pangram_analyzer.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "PT_LETTERS_BASE = \"abcdefghijklmnopqrstuvwxyz\"\n",
    "PT_LETTERS_DIACRITICS = \"áàãâçéêíóõôú\"\n",
    "PT_LETTERS_DIACRITICS_CONV = \"aaaaceeiooou\"\n",
    "PT_LETTERS_CONV = str.maketrans(PT_LETTERS_DIACRITICS, PT_LETTERS_DIACRITICS_CONV)\n",
    "PT_LETTERS_ALL = PT_LETTERS_BASE + PT_LETTERS_DIACRITICS\n",
    "PT_DIACRITICS = {\n",
    "    'acute': set('áéíóú'),\n",
    "    'grave': set('à'),\n",
    "    'tilde': set('ãõ'),\n",
    "    'circumflex': set('âêô'),\n",
    "    'cedil': set('ç'),\n",
    "}\n",
    "\n",
    "MARKER_NOT_LETTER = ' '\n",
    "MARKER_UNIQUE = '^'\n",
    "MARKER_DIACRITIC_UNIQUE = MARKER_UNIQUE\n",
    "MARKER_OVER_10 = '+'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def analyze_pangram(pangram):\n",
    "    # normalize string by lower-casing it and removing non-letters\n",
    "    normalized_lower = pangram.lower()\n",
    "    normalized = ''.join(filter(lambda l: l in PT_LETTERS_ALL, normalized_lower))\n",
    "    \n",
    "    # Counters\n",
    "    normalized_base = normalized.translate(PT_LETTERS_CONV)\n",
    "    \n",
    "    letter_counter = Counter(normalized)\n",
    "    letter_base_counter = Counter(normalized_base)\n",
    "    \n",
    "    # Inline preview with markers\n",
    "    pangram_markers = []\n",
    "    for letter in normalized_lower:\n",
    "        # Not counted, not a letter\n",
    "        if letter not in letter_counter:\n",
    "            pangram_markers.append(MARKER_NOT_LETTER)\n",
    "        # Diacritic, unique\n",
    "        elif letter not in letter_base_counter and letter in letter_counter:\n",
    "            pangram_markers.append(MARKER_DIACRITIC_UNIQUE)\n",
    "        # Non diacritic, unique\n",
    "        elif letter_counter[letter] == 1:\n",
    "            pangram_markers.append(MARKER_UNIQUE)\n",
    "        # Letter with one or more duplicates\n",
    "        else:\n",
    "            count = letter_base_counter[letter]\n",
    "            pangram_markers.append(str(count) if count <= 9 else MARKER_OVER_10)\n",
    "    \n",
    "    print(pangram)\n",
    "    print(''.join(pangram_markers))\n",
    "    print()\n",
    "    \n",
    "    total_length = len(normalized)\n",
    "    print(\"{} letters in length ({} characters).\".format(total_length, len(pangram)))\n",
    "    \n",
    "    # Base letters\n",
    "    letters_present = set(''.join(letter_base_counter))\n",
    "    letters_missing = sorted(set(PT_LETTERS_BASE) - letters_present)\n",
    "    \n",
    "    if letters_missing:\n",
    "        print(\"Missing letters: {}\".format(', '.join(letters_missing)))\n",
    "    else:\n",
    "        print(\"No letters missing.\")\n",
    "    \n",
    "    # Diacritics and other diacritics\n",
    "    diacritics_present = set(letter_counter) & set(PT_LETTERS_DIACRITICS)\n",
    "    diacritics_missing = list(PT_DIACRITICS.keys())\n",
    "    \n",
    "    for diacritic, letters in PT_DIACRITICS.items():\n",
    "        if letters & diacritics_present:\n",
    "            diacritics_missing.remove(diacritic)\n",
    "    \n",
    "    if diacritics_missing:\n",
    "        print(\"Missing diacritics: {}\".format(', '.join(diacritics_missing)))\n",
    "    else:\n",
    "        print(\"No diacritics missing.\")\n",
    "    print()\n",
    "    \n",
    "    # Duplicate letters\n",
    "    print(\"Frequency of duplicates:\")\n",
    "    for letter, count in letter_base_counter.most_common():\n",
    "        if count <= 1:\n",
    "            break\n",
    "        print(\"    {} | {: >2d} ({:>4.1f}%) | {}\".format(\n",
    "            letter, count, round(count / total_length * 100, 1), '#' * count))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Açor frágil, viaja amanhã para Sul, traz o kiwi de nylon àquela bruxa robô.\n",
      "+^56 ^6^^44  ^4+^+ +^+3^^ ^+6+ ^34  ^6+^ 5 ^4^4 ^2 3^453 ^^324+ 263^+ 652^ \n",
      "\n",
      "59 letters in length (75 characters).\n",
      "No letters missing.\n",
      "No diacritics missing.\n",
      "\n",
      "Frequency of duplicates:\n",
      "    a | 13 (22.0%) | #############\n",
      "    r |  6 (10.2%) | ######\n",
      "    o |  5 ( 8.5%) | #####\n",
      "    i |  4 ( 6.8%) | ####\n",
      "    l |  4 ( 6.8%) | ####\n",
      "    n |  3 ( 5.1%) | ###\n",
      "    u |  3 ( 5.1%) | ###\n",
      "    e |  2 ( 3.4%) | ##\n",
      "    b |  2 ( 3.4%) | ##\n"
     ]
    }
   ],
   "source": [
    "analyze_pangram(\"Açor frágil, viaja amanhã para Sul, traz o kiwi de nylon àquela bruxa robô.\")"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}