{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "// A simple example of a substring index; mirrors example from lecture notes\n",
    "\n",
    "// we're going to extract 4 substrings like this:\n",
    "// t:           CGTGCCTACTTACTTACAT\n",
    "// substring 1: CGTGC\n",
    "// substring 2:     CCTAC\n",
    "// substring 3:         CTTAC\n",
    "// substring 4:             CTTAC\n",
    "t := \"CGTGCCTACTTACTTACAT\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "// From t, make list of pairs, where first pair item is substring, second is its offset\n",
    "func substringize(t string, ln int, iv int) ([]string, []int) {\n",
    "    // ln = length of substrings to extract\n",
    "    // iv = distance between substings to extract; e.g. 1 means take *every* substring\n",
    "    strings := make([]string, 0)\n",
    "    offsets := make([]int, 0)\n",
    "    for i := 0; i < len(t) - ln + 1; i += iv {\n",
    "        strings = append(strings, t[i:i+ln])\n",
    "        offsets = append(offsets, i)\n",
    "    }\n",
    "    return strings, offsets\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[CGTGC CCTAC CTTAC CTTAC] [0 4 8 12]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "substringize(\"CGTGCCTACTTACTTACAT\", 5, 4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "// Like substringize, but uses a map data structure\n",
    "func mapize(t string, ln int, iv int) map[string][]int {\n",
    "    index := make(map[string][]int)\n",
    "    for i := 0; i < len(t) - ln + 1; i += iv {\n",
    "        sub := t[i:i+ln]\n",
    "        index[sub] = append(index[sub], i)\n",
    "    }\n",
    "    return index\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "map[CGTGC:[0] CCTAC:[4] CTTAC:[8 12]]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index := mapize(\"CGTGCCTACTTACTTACAT\", 5, 4)\n",
    "index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "p := \"CTTACTTA\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[8 12]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "// index: give me a hint where I should look for occurrences of p in t\n",
    "elem, ok := index[p[:5]]\n",
    "elem"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Go",
   "language": "go",
   "name": "gophernotes"
  },
  "language_info": {
   "codemirror_mode": "",
   "file_extension": ".go",
   "mimetype": "",
   "name": "go",
   "nbconvert_exporter": "",
   "pygments_lexer": "",
   "version": "go1.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}