{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 196,
   "id": "2f61df31-f3c1-4b2e-ae96-96bf06089b17",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_digits(string):\n",
    "    splat = string.split(\")\")\n",
    "    num = splat[0]\n",
    "    l = len(num)\n",
    "    return int(num),l\n",
    "\n",
    "def token_generator(string):\n",
    "    \n",
    "    start = 0\n",
    "    str_len = len(string)\n",
    "    \n",
    "    \n",
    "    while start < str_len:\n",
    "        substring = string[start:]\n",
    "        \n",
    "        #check for cid\n",
    "        if (str_len - start > 6) and (substring[0:5] == \"(cid:\"):\n",
    "            \n",
    "            num,length = get_digits(substring[5:])\n",
    "            start += length + 6\n",
    "            yield num\n",
    "            \n",
    "        elif (str_len - start > 1):\n",
    "            start += 1\n",
    "            yield substring[0]\n",
    "        else:\n",
    "            start += 1\n",
    "            yield substring\n",
    "\n",
    "class UnknownSymbol():\n",
    "    def __init__(self, symbol):\n",
    "        self.symbol = symbol\n",
    "        \n",
    "    def __repr__(self):\n",
    "        return \"UnknownSymbol: {} of type {}\".format(self.symbol, type(self.symbol))\n",
    "    \n",
    "    def __str__(self):\n",
    "        return \"\\uFFFD\"\n",
    "\n",
    "class Parser:\n",
    "    def __init__(self, lookup_table):\n",
    "        self._lookup_table = lookup_table\n",
    "        \n",
    "    def convert(self,symbol):\n",
    "        try:\n",
    "            return self._lookup_table[symbol]\n",
    "        except:\n",
    "            return  UnknownSymbol(symbol)\n",
    "    \n",
    "    def convert_stream(self,token_stream):\n",
    "        for token in token_stream:\n",
    "            yield self.convert(token)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "id": "e2c1e39b-0ac5-4ad7-9176-ef8ea69feeec",
   "metadata": {},
   "outputs": [],
   "source": [
    "ob2020 = Parser({\n",
    "    23:\"4\"\n",
    "    ,19:\"0\"\n",
    "    ,\"7\":\"T\"\n",
    "    ,\"+\":\"H\"\n",
    "    ,3:\" \"\n",
    "    ,\"(\":\"E\"\n",
    "    ,\"’\":\"D\"\n",
    "    ,\",\":\"I\"\n",
    "    ,\"2\":\"O\"\n",
    "    ,\"1\":\"N\"\n",
    "    ,16:\"-\"\n",
    "    ,21:\"2\"\n",
    "    ,\"$\":\"A\"\n",
    "    ,\"3\":\"P\"\n",
    "    ,\"5\":\"R\"\n",
    "    ,\"9\":\"V\"\n",
    "    ,\"8\":\"U\"\n",
    "    ,\"*\":\"G\"\n",
    "    ,\"&\":\"C\"\n",
    "    ,\"/\":\"L\"\n",
    "    ,\"6\":\"S\"\n",
    "    ,22:\"3\"\n",
    "    ,20:\"1\"\n",
    "    ,11:\" \"\n",
    "    ,\"R\":\"(\"\n",
    "    ,\"I\":\"of\"\n",
    "    ,24:\"5\"\n",
    "    ,12:\")\"\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "c02896ab-fc75-44cc-bb27-a5dcf1b6d7f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'40TH EDITION - 2020 - APPROVED DRUG PRODUCT LIST'"
      ]
     },
     "execution_count": 214,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\".join([x for x in ob2020.convert_stream(token_generator(b))])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "1794e826-fa1f-4aba-8eab-6d603a06dfe0",
   "metadata": {},
   "outputs": [],
   "source": [
    "c = \"35(6&5,37,21(cid:3)’58*(cid:3)352’8&7(cid:3)/,67(cid:3)\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "id": "c8b67d79-81ad-4b3a-be8b-bace9a8d943a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'PRESCRIPTION DRUG PRODUCT LIST '"
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\".join([x for x in ob2020.convert_stream(token_generator(c))])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "f76d9760-fe69-4743-ab47-41cf74866d70",
   "metadata": {},
   "outputs": [],
   "source": [
    "d = \"(cid:22)(cid:16)(cid:20)(cid:11)RI(cid:3)(cid:23)(cid:24)(cid:22)(cid:12)\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 218,
   "id": "ee925997-0701-4d8e-b713-6f39c6a50a5b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['3', '-', '1', ' ', '(', 'of', ' ', '4', '5', '3', ')']"
      ]
     },
     "execution_count": 218,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[x for x in ob2020.convert_stream(token_generator(d))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ae152c75-5fd6-4756-a473-fcea2de5ee30",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}