Python String Tutorial

DaBeazStrings.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> A short esoteric string tutorial\n",
    "\n",
    "> ![](https://pbs.twimg.com/media/DNkOxYEWAAE8Zbx.jpg)\n",
    "\n",
    "> — https://twitter.com/dabeaz/status/925787482515533830\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "74\n",
      "0B 00 00 00 00 00 00 00 F0 5B 43 0A 01 00 00 00    ........ð[C.....\n",
      "01 00 00 00 00 00 00 00 F1 A4 50 36 2E 61 0B C4    ........ñ¤P6.a.Ä\n",
      "A4 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00    ¤...............\n",
      "00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00    ................\n",
      "00 00 00 00 00 00 00 00 F1 00                      ........ñ.\n",
      "-----\n",
      "77\n",
      "0B 00 00 00 00 00 00 00 F0 5B 43 0A 01 00 00 00    ........ð[C.....\n",
      "01 00 00 00 00 00 00 00 F1 A4 50 36 2E 61 0B C4    ........ñ¤P6.a.Ä\n",
      "A4 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00    ¤...............\n",
      "02 00 00 00 00 00 00 00 90 8C 88 0B 01 00 00 00    ................\n",
      "00 00 00 00 00 00 00 00 F1 00 00 00 00             ........ñ....\n"
     ]
    }
   ],
   "source": [
    "import ctypes\n",
    "import sys\n",
    "\n",
    "def memdumpobj(obj):\n",
    "    size = sys.getsizeof(obj)\n",
    "    ptr = ctypes.cast(id(a), ctypes.POINTER(ctypes.c_uint8))\n",
    "    return bytes([ptr[i] for i in range(size)])\n",
    "\n",
    "def chunks(l, n):\n",
    "    \"\"\"Yield successive n-sized chunks from l.\"\"\"\n",
    "    # https://stackoverflow.com/a/312464/194586\n",
    "    for i in range(0, len(l), n):\n",
    "        yield l[i:i + n]\n",
    "\n",
    "def nicedump(obj):\n",
    "    dump = memdumpobj(obj)\n",
    "    for line in chunks(dump, 16):\n",
    "        hex = ' '.join(format(c, '02X') for c in line)\n",
    "        raw = ''.join(chr(c) if c >= 32 and len(repr(chr(c))) == 3 else '.' for c in line)\n",
    "        print('{:<50} {}'.format(hex, raw))\n",
    "        \n",
    "a = 'ñ'\n",
    "print(sys.getsizeof(a))\n",
    "nicedump(a)\n",
    "\n",
    "print('-----')\n",
    "\n",
    "try:\n",
    "    float(a)\n",
    "except ValueError:\n",
    "    pass\n",
    "print(sys.getsizeof(a))\n",
    "nicedump(a)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Values change! I dunno...need to look at the actual definition of the string type to see what is what."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "OS Clients (3.6)",
   "language": "python",
   "name": "os36"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}