python_list_tokens_hashing

list-tokens-hash.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import hashlib  # use sha256"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "tokenize turns a string, or file, into a list of tokens\n",
    "flat list no depth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def tokenize(source:str) -> list:\n",
    "    \"\"\"Tokenizes the source string into a list of tokens\"\"\"\n",
    "    source = source \\\n",
    "        .replace('(', ' ( ').replace(')', ' ) ') \\\n",
    "        .replace('[', ' ( ').replace(']', ' ) ')\n",
    "    return source.split()"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "an example of a function, which is a nested list\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['(', 'define', '(', 'square', 'x', ')', '(', '*', 'x', 'x', ')', ')']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r = tokenize('(define (square x) (* x x))')\n",
    "r"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "a simple expression, not a nested list\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['(', '+', '1', '2', '3', ')']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "t = tokenize('[+ 1 2 3]')\n",
    "t"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sha256(s:str) -> bytes:\n",
    "    \"\"\"Returns the SHA256 hash of the input\"\"\"\n",
    "    import hashlib\n",
    "    return hashlib.sha256(s.encode('utf-8')).hexdigest()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['32ebb1abcc1c601ceb9c4e3c4faba0caa5b85bb98c4f1e6612c40faa528a91c9',\n",
       " 'a318c24216defe206feeb73ef5be00033fa9c4a74d0b967f6532a26ca5906d3b',\n",
       " '6b86b273ff34fce19d6b804eff5a3f5747ada4eaa22f1d49c01e52ddb7875b4b',\n",
       " 'd4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35',\n",
       " '4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce',\n",
       " 'ba5ec51d07a4ac0e951608704431d59a02b21a4e951acc10505a8dc407c501ee']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "t_hash = [sha256(t) for t in t]\n",
    "t_hash"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "hash_map: {'*': '684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1', '2': 'd4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35', '3': '4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce'}\n",
      "hashes: ['684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1', 'd4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35', '4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce']\n",
      "hash_of_map: 137a5e74a65d4a4306bd5474ba4e68269cdac3547a1647f085e3d784c436dfdb\n",
      "hash_chain: [('4e07408562bedb8b60ce05c1decfe3ad16b72230967de01f640b7e4729b49fce', 'd4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35', 'ef3b42c1086b0493172457c03f4ddf2dcd0e69a9009e131e90196ee06cbc44be'), ('d4735e3a265e16eee03f59718b9b5d03019c07d8b6c51f90da3a666eec13ab35', '684888c0ebb17f374298b65ee2807526c066094c701bcc7ebbe1c1095f494fc1', 'a93e57189011b4a14fcd8f6b08825e8ddcf95d87c8d5cc3bda768b7b91fa040f')]\n",
      "a93e57189011b4a14fcd8f6b08825e8ddcf95d87c8d5cc3bda768b7b91fa040f\n"
     ]
    }
   ],
   "source": [
    "# make a hash of a list\n",
    "def hash_of_list(tokens:list) -> str:\n",
    "    \"\"\"Returns the SHA256 hash of the input list\"\"\"\n",
    "    if tokens[0] == '(':\n",
    "        tokens = tokens[1:-1]\n",
    "    if tokens[-1]==')':\n",
    "        tokens = tokens[:-1]\n",
    "    hash_map = {}\n",
    "    hashes = []\n",
    "    for t in tokens:\n",
    "        h = sha256(t)\n",
    "        hash_map[t] = h\n",
    "        hashes.append(h)\n",
    "    print(f'hash_map: {hash_map}')\n",
    "    print(f'hashes: {hashes}')\n",
    "    \n",
    "    hash_of_map = sha256(str(hash_map))\n",
    "    print(f'hash_of_map: {hash_of_map}')\n",
    "    # return hash_of_map\n",
    "\n",
    "    revd = tokens[::-1]\n",
    "    hash_chain = []\n",
    "    last_hash = sha256(revd.pop(0))\n",
    "    while len(revd):\n",
    "        next_hash = sha256(revd.pop(0))\n",
    "        combine = sha256(last_hash +' '+ next_hash)\n",
    "\n",
    "        hash_chain.append((last_hash, next_hash, combine))\n",
    "        last_hash = next_hash\n",
    "    print(f'hash_chain: {hash_chain}')\n",
    "    return hash_chain[-1][-1]\n",
    "\n",
    "print(hash_of_list(tokenize('(* 2 3)')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.9.7"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "40d3a090f54c6569ab1632332b64b2c03c39dcf918b08424e98f38b5ae0af88f"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}