chunked.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from twisted.web.http import _ChunkedTransferDecoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def decode_chunked_transfer(chunked_body):\n",
    "    \"\"\"Parsed body received with chunked transfer encoding, and return the\n",
    "    decoded body.\n",
    "\n",
    "    For more info see:\n",
    "    http://en.wikipedia.org/wiki/Chunked_transfer_encoding\n",
    "\n",
    "    \"\"\"\n",
    "    body_parts, h, t = [], b'', chunked_body\n",
    "    while t:\n",
    "        h, t = t.split(b'\\r\\n', 1)\n",
    "        if h == b'0':\n",
    "            break\n",
    "        size = int(h, 16)\n",
    "        body_parts.append(t[:size])\n",
    "        t = t[size+2:]\n",
    "    return b''.join(body_parts)\n",
    "\n",
    "\n",
    "def decode_chunked_transfer_fast(chunked_body):\n",
    "    \"\"\"Parsed body received with chunked transfer encoding, and return the\n",
    "    decoded body.\n",
    "\n",
    "    For more info see:\n",
    "    http://en.wikipedia.org/wiki/Chunked_transfer_encoding\n",
    "\n",
    "    \"\"\"\n",
    "    body_parts = []\n",
    "    pos = 0\n",
    "    while pos < len(chunked_body):\n",
    "        separator_pos = chunked_body.find(b'\\r\\n', pos)\n",
    "        if separator_pos == -1:\n",
    "            separator_pos = len(chunked_body)\n",
    "            \n",
    "        chunk_size = chunked_body[pos:separator_pos]\n",
    "        if chunk_size == b'0':\n",
    "            break\n",
    "        size = int(chunk_size, 16)\n",
    "        pos = separator_pos + 2\n",
    "        chunk_data = chunked_body[pos:pos+size]\n",
    "        body_parts.append(chunk_data)\n",
    "        pos += size + 2\n",
    "        \n",
    "    return b''.join(body_parts)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1960005"
      ]
     },
     "execution_count": 171,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chunked_body = b\"25\\r\\n\" + b\"This is the data in the first chunk\\r\\n\\r\\n\"\n",
    "chunked_body += b\"1C\\r\\n\" + b\"and this is the second one\\r\\n\\r\\n\"\n",
    "chunked_body += b\"3\\r\\n\" + b\"con\\r\\n\"\n",
    "chunked_body += b\"8\\r\\n\" + b\"sequence\\r\\n\"\n",
    "\n",
    "chunked_body = chunked_body * 20000\n",
    "\n",
    "chunked_body += b\"0\\r\\n\\r\\n\"\n",
    "\n",
    "len(chunked_body)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def decode_chunked_transfer_twisted(chunked_body):\n",
    "    parts = []\n",
    "    dec = _ChunkedTransferDecoder(parts.append, lambda _:None)\n",
    "    size = 10000\n",
    "    pos = 0\n",
    "    while pos < len(chunked_body):\n",
    "        dec.dataReceived(chunked_body[pos:pos+size])\n",
    "        pos += size\n",
    "    return b''.join(parts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# decode_chunked_transfer_fast(chunked_body)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 170,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "decode_chunked_transfer(chunked_body) == decode_chunked_transfer_twisted(chunked_body)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 loop, best of 3: 418 ms per loop\n"
     ]
    }
   ],
   "source": [
    "%timeit decode_chunked_transfer_twisted(chunked_body)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[b'sdf']"
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "b'sdf'.split(b'23', 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# decode_chunked_transfer(chunked_body)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "chunked_body.find?"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}