Merge pull request #4552 from minrk/use_dill

add pickleutil.use_dill

docs/source/whatsnew/pr/use-dill.rst

@@ -0,0 +1,7 b''
+Using dill to expand serialization support
+------------------------------------------
+
+adds :func:`~IPython.utils.pickleutil.use_dill` for allowing
+dill to extend serialization support in :mod:`IPython.parallel` (closures, etc.).
+Also adds :meth:`DirectView.use_dill` convenience method for enabling dill
+locally and on all engines with one call.

examples/parallel/Using Dill.ipynb

@@ -0,0 +1,463 b''
+{
+ "metadata": {
+  "gist_id": "5241793",
+  "name": ""
+ },
+ "nbformat": 3,
+ "nbformat_minor": 0,
+ "worksheets": [
+  {
+   "cells": [
+    {
+     "cell_type": "heading",
+     "level": 1,
+     "metadata": {},
+     "source": [
+      "Using dill to pickle anything"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "IPython.parallel doesn't do much in the way of serialization.\n",
+      "It has custom zero-copy handling of numpy arrays,\n",
+      "but other than that, it doesn't do anything other than the bare minimum to make basic interactively defined functions and classes sendable.\n",
+      "\n",
+      "There are a few projects that extend pickle to make just about anything sendable, and one of these is [dill](http://www.cacr.caltech.edu/~mmckerns/dill).\n",
+      "\n",
+      "To install dill:\n",
+      "        \n",
+      "    pip install dill"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "First, as always, we create a task function, this time with a closure"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "def make_closure(a):\n",
+      "    \"\"\"make a function with a closure, and return it\"\"\"\n",
+      "    def has_closure(b):\n",
+      "        return a * b\n",
+      "    return has_closure"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 1
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "closed = make_closure(5)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 2
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "closed(2)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 3,
+       "text": [
+        "10"
+       ]
+      }
+     ],
+     "prompt_number": 3
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "import pickle"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 4
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Without help, pickle can't deal with closures"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "pickle.dumps(closed)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "ename": "PicklingError",
+       "evalue": "Can't pickle <function has_closure at 0x10d2552a8>: it's not found as __main__.has_closure",
+       "output_type": "pyerr",
+       "traceback": [
+        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mPicklingError\u001b[0m                             Traceback (most recent call last)",
+        "\u001b[1;32m<ipython-input-5-0f1f376cfea0>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mpickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mclosed\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+        "\u001b[1;32m/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.pyc\u001b[0m in \u001b[0;36mdumps\u001b[1;34m(obj, protocol)\u001b[0m\n\u001b[0;32m   1372\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mprotocol\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1373\u001b[0m     \u001b[0mfile\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mStringIO\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1374\u001b[1;33m     \u001b[0mPickler\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mprotocol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdump\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1375\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mfile\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetvalue\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1376\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.pyc\u001b[0m in \u001b[0;36mdump\u001b[1;34m(self, obj)\u001b[0m\n\u001b[0;32m    222\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mproto\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[1;36m2\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    223\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mPROTO\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mchr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mproto\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 224\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    225\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mSTOP\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    226\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.pyc\u001b[0m in \u001b[0;36msave\u001b[1;34m(self, obj)\u001b[0m\n\u001b[0;32m    284\u001b[0m         \u001b[0mf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdispatch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mt\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    285\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 286\u001b[1;33m             \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# Call unbound method with explicit self\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    287\u001b[0m             \u001b[1;32mreturn\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    288\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/pickle.pyc\u001b[0m in \u001b[0;36msave_global\u001b[1;34m(self, obj, name, pack)\u001b[0m\n\u001b[0;32m    746\u001b[0m             raise PicklingError(\n\u001b[0;32m    747\u001b[0m                 \u001b[1;34m\"Can't pickle %r: it's not found as %s.%s\"\u001b[0m \u001b[1;33m%\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 748\u001b[1;33m                 (obj, module, name))\n\u001b[0m\u001b[0;32m    749\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    750\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mklass\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;31mPicklingError\u001b[0m: Can't pickle <function has_closure at 0x10d2552a8>: it's not found as __main__.has_closure"
+       ]
+      }
+     ],
+     "prompt_number": 5
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "But after we import dill, magic happens"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "import dill"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 6
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "pickle.dumps(closed)[:64] + '...'"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 7,
+       "text": [
+        "\"cdill.dill\\n_load_type\\np0\\n(S'FunctionType'\\np1\\ntp2\\nRp3\\n(cdill.dill...\""
+       ]
+      }
+     ],
+     "prompt_number": 7
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "So from now on, pretty much everything is pickleable."
+     ]
+    },
+    {
+     "cell_type": "heading",
+     "level": 2,
+     "metadata": {},
+     "source": [
+      "Now use this in IPython.parallel"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "As usual, we start by creating our Client and View"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "from IPython import parallel\n",
+      "rc = parallel.Client()\n",
+      "view = rc.load_balanced_view()"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 8
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Now let's try sending our function with a closure:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "view.apply_sync(closed, 3)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "ename": "ValueError",
+       "evalue": "Sorry, cannot pickle code objects with closures",
+       "output_type": "pyerr",
+       "traceback": [
+        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+        "\u001b[1;32m<ipython-input-9-23a646829fdc>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mview\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_sync\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mclosed\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m3\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36mapply_sync\u001b[1;34m(self, f, *args, **kwargs)\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36mspin_after\u001b[1;34m(f, self, *args, **kwargs)\u001b[0m\n\u001b[0;32m     73\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mspin_after\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     74\u001b[0m     \u001b[1;34m\"\"\"call spin after the method.\"\"\"\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 75\u001b[1;33m     \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     76\u001b[0m     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mspin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     77\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mret\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36mapply_sync\u001b[1;34m(self, f, *args, **kwargs)\u001b[0m\n\u001b[0;32m    248\u001b[0m         \u001b[0mreturns\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mactual\u001b[0m \u001b[0mresult\u001b[0m \u001b[0mof\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    249\u001b[0m         \"\"\"\n\u001b[1;32m--> 250\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_really_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mblock\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    251\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    252\u001b[0m     \u001b[1;31m#----------------------------------------------------------------\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36m_really_apply\u001b[1;34m(self, f, args, kwargs, block, track, after, follow, timeout, targets, retries)\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36msync_results\u001b[1;34m(f, self, *args, **kwargs)\u001b[0m\n\u001b[0;32m     64\u001b[0m     \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_in_sync_results\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     65\u001b[0m     \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 66\u001b[1;33m         \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     67\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     68\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_in_sync_results\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mFalse\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36m_really_apply\u001b[1;34m(self, f, args, kwargs, block, track, after, follow, timeout, targets, retries)\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36msave_ids\u001b[1;34m(f, self, *args, **kwargs)\u001b[0m\n\u001b[0;32m     49\u001b[0m     \u001b[0mn_previous\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclient\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhistory\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     50\u001b[0m     \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 51\u001b[1;33m         \u001b[0mret\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     52\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     53\u001b[0m         \u001b[0mnmsgs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclient\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhistory\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m-\u001b[0m \u001b[0mn_previous\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/view.pyc\u001b[0m in \u001b[0;36m_really_apply\u001b[1;34m(self, f, args, kwargs, block, track, after, follow, timeout, targets, retries)\u001b[0m\n\u001b[0;32m   1053\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1054\u001b[0m         msg = self.client.send_apply_request(self._socket, f, args, kwargs, track=track,\n\u001b[1;32m-> 1055\u001b[1;33m                                 metadata=metadata)\n\u001b[0m\u001b[0;32m   1056\u001b[0m         \u001b[0mtracker\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mNone\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mtrack\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mFalse\u001b[0m \u001b[1;32melse\u001b[0m \u001b[0mmsg\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'tracker'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1057\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/parallel/client/client.pyc\u001b[0m in \u001b[0;36msend_apply_request\u001b[1;34m(self, socket, f, args, kwargs, metadata, track, ident)\u001b[0m\n\u001b[0;32m   1252\u001b[0m         bufs = serialize.pack_apply_message(f, args, kwargs,\n\u001b[0;32m   1253\u001b[0m             \u001b[0mbuffer_threshold\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuffer_threshold\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1254\u001b[1;33m             \u001b[0mitem_threshold\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitem_threshold\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1255\u001b[0m         )\n\u001b[0;32m   1256\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/kernel/zmq/serialize.pyc\u001b[0m in \u001b[0;36mpack_apply_message\u001b[1;34m(f, args, kwargs, buffer_threshold, item_threshold)\u001b[0m\n\u001b[0;32m    163\u001b[0m     \u001b[0minfo\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnargs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnarg_bufs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marg_bufs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkw_keys\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkw_keys\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    164\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 165\u001b[1;33m     \u001b[0mmsg\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mpickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcan\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    166\u001b[0m     \u001b[0mmsg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0minfo\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    167\u001b[0m     \u001b[0mmsg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marg_bufs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/utils/codeutil.pyc\u001b[0m in \u001b[0;36mreduce_code\u001b[1;34m(co)\u001b[0m\n\u001b[0;32m     36\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mreduce_code\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mco\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     37\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_freevars\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_cellvars\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 38\u001b[1;33m         \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Sorry, cannot pickle code objects with closures\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     39\u001b[0m     args =  [co.co_argcount, co.co_nlocals, co.co_stacksize,\n\u001b[0;32m     40\u001b[0m             \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_flags\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_code\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_consts\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_names\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+        "\u001b[1;31mValueError\u001b[0m: Sorry, cannot pickle code objects with closures"
+       ]
+      }
+     ],
+     "prompt_number": 9
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Oops, no dice. For IPython to work with dill,\n",
+      "there are one or two more steps. IPython will do these for you if you call `pickleutil.use_dill`:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "from IPython.utils import pickleutil\n",
+      "pickleutil.use_dill()"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 10
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Now let's try again"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "view.apply_sync(closed, 3)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 11,
+       "text": [
+        "15"
+       ]
+      }
+     ],
+     "prompt_number": 11
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Yay! Now we can use dill to allow IPython.parallel to send anything.\n",
+      "\n",
+      "And that's it! We can send closures and other previously non-pickleables to our engines.\n",
+      "\n",
+      "But wait, there's more!"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "view.apply_sync(make_closure, 2)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "ename": "RemoteError",
+       "evalue": "ValueError(Sorry, cannot pickle code objects with closures)",
+       "output_type": "pyerr",
+       "traceback": [
+        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+        "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/kernel/zmq/serialize.pyc\u001b[0m in \u001b[0;36mserialize_object\u001b[1;34m(obj, buffer_threshold, item_threshold)\u001b[0m",
+        "\u001b[0;32m    100\u001b[0m         \u001b[0mbuffers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_extract_buffers\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbuffer_threshold\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[0;32m    101\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[1;32m--> 102\u001b[1;33m     \u001b[0mbuffers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdumps\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcobj\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[0m\u001b[0;32m    103\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mbuffers\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[0;32m    104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[1;32m/Users/minrk/dev/ip/mine/IPython/utils/codeutil.pyc\u001b[0m in \u001b[0;36mreduce_code\u001b[1;34m(co)\u001b[0m",
+        "\u001b[0;32m     36\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mreduce_code\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mco\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[0;32m     37\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_freevars\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_cellvars\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[1;32m---> 38\u001b[1;33m         \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Sorry, cannot pickle code objects with closures\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[0m\u001b[0;32m     39\u001b[0m     args =  [co.co_argcount, co.co_nlocals, co.co_stacksize,",
+        "\u001b[0;32m     40\u001b[0m             \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_flags\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_code\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_consts\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mco\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mco_names\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m",
+        "\u001b[1;31mValueError\u001b[0m: Sorry, cannot pickle code objects with closures"
+       ]
+      }
+     ],
+     "prompt_number": 12
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "If we want dill support for objects coming *from* the engines,\n",
+      "then we need to call `use_dill()` there as well.\n",
+      "\n",
+      "`DirectView` objects have a method to call `use_dill` locally and on every engine:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "rc[:].use_dill()"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 13,
+       "text": [
+        "<AsyncResult: use_dill>"
+       ]
+      }
+     ],
+     "prompt_number": 13
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "This is equivalent to\n",
+      "\n",
+      "```python\n",
+      "from IPython.utils.pickleutil import use_dill\n",
+      "use_dill()\n",
+      "rc[:].apply(use_dill)\n",
+      "```"
+     ]
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "Let's give it a try now:"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "remote_closure = view.apply_sync(make_closure, 4)\n",
+      "remote_closure(5)"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 14,
+       "text": [
+        "20"
+       ]
+      }
+     ],
+     "prompt_number": 14
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "At this point, we can send/recv all kinds of stuff"
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "def outer(a):\n",
+      "    def inner(b):\n",
+      "        def inner_again(c):\n",
+      "            return c * b * a\n",
+      "        return inner_again\n",
+      "    return inner"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [],
+     "prompt_number": 15
+    },
+    {
+     "cell_type": "markdown",
+     "metadata": {},
+     "source": [
+      "So outer returns a function with a closure, which returns a function with a closure.\n",
+      "\n",
+      "Now, we can resolve the first closure on the engine, the second here, and the third on a different engine,\n",
+      "after passing through a lambda we define here and call there, just for good measure."
+     ]
+    },
+    {
+     "cell_type": "code",
+     "collapsed": false,
+     "input": [
+      "view.apply_sync(lambda f: f(3),view.apply_sync(outer, 1)(2))"
+     ],
+     "language": "python",
+     "metadata": {},
+     "outputs": [
+      {
+       "metadata": {},
+       "output_type": "pyout",
+       "prompt_number": 16,
+       "text": [
+        "6"
+       ]
+      }
+     ],
+     "prompt_number": 16
+    }
+   ],
+   "metadata": {}
+  }
+ ]
+}
  No newline at end of file

IPython/parallel/client/view.py

@@ -1,1114 +1,1125 b''
 """Views of remote engines.
 
 Authors:
 
 * Min RK
 """
 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 imp
 import sys
 import warnings
 from contextlib import contextmanager
 from types import ModuleType
 
 import zmq
 
 from IPython.testing.skipdoctest import skip_doctest
+from IPython.utils import pickleutil
 from IPython.utils.traitlets import (
     HasTraits, Any, Bool, List, Dict, Set, Instance, CFloat, Integer
 )
 from IPython.external.decorator import decorator
 
 from IPython.parallel import util
 from IPython.parallel.controller.dependency import Dependency, dependent
 from IPython.utils.py3compat import string_types, iteritems, PY3
 
 from . import map as Map
 from .asyncresult import AsyncResult, AsyncMapResult
 from .remotefunction import ParallelFunction, parallel, remote, getname
 
 #-----------------------------------------------------------------------------
 # Decorators
 #-----------------------------------------------------------------------------
 
 @decorator
 def save_ids(f, self, *args, **kwargs):
     """Keep our history and outstanding attributes up to date after a method call."""
     n_previous = len(self.client.history)
     try:
         ret = f(self, *args, **kwargs)
     finally:
         nmsgs = len(self.client.history) - n_previous
         msg_ids = self.client.history[-nmsgs:]
         self.history.extend(msg_ids)
         self.outstanding.update(msg_ids)
     return ret
 
 @decorator
 def sync_results(f, self, *args, **kwargs):
     """sync relevant results from self.client to our results attribute."""
     if self._in_sync_results:
         return f(self, *args, **kwargs)
     self._in_sync_results = True
     try:
         ret = f(self, *args, **kwargs)
     finally:
         self._in_sync_results = False
         self._sync_results()
     return ret
 
 @decorator
 def spin_after(f, self, *args, **kwargs):
     """call spin after the method."""
     ret = f(self, *args, **kwargs)
     self.spin()
     return ret
 
 #-----------------------------------------------------------------------------
 # Classes
 #-----------------------------------------------------------------------------
 
 @skip_doctest
 class View(HasTraits):
     """Base View class for more convenint apply(f,*args,**kwargs) syntax via attributes.
 
     Don't use this class, use subclasses.
 
     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
         get_result, queue_status, purge_results, result_status
 
     control methods
         abort, shutdown
 
     """
     # flags
     block=Bool(False)
     track=Bool(True)
     targets = Any()
 
     history=List()
     outstanding = Set()
     results = Dict()
     client = Instance('IPython.parallel.Client')
 
     _socket = Instance('zmq.Socket')
     _flag_names = List(['targets', 'block', 'track'])
     _in_sync_results = Bool(False)
     _targets = Any()
     _idents = Any()
 
     def __init__(self, client=None, socket=None, **flags):
         super(View, self).__init__(client=client, _socket=socket)
         self.results = client.results
         self.block = client.block
 
         self.set_flags(**flags)
 
         assert not self.__class__ is View, "Don't use base View objects, use subclasses"
 
     def __repr__(self):
         strtargets = str(self.targets)
         if len(strtargets) > 16:
             strtargets = strtargets[:12]+'...]'
         return "<%s %s>"%(self.__class__.__name__, strtargets)
     
     def __len__(self):
         if isinstance(self.targets, list):
             return len(self.targets)
         elif isinstance(self.targets, int):
             return 1
         else:
             return len(self.client)
     
     def set_flags(self, **kwargs):
         """set my attribute flags by keyword.
 
         Views determine behavior with a few attributes (`block`, `track`, etc.).
         These attributes can be set all at once by name with this method.
 
         Parameters
         ----------
 
         block : bool
             whether to wait for results
         track : bool
             whether to create a MessageTracker to allow the user to
             safely edit after arrays and buffers during non-copying
             sends.
         """
         for name, value in iteritems(kwargs):
             if name not in self._flag_names:
                 raise KeyError("Invalid name: %r"%name)
             else:
                 setattr(self, name, value)
 
     @contextmanager
     def temp_flags(self, **kwargs):
         """temporarily set flags, for use in `with` statements.
 
         See set_flags for permanent setting of flags
 
         Examples
         --------
 
         >>> view.track=False
         ...
         >>> with view.temp_flags(track=True):
         ...    ar = view.apply(dostuff, my_big_array)
         ...    ar.tracker.wait() # wait for send to finish
         >>> view.track
         False
 
         """
         # preflight: save flags, and set temporaries
         saved_flags = {}
         for f in self._flag_names:
             saved_flags[f] = getattr(self, f)
         self.set_flags(**kwargs)
         # yield to the with-statement block
         try:
             yield
         finally:
             # postflight: restore saved flags
             self.set_flags(**saved_flags)
 
 
     #----------------------------------------------------------------
     # apply
     #----------------------------------------------------------------
 
     def _sync_results(self):
         """to be called by @sync_results decorator
         
         after submitting any tasks.
         """
         delta = self.outstanding.difference(self.client.outstanding)
         completed = self.outstanding.intersection(delta)
         self.outstanding = self.outstanding.difference(completed)
         
     @sync_results
     @save_ids
     def _really_apply(self, f, args, kwargs, block=None, **options):
         """wrapper for client.send_apply_request"""
         raise NotImplementedError("Implement in subclasses")
 
     def apply(self, f, *args, **kwargs):
         """calls ``f(*args, **kwargs)`` on remote engines, returning the result.
 
         This method sets all apply flags via this View's attributes.
 
         Returns :class:`~IPython.parallel.client.asyncresult.AsyncResult`
         instance if ``self.block`` is False, otherwise the return value of
         ``f(*args, **kwargs)``.
         """
         return self._really_apply(f, args, kwargs)
 
     def apply_async(self, f, *args, **kwargs):
         """calls ``f(*args, **kwargs)`` on remote engines in a nonblocking manner.
 
         Returns :class:`~IPython.parallel.client.asyncresult.AsyncResult` instance.
         """
         return self._really_apply(f, args, kwargs, block=False)
 
     @spin_after
     def apply_sync(self, f, *args, **kwargs):
         """calls ``f(*args, **kwargs)`` on remote engines in a blocking manner,
          returning the result.
         """
         return self._really_apply(f, args, kwargs, block=True)
 
     #----------------------------------------------------------------
     # wrappers for client and control methods
     #----------------------------------------------------------------
     @sync_results
     def spin(self):
         """spin the client, and sync"""
         self.client.spin()
 
     @sync_results
     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
         """
         if jobs is None:
             jobs = self.history
         return self.client.wait(jobs, timeout)
 
     def abort(self, jobs=None, targets=None, block=None):
         """Abort jobs on my engines.
 
         Parameters
         ----------
 
         jobs : None, str, list of strs, optional
             if None: abort all jobs.
             else: abort specific msg_id(s).
         """
         block = block if block is not None else self.block
         targets = targets if targets is not None else self.targets
         jobs = jobs if jobs is not None else list(self.outstanding)
         
         return self.client.abort(jobs=jobs, targets=targets, block=block)
 
     def queue_status(self, targets=None, verbose=False):
         """Fetch the Queue status of my engines"""
         targets = targets if targets is not None else self.targets
         return self.client.queue_status(targets=targets, verbose=verbose)
 
     def purge_results(self, jobs=[], targets=[]):
         """Instruct the controller to forget specific results."""
         if targets is None or targets == 'all':
             targets = self.targets
         return self.client.purge_results(jobs=jobs, targets=targets)
 
     def shutdown(self, targets=None, restart=False, hub=False, block=None):
         """Terminates one or more engine processes, optionally including the hub.
         """
         block = self.block if block is None else block
         if targets is None or targets == 'all':
             targets = self.targets
         return self.client.shutdown(targets=targets, restart=restart, hub=hub, block=block)
 
     @spin_after
     def get_result(self, indices_or_msg_ids=None):
         """return one or more results, specified by history index or msg_id.
 
         See :meth:`IPython.parallel.client.client.Client.get_result` for details.
         """
 
         if indices_or_msg_ids is None:
             indices_or_msg_ids = -1
         if isinstance(indices_or_msg_ids, int):
             indices_or_msg_ids = self.history[indices_or_msg_ids]
         elif isinstance(indices_or_msg_ids, (list,tuple,set)):
             indices_or_msg_ids = list(indices_or_msg_ids)
             for i,index in enumerate(indices_or_msg_ids):
                 if isinstance(index, int):
                     indices_or_msg_ids[i] = self.history[index]
         return self.client.get_result(indices_or_msg_ids)
 
     #-------------------------------------------------------------------
     # Map
     #-------------------------------------------------------------------
 
     @sync_results
     def map(self, f, *sequences, **kwargs):
         """override in subclasses"""
         raise NotImplementedError
 
     def map_async(self, f, *sequences, **kwargs):
         """Parallel version of builtin :func:`python:map`, using this view's engines.
 
         This is equivalent to ``map(...block=False)``.
 
         See `self.map` for details.
         """
         if 'block' in kwargs:
             raise TypeError("map_async doesn't take a `block` keyword argument.")
         kwargs['block'] = False
         return self.map(f,*sequences,**kwargs)
 
     def map_sync(self, f, *sequences, **kwargs):
         """Parallel version of builtin :func:`python:map`, using this view's engines.
 
         This is equivalent to ``map(...block=True)``.
 
         See `self.map` for details.
         """
         if 'block' in kwargs:
             raise TypeError("map_sync doesn't take a `block` keyword argument.")
         kwargs['block'] = True
         return self.map(f,*sequences,**kwargs)
 
     def imap(self, f, *sequences, **kwargs):
         """Parallel version of :func:`itertools.imap`.
 
         See `self.map` for details.
 
         """
 
         return iter(self.map_async(f,*sequences, **kwargs))
 
     #-------------------------------------------------------------------
     # Decorators
     #-------------------------------------------------------------------
 
     def remote(self, block=None, **flags):
         """Decorator for making a RemoteFunction"""
         block = self.block if block is None else block
         return remote(self, block=block, **flags)
 
     def parallel(self, dist='b', block=None, **flags):
         """Decorator for making a ParallelFunction"""
         block = self.block if block is None else block
         return parallel(self, dist=dist, block=block, **flags)
 
 @skip_doctest
 class DirectView(View):
     """Direct Multiplexer View of one or more engines.
 
     These are created via indexed access to a client:
 
     >>> dv_1 = client[1]
     >>> dv_all = client[:]
     >>> dv_even = client[::2]
     >>> dv_some = client[1:3]
 
     This object provides dictionary access to engine namespaces:
 
     # push a=5:
     >>> dv['a'] = 5
     # pull 'foo':
     >>> db['foo']
 
     """
 
     def __init__(self, client=None, socket=None, targets=None):
         super(DirectView, self).__init__(client=client, socket=socket, targets=targets)
 
     @property
     def importer(self):
         """sync_imports(local=True) as a property.
 
         See sync_imports for details.
 
         """
         return self.sync_imports(True)
 
     @contextmanager
     def sync_imports(self, local=True, quiet=False):
         """Context Manager for performing simultaneous local and remote imports.
 
         'import x as y' will *not* work.  The 'as y' part will simply be ignored.
         
         If `local=True`, then the package will also be imported locally.
         
         If `quiet=True`, no output will be produced when attempting remote 
         imports. 
         
         Note that remote-only (`local=False`) imports have not been implemented.
         
         >>> with view.sync_imports():
         ...    from numpy import recarray
         importing recarray from numpy on engine(s)
 
         """
         from IPython.utils.py3compat import builtin_mod
         local_import = builtin_mod.__import__
         modules = set()
         results = []
         @util.interactive
         def remote_import(name, fromlist, level):
             """the function to be passed to apply, that actually performs the import
             on the engine, and loads up the user namespace.
             """
             import sys
             user_ns = globals()
             mod = __import__(name, fromlist=fromlist, level=level)
             if fromlist:
                 for key in fromlist:
                     user_ns[key] = getattr(mod, key)
             else:
                 user_ns[name] = sys.modules[name]
 
         def view_import(name, globals={}, locals={}, fromlist=[], level=0):
             """the drop-in replacement for __import__, that optionally imports
             locally as well.
             """
             # don't override nested imports
             save_import = builtin_mod.__import__
             builtin_mod.__import__ = local_import
 
             if imp.lock_held():
                 # this is a side-effect import, don't do it remotely, or even
                 # ignore the local effects
                 return local_import(name, globals, locals, fromlist, level)
 
             imp.acquire_lock()
             if local:
                 mod = local_import(name, globals, locals, fromlist, level)
             else:
                 raise NotImplementedError("remote-only imports not yet implemented")
             imp.release_lock()
 
             key = name+':'+','.join(fromlist or [])
             if level <= 0 and key not in modules:
                 modules.add(key)
                 if not quiet:
                     if fromlist:
                         print("importing %s from %s on engine(s)"%(','.join(fromlist), name))
                     else:
                         print("importing %s on engine(s)"%name)
                 results.append(self.apply_async(remote_import, name, fromlist, level))
             # restore override
             builtin_mod.__import__ = save_import
 
             return mod
 
         # override __import__
         builtin_mod.__import__ = view_import
         try:
             # enter the block
             yield
         except ImportError:
             if local:
                 raise
             else:
                 # ignore import errors if not doing local imports
                 pass
         finally:
             # always restore __import__
             builtin_mod.__import__ = local_import
 
         for r in results:
             # raise possible remote ImportErrors here
             r.get()
+    
+    def use_dill(self):
+        """Expand serialization support with dill
+        
+        adds support for closures, etc.
+        
+        This calls IPython.utils.pickleutil.use_dill() here and on each engine.
+        """
+        pickleutil.use_dill()
+        return self.apply(pickleutil.use_dill)
 
 
     @sync_results
     @save_ids
     def _really_apply(self, f, args=None, kwargs=None, targets=None, block=None, track=None):
         """calls f(*args, **kwargs) on remote engines, returning the result.
 
         This method sets all of `apply`'s flags via this View's attributes.
 
         Parameters
         ----------
 
         f : callable
 
         args : list [default: empty]
 
         kwargs : dict [default: empty]
 
         targets : target list [default: self.targets]
             where to run
         block : bool [default: self.block]
             whether to block
         track : bool [default: self.track]
             whether to ask zmq to track the message, for safe non-copying sends
 
         Returns
         -------
 
         if self.block is False:
             returns AsyncResult
         else:
             returns actual result of f(*args, **kwargs) on the engine(s)
             This will be a list of self.targets is also a list (even length 1), or
             the single result if self.targets is an integer engine id
         """
         args = [] if args is None else args
         kwargs = {} if kwargs is None else kwargs
         block = self.block if block is None else block
         track = self.track if track is None else track
         targets = self.targets if targets is None else targets
         
         _idents, _targets = self.client._build_targets(targets)
         msg_ids = []
         trackers = []
         for ident in _idents:
             msg = self.client.send_apply_request(self._socket, f, args, kwargs, track=track,
                                     ident=ident)
             if track:
                 trackers.append(msg['tracker'])
             msg_ids.append(msg['header']['msg_id'])
         if isinstance(targets, int):
             msg_ids = msg_ids[0]
         tracker = None if track is False else zmq.MessageTracker(*trackers)
         ar = AsyncResult(self.client, msg_ids, fname=getname(f), targets=_targets, tracker=tracker)
         if block:
             try:
                 return ar.get()
             except KeyboardInterrupt:
                 pass
         return ar
 
 
     @sync_results
     def map(self, f, *sequences, **kwargs):
         """``view.map(f, *sequences, block=self.block)`` => list|AsyncMapResult
 
         Parallel version of builtin `map`, using this View's `targets`.
 
         There will be one task per target, so work will be chunked
         if the sequences are longer than `targets`.
 
         Results can be iterated as they are ready, but will become available in chunks.
 
         Parameters
         ----------
 
         f : callable
             function to be mapped
         *sequences: one or more sequences of matching length
             the sequences to be distributed and passed to `f`
         block : bool
             whether to wait for the result or not [default self.block]
 
         Returns
         -------
 
 
         If block=False
           An :class:`~IPython.parallel.client.asyncresult.AsyncMapResult` instance.
           An object like AsyncResult, but which reassembles the sequence of results
           into a single list. AsyncMapResults can be iterated through before all
           results are complete.
         else
             A list, the result of ``map(f,*sequences)``
         """
 
         block = kwargs.pop('block', self.block)
         for k in kwargs.keys():
             if k not in ['block', 'track']:
                 raise TypeError("invalid keyword arg, %r"%k)
 
         assert len(sequences) > 0, "must have some sequences to map onto!"
         pf = ParallelFunction(self, f, block=block, **kwargs)
         return pf.map(*sequences)
 
     @sync_results
     @save_ids
     def execute(self, code, silent=True, targets=None, block=None):
         """Executes `code` on `targets` in blocking or nonblocking manner.
 
         ``execute`` is always `bound` (affects engine namespace)
 
         Parameters
         ----------
 
         code : str
                 the code string to be executed
         block : bool
                 whether or not to wait until done to return
                 default: self.block
         """
         block = self.block if block is None else block
         targets = self.targets if targets is None else targets
 
         _idents, _targets = self.client._build_targets(targets)
         msg_ids = []
         trackers = []
         for ident in _idents:
             msg = self.client.send_execute_request(self._socket, code, silent=silent, ident=ident)
             msg_ids.append(msg['header']['msg_id'])
         if isinstance(targets, int):
             msg_ids = msg_ids[0]
         ar = AsyncResult(self.client, msg_ids, fname='execute', targets=_targets)
         if block:
             try:
                 ar.get()
             except KeyboardInterrupt:
                 pass
         return ar
 
     def run(self, filename, targets=None, block=None):
         """Execute contents of `filename` on my engine(s).
 
         This simply reads the contents of the file and calls `execute`.
 
         Parameters
         ----------
 
         filename : str
                 The path to the file
         targets : int/str/list of ints/strs
                 the engines on which to execute
                 default : all
         block : bool
                 whether or not to wait until done
                 default: self.block
 
         """
         with open(filename, 'r') as f:
             # add newline in case of trailing indented whitespace
             # which will cause SyntaxError
             code = f.read()+'\n'
         return self.execute(code, block=block, targets=targets)
 
     def update(self, ns):
         """update remote namespace with dict `ns`
 
         See `push` for details.
         """
         return self.push(ns, block=self.block, track=self.track)
 
     def push(self, ns, targets=None, block=None, track=None):
         """update remote namespace with dict `ns`
 
         Parameters
         ----------
 
         ns : dict
             dict of keys with which to update engine namespace(s)
         block : bool [default : self.block]
             whether to wait to be notified of engine receipt
 
         """
 
         block = block if block is not None else self.block
         track = track if track is not None else self.track
         targets = targets if targets is not None else self.targets
         # applier = self.apply_sync if block else self.apply_async
         if not isinstance(ns, dict):
             raise TypeError("Must be a dict, not %s"%type(ns))
         return self._really_apply(util._push, kwargs=ns, block=block, track=track, targets=targets)
 
     def get(self, key_s):
         """get object(s) by `key_s` from remote namespace
 
         see `pull` for details.
         """
         # block = block if block is not None else self.block
         return self.pull(key_s, block=True)
 
     def pull(self, names, targets=None, block=None):
         """get object(s) by `name` from remote namespace
 
         will return one object if it is a key.
         can also take a list of keys, in which case it will return a list of objects.
         """
         block = block if block is not None else self.block
         targets = targets if targets is not None else self.targets
         applier = self.apply_sync if block else self.apply_async
         if isinstance(names, string_types):
             pass
         elif isinstance(names, (list,tuple,set)):
             for key in names:
                 if not isinstance(key, string_types):
                     raise TypeError("keys must be str, not type %r"%type(key))
         else:
             raise TypeError("names must be strs, not %r"%names)
         return self._really_apply(util._pull, (names,), block=block, targets=targets)
 
     def scatter(self, key, seq, dist='b', flatten=False, targets=None, block=None, track=None):
         """
         Partition a Python sequence and send the partitions to a set of engines.
         """
         block = block if block is not None else self.block
         track = track if track is not None else self.track
         targets = targets if targets is not None else self.targets
         
         # construct integer ID list:
         targets = self.client._build_targets(targets)[1]
 
         mapObject = Map.dists[dist]()
         nparts = len(targets)
         msg_ids = []
         trackers = []
         for index, engineid in enumerate(targets):
             partition = mapObject.getPartition(seq, index, nparts)
             if flatten and len(partition) == 1:
                 ns = {key: partition[0]}
             else:
                 ns = {key: partition}
             r = self.push(ns, block=False, track=track, targets=engineid)
             msg_ids.extend(r.msg_ids)
             if track:
                 trackers.append(r._tracker)
 
         if track:
             tracker = zmq.MessageTracker(*trackers)
         else:
             tracker = None
 
         r = AsyncResult(self.client, msg_ids, fname='scatter', targets=targets, tracker=tracker)
         if block:
             r.wait()
         else:
             return r
 
     @sync_results
     @save_ids
     def gather(self, key, dist='b', targets=None, block=None):
         """
         Gather a partitioned sequence on a set of engines as a single local seq.
         """
         block = block if block is not None else self.block
         targets = targets if targets is not None else self.targets
         mapObject = Map.dists[dist]()
         msg_ids = []
 
         # construct integer ID list:
         targets = self.client._build_targets(targets)[1]
         
         for index, engineid in enumerate(targets):
             msg_ids.extend(self.pull(key, block=False, targets=engineid).msg_ids)
 
         r = AsyncMapResult(self.client, msg_ids, mapObject, fname='gather')
 
         if block:
             try:
                 return r.get()
             except KeyboardInterrupt:
                 pass
         return r
 
     def __getitem__(self, key):
         return self.get(key)
 
     def __setitem__(self,key, value):
         self.update({key:value})
 
     def clear(self, targets=None, block=None):
         """Clear the remote namespaces on my engines."""
         block = block if block is not None else self.block
         targets = targets if targets is not None else self.targets
         return self.client.clear(targets=targets, block=block)
 
     #----------------------------------------
     # activate for %px, %autopx, etc. magics
     #----------------------------------------
 
     def activate(self, suffix=''):
         """Activate IPython magics associated with this View
         
         Defines the magics `%px, %autopx, %pxresult, %%px, %pxconfig`
         
         Parameters
         ----------
         
         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[::2].activate(suffix='_even')`` will give you
             the magics ``%px_even``, ``%pxresult_even``, etc. for running magics 
             on the even engines.
         """
         
         from IPython.parallel.client.magics import ParallelMagics
         
         try:
             # This is injected into __builtins__.
             ip = get_ipython()
         except NameError:
             print("The IPython parallel magics (%px, etc.) only work within IPython.")
             return
         
         M = ParallelMagics(ip, self, suffix)
         ip.magics_manager.register(M)
 
 
 @skip_doctest
 class LoadBalancedView(View):
     """An load-balancing View that only executes via the Task scheduler.
 
     Load-balanced views can be created with the client's `view` method:
 
     >>> v = client.load_balanced_view()
 
     or targets can be specified, to restrict the potential destinations:
 
     >>> v = client.client.load_balanced_view([1,3])
 
     which would restrict loadbalancing to between engines 1 and 3.
 
     """
 
     follow=Any()
     after=Any()
     timeout=CFloat()
     retries = Integer(0)
 
     _task_scheme = Any()
     _flag_names = List(['targets', 'block', 'track', 'follow', 'after', 'timeout', 'retries'])
 
     def __init__(self, client=None, socket=None, **flags):
         super(LoadBalancedView, self).__init__(client=client, socket=socket, **flags)
         self._task_scheme=client._task_scheme
 
     def _validate_dependency(self, dep):
         """validate a dependency.
 
         For use in `set_flags`.
         """
         if dep is None or isinstance(dep, string_types + (AsyncResult, Dependency)):
             return True
         elif isinstance(dep, (list,set, tuple)):
             for d in dep:
                 if not isinstance(d, string_types + (AsyncResult,)):
                     return False
         elif isinstance(dep, dict):
             if set(dep.keys()) != set(Dependency().as_dict().keys()):
                 return False
             if not isinstance(dep['msg_ids'], list):
                 return False
             for d in dep['msg_ids']:
                 if not isinstance(d, string_types):
                     return False
         else:
             return False
 
         return True
 
     def _render_dependency(self, dep):
         """helper for building jsonable dependencies from various input forms."""
         if isinstance(dep, Dependency):
             return dep.as_dict()
         elif isinstance(dep, AsyncResult):
             return dep.msg_ids
         elif dep is None:
             return []
         else:
             # pass to Dependency constructor
             return list(Dependency(dep))
 
     def set_flags(self, **kwargs):
         """set my attribute flags by keyword.
 
         A View is a wrapper for the Client's apply method, but with attributes
         that specify keyword arguments, those attributes can be set by keyword
         argument with this method.
 
         Parameters
         ----------
 
         block : bool
             whether to wait for results
         track : bool
             whether to create a MessageTracker to allow the user to
             safely edit after arrays and buffers during non-copying
             sends.
 
         after : Dependency or collection of msg_ids
             Only for load-balanced execution (targets=None)
             Specify a list of msg_ids as a time-based dependency.
             This job will only be run *after* the dependencies
             have been met.
 
         follow : Dependency or collection of msg_ids
             Only for load-balanced execution (targets=None)
             Specify a list of msg_ids as a location-based dependency.
             This job will only be run on an engine where this dependency
             is met.
 
         timeout : float/int or None
             Only for load-balanced execution (targets=None)
             Specify an amount of time (in seconds) for the scheduler to
             wait for dependencies to be met before failing with a
             DependencyTimeout.
 
         retries : int
             Number of times a task will be retried on failure.
         """
 
         super(LoadBalancedView, self).set_flags(**kwargs)
         for name in ('follow', 'after'):
             if name in kwargs:
                 value = kwargs[name]
                 if self._validate_dependency(value):
                     setattr(self, name, value)
                 else:
                     raise ValueError("Invalid dependency: %r"%value)
         if 'timeout' in kwargs:
             t = kwargs['timeout']
             if not isinstance(t, (int, float, type(None))):
                 if (not PY3) and (not isinstance(t, long)):
                     raise TypeError("Invalid type for timeout: %r"%type(t))
             if t is not None:
                 if t < 0:
                     raise ValueError("Invalid timeout: %s"%t)
             self.timeout = t
 
     @sync_results
     @save_ids
     def _really_apply(self, f, args=None, kwargs=None, block=None, track=None,
                                         after=None, follow=None, timeout=None,
                                         targets=None, retries=None):
         """calls f(*args, **kwargs) on a remote engine, returning the result.
 
         This method temporarily sets all of `apply`'s flags for a single call.
 
         Parameters
         ----------
 
         f : callable
 
         args : list [default: empty]
 
         kwargs : dict [default: empty]
 
         block : bool [default: self.block]
             whether to block
         track : bool [default: self.track]
             whether to ask zmq to track the message, for safe non-copying sends
 
         !!!!!! TODO: THE REST HERE  !!!!
 
         Returns
         -------
 
         if self.block is False:
             returns AsyncResult
         else:
             returns actual result of f(*args, **kwargs) on the engine(s)
             This will be a list of self.targets is also a list (even length 1), or
             the single result if self.targets is an integer engine id
         """
 
         # validate whether we can run
         if self._socket.closed:
             msg = "Task farming is disabled"
             if self._task_scheme == 'pure':
                 msg += " because the pure ZMQ scheduler cannot handle"
                 msg += " disappearing engines."
             raise RuntimeError(msg)
 
         if self._task_scheme == 'pure':
             # pure zmq scheme doesn't support extra features
             msg = "Pure ZMQ scheduler doesn't support the following flags:"
             "follow, after, retries, targets, timeout"
             if (follow or after or retries or targets or timeout):
                 # hard fail on Scheduler flags
                 raise RuntimeError(msg)
             if isinstance(f, dependent):
                 # soft warn on functional dependencies
                 warnings.warn(msg, RuntimeWarning)
 
         # build args
         args = [] if args is None else args
         kwargs = {} if kwargs is None else kwargs
         block = self.block if block is None else block
         track = self.track if track is None else track
         after = self.after if after is None else after
         retries = self.retries if retries is None else retries
         follow = self.follow if follow is None else follow
         timeout = self.timeout if timeout is None else timeout
         targets = self.targets if targets is None else targets
 
         if not isinstance(retries, int):
             raise TypeError('retries must be int, not %r'%type(retries))
 
         if targets is None:
             idents = []
         else:
             idents = self.client._build_targets(targets)[0]
             # ensure *not* bytes
             idents = [ ident.decode() for ident in idents ]
 
         after = self._render_dependency(after)
         follow = self._render_dependency(follow)
         metadata = dict(after=after, follow=follow, timeout=timeout, targets=idents, retries=retries)
 
         msg = self.client.send_apply_request(self._socket, f, args, kwargs, track=track,
                                 metadata=metadata)
         tracker = None if track is False else msg['tracker']
 
         ar = AsyncResult(self.client, msg['header']['msg_id'], fname=getname(f), targets=None, tracker=tracker)
 
         if block:
             try:
                 return ar.get()
             except KeyboardInterrupt:
                 pass
         return ar
 
     @sync_results
     @save_ids
     def map(self, f, *sequences, **kwargs):
         """``view.map(f, *sequences, block=self.block, chunksize=1, ordered=True)`` => list|AsyncMapResult
 
         Parallel version of builtin `map`, load-balanced by this View.
 
         `block`, and `chunksize` can be specified by keyword only.
 
         Each `chunksize` elements will be a separate task, and will be
         load-balanced. This lets individual elements be available for iteration
         as soon as they arrive.
 
         Parameters
         ----------
 
         f : callable
             function to be mapped
         *sequences: one or more sequences of matching length
             the sequences to be distributed and passed to `f`
         block : bool [default self.block]
             whether to wait for the result or not
         track : bool
             whether to create a MessageTracker to allow the user to
             safely edit after arrays and buffers during non-copying
             sends.
         chunksize : int [default 1]
             how many elements should be in each task.
         ordered : bool [default True]
             Whether the results should be gathered as they arrive, or enforce
             the order of submission.
             
             Only applies when iterating through AsyncMapResult as results arrive.
             Has no effect when block=True.
 
         Returns
         -------
 
         if block=False
           An :class:`~IPython.parallel.client.asyncresult.AsyncMapResult` instance.
           An object like AsyncResult, but which reassembles the sequence of results
           into a single list. AsyncMapResults can be iterated through before all
           results are complete.
         else
             A list, the result of ``map(f,*sequences)``
         """
 
         # default
         block = kwargs.get('block', self.block)
         chunksize = kwargs.get('chunksize', 1)
         ordered = kwargs.get('ordered', True)
 
         keyset = set(kwargs.keys())
         extra_keys = keyset.difference_update(set(['block', 'chunksize']))
         if extra_keys:
             raise TypeError("Invalid kwargs: %s"%list(extra_keys))
 
         assert len(sequences) > 0, "must have some sequences to map onto!"
 
         pf = ParallelFunction(self, f, block=block, chunksize=chunksize, ordered=ordered)
         return pf.map(*sequences)
 
 __all__ = ['LoadBalancedView', 'DirectView']

IPython/utils/pickleutil.py

@@ -1,352 +1,382 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 logging
 import sys
 from types import FunctionType
 
 try:
     import cPickle as pickle
 except ImportError:
     import pickle
 
 from . import codeutil  # This registers a hook when it's imported
 from . import py3compat
 from .importstring import import_item
 from .py3compat import string_types, iteritems
 
 from IPython.config import Application
 
 if py3compat.PY3:
     buffer = memoryview
     class_type = type
 else:
     from types import ClassType
     class_type = (type, ClassType)
 
 #-------------------------------------------------------------------------------
+# Functions
+#-------------------------------------------------------------------------------
+
+
+def use_dill():
+    """use dill to expand serialization support
+    
+    adds support for object methods and closures to serialization.
+    """
+    # import dill causes most of the magic
+    import dill
+    
+    # dill doesn't work with cPickle,
+    # tell the two relevant modules to use plain pickle
+    
+    global pickle
+    pickle = dill
+
+    try:
+        from IPython.kernel.zmq import serialize
+    except ImportError:
+        pass
+    else:
+        serialize.pickle = dill
+    
+    # disable special function handling, let dill take care of it
+    can_map.pop(FunctionType, None)
+
+
+#-------------------------------------------------------------------------------
 # Classes
 #-------------------------------------------------------------------------------
 
 
 class CannedObject(object):
     def __init__(self, obj, keys=[], hook=None):
         """can an object for safe pickling
         
         Parameters
         ==========
         
         obj:
             The object to be canned
         keys: list (optional)
             list of attribute names that will be explicitly canned / uncanned
         hook: callable (optional)
             An optional extra callable,
             which can do additional processing of the uncanned object.
         
         large data may be offloaded into the buffers list,
         used for zero-copy transfers.
         """
         self.keys = keys
         self.obj = copy.copy(obj)
         self.hook = can(hook)
         for key in keys:
             setattr(self.obj, key, can(getattr(obj, key)))
         
         self.buffers = []
 
     def get_object(self, g=None):
         if g is None:
             g = {}
         obj = self.obj
         for key in self.keys:
             setattr(obj, key, uncan(getattr(obj, key), g))
         
         if self.hook:
             self.hook = uncan(self.hook, g)
             self.hook(obj, g)
         return self.obj
     
 
 class Reference(CannedObject):
     """object for wrapping a remote reference by name."""
     def __init__(self, name):
         if not isinstance(name, string_types):
             raise TypeError("illegal name: %r"%name)
         self.name = name
         self.buffers = []
 
     def __repr__(self):
         return "<Reference: %r>"%self.name
 
     def get_object(self, g=None):
         if g is None:
             g = {}
         
         return eval(self.name, g)
 
 
 class CannedFunction(CannedObject):
 
     def __init__(self, f):
         self._check_type(f)
         self.code = f.__code__
         if f.__defaults__:
             self.defaults = [ can(fd) for fd in f.__defaults__ ]
         else:
             self.defaults = None
         self.module = f.__module__ or '__main__'
         self.__name__ = f.__name__
         self.buffers = []
 
     def _check_type(self, obj):
         assert isinstance(obj, FunctionType), "Not a function type"
 
     def get_object(self, g=None):
         # try to load function back into its module:
         if not self.module.startswith('__'):
             __import__(self.module)
             g = sys.modules[self.module].__dict__
 
         if g is None:
             g = {}
         if self.defaults:
             defaults = tuple(uncan(cfd, g) for cfd in self.defaults)
         else:
             defaults = None
         newFunc = FunctionType(self.code, g, self.__name__, defaults)
         return newFunc
 
 class CannedClass(CannedObject):
 
     def __init__(self, cls):
         self._check_type(cls)
         self.name = cls.__name__
         self.old_style = not isinstance(cls, type)
         self._canned_dict = {}
         for k,v in cls.__dict__.items():
             if k not in ('__weakref__', '__dict__'):
                 self._canned_dict[k] = can(v)
         if self.old_style:
             mro = []
         else:
             mro = cls.mro()
         
         self.parents = [ can(c) for c in mro[1:] ]
         self.buffers = []
 
     def _check_type(self, obj):
         assert isinstance(obj, class_type), "Not a class type"
 
     def get_object(self, g=None):
         parents = tuple(uncan(p, g) for p in self.parents)
         return type(self.name, parents, uncan_dict(self._canned_dict, g=g))
 
 class CannedArray(CannedObject):
     def __init__(self, obj):
         from numpy import ascontiguousarray
         self.shape = obj.shape
         self.dtype = obj.dtype.descr if obj.dtype.fields else obj.dtype.str
         if sum(obj.shape) == 0:
             # just pickle it
             self.buffers = [pickle.dumps(obj, -1)]
         else:
             # ensure contiguous
             obj = ascontiguousarray(obj, dtype=None)
             self.buffers = [buffer(obj)]
     
     def get_object(self, g=None):
         from numpy import frombuffer
         data = self.buffers[0]
         if sum(self.shape) == 0:
             # no shape, we just pickled it
             return pickle.loads(data)
         else:
             return 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 _logger():
     """get the logger for the current Application
     
     the root logger will be used if no Application is running
     """
     if Application.initialized():
         logger = Application.instance().log
     else:
         logger = logging.getLogger()
         if not logger.handlers:
             logging.basicConfig()
     
     return logger
 
 def _import_mapping(mapping, original=None):
     """import any string-keys in a type mapping
     
     """
     log = _logger()
     log.debug("Importing canning map")
     for key,value in list(mapping.items()):
         if isinstance(key, string_types):
             try:
                 cls = import_item(key)
             except Exception:
                 if original and key not in original:
                     # only message on user-added classes
                     log.error("canning class not importable: %r", key, exc_info=True)
                 mapping.pop(key)
             else:
                 mapping[cls] = mapping.pop(key)
 
 def istype(obj, check):
     """like isinstance(obj, check), but strict
     
     This won't catch subclasses.
     """
     if isinstance(check, tuple):
         for cls in check:
             if type(obj) is cls:
                 return True
         return False
     else:
         return type(obj) is check
 
 def can(obj):
     """prepare an object for pickling"""
     
     import_needed = False
     
     for cls,canner in iteritems(can_map):
         if isinstance(cls, string_types):
             import_needed = True
             break
         elif istype(obj, cls):
             return canner(obj)
     
     if import_needed:
         # perform can_map imports, then try again
         # this will usually only happen once
         _import_mapping(can_map, _original_can_map)
         return can(obj)
     
     return obj
 
 def can_class(obj):
     if isinstance(obj, class_type) and obj.__module__ == '__main__':
         return CannedClass(obj)
     else:
         return obj
 
 def can_dict(obj):
     """can the *values* of a dict"""
     if istype(obj, dict):
         newobj = {}
         for k, v in iteritems(obj):
             newobj[k] = can(v)
         return newobj
     else:
         return obj
 
 sequence_types = (list, tuple, set)
 
 def can_sequence(obj):
     """can the elements of a sequence"""
     if istype(obj, sequence_types):
         t = type(obj)
         return t([can(i) for i in obj])
     else:
         return obj
 
 def uncan(obj, g=None):
     """invert canning"""
     
     import_needed = False
     for cls,uncanner in iteritems(uncan_map):
         if isinstance(cls, string_types):
             import_needed = True
             break
         elif isinstance(obj, cls):
             return uncanner(obj, g)
     
     if import_needed:
         # perform uncan_map imports, then try again
         # this will usually only happen once
         _import_mapping(uncan_map, _original_uncan_map)
         return uncan(obj, g)
     
     return obj
 
 def uncan_dict(obj, g=None):
     if istype(obj, dict):
         newobj = {}
         for k, v in iteritems(obj):
             newobj[k] = uncan(v,g)
         return newobj
     else:
         return obj
 
 def uncan_sequence(obj, g=None):
     if istype(obj, sequence_types):
         t = type(obj)
         return t([uncan(i,g) for i in obj])
     else:
         return obj
 
 def _uncan_dependent_hook(dep, g=None):
     dep.check_dependency()
     
 def can_dependent(obj):
     return CannedObject(obj, keys=('f', 'df'), hook=_uncan_dependent_hook)
 
 #-------------------------------------------------------------------------------
 # API dictionaries
 #-------------------------------------------------------------------------------
 
 # These dicts can be extended for custom serialization of new objects
 
 can_map = {
     'IPython.parallel.dependent' : can_dependent,
     'numpy.ndarray' : CannedArray,
     FunctionType : CannedFunction,
     bytes : CannedBytes,
     buffer : CannedBuffer,
     class_type : can_class,
 }
 
 uncan_map = {
     CannedObject : lambda obj, g: obj.get_object(g),
 }
 
 # for use in _import_mapping:
 _original_can_map = can_map.copy()
 _original_uncan_map = uncan_map.copy()