url_shortener.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import hashlib, math, struct, sys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def base62(num, domain=\"byte.ly\"):\n",
    "    lookup = \"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ\"\n",
    "    s = \"\"\n",
    "    while num > 0:\n",
    "        s = str(lookup[num % 62]) + s\n",
    "        num //= 62\n",
    "    return \"{}{}/{}\".format(\"https://\", domain, s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This simple hash is only here to show that we can cook up something quickly.\n",
    "# The MD5 hash below is way better, and ideally we would use say SHA-256.\n",
    "def simple_hash(string):\n",
    "    num = 0\n",
    "    for i, c in enumerate(string):\n",
    "        num = (num*10 + ord(c)) % sys.maxsize\n",
    "    return num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def md5_hash(string, encoded_len=7):\n",
    "    m = hashlib.md5()\n",
    "    m.update(string.encode('utf-8'))\n",
    "    return struct.unpack('>QQ', m.digest())[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def url_shortener_base62(string, base62_len=7, hash_fun=md5_hash):\n",
    "    num = hash_fun(string)\n",
    "    num %= int(math.pow(62, base62_len)-1)\n",
    "    return base62(num)    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Short length=5\n",
      "https://facebook.com -> https://byte.ly/lIB9Z\n",
      "https://google.com -> https://byte.ly/ozP5H\n",
      "https://amazon.com -> https://byte.ly/uxot5\n",
      "\n",
      "Short length=7\n",
      "https://facebook.com -> https://byte.ly/P6BwfKK\n",
      "https://google.com -> https://byte.ly/lSdbdlp\n",
      "https://amazon.com -> https://byte.ly/qN3tn6K\n",
      "\n",
      "Short length=9\n",
      "https://facebook.com -> https://byte.ly/q5P6BivkF\n",
      "https://google.com -> https://byte.ly/BNlScY1JC\n",
      "https://amazon.com -> https://byte.ly/4sqN3sW2i\n"
     ]
    }
   ],
   "source": [
    "for short_len in [5, 7, 9]:\n",
    "    print(\"\\nShort length={}\".format(short_len))\n",
    "    for url in [\"https://facebook.com\", \"https://google.com\", \"https://amazon.com\"]:\n",
    "        print(\"{} -> {}\".format(url, url_shortener_base62(url, base62_len=short_len)))"
   ]
  }
 ],
 "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}