{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# reads a string and returns a masked version of the string,\n",
    "# where sequences of `length` (default=9) digits are replaced \n",
    "# with the replacement character (default='X')\n",
    "#\n",
    "# if the string does not fit in memory, we'll need a stream-based approach instead\n",
    "def mask_digit_sequences(input_str, length=None, replacement=None):\n",
    "    # this is the recommended way to use default arguments in \n",
    "    # python functions\n",
    "    if length is None:\n",
    "        length = 9\n",
    "    if replacement is None:\n",
    "        replacement = \"X\"\n",
    "        \n",
    "    # i'll use a state-machine approach that counts the number of\n",
    "    # digits seen in the current sentence\n",
    "    \n",
    "    current_sequence = \"\"\n",
    "    \n",
    "    for (i,char) in enumerate(input_str):\n",
    "        if char.isdigit():\n",
    "            current_sequence += char\n",
    "        else: # not a digit\n",
    "            # broken sequence\n",
    "            if len(current_sequence) != 0:\n",
    "                print(current_sequence, end='')\n",
    "                current_sequence = \"\"\n",
    "            else:\n",
    "                print(char, end='')\n",
    "        \n",
    "        if len(current_sequence) == length:\n",
    "            for i in range(length):\n",
    "                print(replacement, end='')\n",
    "            current_sequence = \"\"\n",
    "        \n",
    "        # we've reached the end of the string and the current sequence is not empty\n",
    "        if i == len(input_str) -1 and len(current_sequence) != 0:\n",
    "            print(current_sequence,end='')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12"
     ]
    }
   ],
   "source": [
    "mask_digit_sequences(\"12\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "aaaa12345678bbbbXXXXXXXXX0123"
     ]
    }
   ],
   "source": [
    "mask_digit_sequences(\"aaaa12345678bbbbb1234567890123\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "aaaa12345678bbbb---------0123"
     ]
    }
   ],
   "source": [
    "mask_digit_sequences(\"aaaa12345678bbbbb1234567890123\",replacement='-')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Claudio’s number is XXXXXXXXX and his friend’s number is XXXXXXXXXXXXXXXXXX55"
     ]
    }
   ],
   "source": [
    "mask_digit_sequences(\"Claudio’s number is 123456789 and his friend’s number is 12345678900033322255\")"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}