel waiting
         in the ZMQ queue.
         """
         idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
         while msg is not None:
             if self.debug:
                 pprint(msg)
             parent = msg['parent_header']
             # ignore IOPub messages with no parent.
             # Caused by print statements or warnings from before the first execution.
             if not parent:
                 idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
                 continue
             msg_id = parent['msg_id']
             content = msg['content']
             header = msg['header']
             msg_type = msg['header']['msg_type']
 
             # init metadata:
             md = self.metadata[msg_id]
 
             if msg_type == 'stream':
                 name = content['name']
                 s = md[name] or ''
                 md[name] = s + content['data']
             elif msg_type == 'pyerr':
                 md.update({'pyerr' : self._unwrap_exception(content)})
             elif msg_type == 'pyin':
                 md.update({'pyin' : content['code']})
             elif msg_type == 'display_data':
                 md['outputs'].append(content)
             elif msg_type == 'pyout':
                 md['pyout'] = content
             elif msg_type == 'data_message':
                 data, remainder = serialize.unserialize_object(msg['buffers'])
                 md['data'].update(data)
             elif msg_type == 'status':
                 # idle message comes after all outputs
                 if content['execution_state'] == 'idle':
                     md['outputs_ready'] = True
             else:
                 # unhandled msg_type (status, etc.)
                 pass
 
             # reduntant?
             self.metadata[msg_id] = md
 
             idents,msg = self.session.recv(sock, mode=zmq.NOBLOCK)
 
     #--------------------------------------------------------------------------
     # len, getitem
     #--------------------------------------------------------------------------
 
     def __len__(self):
         """len(client) returns # of engines."""
         return len(self.ids)
 
     def __getitem__(self, key):
         """index access returns DirectView multiplexer objects
 
         Must be int, slice, or list/tuple/xrange of ints"""
         if not isinstance(key, (int, slice, tuple, list, xrange)):
             raise TypeError("key by int/slice/iterable of ints only, not %s"%(type(key)))
         else:
             return self.direct_view(key)
 
     #--------------------------------------------------------------------------
     # Begin public methods
     #--------------------------------------------------------------------------
 
     @property
     def ids(self):
         """Always up-to-date ids property."""
         self._flush_notifications()
         # always copy:
         return list(self._ids)
 
     def activate(self, targets='all', suffix=''):
         """Create a DirectView and register it with IPython magics
         
         Defines the magics `%px, %autopx, %pxresult, %%px`
         
         Parameters
         ----------
         
         targets: int, list of ints, or 'all'
             The engines on which the view's magics will run
         suffix: str [default: '']
             The suffix, if any, for the magics.  This allows you to have
             multiple views associated with parallel magics at the same time.
             
             e.g. ``rc.activate(targets=0, suffix='0')`` will give you
             the magics ``%px0``, ``%pxresult0``, etc. for running magics just
             on engine 0.
         """
         view = self.direct_view(targets)
         view.block = True
         view.activate(suffix)
         return view
 
     def close(self, linger=None):
         """Close my zmq Sockets
         
         If `linger`, set the zmq LINGER socket option,
         which allows discarding of messages.
         """
         if self._closed:
             return
         self.stop_spin_thread()
         snames = [ trait for trait in self.trait_names() if trait.endswith("socket") ]
         for name in snames:
             socket = getattr(self, name)
             if socket is not None and not socket.closed:
                 if linger is not None:
                     socket.close(linger=linger)
                 else:
                     socket.close()
         self._closed = True
 
     def _spin_every(self, interval=1):
         """target func for use in spin_thread"""
         while True:
             if self._stop_spinning.is_set():
                 return
             time.sleep(interval)
             self.spin()
 
     def spin_thread(self, interval=1):
         """call Client.spin() in a background thread on some regular interval
         
         This helps ensure that messages don't pile up too much in the zmq queue
         while you are working on other things, or just leaving an idle terminal.
         
         It also helps limit potential padding of the `received` timestamp
         on AsyncResult objects, used for timings.
         
         Parameters
         ----------
         
         interval : float, optional
             The interval on which to spin the client in the background thread
             (simply passed to time.sleep).
         
         Notes
         -----
         
         For precision timing, you may want to use this method to put a bound
         on the jitter (in seconds) in `received` timestamps used
         in AsyncResult.wall_time.
         
         """
         if self._spin_thread is not None:
             self.stop_spin_thread()
         self._stop_spinning.clear()
         self._spin_thread = Thread(target=self._spin_every, args=(interval,))
         self._spin_thread.daemon = True
         self._spin_thread.start()
     
     def stop_spin_thread(self):
         """stop background spin_thread, if any"""
         if self._spin_thread is not None:
             self._stop_spinning.set()
             self._spin_thread.join()
             self._spin_thread = None
 
     def spin(self):
         """Flush any registration notifications and execution results
         waiting in the ZMQ queue.
         """
         if self._notification_socket:
             self._flush_notifications()
         if self._iopub_socket:
             self._flush_iopub(self._iopub_socket)
         if self._mux_socket:
             self._flush_results(self._mux_socket)
         if self._task_socket:
             self._flush_results(self._task_socket)
         if self._control_socket:
             self._flush_control(self._control_socket)
         if self._query_socket:
             self._flush_ignored_hub_replies()
 
     def wait(self, jobs=None, timeout=-1):
         """waits on one or more `jobs`, for up to `timeout` seconds.
 
         Parameters
         ----------
 
         jobs : int, str, or list of ints and/or strs, or one or more AsyncResult objects
                 ints are indices to self.history
                 strs are msg_ids
                 default: wait on all outstanding messages
         timeout : float
                 a time in seconds, after which to give up.
                 default is -1, which means no timeout
 
         Returns
         -------
 
         True : when all msg_ids are done
         False : timeout reached, some msg_ids still outstanding
         """
         tic = time.time()
         if jobs is None:
             theids = self.outstanding
         else:
             if isinstance(jobs, string_types + (int, AsyncResult)):
                 jobs = [jobs]
             theids = set()
             for job in jobs:
                 if isinstance(job, int):
                     # index access
                     job = self.history[job]
                 elif isinstance(job, AsyncResult):
                     theids.update(job.msg_ids)
                     continue
                 theids.add(job)
         if not theids.intersection(self.outstanding):
             return True
         self.spin()
         while theids.intersection(self.outstanding):
             if timeout >= 0 and ( time.time()-tic ) > timeout:
                 break
             time.sleep(1e-3)
             self.spin()
         return len(theids.intersection(self.outstanding)) == 0
 
     #--------------------------------------------------------------------------
     # Control methods
     #--------------------------------------------------------------------------
 
     @spin_first
     def clear(self, targets=None, block=None):
         """Clear the namespace in target(s)."""
         block = self.block if block is None else block
         targets = self._build_targets(targets)[0]
         for t in targets:
             self.session.send(self._control_socket, 'clear_request', content={}, ident=t)
         error = False
         if block:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket,0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
         if error:
             raise error
 
 
     @spin_first
     def abort(self, jobs=None, targets=None, block=None):
         """Abort specific jobs from the execution queues of target(s).
 
         This is a mechanism to prevent jobs that have already been submitted
         from executing.
 
         Parameters
         ----------
 
         jobs : msg_id, list of msg_ids, or AsyncResult
             The jobs to be aborted
             
             If unspecified/None: abort all outstanding jobs.
 
         """
         block = self.block if block is None else block
         jobs = jobs if jobs is not None else list(self.outstanding)
         targets = self._build_targets(targets)[0]
         
         msg_ids = []
         if isinstance(jobs, string_types + (AsyncResult,)):
             jobs = [jobs]
         bad_ids = [obj for obj in jobs if not isinstance(obj, string_types + (AsyncResult,))]
         if bad_ids:
             raise TypeError("Invalid msg_id type %r, expected str or AsyncResult"%bad_ids[0])
         for j in jobs:
             if isinstance(j, AsyncResult):
                 msg_ids.extend(j.msg_ids)
             else:
                 msg_ids.append(j)
         content = dict(msg_ids=msg_ids)
         for t in targets:
             self.session.send(self._control_socket, 'abort_request',
                     content=content, ident=t)
         error = False
         if block:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket,0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
         if error:
             raise error
 
     @spin_first
     def shutdown(self, targets='all', restart=False, hub=False, block=None):
         """Terminates one or more engine processes, optionally including the hub.
         
         Parameters
         ----------
         
         targets: list of ints or 'all' [default: all]
             Which engines to shutdown.
         hub: bool [default: False]
             Whether to include the Hub.  hub=True implies targets='all'.
         block: bool [default: self.block]
             Whether to wait for clean shutdown replies or not.
         restart: bool [default: False]
             NOT IMPLEMENTED
             whether to restart engines after shutting them down.
         """
         from IPython.parallel.error import NoEnginesRegistered
         if restart:
             raise NotImplementedError("Engine restart is not yet implemented")
         
         block = self.block if block is None else block
         if hub:
             targets = 'all'
         try:
             targets = self._build_targets(targets)[0]
         except NoEnginesRegistered:
             targets = []
         for t in targets:
             self.session.send(self._control_socket, 'shutdown_request',
                         content={'restart':restart},ident=t)
         error = False
         if block or hub:
             self._flush_ignored_control()
             for i in range(len(targets)):
                 idents,msg = self.session.recv(self._control_socket, 0)
                 if self.debug:
                     pprint(msg)
                 if msg['content']['status'] != 'ok':
                     error = self._unwrap_exception(msg['content'])
         else:
             self._ignored_control_replies += len(targets)
 
         if hub:
             time.sleep(0.25)
             self.session.send(self._query_socket, 'shutdown_request')
             idents,msg = self.session.recv(self._query_socket, 0)
             if self.debug:
                 pprint(msg)
             if msg['content']['status'] != 'ok':
                 error = self._unwrap_exception(msg['content'])
 
         if error:
             raise error
 
     #--------------------------------------------------------------------------
     # Execution related methods
     #--------------------------------------------------------------------------
 
     def _maybe_raise(self, result):
         """wrapper for maybe raising an exception if apply failed."""
         if isinstance(result, error.RemoteError):
             raise result
 
         return result
 
     def send_apply_request(self, socket, f, args=None, kwargs=None, metadata=None, track=False,
                             ident=None):
         """construct and send an apply message via a socket.
 
         This is the principal method with which all engine execution is performed by views.
         """
 
         if self._closed:
             raise RuntimeError("Client cannot be used after its sockets have been closed")
         
         # defaults:
         args = args if args is not None else []
         kwargs = kwargs if kwargs is not None else {}
         metadata = metadata if metadata is not None else {}
 
         # validate arguments
         if not callable(f) and not isinstance(f, Reference):
             raise TypeError("f must be callable, not %s"%type(f))
         if not isinstance(args, (tuple, list)):
             raise TypeError("args must be tuple or list, not %s"%type(args))
         if not isinstance(kwargs, dict):
             raise TypeError("kwargs must be dict, not %s"%type(kwargs))
         if not isinstance(metadata, dict):
             raise TypeError("metadata must be dict, not %s"%type(metadata))
 
         bufs = serialize.pack_apply_message(f, args, kwargs,
             buffer_threshold=self.session.buffer_threshold,
             item_threshold=self.session.item_threshold,
         )
 
         msg = self.session.send(socket, "apply_request", buffers=bufs, ident=ident,
                             metadata=metadata, track=track)
 
         msg_id = msg['header']['msg_id']
         self.outstanding.add(msg_id)
         if ident:
             # possibly routed to a specific engine
             if isinstance(ident, list):
                 ident = ident[-1]
             if ident in self._engines.values():
                 # save for later, in case of engine death
                 self._outstanding_dict[ident].add(msg_id)
         self.history.append(msg_id)
         self.metadata[msg_id]['submitted'] = datetime.now()
 
         return msg
 
     def send_execute_request(self, socket, code, silent=True, metadata=None, ident=None):
         """construct and send an execute request via a socket.
 
         """
 
         if self._closed:
             raise RuntimeError("Client cannot be used after its sockets have been closed")
         
         # defaults:
         metadata = metadata if metadata is not None else {}
 
         # validate arguments
         if not isinstance(code, string_types):
             raise TypeError("code must be text, not %s" % type(code))
         if not isinstance(metadata, dict):
             raise TypeError("metadata must be dict, not %s" % type(metadata))
         
         content = dict(code=code, silent=bool(silent), user_variables=[], user_expressions={})
 
 
         msg = self.session.send(socket, "execute_request", content=content, ident=ident,
                             metadata=metadata)
 
         msg_id = msg['header']['msg_id']
         self.outstanding.add(msg_id)
         if ident:
             # possibly routed to a specific engine
             if isinstance(ident, list):
                 ident = ident[-1]
             if ident in self._engines.values():
                 # save for later, in case of engine death
                 self._outstanding_dict[ident].add(msg_id)
         self.history.append(msg_id)
         self.metadata[msg_id]['submitted'] = datetime.now()
 
         return msg
 
     #--------------------------------------------------------------------------
     # construct a View object
     #--------------------------------------------------------------------------
 
     def load_balanced_view(self, targets=None):
         """construct a DirectView object.
 
         If no arguments are specified, create a LoadBalancedView
         using all engines.
 
         Parameters
         ----------
 
         targets: list,slice,int,etc. [default: use all engines]
             The subset of engines across which to load-balance
         """
         if targets == 'all':
             targets = None
         if targets is not None:
             targets = self._build_targets(targets)[1]
         return LoadBalancedView(client=self, socket=self._task_socket, targets=targets)
 
     def direct_view(self, targets='all'):
         """construct a DirectView object.
 
         If no targets are specified, create a DirectView using all engines.
         
         rc.direct_view('all') is distinguished from rc[:] in that 'all' will
         evaluate the target engines at each execution, whereas rc[:] will connect to
         all *current* engines, and that list will not change.
         
         That is, 'all' will always use all engines, whereas rc[:] will not use
         engines added after the DirectView is constructed.
 
         Parameters
         ----------
 
         targets: list,slice,int,etc. [default: use all engines]
             The engines to use for the View
         """
         single = isinstance(targets, int)
         # allow 'all' to be lazily evaluated at each execution
         if targets != 'all':
             targets = self._build_targets(targets)[1]
         if single:
             targets = targets[0]
         return DirectView(client=self, socket=self._mux_socket, targets=targets)
 
     #--------------------------------------------------------------------------
     # Query methods
     #--------------------------------------------------------------------------
 
     @spin_first
     def get_result(self, indices_or_msg_ids=None, block=None):
         """Retrieve a result by msg_id or history index, wrapped in an AsyncResult object.
 
         If the client already has the results, no request to the Hub will be made.
 
         This is a convenient way to construct AsyncResult objects, which are wrappers
         that include metadata about execution, and allow for awaiting results that
         were not submitted by this Client.
 
         It can also be a convenient way to retrieve the metadata associated with
         blocking execution, since it always retrieves
 
         Examples
         --------
         ::
 
             In [10]: r = client.apply()
 
         Parameters
         ----------
 
         indices_or_msg_ids : integer history index, str msg_id, or list of either
             The indices or msg_ids of indices to be retrieved
 
         block : bool
             Whether to wait for the result to be done
 
         Returns
         -------
 
         AsyncResult
             A single AsyncResult object will always be returned.
 
         AsyncHubResult
             A subclass of AsyncResult that retrieves results from the Hub
 
         """
         block = self.block if block is None else block
         if indices_or_msg_ids is None:
             indices_or_msg_ids = -1
         
         single_result = False
         if not isinstance(indices_or_msg_ids, (list,tuple)):
             indices_or_msg_ids = [indices_or_msg_ids]
             single_result = True
 
         theids = []
         for id in indices_or_msg_ids:
             if isinstance(id, int):
                 id = self.history[id]
             if not isinstance(id, string_types):
                 raise TypeError("indices must be str or int, not %r"%id)
             theids.append(id)
 
         local_ids = [msg_id for msg_id in theids if (msg_id in self.outstanding or msg_id in self.results)]
         remote_ids = [msg_id for msg_id in theids if msg_id not in local_ids]
         
         # given single msg_id initially, get_result shot get the result itself,
         # not a length-one list
         if single_result:
             theids = theids[0]
 
         if remote_ids:
             ar = AsyncHubResult(self, msg_ids=theids)
         else:
             ar = AsyncResult(self, msg_ids=theids)
 
         if block:
             ar.wait()
 
         return ar
 
     @spin_first
     def resubmit(self, indices_or_msg_ids=None, metadata=None, block=None):
         """Resubmit one or more tasks.
 
         in-flight tasks may not be resubmitted.
 
         Parameters
         ----------
 
         indices_or_msg_ids : integer history index, str msg_id, or list of either
             The indices or msg_ids of indices to be retrieved
 
         block : bool
             Whether to wait for the result to be done
 
         Returns
         -------
 
         AsyncHubResult
             A subclass of AsyncResult that retrieves results from the Hub
 
         """
         block = self.block if block is None else block
         if indices_or_msg_ids is None:
             indices_or_msg_ids = -1
 
         if not isinstance(indices_or_msg_ids, (list,tuple)):
             indices_or_msg_ids = [indices_or_msg_ids]
 
         theids = []
         for id in indices_or_msg_ids:
             if isinstance(id, int):
                 id = self.history[id]
             if not isinstance(id, string_types):
                 raise TypeError("indices must be str or int, not %r"%id)
             theids.append(id)
 
         content = dict(msg_ids = theids)
 
         self.session.send(self._query_socket, 'resubmit_request', content)
 
         zmq.select([self._query_socket], [], [])
         idents,msg = self.session.recv(self._query_socket, zmq.NOBLOCK)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
         mapping = content['resubmitted']
         new_ids = [ mapping[msg_id] for msg_id in theids ]
 
         ar = AsyncHubResult(self, msg_ids=new_ids)
 
         if block:
             ar.wait()
 
         return ar
 
     @spin_first
     def result_status(self, msg_ids, status_only=True):
         """Check on the status of the result(s) of the apply request with `msg_ids`.
 
         If status_only is False, then the actual results will be retrieved, else
         only the status of the results will be checked.
 
         Parameters
         ----------
 
         msg_ids : list of msg_ids
             if int:
                 Passed as index to self.history for convenience.
         status_only : bool (default: True)
             if False:
                 Retrieve the actual results of completed tasks.
 
         Returns
         -------
 
         results : dict
             There will always be the keys 'pending' and 'completed', which will
             be lists of msg_ids that are incomplete or complete. If `status_only`
             is False, then completed results will be keyed by their `msg_id`.
         """
         if not isinstance(msg_ids, (list,tuple)):
             msg_ids = [msg_ids]
 
         theids = []
         for msg_id in msg_ids:
             if isinstance(msg_id, int):
                 msg_id = self.history[msg_id]
             if not isinstance(msg_id, string_types):
                 raise TypeError("msg_ids must be str, not %r"%msg_id)
             theids.append(msg_id)
 
         completed = []
         local_results = {}
 
         # comment this block out to temporarily disable local shortcut:
         for msg_id in theids:
             if msg_id in self.results:
                 completed.append(msg_id)
                 local_results[msg_id] = self.results[msg_id]
                 theids.remove(msg_id)
 
         if theids: # some not locally cached
             content = dict(msg_ids=theids, status_only=status_only)
             msg = self.session.send(self._query_socket, "result_request", content=content)
             zmq.select([self._query_socket], [], [])
             idents,msg = self.session.recv(self._query_socket, zmq.NOBLOCK)
             if self.debug:
                 pprint(msg)
             content = msg['content']
             if content['status'] != 'ok':
                 raise self._unwrap_exception(content)
             buffers = msg['buffers']
         else:
             content = dict(completed=[],pending=[])
 
         content['completed'].extend(completed)
 
         if status_only:
             return content
 
         failures = []
         # load cached results into result:
         content.update(local_results)
 
         # update cache with results:
         for msg_id in sorted(theids):
             if msg_id in content['completed']:
                 rec = content[msg_id]
-                parent = rec['header']
-                header = rec['result_header']
+                parent = extract_dates(rec['header'])
+                header = extract_dates(rec['result_header'])
                 rcontent = rec['result_content']
                 iodict = rec['io']
                 if isinstance(rcontent, str):
                     rcontent = self.session.unpack(rcontent)
 
                 md = self.metadata[msg_id]
                 md_msg = dict(
                     content=rcontent,
                     parent_header=parent,
                     header=header,
                     metadata=rec['result_metadata'],
                 )
                 md.update(self._extract_metadata(md_msg))
                 if rec.get('received'):
-                    md['received'] = rec['received']
+                    md['received'] = parse_date(rec['received'])
                 md.update(iodict)
                 
                 if rcontent['status'] == 'ok':
                     if header['msg_type'] == 'apply_reply':
                         res,buffers = serialize.unserialize_object(buffers)
                     elif header['msg_type'] == 'execute_reply':
                         res = ExecuteReply(msg_id, rcontent, md)
                     else:
                         raise KeyError("unhandled msg type: %r" % header['msg_type'])
                 else:
                     res = self._unwrap_exception(rcontent)
                     failures.append(res)
 
                 self.results[msg_id] = res
                 content[msg_id] = res
 
         if len(theids) == 1 and failures:
             raise failures[0]
 
         error.collect_exceptions(failures, "result_status")
         return content
 
     @spin_first
     def queue_status(self, targets='all', verbose=False):
         """Fetch the status of engine queues.
 
         Parameters
         ----------
 
         targets : int/str/list of ints/strs
                 the engines whose states are to be queried.
                 default : all
         verbose : bool
                 Whether to return lengths only, or lists of ids for each element
         """
         if targets == 'all':
             # allow 'all' to be evaluated on the engine
             engine_ids = None
         else:
             engine_ids = self._build_targets(targets)[1]
         content = dict(targets=engine_ids, verbose=verbose)
         self.session.send(self._query_socket, "queue_request", content=content)
         idents,msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         status = content.pop('status')
         if status != 'ok':
             raise self._unwrap_exception(content)
         content = rekey(content)
         if isinstance(targets, int):
             return content[targets]
         else:
             return content
 
     def _build_msgids_from_target(self, targets=None):
         """Build a list of msg_ids from the list of engine targets"""
         if not targets: # needed as _build_targets otherwise uses all engines
             return []
         target_ids = self._build_targets(targets)[0] 
         return [md_id for md_id in self.metadata if self.metadata[md_id]["engine_uuid"] in target_ids]
     
     def _build_msgids_from_jobs(self, jobs=None):
         """Build a list of msg_ids from "jobs" """
         if not jobs:
             return []
         msg_ids = []
         if isinstance(jobs, string_types + (AsyncResult,)):
             jobs = [jobs]
         bad_ids = [obj for obj in jobs if not isinstance(obj, string_types + (AsyncResult,))]
         if bad_ids:
             raise TypeError("Invalid msg_id type %r, expected str or AsyncResult"%bad_ids[0])
         for j in jobs:
             if isinstance(j, AsyncResult):
                 msg_ids.extend(j.msg_ids)
             else:
                 msg_ids.append(j)
         return msg_ids        
         
     def purge_local_results(self, jobs=[], targets=[]):
         """Clears the client caches of results and frees such memory.
         
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_local_results('all')` to scrub everything from the Clients's db.
 
         The client must have no outstanding tasks before purging the caches.
         Raises `AssertionError` if there are still outstanding tasks.
 
         After this call all `AsyncResults` are invalid and should be discarded.
 
         If you must "reget" the results, you can still do so by using
         `client.get_result(msg_id)` or `client.get_result(asyncresult)`. This will
         redownload the results from the hub if they are still available
         (i.e `client.purge_hub_results(...)` has not been called.        
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be purged.
         targets : int/str/list of ints/strs
                 The targets, by int_id, whose entire results are to be purged.
 
                 default : None
         """
         assert not self.outstanding, "Can't purge a client with outstanding tasks!"
         
         if not targets and not jobs:
             raise ValueError("Must specify at least one of `targets` and `jobs`")
                 
         if jobs == 'all':
             self.results.clear()
             self.metadata.clear()
             return
         else:
             msg_ids = []
             msg_ids.extend(self._build_msgids_from_target(targets))
             msg_ids.extend(self._build_msgids_from_jobs(jobs))
             for mid in msg_ids:
                 self.results.pop(mid)
                 self.metadata.pop(mid)
 
 
     @spin_first
     def purge_hub_results(self, jobs=[], targets=[]):
         """Tell the Hub to forget results.
 
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_results('all')` to scrub everything from the Hub's db.
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be forgotten.
         targets : int/str/list of ints/strs
                 The targets, by int_id, whose entire history is to be purged.
 
                 default : None
         """
         if not targets and not jobs:
             raise ValueError("Must specify at least one of `targets` and `jobs`")
         if targets:
             targets = self._build_targets(targets)[1]
 
         # construct msg_ids from jobs
         if jobs == 'all':
             msg_ids = jobs
         else:
             msg_ids = self._build_msgids_from_jobs(jobs)
 
         content = dict(engine_ids=targets, msg_ids=msg_ids)
         self.session.send(self._query_socket, "purge_request", content=content)
         idents, msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
 
     def purge_results(self,  jobs=[], targets=[]):
         """Clears the cached results from both the hub and the local client
                 
         Individual results can be purged by msg_id, or the entire
         history of specific targets can be purged.
 
         Use `purge_results('all')` to scrub every cached result from both the Hub's and 
         the Client's db.
         
         Equivalent to calling both `purge_hub_results()` and `purge_client_results()` with 
         the same arguments.
 
         Parameters
         ----------
 
         jobs : str or list of str or AsyncResult objects
                 the msg_ids whose results should be forgotten.
         targets : int/str/list of ints/strs
                 The targets, by int_id, whose entire history is to be purged.
 
                 default : None
         """
         self.purge_local_results(jobs=jobs, targets=targets)
         self.purge_hub_results(jobs=jobs, targets=targets)
 
     def purge_everything(self):
         """Clears all content from previous Tasks from both the hub and the local client
         
         In addition to calling `purge_results("all")` it also deletes the history and 
         other bookkeeping lists.        
         """
         self.purge_results("all")
         self.history = []
         self.session.digest_history.clear()
 
     @spin_first
     def hub_history(self):
         """Get the Hub's history
 
         Just like the Client, the Hub has a history, which is a list of msg_ids.
         This will contain the history of all clients, and, depending on configuration,
         may contain history across multiple cluster sessions.
 
         Any msg_id returned here is a valid argument to `get_result`.
 
         Returns
         -------
 
         msg_ids : list of strs
                 list of all msg_ids, ordered by task submission time.
         """
 
         self.session.send(self._query_socket, "history_request", content={})
         idents, msg = self.session.recv(self._query_socket, 0)
 
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
         else:
             return content['history']
 
     @spin_first
     def db_query(self, query, keys=None):
         """Query the Hub's TaskRecord database
 
         This will return a list of task record dicts that match `query`
 
         Parameters
         ----------
 
         query : mongodb query dict
             The search dict. See mongodb query docs for details.
         keys : list of strs [optional]
             The subset of keys to be returned.  The default is to fetch everything but buffers.
             'msg_id' will *always* be included.
         """
         if isinstance(keys, string_types):
             keys = [keys]
         content = dict(query=query, keys=keys)
         self.session.send(self._query_socket, "db_request", content=content)
         idents, msg = self.session.recv(self._query_socket, 0)
         if self.debug:
             pprint(msg)
         content = msg['content']
         if content['status'] != 'ok':
             raise self._unwrap_exception(content)
 
         records = content['records']
 
         buffer_lens = content['buffer_lens']
         result_buffer_lens = content['result_buffer_lens']
         buffers = msg['buffers']
         has_bufs = buffer_lens is not None
         has_rbufs = result_buffer_lens is not None
         for i,rec in enumerate(records):
+            # unpack datetime objects
+            for hkey in ('header', 'result_header'):
+                if hkey in rec:
+                    rec[hkey] = extract_dates(rec[hkey])
+            for dtkey in ('submitted', 'started', 'completed', 'received'):
+                if dtkey in rec:
+                    rec[dtkey] = parse_date(rec[dtkey])
             # relink buffers
             if has_bufs:
                 blen = buffer_lens[i]
                 rec['buffers'], buffers = buffers[:blen],buffers[blen:]
             if has_rbufs:
                 blen = result_buffer_lens[i]
                 rec['result_buffers'], buffers = buffers[:blen],buffers[blen:]
 
         return records
 
 __all__ = [ 'Client' ]

IPython/parallel/controller/hub.py

@@ -1,1421 +1,1422
 """The IPython Controller Hub with 0MQ
 This is the master object that handles connections from engines and clients,
 and monitors traffic through the various queues.
 
 Authors:
 
 * Min RK
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 from __future__ import print_function
 
 import json
 import os
 import sys
 import time
 from datetime import datetime
 
 import zmq
 from zmq.eventloop import ioloop
 from zmq.eventloop.zmqstream import ZMQStream
 
 # internal:
 from IPython.utils.importstring import import_item
+from IPython.utils.jsonutil import extract_dates
 from IPython.utils.localinterfaces import localhost
 from IPython.utils.py3compat import cast_bytes, unicode_type, iteritems
 from IPython.utils.traitlets import (
         HasTraits, Instance, Integer, Unicode, Dict, Set, Tuple, CBytes, DottedObjectName
         )
 
 from IPython.parallel import error, util
 from IPython.parallel.factory import RegistrationFactory
 
 from IPython.kernel.zmq.session import SessionFactory
 
 from .heartmonitor import HeartMonitor
 
 #-----------------------------------------------------------------------------
 # Code
 #-----------------------------------------------------------------------------
 
 def _passer(*args, **kwargs):
     return
 
 def _printer(*args, **kwargs):
     print (args)
     print (kwargs)
 
 def empty_record():
     """Return an empty dict with all record keys."""
     return {
         'msg_id' : None,
         'header' : None,
         'metadata' : None,
         'content': None,
         'buffers': None,
         'submitted': None,
         'client_uuid' : None,
         'engine_uuid' : None,
         'started': None,
         'completed': None,
         'resubmitted': None,
         'received': None,
         'result_header' : None,
         'result_metadata' : None,
         'result_content' : None,
         'result_buffers' : None,
         'queue' : None,
         'pyin' : None,
         'pyout': None,
         'pyerr': None,
         'stdout': '',
         'stderr': '',
     }
 
 def init_record(msg):
     """Initialize a TaskRecord based on a request."""
     header = msg['header']
     return {
         'msg_id' : header['msg_id'],
         'header' : header,
         'content': msg['content'],
         'metadata': msg['metadata'],
         'buffers': msg['buffers'],
         'submitted': header['date'],
         'client_uuid' : None,
         'engine_uuid' : None,
         'started': None,
         'completed': None,
         'resubmitted': None,
         'received': None,
         'result_header' : None,
         'result_metadata': None,
         'result_content' : None,
         'result_buffers' : None,
         'queue' : None,
         'pyin' : None,
         'pyout': None,
         'pyerr': None,
         'stdout': '',
         'stderr': '',
     }
 
 
 class EngineConnector(HasTraits):
     """A simple object for accessing the various zmq connections of an object.
     Attributes are:
     id (int): engine ID
     uuid (unicode): engine UUID
     pending: set of msg_ids
     stallback: DelayedCallback for stalled registration
     """
     
     id = Integer(0)
     uuid = Unicode()
     pending = Set()
     stallback = Instance(ioloop.DelayedCallback)
 
 
 _db_shortcuts = {
     'sqlitedb' : 'IPython.parallel.controller.sqlitedb.SQLiteDB',
     'mongodb'  : 'IPython.parallel.controller.mongodb.MongoDB',
     'dictdb'   : 'IPython.parallel.controller.dictdb.DictDB',
     'nodb'     : 'IPython.parallel.controller.dictdb.NoDB',
 }
 
 class HubFactory(RegistrationFactory):
     """The Configurable for setting up a Hub."""
 
     # port-pairs for monitoredqueues:
     hb = Tuple(Integer,Integer,config=True,
         help="""PUB/ROUTER Port pair for Engine heartbeats""")
     def _hb_default(self):
         return tuple(util.select_random_ports(2))
 
     mux = Tuple(Integer,Integer,config=True,
         help="""Client/Engine Port pair for MUX queue""")
 
     def _mux_default(self):
         return tuple(util.select_random_ports(2))
 
     task = Tuple(Integer,Integer,config=True,
         help="""Client/Engine Port pair for Task queue""")
     def _task_default(self):
         return tuple(util.select_random_ports(2))
 
     control = Tuple(Integer,Integer,config=True,
         help="""Client/Engine Port pair for Control queue""")
 
     def _control_default(self):
         return tuple(util.select_random_ports(2))
 
     iopub = Tuple(Integer,Integer,config=True,
         help="""Client/Engine Port pair for IOPub relay""")
 
     def _iopub_default(self):
         return tuple(util.select_random_ports(2))
 
     # single ports:
     mon_port = Integer(config=True,
         help="""Monitor (SUB) port for queue traffic""")
 
     def _mon_port_default(self):
         return util.select_random_ports(1)[0]
 
     notifier_port = Integer(config=True,
         help="""PUB port for sending engine status notifications""")
 
     def _notifier_port_default(self):
         return util.select_random_ports(1)[0]
 
     engine_ip = Unicode(config=True,
         help="IP on which to listen for engine connections. [default: loopback]")
     def _engine_ip_default(self):
         return localhost()
     engine_transport = Unicode('tcp', config=True,
         help="0MQ transport for engine connections. [default: tcp]")
 
     client_ip = Unicode(config=True,
         help="IP on which to listen for client connections. [default: loopback]")
     client_transport = Unicode('tcp', config=True,
         help="0MQ transport for client connections. [default : tcp]")
 
     monitor_ip = Unicode(config=True,
         help="IP on which to listen for monitor messages. [default: loopback]")
     monitor_transport = Unicode('tcp', config=True,
         help="0MQ transport for monitor messages. [default : tcp]")
 
     _client_ip_default = _monitor_ip_default = _engine_ip_default
 
 
     monitor_url = Unicode('')
 
     db_class = DottedObjectName('NoDB',
         config=True, help="""The class to use for the DB backend
         
         Options include:
         
         SQLiteDB: SQLite
         MongoDB : use MongoDB
         DictDB  : in-memory storage (fastest, but be mindful of memory growth of the Hub)
         NoDB    : disable database altogether (default)
         
         """)
 
     # not configurable
     db = Instance('IPython.parallel.controller.dictdb.BaseDB')
     heartmonitor = Instance('IPython.parallel.controller.heartmonitor.HeartMonitor')
 
     def _ip_changed(self, name, old, new):
         self.engine_ip = new
         self.client_ip = new
         self.monitor_ip = new
         self._update_monitor_url()
 
     def _update_monitor_url(self):
         self.monitor_url = "%s://%s:%i" % (self.monitor_transport, self.monitor_ip, self.mon_port)
 
     def _transport_changed(self, name, old, new):
         self.engine_transport = new
         self.client_transport = new
         self.monitor_transport = new
         self._update_monitor_url()
 
     def __init__(self, **kwargs):
         super(HubFactory, self).__init__(**kwargs)
         self._update_monitor_url()
 
 
     def construct(self):
         self.init_hub()
 
     def start(self):
         self.heartmonitor.start()
         self.log.info("Heartmonitor started")
 
     def client_url(self, channel):
         """return full zmq url for a named client channel"""
         return "%s://%s:%i" % (self.client_transport, self.client_ip, self.client_info[channel])
     
     def engine_url(self, channel):
         """return full zmq url for a named engine channel"""
         return "%s://%s:%i" % (self.engine_transport, self.engine_ip, self.engine_info[channel])
     
     def init_hub(self):
         """construct Hub object"""
 
         ctx = self.context
         loop = self.loop
         if 'TaskScheduler.scheme_name' in self.config:
             scheme = self.config.TaskScheduler.scheme_name
         else:
             from .scheduler import TaskScheduler
             scheme = TaskScheduler.scheme_name.get_default_value()
         
         # build connection dicts
         engine = self.engine_info = {
             'interface'     : "%s://%s" % (self.engine_transport, self.engine_ip),
             'registration'  : self.regport,
             'control'       : self.control[1],
             'mux'           : self.mux[1],
             'hb_ping'       : self.hb[0],
             'hb_pong'       : self.hb[1],
             'task'          : self.task[1],
             'iopub'         : self.iopub[1],
             }
 
         client = self.client_info = {
             'interface'     : "%s://%s" % (self.client_transport, self.client_ip),
             'registration'  : self.regport,
             'control'       : self.control[0],
             'mux'           : self.mux[0],
             'task'          : self.task[0],
             'task_scheme'   : scheme,
             'iopub'         : self.iopub[0],
             'notification'  : self.notifier_port,
             }
         
         self.log.debug("Hub engine addrs: %s", self.engine_info)
         self.log.debug("Hub client addrs: %s", self.client_info)
         
         # Registrar socket
         q = ZMQStream(ctx.socket(zmq.ROUTER), loop)
         util.set_hwm(q, 0)
         q.bind(self.client_url('registration'))
         self.log.info("Hub listening on %s for registration.", self.client_url('registration'))
         if self.client_ip != self.engine_ip:
             q.bind(self.engine_url('registration'))
             self.log.info("Hub listening on %s for registration.", self.engine_url('registration'))
 
         ### Engine connections ###
 
         # heartbeat
         hpub = ctx.socket(zmq.PUB)
         hpub.bind(self.engine_url('hb_ping'))
         hrep = ctx.socket(zmq.ROUTER)
         util.set_hwm(hrep, 0)
         hrep.bind(self.engine_url('hb_pong'))
         self.heartmonitor = HeartMonitor(loop=loop, parent=self, log=self.log,
                                 pingstream=ZMQStream(hpub,loop),
                                 pongstream=ZMQStream(hrep,loop)
                             )
 
         ### Client connections ###
         
         # Notifier socket
         n = ZMQStream(ctx.socket(zmq.PUB), loop)
         n.bind(self.client_url('notification'))
 
         ### build and launch the queues ###
 
         # monitor socket
         sub = ctx.socket(zmq.SUB)
         sub.setsockopt(zmq.SUBSCRIBE, b"")
         sub.bind(self.monitor_url)
         sub.bind('inproc://monitor')
         sub = ZMQStream(sub, loop)
 
         # connect the db
         db_class = _db_shortcuts.get(self.db_class.lower(), self.db_class)
         self.log.info('Hub using DB backend: %r', (db_class.split('.')[-1]))
         self.db = import_item(str(db_class))(session=self.session.session,
                                             parent=self, log=self.log)
         time.sleep(.25)
 
         # resubmit stream
         r = ZMQStream(ctx.socket(zmq.DEALER), loop)
         url = util.disambiguate_url(self.client_url('task'))
         r.connect(url)
 
         self.hub = Hub(loop=loop, session=self.session, monitor=sub, heartmonitor=self.heartmonitor,
                 query=q, notifier=n, resubmit=r, db=self.db,
                 engine_info=self.engine_info, client_info=self.client_info,
                 log=self.log)
 
 
 class Hub(SessionFactory):
     """The IPython Controller Hub with 0MQ connections
 
     Parameters
     ==========
     loop: zmq IOLoop instance
     session: Session object
     <removed> context: zmq context for creating new connections (?)
     queue: ZMQStream for monitoring the command queue (SUB)
     query: ZMQStream for engine registration and client queries requests (ROUTER)
     heartbeat: HeartMonitor object checking the pulse of the engines
     notifier: ZMQStream for broadcasting engine registration changes (PUB)
     db: connection to db for out of memory logging of commands
                 NotImplemented
     engine_info: dict of zmq connection information for engines to connect
                 to the queues.
     client_info: dict of zmq connection information for engines to connect
                 to the queues.
     """
     
     engine_state_file = Unicode()
     
     # internal data structures:
     ids=Set() # engine IDs
     keytable=Dict()
     by_ident=Dict()
     engines=Dict()
     clients=Dict()
     hearts=Dict()
     pending=Set()
     queues=Dict()  # pending msg_ids keyed by engine_id
     tasks=Dict() # pending msg_ids submitted as tasks, keyed by client_id
     completed=Dict() # completed msg_ids keyed by engine_id
     all_completed=Set() # completed msg_ids keyed by engine_id
     dead_engines=Set() # completed msg_ids keyed by engine_id
     unassigned=Set() # set of task msg_ds not yet assigned a destination
     incoming_registrations=Dict()
     registration_timeout=Integer()
     _idcounter=Integer(0)
 
     # objects from constructor:
     query=Instance(ZMQStream)
     monitor=Instance(ZMQStream)
     notifier=Instance(ZMQStream)
     resubmit=Instance(ZMQStream)
     heartmonitor=Instance(HeartMonitor)
     db=Instance(object)
     client_info=Dict()
     engine_info=Dict()
 
 
     def __init__(self, **kwargs):
         """
         # universal:
         loop: IOLoop for creating future connections
         session: streamsession for sending serialized data
         # engine:
         queue: ZMQStream for monitoring queue messages
         query: ZMQStream for engine+client registration and client requests
         heartbeat: HeartMonitor object for tracking engines
         # extra:
         db: ZMQStream for db connection (NotImplemented)
         engine_info: zmq address/protocol dict for engine connections
         client_info: zmq address/protocol dict for client connections
         """
 
         super(Hub, self).__init__(**kwargs)
         self.registration_timeout = max(10000, 5*self.heartmonitor.period)
 
         # register our callbacks
         self.query.on_recv(self.dispatch_query)
         self.monitor.on_recv(self.dispatch_monitor_traffic)
 
         self.heartmonitor.add_heart_failure_handler(self.handle_heart_failure)
         self.heartmonitor.add_new_heart_handler(self.handle_new_heart)
 
         self.monitor_handlers = {b'in' : self.save_queue_request,
                                 b'out': self.save_queue_result,
                                 b'intask': self.save_task_request,
                                 b'outtask': self.save_task_result,
                                 b'tracktask': self.save_task_destination,
                                 b'incontrol': _passer,
                                 b'outcontrol': _passer,
                                 b'iopub': self.save_iopub_message,
         }
 
         self.query_handlers = {'queue_request': self.queue_status,
                                 'result_request': self.get_results,
                                 'history_request': self.get_history,
                                 'db_request': self.db_query,
                                 'purge_request': self.purge_results,
                                 'load_request': self.check_load,
                                 'resubmit_request': self.resubmit_task,
                                 'shutdown_request': self.shutdown_request,
                                 'registration_request' : self.register_engine,
                                 'unregistration_request' : self.unregister_engine,
                                 'connection_request': self.connection_request,
         }
 
         # ignore resubmit replies
         self.resubmit.on_recv(lambda msg: None, copy=False)
 
         self.log.info("hub::created hub")
     
     @property
     def _next_id(self):
         """gemerate a new ID.
 
         No longer reuse old ids, just count from 0."""
         newid = self._idcounter
         self._idcounter += 1
         return newid
         # newid = 0
         # incoming = [id[0] for id in itervalues(self.incoming_registrations)]
         # # print newid, self.ids, self.incoming_registrations
         # while newid in self.ids or newid in incoming:
         #     newid += 1
         # return newid
     
     #-----------------------------------------------------------------------------
     # message validation
     #-----------------------------------------------------------------------------
 
     def _validate_targets(self, targets):
         """turn any valid targets argument into a list of integer ids"""
         if targets is None:
             # default to all
             return self.ids
 
         if isinstance(targets, (int,str,unicode_type)):
             # only one target specified
             targets = [targets]
         _targets = []
         for t in targets:
             # map raw identities to ids
             if isinstance(t, (str,unicode_type)):
                 t = self.by_ident.get(cast_bytes(t), t)
             _targets.append(t)
         targets = _targets
         bad_targets = [ t for t in targets if t not in self.ids ]
         if bad_targets:
             raise IndexError("No Such Engine: %r" % bad_targets)
         if not targets:
             raise IndexError("No Engines Registered")
         return targets
 
     #-----------------------------------------------------------------------------
     # dispatch methods (1 per stream)
     #-----------------------------------------------------------------------------
 
 
     @util.log_errors
     def dispatch_monitor_traffic(self, msg):
         """all ME and Task queue messages come through here, as well as
         IOPub traffic."""
         self.log.debug("monitor traffic: %r", msg[0])
         switch = msg[0]
         try:
             idents, msg = self.session.feed_identities(msg[1:])
         except ValueError:
             idents=[]
         if not idents:
             self.log.error("Monitor message without topic: %r", msg)
             return
         handler = self.monitor_handlers.get(switch, None)
         if handler is not None:
             handler(idents, msg)
         else:
             self.log.error("Unrecognized monitor topic: %r", switch)
 
 
     @util.log_errors
     def dispatch_query(self, msg):
         """Route registration requests and queries from clients."""
         try:
             idents, msg = self.session.feed_identities(msg)
         except ValueError:
             idents = []
         if not idents:
             self.log.error("Bad Query Message: %r", msg)
             return
         client_id = idents[0]
         try:
             msg = self.session.unserialize(msg, content=True)
         except Exception:
             content = error.wrap_exception()
             self.log.error("Bad Query Message: %r", msg, exc_info=True)
             self.session.send(self.query, "hub_error", ident=client_id,
                     content=content)
             return
         # print client_id, header, parent, content
         #switch on message type:
         msg_type = msg['header']['msg_type']
         self.log.info("client::client %r requested %r", client_id, msg_type)
         handler = self.query_handlers.get(msg_type, None)
         try:
             assert handler is not None, "Bad Message Type: %r" % msg_type
         except:
             content = error.wrap_exception()
             self.log.error("Bad Message Type: %r", msg_type, exc_info=True)
             self.session.send(self.query, "hub_error", ident=client_id,
                     content=content)
             return
 
         else:
             handler(idents, msg)
 
     def dispatch_db(self, msg):
         """"""
         raise NotImplementedError
 
     #---------------------------------------------------------------------------
     # handler methods (1 per event)
     #---------------------------------------------------------------------------
 
     #----------------------- Heartbeat --------------------------------------
 
     def handle_new_heart(self, heart):
         """handler to attach to heartbeater.
         Called when a new heart starts to beat.
         Triggers completion of registration."""
         self.log.debug("heartbeat::handle_new_heart(%r)", heart)
         if heart not in self.incoming_registrations:
             self.log.info("heartbeat::ignoring new heart: %r", heart)
         else:
             self.finish_registration(heart)
 
 
     def handle_heart_failure(self, heart):
         """handler to attach to heartbeater.
         called when a previously registered heart fails to respond to beat request.
         triggers unregistration"""
         self.log.debug("heartbeat::handle_heart_failure(%r)", heart)
         eid = self.hearts.get(heart, None)
         uuid = self.engines[eid].uuid
         if eid is None or self.keytable[eid] in self.dead_engines:
             self.log.info("heartbeat::ignoring heart failure %r (not an engine or already dead)", heart)
         else:
             self.unregister_engine(heart, dict(content=dict(id=eid, queue=uuid)))
 
     #----------------------- MUX Queue Traffic ------------------------------
 
     def save_queue_request(self, idents, msg):
         if len(idents) < 2:
             self.log.error("invalid identity prefix: %r", idents)
             return
         queue_id, client_id = idents[:2]
         try:
             msg = self.session.unserialize(msg)
         except Exception:
             self.log.error("queue::client %r sent invalid message to %r: %r", client_id, queue_id, msg, exc_info=True)
             return
 
         eid = self.by_ident.get(queue_id, None)
         if eid is None:
             self.log.error("queue::target %r not registered", queue_id)
             self.log.debug("queue::    valid are: %r", self.by_ident.keys())
             return
         record = init_record(msg)
         msg_id = record['msg_id']
         self.log.info("queue::client %r submitted request %r to %s", client_id, msg_id, eid)
         # Unicode in records
         record['engine_uuid'] = queue_id.decode('ascii')
         record['client_uuid'] = msg['header']['session']
         record['queue'] = 'mux'
 
         try:
             # it's posible iopub arrived first:
             existing = self.db.get_record(msg_id)
             for key,evalue in iteritems(existing):
                 rvalue = record.get(key, None)
                 if evalue and rvalue and evalue != rvalue:
                     self.log.warn("conflicting initial state for record: %r:%r <%r> %r", msg_id, rvalue, key, evalue)
                 elif evalue and not rvalue:
                     record[key] = evalue
             try:
                 self.db.update_record(msg_id, record)
             except Exception:
                 self.log.error("DB Error updating record %r", msg_id, exc_info=True)
         except KeyError:
             try:
                 self.db.add_record(msg_id, record)
             except Exception:
                 self.log.error("DB Error adding record %r", msg_id, exc_info=True)
 
 
         self.pending.add(msg_id)
         self.queues[eid].append(msg_id)
 
     def save_queue_result(self, idents, msg):
         if len(idents) < 2:
             self.log.error("invalid identity prefix: %r", idents)
             return
 
         client_id, queue_id = idents[:2]
         try:
             msg = self.session.unserialize(msg)
         except Exception:
             self.log.error("queue::engine %r sent invalid message to %r: %r",
                     queue_id, client_id, msg, exc_info=True)
             return
 
         eid = self.by_ident.get(queue_id, None)
         if eid is None:
             self.log.error("queue::unknown engine %r is sending a reply: ", queue_id)
             return
 
         parent = msg['parent_header']
         if not parent:
             return
         msg_id = parent['msg_id']
         if msg_id in self.pending:
             self.pending.remove(msg_id)
             self.all_completed.add(msg_id)
             self.queues[eid].remove(msg_id)
             self.completed[eid].append(msg_id)
             self.log.info("queue::request %r completed on %s", msg_id, eid)
         elif msg_id not in self.all_completed:
             # it could be a result from a dead engine that died before delivering the
             # result
             self.log.warn("queue:: unknown msg finished %r", msg_id)
             return
         # update record anyway, because the unregistration could have been premature
         rheader = msg['header']
         md = msg['metadata']
         completed = rheader['date']
         started = md.get('started', None)
         result = {
             'result_header' : rheader,
             'result_metadata': md,
             'result_content': msg['content'],
             'received': datetime.now(),
             'started' : started,
             'completed' : completed
         }
 
         result['result_buffers'] = msg['buffers']
         try:
             self.db.update_record(msg_id, result)
         except Exception:
             self.log.error("DB Error updating record %r", msg_id, exc_info=True)
 
 
     #--------------------- Task Queue Traffic ------------------------------
 
     def save_task_request(self, idents, msg):
         """Save the submission of a task."""
         client_id = idents[0]
 
         try:
             msg = self.session.unserialize(msg)
         except Exception:
             self.log.error("task::client %r sent invalid task message: %r",
                     client_id, msg, exc_info=True)
             return
         record = init_record(msg)
 
         record['client_uuid'] = msg['header']['session']
         record['queue'] = 'task'
         header = msg['header']
         msg_id = header['msg_id']
         self.pending.add(msg_id)
         self.unassigned.add(msg_id)
         try:
             # it's posible iopub arrived first:
             existing = self.db.get_record(msg_id)
             if existing['resubmitted']:
                 for key in ('submitted', 'client_uuid', 'buffers'):
                     # don't clobber these keys on resubmit
                     # submitted and client_uuid should be different
                     # and buffers might be big, and shouldn't have changed
                     record.pop(key)
                     # still check content,header which should not change
                     # but are not expensive to compare as buffers
 
             for key,evalue in iteritems(existing):
                 if key.endswith('buffers'):
                     # don't compare buffers
                     continue
                 rvalue = record.get(key, None)
                 if evalue and rvalue and evalue != rvalue:
                     self.log.warn("conflicting initial state for record: %r:%r <%r> %r", msg_id, rvalue, key, evalue)
                 elif evalue and not rvalue:
                     record[key] = evalue
             try:
                 self.db.update_record(msg_id, record)
             except Exception:
                 self.log.error("DB Error updating record %r", msg_id, exc_info=True)
         except KeyError:
             try:
                 self.db.add_record(msg_id, record)
             except Exception:
                 self.log.error("DB Error adding record %r", msg_id, exc_info=True)
         except Exception:
             self.log.error("DB Error saving task request %r", msg_id, exc_info=True)
 
     def save_task_result(self, idents, msg):
         """save the result of a completed task."""
         client_id = idents[0]
         try:
             msg = self.session.unserialize(msg)
         except Exception:
             self.log.error("task::invalid task result message send to %r: %r",
                     client_id, msg, exc_info=True)
             return
 
         parent = msg['parent_header']
         if not parent:
             # print msg
             self.log.warn("Task %r had no parent!", msg)
             return
         msg_id = parent['msg_id']
         if msg_id in self.unassigned:
             self.unassigned.remove(msg_id)
 
         header = msg['header']
         md = msg['metadata']
         engine_uuid = md.get('engine', u'')
         eid = self.by_ident.get(cast_bytes(engine_uuid), None)
         
         status = md.get('status', None)
 
         if msg_id in self.pending:
             self.log.info("task::task %r finished on %s", msg_id, eid)
             self.pending.remove(msg_id)
             self.all_completed.add(msg_id)
             if eid is not None:
                 if status != 'aborted':
                     self.completed[eid].append(msg_id)
                 if msg_id in self.tasks[eid]:
                     self.tasks[eid].remove(msg_id)
             completed = header['date']
             started = md.get('started', None)
             result = {
                 'result_header' : header,
                 'result_metadata': msg['metadata'],
                 'result_content': msg['content'],
                 'started' : started,
                 'completed' : completed,
                 'received' : datetime.now(),
                 'engine_uuid': engine_uuid,
             }
 
             result['result_buffers'] = msg['buffers']
             try:
                 self.db.update_record(msg_id, result)
             except Exception:
                 self.log.error("DB Error saving task request %r", msg_id, exc_info=True)
 
         else:
             self.log.debug("task::unknown task %r finished", msg_id)
 
     def save_task_destination(self, idents, msg):
         try:
             msg = self.session.unserialize(msg, content=True)
         except Exception:
             self.log.error("task::invalid task tracking message", exc_info=True)
             return
         content = msg['content']
         # print (content)
         msg_id = content['msg_id']
         engine_uuid = content['engine_id']
         eid = self.by_ident[cast_bytes(engine_uuid)]
 
         self.log.info("task::task %r arrived on %r", msg_id, eid)
         if msg_id in self.unassigned:
             self.unassigned.remove(msg_id)
         # else:
         #     self.log.debug("task::task %r not listed as MIA?!"%(msg_id))
 
         self.tasks[eid].append(msg_id)
         # self.pending[msg_id][1].update(received=datetime.now(),engine=(eid,engine_uuid))
         try:
             self.db.update_record(msg_id, dict(engine_uuid=engine_uuid))
         except Exception:
             self.log.error("DB Error saving task destination %r", msg_id, exc_info=True)
 
 
     def mia_task_request(self, idents, msg):
         raise NotImplementedError
         client_id = idents[0]
         # content = dict(mia=self.mia,status='ok')
         # self.session.send('mia_reply', content=content, idents=client_id)
 
 
     #--------------------- IOPub Traffic ------------------------------
 
     def save_iopub_message(self, topics, msg):
         """save an iopub message into the db"""
         # print (topics)
         try:
             msg = self.session.unserialize(msg, content=True)
         except Exception:
             self.log.error("iopub::invalid IOPub message", exc_info=True)
             return
 
         parent = msg['parent_header']
         if not parent:
             self.log.warn("iopub::IOPub message lacks parent: %r", msg)
             return
         msg_id = parent['msg_id']
         msg_type = msg['header']['msg_type']
         content = msg['content']
 
         # ensure msg_id is in db
         try:
             rec = self.db.get_record(msg_id)
         except KeyError:
             rec = empty_record()
             rec['msg_id'] = msg_id
             self.db.add_record(msg_id, rec)
         # stream
         d = {}
         if msg_type == 'stream':
             name = content['name']
             s = rec[name] or ''
             d[name] = s + content['data']
 
         elif msg_type == 'pyerr':
             d['pyerr'] = content
         elif msg_type == 'pyin':
             d['pyin'] = content['code']
         elif msg_type in ('display_data', 'pyout'):
             d[msg_type] = content
         elif msg_type == 'status':
             pass
         elif msg_type == 'data_pub':
             self.log.info("ignored data_pub message for %s" % msg_id)
         else:
             self.log.warn("unhandled iopub msg_type: %r", msg_type)
 
         if not d:
             return
 
         try:
             self.db.update_record(msg_id, d)
         except Exception:
             self.log.error("DB Error saving iopub message %r", msg_id, exc_info=True)
 
 
 
     #-------------------------------------------------------------------------
     # Registration requests
     #-------------------------------------------------------------------------
 
     def connection_request(self, client_id, msg):
         """Reply with connection addresses for clients."""
         self.log.info("client::client %r connected", client_id)
         content = dict(status='ok')
         jsonable = {}
         for k,v in iteritems(self.keytable):
             if v not in self.dead_engines:
                 jsonable[str(k)] = v
         content['engines'] = jsonable
         self.session.send(self.query, 'connection_reply', content, parent=msg, ident=client_id)
 
     def register_engine(self, reg, msg):
         """Register a new engine."""
         content = msg['content']
         try:
             uuid = content['uuid']
         except KeyError:
             self.log.error("registration::queue not specified", exc_info=True)
             return
 
         eid = self._next_id
 
         self.log.debug("registration::register_engine(%i, %r)", eid, uuid)
 
         content = dict(id=eid,status='ok',hb_period=self.heartmonitor.period)
         # check if requesting available IDs:
         if cast_bytes(uuid) in self.by_ident:
             try:
                 raise KeyError("uuid %r in use" % uuid)
             except:
                 content = error.wrap_exception()
                 self.log.error("uuid %r in use", uuid, exc_info=True)
         else:
             for h, ec in iteritems(self.incoming_registrations):
                 if uuid == h:
                     try:
                         raise KeyError("heart_id %r in use" % uuid)
                     except:
                         self.log.error("heart_id %r in use", uuid, exc_info=True)
                         content = error.wrap_exception()
                     break
                 elif uuid == ec.uuid:
                     try:
                         raise KeyError("uuid %r in use" % uuid)
                     except:
                         self.log.error("uuid %r in use", uuid, exc_info=True)
                         content = error.wrap_exception()
                     break
 
         msg = self.session.send(self.query, "registration_reply",
                 content=content,
                 ident=reg)
 
         heart = cast_bytes(uuid)
 
         if content['status'] == 'ok':
             if heart in self.heartmonitor.hearts:
                 # already beating
                 self.incoming_registrations[heart] = EngineConnector(id=eid,uuid=uuid)
                 self.finish_registration(heart)
             else:
                 purge = lambda : self._purge_stalled_registration(heart)
                 dc = ioloop.DelayedCallback(purge, self.registration_timeout, self.loop)
                 dc.start()
                 self.incoming_registrations[heart] = EngineConnector(id=eid,uuid=uuid,stallback=dc)
         else:
             self.log.error("registration::registration %i failed: %r", eid, content['evalue'])
         
         return eid
 
     def unregister_engine(self, ident, msg):
         """Unregister an engine that explicitly requested to leave."""
         try:
             eid = msg['content']['id']
         except:
             self.log.error("registration::bad engine id for unregistration: %r", ident, exc_info=True)
             return
         self.log.info("registration::unregister_engine(%r)", eid)
         # print (eid)
         uuid = self.keytable[eid]
         content=dict(id=eid, uuid=uuid)
         self.dead_engines.add(uuid)
         # self.ids.remove(eid)
         # uuid = self.keytable.pop(eid)
         #
         # ec = self.engines.pop(eid)
         # self.hearts.pop(ec.heartbeat)
         # self.by_ident.pop(ec.queue)
         # self.completed.pop(eid)
         handleit = lambda : self._handle_stranded_msgs(eid, uuid)
         dc = ioloop.DelayedCallback(handleit, self.registration_timeout, self.loop)
         dc.start()
         ############## TODO: HANDLE IT ################
         
         self._save_engine_state()
 
         if self.notifier:
             self.session.send(self.notifier, "unregistration_notification", content=content)
 
     def _handle_stranded_msgs(self, eid, uuid):
         """Handle messages known to be on an engine when the engine unregisters.
 
         It is possible that this will fire prematurely - that is, an engine will
         go down after completing a result, and the client will be notified
         that the result failed and later receive the actual result.
         """
 
         outstanding = self.queues[eid]
 
         for msg_id in outstanding:
             self.pending.remove(msg_id)
             self.all_completed.add(msg_id)
             try:
                 raise error.EngineError("Engine %r died while running task %r" % (eid, msg_id))
             except:
                 content = error.wrap_exception()
             # build a fake header:
             header = {}
             header['engine'] = uuid
             header['date'] = datetime.now()
             rec = dict(result_content=content, result_header=header, result_buffers=[])
             rec['completed'] = header['date']
             rec['engine_uuid'] = uuid
             try:
                 self.db.update_record(msg_id, rec)
             except Exception:
                 self.log.error("DB Error handling stranded msg %r", msg_id, exc_info=True)
 
 
     def finish_registration(self, heart):
         """Second half of engine registration, called after our HeartMonitor
         has received a beat from the Engine's Heart."""
         try:
             ec = self.incoming_registrations.pop(heart)
         except KeyError:
             self.log.error("registration::tried to finish nonexistant registration", exc_info=True)
             return
         self.log.info("registration::finished registering engine %i:%s", ec.id, ec.uuid)
         if ec.stallback is not None:
             ec.stallback.stop()
         eid = ec.id
         self.ids.add(eid)
         self.keytable[eid] = ec.uuid
         self.engines[eid] = ec
         self.by_ident[cast_bytes(ec.uuid)] = ec.id
         self.queues[eid] = list()
         self.tasks[eid] = list()
         self.completed[eid] = list()
         self.hearts[heart] = eid
         content = dict(id=eid, uuid=self.engines[eid].uuid)
         if self.notifier:
             self.session.send(self.notifier, "registration_notification", content=content)
         self.log.info("engine::Engine Connected: %i", eid)
         
         self._save_engine_state()
 
     def _purge_stalled_registration(self, heart):
         if heart in self.incoming_registrations:
             ec = self.incoming_registrations.pop(heart)
             self.log.info("registration::purging stalled registration: %i", ec.id)
         else:
             pass
 
     #-------------------------------------------------------------------------
     # Engine State
     #-------------------------------------------------------------------------
 
 
     def _cleanup_engine_state_file(self):
         """cleanup engine state mapping"""
         
         if os.path.exists(self.engine_state_file):
             self.log.debug("cleaning up engine state: %s", self.engine_state_file)
             try:
                 os.remove(self.engine_state_file)
             except IOError:
                 self.log.error("Couldn't cleanup file: %s", self.engine_state_file, exc_info=True)
 
 
     def _save_engine_state(self):
         """save engine mapping to JSON file"""
         if not self.engine_state_file:
             return
         self.log.debug("save engine state to %s" % self.engine_state_file)
         state = {}
         engines = {}
         for eid, ec in iteritems(self.engines):
             if ec.uuid not in self.dead_engines:
                 engines[eid] = ec.uuid
         
         state['engines'] = engines
         
         state['next_id'] = self._idcounter
         
         with open(self.engine_state_file, 'w') as f:
             json.dump(state, f)
 
 
     def _load_engine_state(self):
         """load engine mapping from JSON file"""
         if not os.path.exists(self.engine_state_file):
             return
         
         self.log.info("loading engine state from %s" % self.engine_state_file)
         
         with open(self.engine_state_file) as f:
             state = json.load(f)
         
         save_notifier = self.notifier
         self.notifier = None
         for eid, uuid in iteritems(state['engines']):
             heart = uuid.encode('ascii')
             # start with this heart as current and beating:
             self.heartmonitor.responses.add(heart)
             self.heartmonitor.hearts.add(heart)
             
             self.incoming_registrations[heart] = EngineConnector(id=int(eid), uuid=uuid)
             self.finish_registration(heart)
         
         self.notifier = save_notifier
         
         self._idcounter = state['next_id']
 
     #-------------------------------------------------------------------------
     # Client Requests
     #-------------------------------------------------------------------------
 
     def shutdown_request(self, client_id, msg):
         """handle shutdown request."""
         self.session.send(self.query, 'shutdown_reply', content={'status': 'ok'}, ident=client_id)
         # also notify other clients of shutdown
         self.session.send(self.notifier, 'shutdown_notice', content={'status': 'ok'})
         dc = ioloop.DelayedCallback(lambda : self._shutdown(), 1000, self.loop)
         dc.start()
 
     def _shutdown(self):
         self.log.info("hub::hub shutting down.")
         time.sleep(0.1)
         sys.exit(0)
 
 
     def check_load(self, client_id, msg):
         content = msg['content']
         try:
             targets = content['targets']
             targets = self._validate_targets(targets)
         except:
             content = error.wrap_exception()
             self.session.send(self.query, "hub_error",
                     content=content, ident=client_id)
             return
 
         content = dict(status='ok')
         # loads = {}
         for t in targets:
             content[bytes(t)] = len(self.queues[t])+len(self.tasks[t])
         self.session.send(self.query, "load_reply", content=content, ident=client_id)
 
 
     def queue_status(self, client_id, msg):
         """Return the Queue status of one or more targets.
         if verbose: return the msg_ids
         else: return len of each type.
         keys: queue (pending MUX jobs)
             tasks (pending Task jobs)
             completed (finished jobs from both queues)"""
         content = msg['content']
         targets = content['targets']
         try:
             targets = self._validate_targets(targets)
         except:
             content = error.wrap_exception()
             self.session.send(self.query, "hub_error",
                     content=content, ident=client_id)
             return
         verbose = content.get('verbose', False)
         content = dict(status='ok')
         for t in targets:
             queue = self.queues[t]
             completed = self.completed[t]
             tasks = self.tasks[t]
             if not verbose:
                 queue = len(queue)
                 completed = len(completed)
                 tasks = len(tasks)
             content[str(t)] = {'queue': queue, 'completed': completed , 'tasks': tasks}
         content['unassigned'] = list(self.unassigned) if verbose else len(self.unassigned)
         # print (content)
         self.session.send(self.query, "queue_reply", content=content, ident=client_id)
 
     def purge_results(self, client_id, msg):
         """Purge results from memory. This method is more valuable before we move
         to a DB based message storage mechanism."""
         content = msg['content']
         self.log.info("Dropping records with %s", content)
         msg_ids = content.get('msg_ids', [])
         reply = dict(status='ok')
         if msg_ids == 'all':
             try:
                 self.db.drop_matching_records(dict(completed={'$ne':None}))
             except Exception:
                 reply = error.wrap_exception()
         else:
             pending = [m for m in msg_ids if (m in self.pending)]
             if pending:
                 try:
                     raise IndexError("msg pending: %r" % pending[0])
                 except:
                     reply = error.wrap_exception()
             else:
                 try:
                     self.db.drop_matching_records(dict(msg_id={'$in':msg_ids}))
                 except Exception:
                     reply = error.wrap_exception()
 
             if reply['status'] == 'ok':
                 eids = content.get('engine_ids', [])
                 for eid in eids:
                     if eid not in self.engines:
                         try:
                             raise IndexError("No such engine: %i" % eid)
                         except:
                             reply = error.wrap_exception()
                         break
                     uid = self.engines[eid].uuid
                     try:
                         self.db.drop_matching_records(dict(engine_uuid=uid, completed={'$ne':None}))
                     except Exception:
                         reply = error.wrap_exception()
                         break
 
         self.session.send(self.query, 'purge_reply', content=reply, ident=client_id)
 
     def resubmit_task(self, client_id, msg):
         """Resubmit one or more tasks."""
         def finish(reply):
             self.session.send(self.query, 'resubmit_reply', content=reply, ident=client_id)
 
         content = msg['content']
         msg_ids = content['msg_ids']
         reply = dict(status='ok')
         try:
             records = self.db.find_records({'msg_id' : {'$in' : msg_ids}}, keys=[
                 'header', 'content', 'buffers'])
         except Exception:
             self.log.error('db::db error finding tasks to resubmit', exc_info=True)
             return finish(error.wrap_exception())
 
         # validate msg_ids
         found_ids = [ rec['msg_id'] for rec in records ]
         pending_ids = [ msg_id for msg_id in found_ids if msg_id in self.pending ]
         if len(records) > len(msg_ids):
             try:
                 raise RuntimeError("DB appears to be in an inconsistent state."
                     "More matching records were found than should exist")
             except Exception:
                 return finish(error.wrap_exception())
         elif len(records) < len(msg_ids):
             missing = [ m for m in msg_ids if m not in found_ids ]
             try:
                 raise KeyError("No such msg(s): %r" % missing)
             except KeyError:
                 return finish(error.wrap_exception())
         elif pending_ids:
             pass
             # no need to raise on resubmit of pending task, now that we
             # resubmit under new ID, but do we want to raise anyway?
             # msg_id = invalid_ids[0]
             # try:
             #     raise ValueError("Task(s) %r appears to be inflight" % )
             # except Exception:
             #     return finish(error.wrap_exception())
 
         # mapping of original IDs to resubmitted IDs
         resubmitted = {}
 
         # send the messages
         for rec in records:
             header = rec['header']
             msg = self.session.msg(header['msg_type'], parent=header)
             msg_id = msg['msg_id']
             msg['content'] = rec['content']
             
             # use the old header, but update msg_id and timestamp
             fresh = msg['header']
             header['msg_id'] = fresh['msg_id']
             header['date'] = fresh['date']
             msg['header'] = header
 
             self.session.send(self.resubmit, msg, buffers=rec['buffers'])
 
             resubmitted[rec['msg_id']] = msg_id
             self.pending.add(msg_id)
             msg['buffers'] = rec['buffers']
             try:
                 self.db.add_record(msg_id, init_record(msg))
             except Exception:
                 self.log.error("db::DB Error updating record: %s", msg_id, exc_info=True)
                 return finish(error.wrap_exception())
 
         finish(dict(status='ok', resubmitted=resubmitted))
         
         # store the new IDs in the Task DB
         for msg_id, resubmit_id in iteritems(resubmitted):
             try:
                 self.db.update_record(msg_id, {'resubmitted' : resubmit_id})
             except Exception:
                 self.log.error("db::DB Error updating record: %s", msg_id, exc_info=True)
 
 
     def _extract_record(self, rec):
         """decompose a TaskRecord dict into subsection of reply for get_result"""
         io_dict = {}
         for key in ('pyin', 'pyout', 'pyerr', 'stdout', 'stderr'):
                 io_dict[key] = rec[key]
         content = { 
             'header': rec['header'],
             'metadata': rec['metadata'],
             'result_metadata': rec['result_metadata'],
             'result_header' : rec['result_header'],
             'result_content': rec['result_content'],
             'received' : rec['received'],
             'io' : io_dict,
         }
         if rec['result_buffers']:
             buffers = list(map(bytes, rec['result_buffers']))
         else:
             buffers = []
 
         return content, buffers
 
     def get_results(self, client_id, msg):
         """Get the result of 1 or more messages."""
         content = msg['content']
         msg_ids = sorted(set(content['msg_ids']))
         statusonly = content.get('status_only', False)
         pending = []
         completed = []
         content = dict(status='ok')
         content['pending'] = pending
         content['completed'] = completed
         buffers = []
         if not statusonly:
             try:
                 matches = self.db.find_records(dict(msg_id={'$in':msg_ids}))
                 # turn match list into dict, for faster lookup
                 records = {}
                 for rec in matches:
                     records[rec['msg_id']] = rec
             except Exception:
                 content = error.wrap_exception()
                 self.session.send(self.query, "result_reply", content=content,
                                                     parent=msg, ident=client_id)
                 return
         else:
             records = {}
         for msg_id in msg_ids:
             if msg_id in self.pending:
                 pending.append(msg_id)
             elif msg_id in self.all_completed:
                 completed.append(msg_id)
                 if not statusonly:
                     c,bufs = self._extract_record(records[msg_id])
                     content[msg_id] = c
                     buffers.extend(bufs)
             elif msg_id in records:
                 if rec['completed']:
                     completed.append(msg_id)
                     c,bufs = self._extract_record(records[msg_id])
                     content[msg_id] = c
                     buffers.extend(bufs)
                 else:
                     pending.append(msg_id)
             else:
                 try:
                     raise KeyError('No such message: '+msg_id)
                 except:
                     content = error.wrap_exception()
                 break
         self.session.send(self.query, "result_reply", content=content,
                                             parent=msg, ident=client_id,
                                             buffers=buffers)
 
     def get_history(self, client_id, msg):
         """Get a list of all msg_ids in our DB records"""
         try:
             msg_ids = self.db.get_history()
         except Exception as e:
             content = error.wrap_exception()
         else:
             content = dict(status='ok', history=msg_ids)
 
         self.session.send(self.query, "history_reply", content=content,
                                             parent=msg, ident=client_id)
 
     def db_query(self, client_id, msg):
         """Perform a raw query on the task record database."""
         content = msg['content']
-        query = content.get('query', {})
+        query = extract_dates(content.get('query', {}))
         keys = content.get('keys', None)
         buffers = []
         empty = list()
         try:
             records = self.db.find_records(query, keys)
         except Exception as e:
             content = error.wrap_exception()
         else:
             # extract buffers from reply content:
             if keys is not None:
                 buffer_lens = [] if 'buffers' in keys else None
                 result_buffer_lens = [] if 'result_buffers' in keys else None
             else:
                 buffer_lens = None
                 result_buffer_lens = None
 
             for rec in records:
                 # buffers may be None, so double check
                 b = rec.pop('buffers', empty) or empty
                 if buffer_lens is not None:
                     buffer_lens.append(len(b))
                     buffers.extend(b)
                 rb = rec.pop('result_buffers', empty) or empty
                 if result_buffer_lens is not None:
                     result_buffer_lens.append(len(rb))
                     buffers.extend(rb)
             content = dict(status='ok', records=records, buffer_lens=buffer_lens,
                                     result_buffer_lens=result_buffer_lens)
         # self.log.debug (content)
         self.session.send(self.query, "db_reply", content=content,
                                             parent=msg, ident=client_id,
                                             buffers=buffers)
 

IPython/utils/jsonutil.py

@@ -1,229 +1,241
 """Utilities to manipulate JSON objects.
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING.txt, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 # stdlib
 import math
 import re
 import types
 from datetime import datetime
 
 try:
     # base64.encodestring is deprecated in Python 3.x
     from base64 import encodebytes
 except ImportError:
     # Python 2.x
     from base64 import encodestring as encodebytes
 
 from IPython.utils import py3compat
 from IPython.utils.py3compat import string_types, unicode_type, iteritems
 from IPython.utils.encoding import DEFAULT_ENCODING
 next_attr_name = '__next__' if py3compat.PY3 else 'next'
 
 #-----------------------------------------------------------------------------
 # Globals and constants
 #-----------------------------------------------------------------------------
 
 # timestamp formats
-ISO8601="%Y-%m-%dT%H:%M:%S.%f"
-ISO8601_PAT=re.compile(r"^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\.\d+)Z?([\+\-]\d{2}:?\d{2})?$")
+ISO8601 = "%Y-%m-%dT%H:%M:%S.%f"
+ISO8601_PAT=re.compile(r"^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\.\d{1,6})Z?([\+\-]\d{2}:?\d{2})?$")
 
 #-----------------------------------------------------------------------------
 # Classes and functions
 #-----------------------------------------------------------------------------
 
 def rekey(dikt):
     """Rekey a dict that has been forced to use str keys where there should be
     ints by json."""
     for k in dikt:
         if isinstance(k, string_types):
             ik=fk=None
             try:
                 ik = int(k)
             except ValueError:
                 try:
                     fk = float(k)
                 except ValueError:
                     continue
             if ik is not None:
                 nk = ik
             else:
                 nk = fk
             if nk in dikt:
                 raise KeyError("already have key %r"%nk)
             dikt[nk] = dikt.pop(k)
     return dikt
 
+def parse_date(s):
+    """parse an ISO8601 date string
+    
+    If it is None or not a valid ISO8601 timestamp,
+    it will be returned unmodified.
+    Otherwise, it will return a datetime object.
+    """
+    if s is None:
+        return s
+    m = ISO8601_PAT.match(s)
+    if m:
+        # FIXME: add actual timezone support
+        # this just drops the timezone info
+        notz = m.groups()[0]
+        return datetime.strptime(notz, ISO8601)
+    return s
 
 def extract_dates(obj):
     """extract ISO8601 dates from unpacked JSON"""
     if isinstance(obj, dict):
-        obj = dict(obj) # don't clobber
+        new_obj = {} # don't clobber
         for k,v in iteritems(obj):
-            obj[k] = extract_dates(v)
+            new_obj[k] = extract_dates(v)
+        obj = new_obj
     elif isinstance(obj, (list, tuple)):
         obj = [ extract_dates(o) for o in obj ]
     elif isinstance(obj, string_types):
-        m = ISO8601_PAT.match(obj)
-        if m:
-            # FIXME: add actual timezone support
-            # this just drops the timezone info
-            notz = m.groups()[0]
-            obj = datetime.strptime(notz, ISO8601)
+        obj = parse_date(obj)
     return obj
 
 def squash_dates(obj):
     """squash datetime objects into ISO8601 strings"""
     if isinstance(obj, dict):
         obj = dict(obj) # don't clobber
         for k,v in iteritems(obj):
             obj[k] = squash_dates(v)
     elif isinstance(obj, (list, tuple)):
         obj = [ squash_dates(o) for o in obj ]
     elif isinstance(obj, datetime):
         obj = obj.isoformat()
     return obj
 
 def date_default(obj):
     """default function for packing datetime objects in JSON."""
     if isinstance(obj, datetime):
         return obj.isoformat()
     else:
         raise TypeError("%r is not JSON serializable"%obj)
 
 
 # constants for identifying png/jpeg data
 PNG = b'\x89PNG\r\n\x1a\n'
 # front of PNG base64-encoded
 PNG64 = b'iVBORw0KG'
 JPEG = b'\xff\xd8'
 # front of JPEG base64-encoded
 JPEG64 = b'/9'
 
 def encode_images(format_dict):
     """b64-encodes images in a displaypub format dict
 
     Perhaps this should be handled in json_clean itself?
 
     Parameters
     ----------
 
     format_dict : dict
         A dictionary of display data keyed by mime-type
 
     Returns
     -------
 
     format_dict : dict
         A copy of the same dictionary,
         but binary image data ('image/png' or 'image/jpeg')
         is base64-encoded.
 
     """
     encoded = format_dict.copy()
 
     pngdata = format_dict.get('image/png')
     if isinstance(pngdata, bytes):
         # make sure we don't double-encode
         if not pngdata.startswith(PNG64):
             pngdata = encodebytes(pngdata)
         encoded['image/png'] = pngdata.decode('ascii')
 
     jpegdata = format_dict.get('image/jpeg')
     if isinstance(jpegdata, bytes):
         # make sure we don't double-encode
         if not jpegdata.startswith(JPEG64):
             jpegdata = encodebytes(jpegdata)
         encoded['image/jpeg'] = jpegdata.decode('ascii')
 
     return encoded
 
 
 def json_clean(obj):
     """Clean an object to ensure it's safe to encode in JSON.
 
     Atomic, immutable objects are returned unmodified.  Sets and tuples are
     converted to lists, lists are copied and dicts are also copied.
 
     Note: dicts whose keys could cause collisions upon encoding (such as a dict
     with both the number 1 and the string '1' as keys) will cause a ValueError
     to be raised.
 
     Parameters
     ----------
     obj : any python object
 
     Returns
     -------
     out : object
 
       A version of the input which will not cause an encoding error when
       encoded as JSON.  Note that this function does not *encode* its inputs,
       it simply sanitizes it so that there will be no encoding errors later.
 
     Examples
     --------
     >>> json_clean(4)
     4
     >>> json_clean(list(range(10)))
     [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
     >>> sorted(json_clean(dict(x=1, y=2)).items())
     [('x', 1), ('y', 2)]
     >>> sorted(json_clean(dict(x=1, y=2, z=[1,2,3])).items())
     [('x', 1), ('y', 2), ('z', [1, 2, 3])]
     >>> json_clean(True)
     True
     """
     # types that are 'atomic' and ok in json as-is.  bool doesn't need to be
     # listed explicitly because bools pass as int instances
     atomic_ok = (unicode_type, int, type(None))
 
     # containers that we need to convert into lists
     container_to_list = (tuple, set, types.GeneratorType)
 
     if isinstance(obj, float):
         # cast out-of-range floats to their reprs
         if math.isnan(obj) or math.isinf(obj):
             return repr(obj)
         return obj
 
     if isinstance(obj, atomic_ok):
         return obj
 
     if isinstance(obj, bytes):
         return obj.decode(DEFAULT_ENCODING, 'replace')
 
     if isinstance(obj, container_to_list) or (
         hasattr(obj, '__iter__') and hasattr(obj, next_attr_name)):
         obj = list(obj)
 
     if isinstance(obj, list):
         return [json_clean(x) for x in obj]
 
     if isinstance(obj, dict):
         # First, validate that the dict won't lose data in conversion due to
         # key collisions after stringification.  This can happen with keys like
         # True and 'true' or 1 and '1', which collide in JSON.
         nkeys = len(obj)
         nkeys_collapsed = len(set(map(str, obj)))
         if nkeys != nkeys_collapsed:
             raise ValueError('dict can not be safely converted to JSON: '
                              'key collision would lead to dropped values')
         # If all OK, proceed by making the new dict that will be json-safe
         out = {}
         for k,v in iteritems(obj):
             out[str(k)] = json_clean(v)
         return out
 
     # If we get here, we don't know how to handle the object, so we just get
     # its repr and return that.  This will catch lambdas, open sockets, class
     # objects, and any other complicated contraption that json can't encode
     return repr(obj)

IPython/utils/tests/test_jsonutil.py

@@ -1,131 +1,143
 """Test suite for our JSON utilities.
 """
 #-----------------------------------------------------------------------------
 #  Copyright (C) 2010-2011  The IPython Development Team
 #
 #  Distributed under the terms of the BSD License.  The full license is in
 #  the file COPYING.txt, distributed as part of this software.
 #-----------------------------------------------------------------------------
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 # stdlib
 import datetime
 import json
 from base64 import decodestring
 
 # third party
 import nose.tools as nt
 
 # our own
 from IPython.utils import jsonutil, tz
 from ..jsonutil import json_clean, encode_images
 from ..py3compat import unicode_to_str, str_to_bytes, iteritems
 
 #-----------------------------------------------------------------------------
 # Test functions
 #-----------------------------------------------------------------------------
 
 def test():
     # list of input/expected output.  Use None for the expected output if it
     # can be the same as the input.
     pairs = [(1, None), # start with scalars
              (1.0, None),
              ('a', None),
              (True, None),
              (False, None),
              (None, None),
              # complex numbers for now just go to strings, as otherwise they
              # are unserializable
              (1j, '1j'),
              # Containers
              ([1, 2], None),
              ((1, 2), [1, 2]),
              (set([1, 2]), [1, 2]),
              (dict(x=1), None),
              ({'x': 1, 'y':[1,2,3], '1':'int'}, None),
              # More exotic objects
              ((x for x in range(3)), [0, 1, 2]),
              (iter([1, 2]), [1, 2]),
              ]
     
     for val, jval in pairs:
         if jval is None:
             jval = val
         out = json_clean(val)
         # validate our cleanup
         nt.assert_equal(out, jval)
         # and ensure that what we return, indeed encodes cleanly
         json.loads(json.dumps(out))
 
 
 
 def test_encode_images():
     # invalid data, but the header and footer are from real files
     pngdata = b'\x89PNG\r\n\x1a\nblahblahnotactuallyvalidIEND\xaeB`\x82'
     jpegdata = b'\xff\xd8\xff\xe0\x00\x10JFIFblahblahjpeg(\xa0\x0f\xff\xd9'
     
     fmt = {
         'image/png'  : pngdata,
         'image/jpeg' : jpegdata,
     }
     encoded = encode_images(fmt)
     for key, value in iteritems(fmt):
         # encoded has unicode, want bytes
         decoded = decodestring(encoded[key].encode('ascii'))
         nt.assert_equal(decoded, value)
     encoded2 = encode_images(encoded)
     nt.assert_equal(encoded, encoded2)
     
     b64_str = {}
     for key, encoded in iteritems(encoded):
         b64_str[key] = unicode_to_str(encoded)
     encoded3 = encode_images(b64_str)
     nt.assert_equal(encoded3, b64_str)
     for key, value in iteritems(fmt):
         # encoded3 has str, want bytes
         decoded = decodestring(str_to_bytes(encoded3[key]))
         nt.assert_equal(decoded, value)
 
 def test_lambda():
     jc = json_clean(lambda : 1)
     assert isinstance(jc, str)
     assert '<lambda>' in jc
     json.dumps(jc)
 
 def test_extract_dates():
     timestamps = [
         '2013-07-03T16:34:52.249482',
         '2013-07-03T16:34:52.249482Z',
         '2013-07-03T16:34:52.249482Z-0800',
         '2013-07-03T16:34:52.249482Z+0800',
         '2013-07-03T16:34:52.249482Z+08:00',
         '2013-07-03T16:34:52.249482Z-08:00',
         '2013-07-03T16:34:52.249482-0800',
         '2013-07-03T16:34:52.249482+0800',
         '2013-07-03T16:34:52.249482+08:00',
         '2013-07-03T16:34:52.249482-08:00',
     ]
     extracted = jsonutil.extract_dates(timestamps)
     ref = extracted[0]
     for dt in extracted:
         nt.assert_true(isinstance(dt, datetime.datetime))
         nt.assert_equal(dt, ref)
 
+def test_parse_ms_precision():
+    base = '2013-07-03T16:34:52.'
+    digits = '1234567890'
+    
+    for i in range(len(digits)):
+        ts = base + digits[:i]
+        parsed = jsonutil.parse_date(ts)
+        if i >= 1 and i <= 6:
+            assert isinstance(parsed, datetime.datetime)
+        else:
+            assert isinstance(parsed, str)
+
 def test_date_default():
     data = dict(today=datetime.datetime.now(), utcnow=tz.utcnow())
     jsondata = json.dumps(data, default=jsonutil.date_default)
     nt.assert_in("+00", jsondata)
     nt.assert_equal(jsondata.count("+00"), 1)
     extracted = jsonutil.extract_dates(json.loads(jsondata))
     for dt in extracted.values():
         nt.assert_true(isinstance(dt, datetime.datetime))
 
 def test_exception():
     bad_dicts = [{1:'number', '1':'string'},
                  {True:'bool', 'True':'string'},
                  ]
     for d in bad_dicts:
         nt.assert_raises(ValueError, json_clean, d)