better serialization for parallel code

* no longer use newserialized
* no longer double-pickle anything
* can/pickleutil handles arrays
* pickleutil has [un]can_map dicts for extensibility
* don't can each element of long sequences

IPython/zmq/tests/test_serialize.py

@@ -0,0 +1,115 b''
+"""test serialization tools"""
+
+#-------------------------------------------------------------------------------
+#  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 pickle
+
+import nose.tools as nt
+
+# from unittest import TestCaes
+from IPython.zmq.serialize import serialize_object, unserialize_object
+from IPython.testing import decorators as dec
+from IPython.utils.pickleutil import CannedArray
+
+def roundtrip(obj):
+    """roundtrip an object through serialization"""
+    bufs = serialize_object(obj)
+    obj2, remainder = unserialize_object(bufs)
+    nt.assert_equals(remainder, [])
+    return obj2
+
+class C(object):
+    """dummy class for """
+    
+    def __init__(self, **kwargs):
+        for key,value in kwargs.iteritems():
+            setattr(self, key, value)
+
[e-mail]
+def test_roundtrip_simple():
+    for obj in [
+        'hello',
+        dict(a='b', b=10),
+        [1,2,'hi'],
+        (b'123', 'hello'),
+    ]:
+        obj2 = roundtrip(obj)
+        yield nt.assert_equals(obj, obj2)
+
[e-mail]
+def test_roundtrip_nested():
+    for obj in [
+        dict(a=range(5), b={1:b'hello'}),
+        [range(5),[range(3),(1,[b'whoda'])]],
+    ]:
+        obj2 = roundtrip(obj)
+        yield nt.assert_equals(obj, obj2)
+
[e-mail]
+def test_roundtrip_buffered():
+    for obj in [
+        dict(a=b"x"*1025),
+        b"hello"*500,
+        [b"hello"*501, 1,2,3]
+    ]:
+        bufs = serialize_object(obj)
+        yield nt.assert_equals(len(bufs), 2)
+        obj2, remainder = unserialize_object(bufs)
+        yield nt.assert_equals(remainder, [])
+        yield nt.assert_equals(obj, obj2)
+
[e-mail]
[e-mail]_without('numpy')
+def test_numpy():
+    import numpy
+    from numpy.testing.utils import assert_array_equal
+    for shape in ((), (0,), (100,), (1024,10), (10,8,6,5)):
+        for dtype in ('uint8', 'float64', 'int32', [('int16', 'float32')]):
+            A = numpy.empty(shape, dtype=dtype)
+            bufs = serialize_object(A)
+            B, r = unserialize_object(bufs)
+            yield nt.assert_equals(r, [])
+            yield assert_array_equal(A,B)
+
[e-mail]
[e-mail]_without('numpy')
+def test_numpy_in_seq():
+    import numpy
+    from numpy.testing.utils import assert_array_equal
+    for shape in ((), (0,), (100,), (1024,10), (10,8,6,5)):
+        for dtype in ('uint8', 'float64', 'int32', [('int16', 'float32')]):
+            A = numpy.empty(shape, dtype=dtype)
+            bufs = serialize_object((A,1,2,b'hello'))
+            canned = pickle.loads(bufs[0])
+            yield nt.assert_true(canned[0], CannedArray)
+            tup, r = unserialize_object(bufs)
+            B = tup[0]
+            yield nt.assert_equals(r, [])
+            yield assert_array_equal(A,B)
+
[e-mail]
[e-mail]_without('numpy')
+def test_numpy_in_dict():
+    import numpy
+    from numpy.testing.utils import assert_array_equal
+    for shape in ((), (0,), (100,), (1024,10), (10,8,6,5)):
+        for dtype in ('uint8', 'float64', 'int32', [('int16', 'float32')]):
+            A = numpy.empty(shape, dtype=dtype)
+            bufs = serialize_object(dict(a=A,b=1,c=range(20)))
+            canned = pickle.loads(bufs[0])
+            yield nt.assert_true(canned['a'], CannedArray)
+            d, r = unserialize_object(bufs)
+            B = d['a']
+            yield nt.assert_equals(r, [])
+            yield assert_array_equal(A,B)
+    
+

IPython/parallel/tests/test_view.py

@@ -1,597 +1,597 b''
 # -*- coding: utf-8 -*-
 """test View objects
 
 Authors:
 
 * Min RK
 """
 #-------------------------------------------------------------------------------
 #  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 sys
 import platform
 import time
 from tempfile import mktemp
 from StringIO import StringIO
 
 import zmq
 from nose import SkipTest
 
 from IPython.testing import decorators as dec
 from IPython.testing.ipunittest import ParametricTestCase
 
 from IPython import parallel  as pmod
 from IPython.parallel import error
 from IPython.parallel import AsyncResult, AsyncHubResult, AsyncMapResult
 from IPython.parallel import DirectView
 from IPython.parallel.util import interactive
 
 from IPython.parallel.tests import add_engines
 
 from .clienttest import ClusterTestCase, crash, wait, skip_without
 
 def setup():
     add_engines(3, total=True)
 
 class TestView(ClusterTestCase, ParametricTestCase):
     
     def setUp(self):
         # On Win XP, wait for resource cleanup, else parallel test group fails
         if platform.system() == "Windows" and platform.win32_ver()[0] == "XP":
             # 1 sec fails. 1.5 sec seems ok. Using 2 sec for margin of safety
             time.sleep(2)
         super(TestView, self).setUp()
 
     def test_z_crash_mux(self):
         """test graceful handling of engine death (direct)"""
         raise SkipTest("crash tests disabled, due to undesirable crash reports")
         # self.add_engines(1)
         eid = self.client.ids[-1]
         ar = self.client[eid].apply_async(crash)
         self.assertRaisesRemote(error.EngineError, ar.get, 10)
         eid = ar.engine_id
         tic = time.time()
         while eid in self.client.ids and time.time()-tic < 5:
             time.sleep(.01)
             self.client.spin()
         self.assertFalse(eid in self.client.ids, "Engine should have died")
     
     def test_push_pull(self):
         """test pushing and pulling"""
         data = dict(a=10, b=1.05, c=range(10), d={'e':(1,2),'f':'hi'})
         t = self.client.ids[-1]
         v = self.client[t]
         push = v.push
         pull = v.pull
         v.block=True
         nengines = len(self.client)
         push({'data':data})
         d = pull('data')
         self.assertEqual(d, data)
         self.client[:].push({'data':data})
         d = self.client[:].pull('data', block=True)
         self.assertEqual(d, nengines*[data])
         ar = push({'data':data}, block=False)
         self.assertTrue(isinstance(ar, AsyncResult))
         r = ar.get()
         ar = self.client[:].pull('data', block=False)
         self.assertTrue(isinstance(ar, AsyncResult))
         r = ar.get()
         self.assertEqual(r, nengines*[data])
         self.client[:].push(dict(a=10,b=20))
         r = self.client[:].pull(('a','b'), block=True)
         self.assertEqual(r, nengines*[[10,20]])
     
     def test_push_pull_function(self):
         "test pushing and pulling functions"
         def testf(x):
             return 2.0*x
         
         t = self.client.ids[-1]
         v = self.client[t]
         v.block=True
         push = v.push
         pull = v.pull
         execute = v.execute
         push({'testf':testf})
         r = pull('testf')
         self.assertEqual(r(1.0), testf(1.0))
         execute('r = testf(10)')
         r = pull('r')
         self.assertEqual(r, testf(10))
         ar = self.client[:].push({'testf':testf}, block=False)
         ar.get()
         ar = self.client[:].pull('testf', block=False)
         rlist = ar.get()
         for r in rlist:
             self.assertEqual(r(1.0), testf(1.0))
         execute("def g(x): return x*x")
         r = pull(('testf','g'))
         self.assertEqual((r[0](10),r[1](10)), (testf(10), 100))
     
     def test_push_function_globals(self):
         """test that pushed functions have access to globals"""
         @interactive
         def geta():
             return a
         # self.add_engines(1)
         v = self.client[-1]
         v.block=True
         v['f'] = geta
         self.assertRaisesRemote(NameError, v.execute, 'b=f()')
         v.execute('a=5')
         v.execute('b=f()')
         self.assertEqual(v['b'], 5)
     
     def test_push_function_defaults(self):
         """test that pushed functions preserve default args"""
         def echo(a=10):
             return a
         v = self.client[-1]
         v.block=True
         v['f'] = echo
         v.execute('b=f()')
         self.assertEqual(v['b'], 10)
 
     def test_get_result(self):
         """test getting results from the Hub."""
         c = pmod.Client(profile='iptest')
         # self.add_engines(1)
         t = c.ids[-1]
         v = c[t]
         v2 = self.client[t]
         ar = v.apply_async(wait, 1)
         # give the monitor time to notice the message
         time.sleep(.25)
         ahr = v2.get_result(ar.msg_ids)
         self.assertTrue(isinstance(ahr, AsyncHubResult))
         self.assertEqual(ahr.get(), ar.get())
         ar2 = v2.get_result(ar.msg_ids)
         self.assertFalse(isinstance(ar2, AsyncHubResult))
         c.spin()
         c.close()
     
     def test_run_newline(self):
         """test that run appends newline to files"""
         tmpfile = mktemp()
         with open(tmpfile, 'w') as f:
             f.write("""def g():
                 return 5
                 """)
         v = self.client[-1]
         v.run(tmpfile, block=True)
         self.assertEqual(v.apply_sync(lambda f: f(), pmod.Reference('g')), 5)
 
     def test_apply_tracked(self):
         """test tracking for apply"""
         # self.add_engines(1)
         t = self.client.ids[-1]
         v = self.client[t]
         v.block=False
         def echo(n=1024*1024, **kwargs):
             with v.temp_flags(**kwargs):
                 return v.apply(lambda x: x, 'x'*n)
         ar = echo(1, track=False)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         self.assertTrue(ar.sent)
         ar = echo(track=True)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         self.assertEqual(ar.sent, ar._tracker.done)
         ar._tracker.wait()
         self.assertTrue(ar.sent)
         
     def test_push_tracked(self):
         t = self.client.ids[-1]
         ns = dict(x='x'*1024*1024)
         v = self.client[t]
         ar = v.push(ns, block=False, track=False)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         self.assertTrue(ar.sent)
         
         ar = v.push(ns, block=False, track=True)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         ar._tracker.wait()
         self.assertEqual(ar.sent, ar._tracker.done)
         self.assertTrue(ar.sent)
         ar.get()
         
     def test_scatter_tracked(self):
         t = self.client.ids
         x='x'*1024*1024
         ar = self.client[t].scatter('x', x, block=False, track=False)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         self.assertTrue(ar.sent)
         
         ar = self.client[t].scatter('x', x, block=False, track=True)
         self.assertTrue(isinstance(ar._tracker, zmq.MessageTracker))
         self.assertEqual(ar.sent, ar._tracker.done)
         ar._tracker.wait()
         self.assertTrue(ar.sent)
         ar.get()
     
     def test_remote_reference(self):
         v = self.client[-1]
         v['a'] = 123
         ra = pmod.Reference('a')
         b = v.apply_sync(lambda x: x, ra)
         self.assertEqual(b, 123)
 
 
     def test_scatter_gather(self):
         view = self.client[:]
         seq1 = range(16)
         view.scatter('a', seq1)
         seq2 = view.gather('a', block=True)
         self.assertEqual(seq2, seq1)
         self.assertRaisesRemote(NameError, view.gather, 'asdf', block=True)
     
     @skip_without('numpy')
     def test_scatter_gather_numpy(self):
         import numpy
         from numpy.testing.utils import assert_array_equal, assert_array_almost_equal
         view = self.client[:]
         a = numpy.arange(64)
-        view.scatter('a', a)
+        view.scatter('a', a, block=True)
         b = view.gather('a', block=True)
         assert_array_equal(b, a)
     
     def test_scatter_gather_lazy(self):
         """scatter/gather with targets='all'"""
         view = self.client.direct_view(targets='all')
         x = range(64)
         view.scatter('x', x)
         gathered = view.gather('x', block=True)
         self.assertEqual(gathered, x)
         
 
     @dec.known_failure_py3
     @skip_without('numpy')
     def test_push_numpy_nocopy(self):
         import numpy
         view = self.client[:]
         a = numpy.arange(64)
         view['A'] = a
         @interactive
         def check_writeable(x):
             return x.flags.writeable
         
         for flag in view.apply_sync(check_writeable, pmod.Reference('A')):
             self.assertFalse(flag, "array is writeable, push shouldn't have pickled it")
         
         view.push(dict(B=a))
         for flag in view.apply_sync(check_writeable, pmod.Reference('B')):
             self.assertFalse(flag, "array is writeable, push shouldn't have pickled it")
     
     @skip_without('numpy')
     def test_apply_numpy(self):
         """view.apply(f, ndarray)"""
         import numpy
         from numpy.testing.utils import assert_array_equal, assert_array_almost_equal
         
         A = numpy.random.random((100,100))
         view = self.client[-1]
         for dt in [ 'int32', 'uint8', 'float32', 'float64' ]:
             B = A.astype(dt)
             C = view.apply_sync(lambda x:x, B)
             assert_array_equal(B,C)
     
     @skip_without('numpy')
     def test_push_pull_recarray(self):
         """push/pull recarrays"""
         import numpy
         from numpy.testing.utils import assert_array_equal
         
         view = self.client[-1]
         
         R = numpy.array([
             (1, 'hi', 0.),
             (2**30, 'there', 2.5),
             (-99999, 'world', -12345.6789),
         ], [('n', int), ('s', '|S10'), ('f', float)])
         
         view['RR'] = R
         R2 = view['RR']
         
         r_dtype, r_shape = view.apply_sync(interactive(lambda : (RR.dtype, RR.shape)))
         self.assertEqual(r_dtype, R.dtype)
         self.assertEqual(r_shape, R.shape)
         self.assertEqual(R2.dtype, R.dtype)
         self.assertEqual(R2.shape, R.shape)
         assert_array_equal(R2, R)
     
     def test_map(self):
         view = self.client[:]
         def f(x):
             return x**2
         data = range(16)
         r = view.map_sync(f, data)
         self.assertEqual(r, map(f, data))
     
     def test_map_iterable(self):
         """test map on iterables (direct)"""
         view = self.client[:]
         # 101 is prime, so it won't be evenly distributed
         arr = range(101)
         # ensure it will be an iterator, even in Python 3
         it = iter(arr)
         r = view.map_sync(lambda x:x, arr)
         self.assertEqual(r, list(arr))
     
-    def test_scatterGatherNonblocking(self):
+    def test_scatter_gather_nonblocking(self):
         data = range(16)
         view = self.client[:]
         view.scatter('a', data, block=False)
         ar = view.gather('a', block=False)
         self.assertEqual(ar.get(), data)
     
     @skip_without('numpy')
     def test_scatter_gather_numpy_nonblocking(self):
         import numpy
         from numpy.testing.utils import assert_array_equal, assert_array_almost_equal
         a = numpy.arange(64)
         view = self.client[:]
         ar = view.scatter('a', a, block=False)
         self.assertTrue(isinstance(ar, AsyncResult))
         amr = view.gather('a', block=False)
         self.assertTrue(isinstance(amr, AsyncMapResult))
         assert_array_equal(amr.get(), a)
 
     def test_execute(self):
         view = self.client[:]
         # self.client.debug=True
         execute = view.execute
         ar = execute('c=30', block=False)
         self.assertTrue(isinstance(ar, AsyncResult))
         ar = execute('d=[0,1,2]', block=False)
         self.client.wait(ar, 1)
         self.assertEqual(len(ar.get()), len(self.client))
         for c in view['c']:
             self.assertEqual(c, 30)
     
     def test_abort(self):
         view = self.client[-1]
         ar = view.execute('import time; time.sleep(1)', block=False)
         ar2 = view.apply_async(lambda : 2)
         ar3 = view.apply_async(lambda : 3)
         view.abort(ar2)
         view.abort(ar3.msg_ids)
         self.assertRaises(error.TaskAborted, ar2.get)
         self.assertRaises(error.TaskAborted, ar3.get)
     
     def test_abort_all(self):
         """view.abort() aborts all outstanding tasks"""
         view = self.client[-1]
         ars = [ view.apply_async(time.sleep, 0.25) for i in range(10) ]
         view.abort()
         view.wait(timeout=5)
         for ar in ars[5:]:
             self.assertRaises(error.TaskAborted, ar.get)
     
     def test_temp_flags(self):
         view = self.client[-1]
         view.block=True
         with view.temp_flags(block=False):
             self.assertFalse(view.block)
         self.assertTrue(view.block)
     
     @dec.known_failure_py3
     def test_importer(self):
         view = self.client[-1]
         view.clear(block=True)
         with view.importer:
             import re
         
         @interactive
         def findall(pat, s):
             # this globals() step isn't necessary in real code
             # only to prevent a closure in the test
             re = globals()['re']
             return re.findall(pat, s)
         
         self.assertEqual(view.apply_sync(findall, '\w+', 'hello world'), 'hello world'.split())
     
     def test_unicode_execute(self):
         """test executing unicode strings"""
         v = self.client[-1]
         v.block=True
         if sys.version_info[0] >= 3:
             code="a='é'"
         else:
             code=u"a=u'é'"
         v.execute(code)
         self.assertEqual(v['a'], u'é')
         
     def test_unicode_apply_result(self):
         """test unicode apply results"""
         v = self.client[-1]
         r = v.apply_sync(lambda : u'é')
         self.assertEqual(r, u'é')
     
     def test_unicode_apply_arg(self):
         """test passing unicode arguments to apply"""
         v = self.client[-1]
         
         @interactive
         def check_unicode(a, check):
             assert isinstance(a, unicode), "%r is not unicode"%a
             assert isinstance(check, bytes), "%r is not bytes"%check
             assert a.encode('utf8') == check, "%s != %s"%(a,check)
         
         for s in [ u'é', u'ßø®∫',u'asdf' ]:
             try:
                 v.apply_sync(check_unicode, s, s.encode('utf8'))
             except error.RemoteError as e:
                 if e.ename == 'AssertionError':
                     self.fail(e.evalue)
                 else:
                     raise e
     
     def test_map_reference(self):
         """view.map(<Reference>, *seqs) should work"""
         v = self.client[:]
         v.scatter('n', self.client.ids, flatten=True)
         v.execute("f = lambda x,y: x*y")
         rf = pmod.Reference('f')
         nlist = list(range(10))
         mlist = nlist[::-1]
         expected = [ m*n for m,n in zip(mlist, nlist) ]
         result = v.map_sync(rf, mlist, nlist)
         self.assertEqual(result, expected)
 
     def test_apply_reference(self):
         """view.apply(<Reference>, *args) should work"""
         v = self.client[:]
         v.scatter('n', self.client.ids, flatten=True)
         v.execute("f = lambda x: n*x")
         rf = pmod.Reference('f')
         result = v.apply_sync(rf, 5)
         expected = [ 5*id for id in self.client.ids ]
         self.assertEqual(result, expected)
     
     def test_eval_reference(self):
         v = self.client[self.client.ids[0]]
         v['g'] = range(5)
         rg = pmod.Reference('g[0]')
         echo = lambda x:x
         self.assertEqual(v.apply_sync(echo, rg), 0)
     
     def test_reference_nameerror(self):
         v = self.client[self.client.ids[0]]
         r = pmod.Reference('elvis_has_left')
         echo = lambda x:x
         self.assertRaisesRemote(NameError, v.apply_sync, echo, r)
 
     def test_single_engine_map(self):
         e0 = self.client[self.client.ids[0]]
         r = range(5)
         check = [ -1*i for i in r ]
         result = e0.map_sync(lambda x: -1*x, r)
         self.assertEqual(result, check)
     
     def test_len(self):
         """len(view) makes sense"""
         e0 = self.client[self.client.ids[0]]
         yield self.assertEqual(len(e0), 1)
         v = self.client[:]
         yield self.assertEqual(len(v), len(self.client.ids))
         v = self.client.direct_view('all')
         yield self.assertEqual(len(v), len(self.client.ids))
         v = self.client[:2]
         yield self.assertEqual(len(v), 2)
         v = self.client[:1]
         yield self.assertEqual(len(v), 1)
         v = self.client.load_balanced_view()
         yield self.assertEqual(len(v), len(self.client.ids))
         # parametric tests seem to require manual closing?
         self.client.close()
 
     
     # begin execute tests
     
     def test_execute_reply(self):
         e0 = self.client[self.client.ids[0]]
         e0.block = True
         ar = e0.execute("5", silent=False)
         er = ar.get()
         self.assertEqual(str(er), "<ExecuteReply[%i]: 5>" % er.execution_count)
         self.assertEqual(er.pyout['data']['text/plain'], '5')
 
     def test_execute_reply_stdout(self):
         e0 = self.client[self.client.ids[0]]
         e0.block = True
         ar = e0.execute("print (5)", silent=False)
         er = ar.get()
         self.assertEqual(er.stdout.strip(), '5')
         
     def test_execute_pyout(self):
         """execute triggers pyout with silent=False"""
         view = self.client[:]
         ar = view.execute("5", silent=False, block=True)
         
         expected = [{'text/plain' : '5'}] * len(view)
         mimes = [ out['data'] for out in ar.pyout ]
         self.assertEqual(mimes, expected)
     
     def test_execute_silent(self):
         """execute does not trigger pyout with silent=True"""
         view = self.client[:]
         ar = view.execute("5", block=True)
         expected = [None] * len(view)
         self.assertEqual(ar.pyout, expected)
     
     def test_execute_magic(self):
         """execute accepts IPython commands"""
         view = self.client[:]
         view.execute("a = 5")
         ar = view.execute("%whos", block=True)
         # this will raise, if that failed
         ar.get(5)
         for stdout in ar.stdout:
             lines = stdout.splitlines()
             self.assertEqual(lines[0].split(), ['Variable', 'Type', 'Data/Info'])
             found = False
             for line in lines[2:]:
                 split = line.split()
                 if split == ['a', 'int', '5']:
                     found = True
                     break
             self.assertTrue(found, "whos output wrong: %s" % stdout)
     
     def test_execute_displaypub(self):
         """execute tracks display_pub output"""
         view = self.client[:]
         view.execute("from IPython.core.display import *")
         ar = view.execute("[ display(i) for i in range(5) ]", block=True)
         
         expected = [ {u'text/plain' : unicode(j)} for j in range(5) ]
         for outputs in ar.outputs:
             mimes = [ out['data'] for out in outputs ]
             self.assertEqual(mimes, expected)
     
     def test_apply_displaypub(self):
         """apply tracks display_pub output"""
         view = self.client[:]
         view.execute("from IPython.core.display import *")
         
         @interactive
         def publish():
             [ display(i) for i in range(5) ]
         
         ar = view.apply_async(publish)
         ar.get(5)
         expected = [ {u'text/plain' : unicode(j)} for j in range(5) ]
         for outputs in ar.outputs:
             mimes = [ out['data'] for out in outputs ]
             self.assertEqual(mimes, expected)
     
     def test_execute_raises(self):
         """exceptions in execute requests raise appropriately"""
         view = self.client[-1]
         ar = view.execute("1/0")
         self.assertRaisesRemote(ZeroDivisionError, ar.get, 2)
     
     @dec.skipif_not_matplotlib
     def test_magic_pylab(self):
         """%pylab works on engines"""
         view = self.client[-1]
         ar = view.execute("%pylab inline")
         # at least check if this raised:
         reply = ar.get(5)
         # include imports, in case user config
         ar = view.execute("plot(rand(100))", silent=False)
         reply = ar.get(5)
         self.assertEqual(len(reply.outputs), 1)
         output = reply.outputs[0]
         self.assertTrue("data" in output)
         data = output['data']
         self.assertTrue("image/png" in data)
         
 

IPython/parallel/util.py

@@ -1,358 +1,352 b''
 """some generic utilities for dealing with classes, urls, and serialization
 
 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
 #-----------------------------------------------------------------------------
 
 # Standard library imports.
 import logging
 import os
 import re
 import stat
 import socket
 import sys
 from signal import signal, SIGINT, SIGABRT, SIGTERM
 try:
     from signal import SIGKILL
 except ImportError:
     SIGKILL=None
 
 try:
     import cPickle
     pickle = cPickle
 except:
     cPickle = None
     import pickle
 
 # System library imports
 import zmq
 from zmq.log import handlers
 
 from IPython.external.decorator import decorator
 
 # IPython imports
 from IPython.config.application import Application
-from IPython.utils import py3compat
-from IPython.utils.pickleutil import can, uncan, canSequence, uncanSequence
-from IPython.utils.newserialized import serialize, unserialize
 from IPython.zmq.log import EnginePUBHandler
 from IPython.zmq.serialize import (
     unserialize_object, serialize_object, pack_apply_message, unpack_apply_message
 )
 
-if py3compat.PY3:
-    buffer = memoryview
-
 #-----------------------------------------------------------------------------
 # Classes
 #-----------------------------------------------------------------------------
 
 class Namespace(dict):
     """Subclass of dict for attribute access to keys."""
     
     def __getattr__(self, key):
         """getattr aliased to getitem"""
         if key in self.iterkeys():
             return self[key]
         else:
             raise NameError(key)
 
     def __setattr__(self, key, value):
         """setattr aliased to setitem, with strict"""
         if hasattr(dict, key):
             raise KeyError("Cannot override dict keys %r"%key)
         self[key] = value
     
 
 class ReverseDict(dict):
     """simple double-keyed subset of dict methods."""
     
     def __init__(self, *args, **kwargs):
         dict.__init__(self, *args, **kwargs)
         self._reverse = dict()
         for key, value in self.iteritems():
             self._reverse[value] = key
     
     def __getitem__(self, key):
         try:
             return dict.__getitem__(self, key)
         except KeyError:
             return self._reverse[key]
     
     def __setitem__(self, key, value):
         if key in self._reverse:
             raise KeyError("Can't have key %r on both sides!"%key)
         dict.__setitem__(self, key, value)
         self._reverse[value] = key
     
     def pop(self, key):
         value = dict.pop(self, key)
         self._reverse.pop(value)
         return value
     
     def get(self, key, default=None):
         try:
             return self[key]
         except KeyError:
             return default
 
 #-----------------------------------------------------------------------------
 # Functions
 #-----------------------------------------------------------------------------
 
 @decorator
 def log_errors(f, self, *args, **kwargs):
     """decorator to log unhandled exceptions raised in a method.
     
     For use wrapping on_recv callbacks, so that exceptions
     do not cause the stream to be closed.
     """
     try:
         return f(self, *args, **kwargs)
     except Exception:
         self.log.error("Uncaught exception in %r" % f, exc_info=True)
     
 
 def is_url(url):
     """boolean check for whether a string is a zmq url"""
     if '://' not in url:
         return False
     proto, addr = url.split('://', 1)
     if proto.lower() not in ['tcp','pgm','epgm','ipc','inproc']:
         return False
     return True
 
 def validate_url(url):
     """validate a url for zeromq"""
     if not isinstance(url, basestring):
         raise TypeError("url must be a string, not %r"%type(url))
     url = url.lower()
     
     proto_addr = url.split('://')
     assert len(proto_addr) == 2, 'Invalid url: %r'%url
     proto, addr = proto_addr
     assert proto in ['tcp','pgm','epgm','ipc','inproc'], "Invalid protocol: %r"%proto
     
     # domain pattern adapted from http://www.regexlib.com/REDetails.aspx?regexp_id=391
     # author: Remi Sabourin
     pat = re.compile(r'^([\w\d]([\w\d\-]{0,61}[\w\d])?\.)*[\w\d]([\w\d\-]{0,61}[\w\d])?$')
     
     if proto == 'tcp':
         lis = addr.split(':')
         assert len(lis) == 2, 'Invalid url: %r'%url
         addr,s_port = lis
         try:
             port = int(s_port)
         except ValueError:
             raise AssertionError("Invalid port %r in url: %r"%(port, url))
         
         assert addr == '*' or pat.match(addr) is not None, 'Invalid url: %r'%url
         
     else:
         # only validate tcp urls currently
         pass
     
     return True
 
 
 def validate_url_container(container):
     """validate a potentially nested collection of urls."""
     if isinstance(container, basestring):
         url = container
         return validate_url(url)
     elif isinstance(container, dict):
         container = container.itervalues()
     
     for element in container:
         validate_url_container(element)
 
 
 def split_url(url):
     """split a zmq url (tcp://ip:port) into ('tcp','ip','port')."""
     proto_addr = url.split('://')
     assert len(proto_addr) == 2, 'Invalid url: %r'%url
     proto, addr = proto_addr
     lis = addr.split(':')
     assert len(lis) == 2, 'Invalid url: %r'%url
     addr,s_port = lis
     return proto,addr,s_port
     
 def disambiguate_ip_address(ip, location=None):
     """turn multi-ip interfaces '0.0.0.0' and '*' into connectable
     ones, based on the location (default interpretation of location is localhost)."""
     if ip in ('0.0.0.0', '*'):
         try:
             external_ips = socket.gethostbyname_ex(socket.gethostname())[2]
         except (socket.gaierror, IndexError):
             # couldn't identify this machine, assume localhost
             external_ips = []
         if location is None or location in external_ips or not external_ips:
             # If location is unspecified or cannot be determined, assume local
             ip='127.0.0.1'
         elif location:
             return location
     return ip
 
 def disambiguate_url(url, location=None):
     """turn multi-ip interfaces '0.0.0.0' and '*' into connectable
     ones, based on the location (default interpretation is localhost).
     
     This is for zeromq urls, such as tcp://*:10101."""
     try:
         proto,ip,port = split_url(url)
     except AssertionError:
         # probably not tcp url; could be ipc, etc.
         return url
     
     ip = disambiguate_ip_address(ip,location)
     
     return "%s://%s:%s"%(proto,ip,port)
 
 
 #--------------------------------------------------------------------------
 # helpers for implementing old MEC API via view.apply
 #--------------------------------------------------------------------------
 
 def interactive(f):
     """decorator for making functions appear as interactively defined.
     This results in the function being linked to the user_ns as globals()
     instead of the module globals().
     """
     f.__module__ = '__main__'
     return f
 
 @interactive
 def _push(**ns):
     """helper method for implementing `client.push` via `client.apply`"""
     globals().update(ns)
 
 @interactive
 def _pull(keys):
     """helper method for implementing `client.pull` via `client.apply`"""
     user_ns = globals()
     if isinstance(keys, (list,tuple, set)):
         for key in keys:
             if key not in user_ns:
                 raise NameError("name '%s' is not defined"%key)
         return map(user_ns.get, keys)
     else:
         if keys not in user_ns:
             raise NameError("name '%s' is not defined"%keys)
         return user_ns.get(keys)
 
 @interactive
 def _execute(code):
     """helper method for implementing `client.execute` via `client.apply`"""
     exec code in globals()
 
 #--------------------------------------------------------------------------
 # extra process management utilities
 #--------------------------------------------------------------------------
 
 _random_ports = set()
 
 def select_random_ports(n):
     """Selects and return n random ports that are available."""
     ports = []
     for i in xrange(n):
         sock = socket.socket()
         sock.bind(('', 0))
         while sock.getsockname()[1] in _random_ports:
             sock.close()
             sock = socket.socket()
             sock.bind(('', 0))
         ports.append(sock)
     for i, sock in enumerate(ports):
         port = sock.getsockname()[1]
         sock.close()
         ports[i] = port
         _random_ports.add(port)
     return ports
 
 def signal_children(children):
     """Relay interupt/term signals to children, for more solid process cleanup."""
     def terminate_children(sig, frame):
         log = Application.instance().log
         log.critical("Got signal %i, terminating children..."%sig)
         for child in children:
             child.terminate()
         
         sys.exit(sig != SIGINT)
         # sys.exit(sig)
     for sig in (SIGINT, SIGABRT, SIGTERM):
         signal(sig, terminate_children)
 
 def generate_exec_key(keyfile):
     import uuid
     newkey = str(uuid.uuid4())
     with open(keyfile, 'w') as f:
         # f.write('ipython-key ')
         f.write(newkey+'\n')
     # set user-only RW permissions (0600)
     # this will have no effect on Windows
     os.chmod(keyfile, stat.S_IRUSR|stat.S_IWUSR)
 
 
 def integer_loglevel(loglevel):
     try:
         loglevel = int(loglevel)
     except ValueError:
         if isinstance(loglevel, str):
             loglevel = getattr(logging, loglevel)
     return loglevel
 
 def connect_logger(logname, context, iface, root="ip", loglevel=logging.DEBUG):
     logger = logging.getLogger(logname)
     if any([isinstance(h, handlers.PUBHandler) for h in logger.handlers]):
         # don't add a second PUBHandler
         return
     loglevel = integer_loglevel(loglevel)
     lsock = context.socket(zmq.PUB)
     lsock.connect(iface)
     handler = handlers.PUBHandler(lsock)
     handler.setLevel(loglevel)
     handler.root_topic = root
     logger.addHandler(handler)
     logger.setLevel(loglevel)
 
 def connect_engine_logger(context, iface, engine, loglevel=logging.DEBUG):
     logger = logging.getLogger()
     if any([isinstance(h, handlers.PUBHandler) for h in logger.handlers]):
         # don't add a second PUBHandler
         return
     loglevel = integer_loglevel(loglevel)
     lsock = context.socket(zmq.PUB)
     lsock.connect(iface)
     handler = EnginePUBHandler(engine, lsock)
     handler.setLevel(loglevel)
     logger.addHandler(handler)
     logger.setLevel(loglevel)
     return logger
 
 def local_logger(logname, loglevel=logging.DEBUG):
     loglevel = integer_loglevel(loglevel)
     logger = logging.getLogger(logname)
     if any([isinstance(h, logging.StreamHandler) for h in logger.handlers]):
         # don't add a second StreamHandler
         return
     handler = logging.StreamHandler()
     handler.setLevel(loglevel)
     formatter = logging.Formatter("%(asctime)s.%(msecs).03d [%(name)s] %(message)s",
                 datefmt="%Y-%m-%d %H:%M:%S")
     handler.setFormatter(formatter)
 
     logger.addHandler(handler)
     logger.setLevel(loglevel)
     return logger
 

IPython/utils/pickleutil.py

@@ -1,151 +1,232 b''
 # encoding: utf-8
 
 """Pickle related utilities. Perhaps this should be called 'can'."""
 
 __docformat__ = "restructuredtext en"
 
 #-------------------------------------------------------------------------------
 #  Copyright (C) 2008-2011  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 copy
 import sys
 from types import FunctionType
 
+try:
+    import cPickle as pickle
+except ImportError:
+    import pickle
+
+try:
+    import numpy
+except:
+    numpy = None
+
 import codeutil
+import py3compat
+from importstring import import_item
+
+if py3compat.PY3:
+    buffer = memoryview
 
 #-------------------------------------------------------------------------------
 # Classes
 #-------------------------------------------------------------------------------
 
 
 class CannedObject(object):
     def __init__(self, obj, keys=[]):
         self.keys = keys
         self.obj = copy.copy(obj)
         for key in keys:
             setattr(self.obj, key, can(getattr(obj, key)))
 
+        self.buffers = []
 
-    def getObject(self, g=None):
+    def get_object(self, g=None):
         if g is None:
-            g = globals()
+            g = {}
         for key in self.keys:
             setattr(self.obj, key, uncan(getattr(self.obj, key), g))
         return self.obj
 
+
 class Reference(CannedObject):
     """object for wrapping a remote reference by name."""
     def __init__(self, name):
         if not isinstance(name, basestring):
             raise TypeError("illegal name: %r"%name)
         self.name = name
+        self.buffers = []
 
     def __repr__(self):
         return "<Reference: %r>"%self.name
 
-    def getObject(self, g=None):
+    def get_object(self, g=None):
         if g is None:
-            g = globals()
+            g = {}
         
         return eval(self.name, g)
 
 
 class CannedFunction(CannedObject):
 
     def __init__(self, f):
-        self._checkType(f)
+        self._check_type(f)
         self.code = f.func_code
         self.defaults = f.func_defaults
         self.module = f.__module__ or '__main__'
         self.__name__ = f.__name__
+        self.buffers = []
 
-    def _checkType(self, obj):
+    def _check_type(self, obj):
         assert isinstance(obj, FunctionType), "Not a function type"
 
-    def getObject(self, g=None):
+    def get_object(self, g=None):
         # try to load function back into its module:
         if not self.module.startswith('__'):
             try:
                 __import__(self.module)
             except ImportError:
                 pass
             else:
                 g = sys.modules[self.module].__dict__
 
         if g is None:
-            g = globals()
+            g = {}
         newFunc = FunctionType(self.code, g, self.__name__, self.defaults)
         return newFunc
 
+
+class CannedArray(CannedObject):
+    def __init__(self, obj):
+        self.shape = obj.shape
+        self.dtype = obj.dtype
+        if sum(obj.shape) == 0:
+            # just pickle it
+            self.buffers = [pickle.dumps(obj, -1)]
+        else:
+            # ensure contiguous
+            obj = numpy.ascontiguousarray(obj, dtype=None)
+            self.buffers = [buffer(obj)]
+    
+    def get_object(self, g=None):
+        data = self.buffers[0]
+        if sum(self.shape) == 0:
+            # no shape, we just pickled it
+            return pickle.loads(data)
+        else:
+            return numpy.frombuffer(data, dtype=self.dtype).reshape(self.shape)
+
+
+class CannedBytes(CannedObject):
+    wrap = bytes
+    def __init__(self, obj):
+        self.buffers = [obj]
+    
+    def get_object(self, g=None):
+        data = self.buffers[0]
+        return self.wrap(data)
+
+def CannedBuffer(CannedBytes):
+    wrap = buffer
+
 #-------------------------------------------------------------------------------
 # Functions
 #-------------------------------------------------------------------------------
 
+
 def can(obj):
-    # import here to prevent module-level circular imports
-    from IPython.parallel import dependent
-    if isinstance(obj, dependent):
-        keys = ('f','df')
-        return CannedObject(obj, keys=keys)
-    elif isinstance(obj, FunctionType):
-        return CannedFunction(obj)
-    elif isinstance(obj,dict):
-        return canDict(obj)
-    elif isinstance(obj, (list,tuple)):
-        return canSequence(obj)
-    else:
+    """prepare an object for pickling"""
+    for cls,canner in can_map.iteritems():
+        if isinstance(cls, basestring):
+            try:
+                cls = import_item(cls)
+            except Exception:
+                # not importable
+                print "not importable: %r" % cls
+                continue
+        if isinstance(obj, cls):
+            return canner(obj)
         return obj
 
-def canDict(obj):
+def can_dict(obj):
+    """can the *values* of a dict"""
     if isinstance(obj, dict):
         newobj = {}
         for k, v in obj.iteritems():
             newobj[k] = can(v)
         return newobj
     else:
         return obj
 
-def canSequence(obj):
+def can_sequence(obj):
+    """can the elements of a sequence"""
     if isinstance(obj, (list, tuple)):
         t = type(obj)
         return t([can(i) for i in obj])
     else:
         return obj
 
 def uncan(obj, g=None):
-    if isinstance(obj, CannedObject):
-        return obj.getObject(g)
-    elif isinstance(obj,dict):
-        return uncanDict(obj, g)
-    elif isinstance(obj, (list,tuple)):
-        return uncanSequence(obj, g)
-    else:
+    """invert canning"""
+    for cls,uncanner in uncan_map.iteritems():
+        if isinstance(cls, basestring):
+            try:
+                cls = import_item(cls)
+            except Exception:
+                # not importable
+                print "not importable: %r" % cls
+                continue
+        if isinstance(obj, cls):
+            return uncanner(obj, g)
         return obj
 
-def uncanDict(obj, g=None):
+def uncan_dict(obj, g=None):
     if isinstance(obj, dict):
         newobj = {}
         for k, v in obj.iteritems():
             newobj[k] = uncan(v,g)
         return newobj
     else:
         return obj
 
-def uncanSequence(obj, g=None):
+def uncan_sequence(obj, g=None):
     if isinstance(obj, (list, tuple)):
         t = type(obj)
         return t([uncan(i,g) for i in obj])
     else:
         return obj
 
 
-def rebindFunctionGlobals(f, glbls):
-    return FunctionType(f.func_code, glbls)
+#-------------------------------------------------------------------------------
+# API dictionary
+#-------------------------------------------------------------------------------
+
+# These dicts can be extended for custom serialization of new objects
+
+can_map = {
+    'IPython.parallel.dependent' : lambda obj: CannedObject(obj, keys=('f','df')),
+    'numpy.ndarray' : CannedArray,
+    FunctionType : CannedFunction,
+    bytes : CannedBytes,
+    buffer : CannedBuffer,
+    # dict : can_dict,
+    # list : can_sequence,
+    # tuple : can_sequence,
+}
+
+uncan_map = {
+    CannedObject : lambda obj, g: obj.get_object(g),
+    # dict : uncan_dict,
+    # list : uncan_sequence,
+    # tuple : uncan_sequence,
+}
+

IPython/zmq/ipkernel.py

@@ -1,925 +1,925 b''
 #!/usr/bin/env python
 """A simple interactive kernel that talks to a frontend over 0MQ.
 
 Things to do:
 
 * Implement `set_parent` logic. Right before doing exec, the Kernel should
   call set_parent on all the PUB objects with the message about to be executed.
 * Implement random port and security key logic.
 * Implement control messages.
 * Implement event loop and poll version.
 """
 
 #-----------------------------------------------------------------------------
 # Imports
 #-----------------------------------------------------------------------------
 from __future__ import print_function
 
 # Standard library imports
 import __builtin__
 import atexit
 import sys
 import time
 import traceback
 import logging
 import uuid
 
 from datetime import datetime
 from signal import (
         signal, getsignal, default_int_handler, SIGINT, SIG_IGN
 )
 
 # System library imports
 import zmq
 from zmq.eventloop import ioloop
 from zmq.eventloop.zmqstream import ZMQStream
 
 # Local imports
 from IPython.config.configurable import Configurable
 from IPython.config.application import boolean_flag, catch_config_error
 from IPython.core.application import ProfileDir
 from IPython.core.error import StdinNotImplementedError
 from IPython.core.shellapp import (
     InteractiveShellApp, shell_flags, shell_aliases
 )
 from IPython.utils import io
 from IPython.utils import py3compat
 from IPython.utils.frame import extract_module_locals
 from IPython.utils.jsonutil import json_clean
 from IPython.utils.traitlets import (
     Any, Instance, Float, Dict, CaselessStrEnum, List, Set, Integer, Unicode
 )
 
 from entry_point import base_launch_kernel
 from kernelapp import KernelApp, kernel_flags, kernel_aliases
 from serialize import serialize_object, unpack_apply_message
 from session import Session, Message
 from zmqshell import ZMQInteractiveShell
 
 
 #-----------------------------------------------------------------------------
 # Main kernel class
 #-----------------------------------------------------------------------------
 
 class Kernel(Configurable):
 
     #---------------------------------------------------------------------------
     # Kernel interface
     #---------------------------------------------------------------------------
 
     # attribute to override with a GUI
     eventloop = Any(None)
     def _eventloop_changed(self, name, old, new):
         """schedule call to eventloop from IOLoop"""
         loop = ioloop.IOLoop.instance()
         loop.add_timeout(time.time()+0.1, self.enter_eventloop)
 
     shell = Instance('IPython.core.interactiveshell.InteractiveShellABC')
     session = Instance(Session)
     profile_dir = Instance('IPython.core.profiledir.ProfileDir')
     shell_streams = List()
     control_stream = Instance(ZMQStream)
     iopub_socket = Instance(zmq.Socket)
     stdin_socket = Instance(zmq.Socket)
     log = Instance(logging.Logger)
     
     user_module = Any()
     def _user_module_changed(self, name, old, new):
         if self.shell is not None:
             self.shell.user_module = new
     
     user_ns = Dict(default_value=None)
     def _user_ns_changed(self, name, old, new):
         if self.shell is not None:
             self.shell.user_ns = new
             self.shell.init_user_ns()
 
     # identities:
     int_id = Integer(-1)
     ident = Unicode()
 
     def _ident_default(self):
         return unicode(uuid.uuid4())
 
 
     # Private interface
     
     # Time to sleep after flushing the stdout/err buffers in each execute
     # cycle.  While this introduces a hard limit on the minimal latency of the
     # execute cycle, it helps prevent output synchronization problems for
     # clients.
     # Units are in seconds.  The minimum zmq latency on local host is probably
     # ~150 microseconds, set this to 500us for now.  We may need to increase it
     # a little if it's not enough after more interactive testing.
     _execute_sleep = Float(0.0005, config=True)
 
     # Frequency of the kernel's event loop.
     # Units are in seconds, kernel subclasses for GUI toolkits may need to
     # adapt to milliseconds.
     _poll_interval = Float(0.05, config=True)
 
     # If the shutdown was requested over the network, we leave here the
     # necessary reply message so it can be sent by our registered atexit
     # handler.  This ensures that the reply is only sent to clients truly at
     # the end of our shutdown process (which happens after the underlying
     # IPython shell's own shutdown).
     _shutdown_message = None
 
     # This is a dict of port number that the kernel is listening on. It is set
     # by record_ports and used by connect_request.
     _recorded_ports = Dict()
     
     # set of aborted msg_ids
     aborted = Set()
 
 
     def __init__(self, **kwargs):
         super(Kernel, self).__init__(**kwargs)
 
         # Initialize the InteractiveShell subclass
         self.shell = ZMQInteractiveShell.instance(config=self.config,
             profile_dir = self.profile_dir,
             user_module = self.user_module,
             user_ns     = self.user_ns,
         )
         self.shell.displayhook.session = self.session
         self.shell.displayhook.pub_socket = self.iopub_socket
         self.shell.displayhook.topic = self._topic('pyout')
         self.shell.display_pub.session = self.session
         self.shell.display_pub.pub_socket = self.iopub_socket
 
         # TMP - hack while developing
         self.shell._reply_content = None
 
         # Build dict of handlers for message types
         msg_types = [ 'execute_request', 'complete_request',
                       'object_info_request', 'history_request',
                       'connect_request', 'shutdown_request',
                       'apply_request',
                     ]
         self.shell_handlers = {}
         for msg_type in msg_types:
             self.shell_handlers[msg_type] = getattr(self, msg_type)
         
         control_msg_types = msg_types + [ 'clear_request', 'abort_request' ]
         self.control_handlers = {}
         for msg_type in control_msg_types:
             self.control_handlers[msg_type] = getattr(self, msg_type)
 
     def dispatch_control(self, msg):
         """dispatch control requests"""
         idents,msg = self.session.feed_identities(msg, copy=False)
         try:
             msg = self.session.unserialize(msg, content=True, copy=False)
         except:
             self.log.error("Invalid Control Message", exc_info=True)
             return
 
         self.log.debug("Control received: %s", msg)
 
         header = msg['header']
         msg_id = header['msg_id']
         msg_type = header['msg_type']
 
         handler = self.control_handlers.get(msg_type, None)
         if handler is None:
             self.log.error("UNKNOWN CONTROL MESSAGE TYPE: %r", msg_type)
         else:
             try:
                 handler(self.control_stream, idents, msg)
             except Exception:
                 self.log.error("Exception in control handler:", exc_info=True)
     
     def dispatch_shell(self, stream, msg):
         """dispatch shell requests"""
         # flush control requests first
         if self.control_stream:
             self.control_stream.flush()
         
         idents,msg = self.session.feed_identities(msg, copy=False)
         try:
             msg = self.session.unserialize(msg, content=True, copy=False)
         except:
             self.log.error("Invalid Message", exc_info=True)
             return
 
         header = msg['header']
         msg_id = header['msg_id']
         msg_type = msg['header']['msg_type']
         
         # Print some info about this message and leave a '--->' marker, so it's
         # easier to trace visually the message chain when debugging.  Each
         # handler prints its message at the end.
         self.log.debug('\n*** MESSAGE TYPE:%s***', msg_type)
         self.log.debug('   Content: %s\n   --->\n   ', msg['content'])
 
         if msg_id in self.aborted:
             self.aborted.remove(msg_id)
             # is it safe to assume a msg_id will not be resubmitted?
             reply_type = msg_type.split('_')[0] + '_reply'
             status = {'status' : 'aborted'}
             md = {'engine' : self.ident}
             md.update(status)
             reply_msg = self.session.send(stream, reply_type, metadata=md,
                         content=status, parent=msg, ident=idents)
             return
         
         handler = self.shell_handlers.get(msg_type, None)
         if handler is None:
             self.log.error("UNKNOWN MESSAGE TYPE: %r", msg_type)
         else:
             # ensure default_int_handler during handler call
             sig = signal(SIGINT, default_int_handler)
             try:
                 handler(stream, idents, msg)
             except Exception:
                 self.log.error("Exception in message handler:", exc_info=True)
             finally:
                 signal(SIGINT, sig)
     
     def enter_eventloop(self):
         """enter eventloop"""
         self.log.info("entering eventloop")
         # restore default_int_handler
         signal(SIGINT, default_int_handler)
         while self.eventloop is not None:
             try:
                 self.eventloop(self)
             except KeyboardInterrupt:
                 # Ctrl-C shouldn't crash the kernel
                 self.log.error("KeyboardInterrupt caught in kernel")
                 continue
             else:
                 # eventloop exited cleanly, this means we should stop (right?)
                 self.eventloop = None
                 break
         self.log.info("exiting eventloop")
         # if eventloop exits, IOLoop should stop
         ioloop.IOLoop.instance().stop()
 
     def start(self):
         """register dispatchers for streams"""
         self.shell.exit_now = False
         if self.control_stream:
             self.control_stream.on_recv(self.dispatch_control, copy=False)
 
         def make_dispatcher(stream):
             def dispatcher(msg):
                 return self.dispatch_shell(stream, msg)
             return dispatcher
 
         for s in self.shell_streams:
             s.on_recv(make_dispatcher(s), copy=False)
     
     def do_one_iteration(self):
         """step eventloop just once"""
         if self.control_stream:
             self.control_stream.flush()
         for stream in self.shell_streams:
             # handle at most one request per iteration
             stream.flush(zmq.POLLIN, 1)
             stream.flush(zmq.POLLOUT)
 
 
     def record_ports(self, ports):
         """Record the ports that this kernel is using.
 
         The creator of the Kernel instance must call this methods if they
         want the :meth:`connect_request` method to return the port numbers.
         """
         self._recorded_ports = ports
 
     #---------------------------------------------------------------------------
     # Kernel request handlers
     #---------------------------------------------------------------------------
     
     def _make_metadata(self, other=None):
         """init metadata dict, for execute/apply_reply"""
         new_md = {
             'dependencies_met' : True,
             'engine' : self.ident,
             'started': datetime.now(),
         }
         if other:
             new_md.update(other)
         return new_md
     
     def _publish_pyin(self, code, parent, execution_count):
         """Publish the code request on the pyin stream."""
 
         self.session.send(self.iopub_socket, u'pyin',
                             {u'code':code, u'execution_count': execution_count},
                             parent=parent, ident=self._topic('pyin')
         )
     
     def _publish_status(self, status, parent=None):
         """send status (busy/idle) on IOPub"""
         self.session.send(self.iopub_socket,
                           u'status',
                           {u'execution_state': status},
                           parent=parent,
                           ident=self._topic('status'),
                           )
         
 
     def execute_request(self, stream, ident, parent):
         """handle an execute_request"""
         
         self._publish_status(u'busy', parent)
         
         try:
             content = parent[u'content']
             code = content[u'code']
             silent = content[u'silent']
         except:
             self.log.error("Got bad msg: ")
             self.log.error("%s", parent)
             return
         
         md = self._make_metadata(parent['metadata'])
 
         shell = self.shell # we'll need this a lot here
 
         # Replace raw_input. Note that is not sufficient to replace
         # raw_input in the user namespace.
         if content.get('allow_stdin', False):
             raw_input = lambda prompt='': self._raw_input(prompt, ident, parent)
         else:
             raw_input = lambda prompt='' : self._no_raw_input()
 
         if py3compat.PY3:
             __builtin__.input = raw_input
         else:
             __builtin__.raw_input = raw_input
 
         # Set the parent message of the display hook and out streams.
         shell.displayhook.set_parent(parent)
         shell.display_pub.set_parent(parent)
         sys.stdout.set_parent(parent)
         sys.stderr.set_parent(parent)
 
         # Re-broadcast our input for the benefit of listening clients, and
         # start computing output
         if not silent:
             self._publish_pyin(code, parent, shell.execution_count)
 
         reply_content = {}
         try:
             # FIXME: the shell calls the exception handler itself.
             shell.run_cell(code, store_history=not silent, silent=silent)
         except:
             status = u'error'
             # FIXME: this code right now isn't being used yet by default,
             # because the run_cell() call above directly fires off exception
             # reporting.  This code, therefore, is only active in the scenario
             # where runlines itself has an unhandled exception.  We need to
             # uniformize this, for all exception construction to come from a
             # single location in the codbase.
             etype, evalue, tb = sys.exc_info()
             tb_list = traceback.format_exception(etype, evalue, tb)
             reply_content.update(shell._showtraceback(etype, evalue, tb_list))
         else:
             status = u'ok'
 
         reply_content[u'status'] = status
 
         # Return the execution counter so clients can display prompts
         reply_content['execution_count'] = shell.execution_count - 1
 
         # FIXME - fish exception info out of shell, possibly left there by
         # runlines.  We'll need to clean up this logic later.
         if shell._reply_content is not None:
             reply_content.update(shell._reply_content)
             e_info = dict(engine_uuid=self.ident, engine_id=self.int_id, method='execute')
             reply_content['engine_info'] = e_info
             # reset after use
             shell._reply_content = None
 
         # At this point, we can tell whether the main code execution succeeded
         # or not.  If it did, we proceed to evaluate user_variables/expressions
         if reply_content['status'] == 'ok':
             reply_content[u'user_variables'] = \
                          shell.user_variables(content.get(u'user_variables', []))
             reply_content[u'user_expressions'] = \
                          shell.user_expressions(content.get(u'user_expressions', {}))
         else:
             # If there was an error, don't even try to compute variables or
             # expressions
             reply_content[u'user_variables'] = {}
             reply_content[u'user_expressions'] = {}
 
         # Payloads should be retrieved regardless of outcome, so we can both
         # recover partial output (that could have been generated early in a
         # block, before an error) and clear the payload system always.
         reply_content[u'payload'] = shell.payload_manager.read_payload()
         # Be agressive about clearing the payload because we don't want
         # it to sit in memory until the next execute_request comes in.
         shell.payload_manager.clear_payload()
 
         # Flush output before sending the reply.
         sys.stdout.flush()
         sys.stderr.flush()
         # FIXME: on rare occasions, the flush doesn't seem to make it to the
         # clients... This seems to mitigate the problem, but we definitely need
         # to better understand what's going on.
         if self._execute_sleep:
             time.sleep(self._execute_sleep)
 
         # Send the reply.
         reply_content = json_clean(reply_content)
         
         md['status'] = reply_content['status']
         if reply_content['status'] == 'error' and \
                         reply_content['ename'] == 'UnmetDependency':
                 md['dependencies_met'] = False
 
         reply_msg = self.session.send(stream, u'execute_reply',
                                       reply_content, parent, metadata=md,
                                       ident=ident)
         
         self.log.debug("%s", reply_msg)
 
         if not silent and reply_msg['content']['status'] == u'error':
             self._abort_queues()
 
         self._publish_status(u'idle', parent)
 
     def complete_request(self, stream, ident, parent):
         txt, matches = self._complete(parent)
         matches = {'matches' : matches,
                    'matched_text' : txt,
                    'status' : 'ok'}
         matches = json_clean(matches)
         completion_msg = self.session.send(stream, 'complete_reply',
                                            matches, parent, ident)
         self.log.debug("%s", completion_msg)
 
     def object_info_request(self, stream, ident, parent):
         content = parent['content']
         object_info = self.shell.object_inspect(content['oname'],
                         detail_level = content.get('detail_level', 0)
         )
         # Before we send this object over, we scrub it for JSON usage
         oinfo = json_clean(object_info)
         msg = self.session.send(stream, 'object_info_reply',
                                 oinfo, parent, ident)
         self.log.debug("%s", msg)
 
     def history_request(self, stream, ident, parent):
         # We need to pull these out, as passing **kwargs doesn't work with
         # unicode keys before Python 2.6.5.
         hist_access_type = parent['content']['hist_access_type']
         raw = parent['content']['raw']
         output = parent['content']['output']
         if hist_access_type == 'tail':
             n = parent['content']['n']
             hist = self.shell.history_manager.get_tail(n, raw=raw, output=output,
                                                             include_latest=True)
 
         elif hist_access_type == 'range':
             session = parent['content']['session']
             start = parent['content']['start']
             stop = parent['content']['stop']
             hist = self.shell.history_manager.get_range(session, start, stop,
                                                         raw=raw, output=output)
 
         elif hist_access_type == 'search':
             pattern = parent['content']['pattern']
             hist = self.shell.history_manager.search(pattern, raw=raw,
                                                      output=output) 
 
         else:
             hist = []
         hist = list(hist)
         content = {'history' : hist}
         content = json_clean(content)
         msg = self.session.send(stream, 'history_reply',
                                 content, parent, ident)
         self.log.debug("Sending history reply with %i entries", len(hist))
 
     def connect_request(self, stream, ident, parent):
         if self._recorded_ports is not None:
             content = self._recorded_ports.copy()
         else:
             content = {}
         msg = self.session.send(stream, 'connect_reply',
                                 content, parent, ident)
         self.log.debug("%s", msg)
 
     def shutdown_request(self, stream, ident, parent):
         self.shell.exit_now = True
         content = dict(status='ok')
         content.update(parent['content'])
         self.session.send(stream, u'shutdown_reply', content, parent, ident=ident)
         # same content, but different msg_id for broadcasting on IOPub
         self._shutdown_message = self.session.msg(u'shutdown_reply',
                                                   content, parent
         )
 
         self._at_shutdown()
         # call sys.exit after a short delay
         loop = ioloop.IOLoop.instance()
         loop.add_timeout(time.time()+0.1, loop.stop)
 
     #---------------------------------------------------------------------------
     # Engine methods
     #---------------------------------------------------------------------------
 
     def apply_request(self, stream, ident, parent):
         try:
             content = parent[u'content']
             bufs = parent[u'buffers']
             msg_id = parent['header']['msg_id']
         except:
             self.log.error("Got bad msg: %s", parent, exc_info=True)
             return
 
         self._publish_status(u'busy', parent)
         
         # Set the parent message of the display hook and out streams.
         shell = self.shell
         shell.displayhook.set_parent(parent)
         shell.display_pub.set_parent(parent)
         sys.stdout.set_parent(parent)
         sys.stderr.set_parent(parent)
 
         # pyin_msg = self.session.msg(u'pyin',{u'code':code}, parent=parent)
         # self.iopub_socket.send(pyin_msg)
         # self.session.send(self.iopub_socket, u'pyin', {u'code':code},parent=parent)
         md = self._make_metadata(parent['metadata'])
         try:
             working = shell.user_ns
 
             prefix = "_"+str(msg_id).replace("-","")+"_"
 
             f,args,kwargs = unpack_apply_message(bufs, working, copy=False)
 
             fname = getattr(f, '__name__', 'f')
 
             fname = prefix+"f"
             argname = prefix+"args"
             kwargname = prefix+"kwargs"
             resultname = prefix+"result"
 
             ns = { fname : f, argname : args, kwargname : kwargs , resultname : None }
             # print ns
             working.update(ns)
             code = "%s = %s(*%s,**%s)" % (resultname, fname, argname, kwargname)
             try:
                 exec code in shell.user_global_ns, shell.user_ns
                 result = working.get(resultname)
             finally:
                 for key in ns.iterkeys():
                     working.pop(key)
 
-            packed_result,buf = serialize_object(result)
-            result_buf = [packed_result]+buf
+            result_buf = serialize_object(result)
+        
         except:
             # invoke IPython traceback formatting
             shell.showtraceback()
             # FIXME - fish exception info out of shell, possibly left there by
             # run_code.  We'll need to clean up this logic later.
             reply_content = {}
             if shell._reply_content is not None:
                 reply_content.update(shell._reply_content)
                 e_info = dict(engine_uuid=self.ident, engine_id=self.int_id, method='apply')
                 reply_content['engine_info'] = e_info
                 # reset after use
                 shell._reply_content = None
             
             self.session.send(self.iopub_socket, u'pyerr', reply_content, parent=parent,
                                 ident=self._topic('pyerr'))
             result_buf = []
 
             if reply_content['ename'] == 'UnmetDependency':
                 md['dependencies_met'] = False
         else:
             reply_content = {'status' : 'ok'}
 
         # put 'ok'/'error' status in header, for scheduler introspection:
         md['status'] = reply_content['status']
 
         # flush i/o
         sys.stdout.flush()
         sys.stderr.flush()
         
         reply_msg = self.session.send(stream, u'apply_reply', reply_content,
                     parent=parent, ident=ident,buffers=result_buf, metadata=md)
 
         self._publish_status(u'idle', parent)
 
     #---------------------------------------------------------------------------
     # Control messages
     #---------------------------------------------------------------------------
 
     def abort_request(self, stream, ident, parent):
         """abort a specifig msg by id"""
         msg_ids = parent['content'].get('msg_ids', None)
         if isinstance(msg_ids, basestring):
             msg_ids = [msg_ids]
         if not msg_ids:
             self.abort_queues()
         for mid in msg_ids:
             self.aborted.add(str(mid))
 
         content = dict(status='ok')
         reply_msg = self.session.send(stream, 'abort_reply', content=content,
                 parent=parent, ident=ident)
         self.log.debug("%s", reply_msg)
 
     def clear_request(self, stream, idents, parent):
         """Clear our namespace."""
         self.shell.reset(False)
         msg = self.session.send(stream, 'clear_reply', ident=idents, parent=parent,
                 content = dict(status='ok'))
 
 
     #---------------------------------------------------------------------------
     # Protected interface
     #---------------------------------------------------------------------------
 
 
     def _wrap_exception(self, method=None):
         # import here, because _wrap_exception is only used in parallel,
         # and parallel has higher min pyzmq version
         from IPython.parallel.error import wrap_exception
         e_info = dict(engine_uuid=self.ident, engine_id=self.int_id, method=method)
         content = wrap_exception(e_info)
         return content
 
     def _topic(self, topic):
         """prefixed topic for IOPub messages"""
         if self.int_id >= 0:
             base = "engine.%i" % self.int_id
         else:
             base = "kernel.%s" % self.ident
         
         return py3compat.cast_bytes("%s.%s" % (base, topic))
     
     def _abort_queues(self):
         for stream in self.shell_streams:
             if stream:
                 self._abort_queue(stream)
 
     def _abort_queue(self, stream):
         poller = zmq.Poller()
         poller.register(stream.socket, zmq.POLLIN)
         while True:
             idents,msg = self.session.recv(stream, zmq.NOBLOCK, content=True)
             if msg is None:
                 return
 
             self.log.info("Aborting:")
             self.log.info("%s", msg)
             msg_type = msg['header']['msg_type']
             reply_type = msg_type.split('_')[0] + '_reply'
 
             status = {'status' : 'aborted'}
             md = {'engine' : self.ident}
             md.update(status)
             reply_msg = self.session.send(stream, reply_type, meatadata=md,
                         content=status, parent=msg, ident=idents)
             self.log.debug("%s", reply_msg)
             # We need to wait a bit for requests to come in. This can probably
             # be set shorter for true asynchronous clients.
             poller.poll(50)
 
 
     def _no_raw_input(self):
         """Raise StdinNotImplentedError if active frontend doesn't support
         stdin."""
         raise StdinNotImplementedError("raw_input was called, but this "
                                        "frontend does not support stdin.") 
         
     def _raw_input(self, prompt, ident, parent):
         # Flush output before making the request.
         sys.stderr.flush()
         sys.stdout.flush()
 
         # Send the input request.
         content = json_clean(dict(prompt=prompt))
         self.session.send(self.stdin_socket, u'input_request', content, parent,
                           ident=ident)
 
         # Await a response.
         while True:
             try:
                 ident, reply = self.session.recv(self.stdin_socket, 0)
             except Exception:
                 self.log.warn("Invalid Message:", exc_info=True)
             else:
                 break
         try:
             value = reply['content']['value']
         except:
             self.log.error("Got bad raw_input reply: ")
             self.log.error("%s", parent)
             value = ''
         if value == '\x04':
             # EOF
             raise EOFError
         return value
 
     def _complete(self, msg):
         c = msg['content']
         try:
             cpos = int(c['cursor_pos'])
         except:
             # If we don't get something that we can convert to an integer, at
             # least attempt the completion guessing the cursor is at the end of
             # the text, if there's any, and otherwise of the line
             cpos = len(c['text'])
             if cpos==0:
                 cpos = len(c['line'])
         return self.shell.complete(c['text'], c['line'], cpos)
 
     def _object_info(self, context):
         symbol, leftover = self._symbol_from_context(context)
         if symbol is not None and not leftover:
             doc = getattr(symbol, '__doc__', '')
         else:
             doc = ''
         object_info = dict(docstring = doc)
         return object_info
 
     def _symbol_from_context(self, context):
         if not context:
             return None, context
 
         base_symbol_string = context[0]
         symbol = self.shell.user_ns.get(base_symbol_string, None)
         if symbol is None:
             symbol = __builtin__.__dict__.get(base_symbol_string, None)
         if symbol is None:
             return None, context
 
         context = context[1:]
         for i, name in enumerate(context):
             new_symbol = getattr(symbol, name, None)
             if new_symbol is None:
                 return symbol, context[i:]
             else:
                 symbol = new_symbol
 
         return symbol, []
 
     def _at_shutdown(self):
         """Actions taken at shutdown by the kernel, called by python's atexit.
         """
         # io.rprint("Kernel at_shutdown") # dbg
         if self._shutdown_message is not None:
             self.session.send(self.iopub_socket, self._shutdown_message, ident=self._topic('shutdown'))
             self.log.debug("%s", self._shutdown_message)
         [ s.flush(zmq.POLLOUT) for s in self.shell_streams ]
 
 #-----------------------------------------------------------------------------
 # Aliases and Flags for the IPKernelApp
 #-----------------------------------------------------------------------------
 
 flags = dict(kernel_flags)
 flags.update(shell_flags)
 
 addflag = lambda *args: flags.update(boolean_flag(*args))
 
 flags['pylab'] = (
     {'IPKernelApp' : {'pylab' : 'auto'}},
     """Pre-load matplotlib and numpy for interactive use with
     the default matplotlib backend."""
 )
 
 aliases = dict(kernel_aliases)
 aliases.update(shell_aliases)
 
 #-----------------------------------------------------------------------------
 # The IPKernelApp class
 #-----------------------------------------------------------------------------
 
 class IPKernelApp(KernelApp, InteractiveShellApp):
     name = 'ipkernel'
 
     aliases = Dict(aliases)
     flags = Dict(flags)
     classes = [Kernel, ZMQInteractiveShell, ProfileDir, Session]
 
     @catch_config_error
     def initialize(self, argv=None):
         super(IPKernelApp, self).initialize(argv)
         self.init_path()
         self.init_shell()
         self.init_gui_pylab()
         self.init_extensions()
         self.init_code()
 
     def init_kernel(self):
         
         shell_stream = ZMQStream(self.shell_socket)
 
         kernel = Kernel(config=self.config, session=self.session,
                                 shell_streams=[shell_stream],
                                 iopub_socket=self.iopub_socket,
                                 stdin_socket=self.stdin_socket,
                                 log=self.log,
                                 profile_dir=self.profile_dir,
         )
         self.kernel = kernel
         kernel.record_ports(self.ports)
         shell = kernel.shell
 
     def init_gui_pylab(self):
         """Enable GUI event loop integration, taking pylab into account."""
 
         # Provide a wrapper for :meth:`InteractiveShellApp.init_gui_pylab`
         # to ensure that any exception is printed straight to stderr.
         # Normally _showtraceback associates the reply with an execution,
         # which means frontends will never draw it, as this exception
         # is not associated with any execute request.
 
         shell = self.shell
         _showtraceback = shell._showtraceback
         try:
             # replace pyerr-sending traceback with stderr
             def print_tb(etype, evalue, stb):
                 print ("GUI event loop or pylab initialization failed",
                        file=io.stderr)
                 print (shell.InteractiveTB.stb2text(stb), file=io.stderr)
             shell._showtraceback = print_tb
             InteractiveShellApp.init_gui_pylab(self)
         finally:
             shell._showtraceback = _showtraceback
 
     def init_shell(self):
         self.shell = self.kernel.shell
         self.shell.configurables.append(self)
 
 
 #-----------------------------------------------------------------------------
 # Kernel main and launch functions
 #-----------------------------------------------------------------------------
 
 def launch_kernel(*args, **kwargs):
     """Launches a localhost IPython kernel, binding to the specified ports.
 
     This function simply calls entry_point.base_launch_kernel with the right
     first command to start an ipkernel.  See base_launch_kernel for arguments.
 
     Returns
     -------
     A tuple of form:
         (kernel_process, shell_port, iopub_port, stdin_port, hb_port)
     where kernel_process is a Popen object and the ports are integers.
     """
     return base_launch_kernel('from IPython.zmq.ipkernel import main; main()',
                               *args, **kwargs)
 
 
 def embed_kernel(module=None, local_ns=None, **kwargs):
     """Embed and start an IPython kernel in a given scope.
     
     Parameters
     ----------
     module : ModuleType, optional
         The module to load into IPython globals (default: caller)
     local_ns : dict, optional
         The namespace to load into IPython user namespace (default: caller)
     
     kwargs : various, optional
         Further keyword args are relayed to the KernelApp constructor,
         allowing configuration of the Kernel.  Will only have an effect
         on the first embed_kernel call for a given process.
     
     """
     # get the app if it exists, or set it up if it doesn't
     if IPKernelApp.initialized():
         app = IPKernelApp.instance()
     else:
         app = IPKernelApp.instance(**kwargs)
         app.initialize([])
         # Undo unnecessary sys module mangling from init_sys_modules.
         # This would not be necessary if we could prevent it
         # in the first place by using a different InteractiveShell
         # subclass, as in the regular embed case.
         main = app.kernel.shell._orig_sys_modules_main_mod
         if main is not None:
             sys.modules[app.kernel.shell._orig_sys_modules_main_name] = main
 
     # load the calling scope if not given
     (caller_module, caller_locals) = extract_module_locals(1)
     if module is None:
         module = caller_module
     if local_ns is None:
         local_ns = caller_locals
     
     app.kernel.user_module = module
     app.kernel.user_ns = local_ns
     app.shell.set_completer_frame()
     app.start()
 
 def main():
     """Run an IPKernel as an application"""
     app = IPKernelApp.instance()
     app.initialize()
     app.start()
 
 
 if __name__ == '__main__':
     main()

IPython/zmq/serialize.py

@@ -1,179 +1,175 b''
 """serialization utilities for apply messages
 
 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
 #-----------------------------------------------------------------------------
 
 # Standard library imports
 import logging
 import os
 import re
 import socket
 import sys
 
 try:
     import cPickle
     pickle = cPickle
 except:
     cPickle = None
     import pickle
 
 
 # IPython imports
 from IPython.utils import py3compat
-from IPython.utils.pickleutil import can, uncan, canSequence, uncanSequence
+from IPython.utils.pickleutil import (
+    can, uncan, can_sequence, uncan_sequence, CannedObject
+) 
 from IPython.utils.newserialized import serialize, unserialize
 
 if py3compat.PY3:
     buffer = memoryview
 
 #-----------------------------------------------------------------------------
 # Serialization Functions
 #-----------------------------------------------------------------------------
 
-def serialize_object(obj, threshold=64e-6):
+# maximum items to iterate through in a container
+MAX_ITEMS = 64
+
+def _extract_buffers(obj, threshold=1024):
+    """extract buffers larger than a certain threshold"""
+    buffers = []
+    if isinstance(obj, CannedObject) and obj.buffers:
+        for i,buf in enumerate(obj.buffers):
+            if len(buf) > threshold:
+                # buffer larger than threshold, prevent pickling
+                obj.buffers[i] = None
+                buffers.append(buf)
+            elif isinstance(buf, buffer):
+                # buffer too small for separate send, coerce to bytes
+                # because pickling buffer objects just results in broken pointers
+                obj.buffers[i] = bytes(buf)
+    return buffers
+
+def _restore_buffers(obj, buffers):
+    """restore buffers extracted by """
+    if isinstance(obj, CannedObject) and obj.buffers:
+        for i,buf in enumerate(obj.buffers):
+            if buf is None:
+                obj.buffers[i] = buffers.pop(0)
+
+def serialize_object(obj, threshold=1024):
     """Serialize an object into a list of sendable buffers.
     
     Parameters
     ----------
     
     obj : object
         The object to be serialized
-    threshold : float
-        The threshold for not double-pickling the content.
-        
+    threshold : int
+        The threshold (in bytes) for pulling out data buffers
+        to avoid pickling them.
     
     Returns
     -------
-    ('pmd', [bufs]) :
-        where pmd is the pickled metadata wrapper,
-        bufs is a list of data buffers
+    [bufs] : list of buffers representing the serialized object.
     """
-    databuffers = []
-    if isinstance(obj, (list, tuple)):
-        clist = canSequence(obj)
-        slist = map(serialize, clist)
-        for s in slist:
-            if s.typeDescriptor in ('buffer', 'ndarray') or s.getDataSize() > threshold:
-                databuffers.append(s.getData())
-                s.data = None
-        return pickle.dumps(slist,-1), databuffers
-    elif isinstance(obj, dict):
-        sobj = {}
+    buffers = []
+    if isinstance(obj, (list, tuple)) and len(obj) < MAX_ITEMS:
+        cobj = can_sequence(obj)
+        for c in cobj:
+            buffers.extend(_extract_buffers(c, threshold))
+    elif isinstance(obj, dict) and len(obj) < MAX_ITEMS:
+        cobj = {}
         for k in sorted(obj.iterkeys()):
-            s = serialize(can(obj[k]))
-            if s.typeDescriptor in ('buffer', 'ndarray') or s.getDataSize() > threshold:
-                databuffers.append(s.getData())
-                s.data = None
-            sobj[k] = s
-        return pickle.dumps(sobj,-1),databuffers
+            c = can(obj[k])
+            buffers.extend(_extract_buffers(c, threshold))
+            cobj[k] = c
     else:
-        s = serialize(can(obj))
-        if s.typeDescriptor in ('buffer', 'ndarray') or s.getDataSize() > threshold:
-            databuffers.append(s.getData())
-            s.data = None
-        return pickle.dumps(s,-1),databuffers
-            
-        
-def unserialize_object(bufs):
-    """reconstruct an object serialized by serialize_object from data buffers."""
-    bufs = list(bufs)
-    sobj = pickle.loads(bufs.pop(0))
-    if isinstance(sobj, (list, tuple)):
-        for s in sobj:
-            if s.data is None:
-                s.data = bufs.pop(0)
-        return uncanSequence(map(unserialize, sobj)), bufs
-    elif isinstance(sobj, dict):
+        cobj = can(obj)
+        buffers.extend(_extract_buffers(cobj, threshold))
+
+    buffers.insert(0, pickle.dumps(cobj,-1))
+    return buffers
+
+def unserialize_object(buffers, g=None):
+    """reconstruct an object serialized by serialize_object from data buffers.
+    
+    Parameters
+    ----------
+    
+    bufs : list of buffers/bytes
+    
+    g : globals to be used when uncanning
+    
+    Returns
+    -------
+    
+    (newobj, bufs) : unpacked object, and the list of remaining unused buffers.
+    """
+    bufs = list(buffers)
+    canned = pickle.loads(bufs.pop(0))
+    if isinstance(canned, (list, tuple)) and len(canned) < MAX_ITEMS:
+        for c in canned:
+            _restore_buffers(c, bufs)
+        newobj = uncan_sequence(canned, g)
+    elif isinstance(canned, dict) and len(canned) < MAX_ITEMS:
         newobj = {}
-        for k in sorted(sobj.iterkeys()):
-            s = sobj[k]
-            if s.data is None:
-                s.data = bufs.pop(0)
-            newobj[k] = uncan(unserialize(s))
-        return newobj, bufs
+        for k in sorted(canned.iterkeys()):
+            c = canned[k]
+            _restore_buffers(c, bufs)
+            newobj[k] = uncan(c, g)
     else:
-        if sobj.data is None:
-            sobj.data = bufs.pop(0)
-        return uncan(unserialize(sobj)), bufs
+        _restore_buffers(canned, bufs)
+        newobj = uncan(canned, g)
 
-def pack_apply_message(f, args, kwargs, threshold=64e-6):
+    return newobj, bufs
+
+def pack_apply_message(f, args, kwargs, threshold=1024):
     """pack up a function, args, and kwargs to be sent over the wire
     as a series of buffers. Any object whose data is larger than `threshold`
-    will not have their data copied (currently only numpy arrays support zero-copy)"""
+    will not have their data copied (currently only numpy arrays support zero-copy)
+    """
     msg = [pickle.dumps(can(f),-1)]
     databuffers = [] # for large objects
-    sargs, bufs = serialize_object(args,threshold)
-    msg.append(sargs)
-    databuffers.extend(bufs)
-    skwargs, bufs = serialize_object(kwargs,threshold)
-    msg.append(skwargs)
-    databuffers.extend(bufs)
+    sargs = serialize_object(args,threshold)
+    msg.append(sargs[0])
+    databuffers.extend(sargs[1:])
+    skwargs = serialize_object(kwargs,threshold)
+    msg.append(skwargs[0])
+    databuffers.extend(skwargs[1:])
     msg.extend(databuffers)
     return msg
 
 def unpack_apply_message(bufs, g=None, copy=True):
     """unpack f,args,kwargs from buffers packed by pack_apply_message()
     Returns: original f,args,kwargs"""
     bufs = list(bufs) # allow us to pop
     assert len(bufs) >= 3, "not enough buffers!"
     if not copy:
         for i in range(3):
             bufs[i] = bufs[i].bytes
-    cf = pickle.loads(bufs.pop(0))
-    sargs = list(pickle.loads(bufs.pop(0)))
-    skwargs = dict(pickle.loads(bufs.pop(0)))
-    # print sargs, skwargs
-    f = uncan(cf, g)
-    for sa in sargs:
-        if sa.data is None:
-            m = bufs.pop(0)
-            if sa.getTypeDescriptor() in ('buffer', 'ndarray'):
-                # always use a buffer, until memoryviews get sorted out
-                sa.data = buffer(m)
-                # disable memoryview support
-                # if copy:
-                #     sa.data = buffer(m)
-                # else:
-                #     sa.data = m.buffer
-            else:
-                if copy:
-                    sa.data = m
-                else:
-                    sa.data = m.bytes
-    
-    args = uncanSequence(map(unserialize, sargs), g)
-    kwargs = {}
-    for k in sorted(skwargs.iterkeys()):
-        sa = skwargs[k]
-        if sa.data is None:
-            m = bufs.pop(0)
-            if sa.getTypeDescriptor() in ('buffer', 'ndarray'):
-                # always use a buffer, until memoryviews get sorted out
-                sa.data = buffer(m)
-                # disable memoryview support
-                # if copy:
-                #     sa.data = buffer(m)
-                # else:
-                #     sa.data = m.buffer
-            else:
-                if copy:
-                    sa.data = m
-                else:
-                    sa.data = m.bytes
-
-        kwargs[k] = uncan(unserialize(sa), g)
+    f = uncan(pickle.loads(bufs.pop(0)), g)
+    # sargs = bufs.pop(0)
+    # pop kwargs out, so first n-elements are args, serialized
+    skwargs = bufs.pop(1)
+    args, bufs = unserialize_object(bufs, g)
+    # put skwargs back in as the first element
+    bufs.insert(0, skwargs)
+    kwargs, bufs = unserialize_object(bufs, g)
+    
+    assert not bufs, "Shouldn't be any data left over"
     
     return f,args,kwargs