{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3\n",
      "Av. Dn. Ana Costa\n",
      "Av. Francisco Nóbrega Barbosa\n",
      "Av. Francisco Nóbrega Barbosa => Avenida Francisco Nóbrega Barbosa\n",
      "Complexo Viário Engenheiro Job Shuji Nogami\n",
      "R. Bergamo\n",
      "R. Bergamo => Rua Bergamo\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Anaconda\\lib\\site-packages\\IPython\\kernel\\__main__.py:72: UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal\n"
     ]
    }
   ],
   "source": [
    "#!/usr/bin/env python\n",
    "#-*- coding: utf-8 -*-\n",
    "#audit.py\n",
    "import xml.etree.cElementTree as ET\n",
    "from collections import defaultdict\n",
    "import re\n",
    "import pprint\n",
    "\n",
    "#arquivo = \"/media/vagner/Seagate Expansion Drive/500Gb/DiskExternoVagner/Cursos/CientistaDados/Modulo_4/DW-OSM-RMSP/sample.osm\"\n",
    "arquivo = r'F:\\500Gb\\DiskExternoVagner\\Cursos\\CientistaDados\\Modulo_4\\DW-OSM-RMSP\\sample.osm'\n",
    "\n",
    "osm_file = open(arquivo, \"r\")\n",
    "\n",
    "street_type_re = re.compile(r'^\\S+\\.?',re.IGNORECASE)\n",
    "street_types = defaultdict(set)\n",
    "\n",
    "\n",
    "\n",
    "expected = [\"Alameda\", \"Avenida\", \"Estrada\", \"Largo\", u\"Praça\", \"Rodovia\", \"Rua\", \"Travessa\", \"Via\",\n",
    "            u\"Calçadão\", \"Rodoanel\", \"Passeio\", u\"Complexo Viário\", \"Marginal\"]\n",
    "\n",
    "mapping = { \"Av\": \"Avenida\",\n",
    "            \"Av.\": \"Avenida\",\n",
    "            \"R\": \"Rua\",\n",
    "            \"R.\": \"Rua\", \n",
    "            \"rua\": \"Rua\",\n",
    "            \"r.\": \"Rua\",\n",
    "            \"r\": \"Rua\",\n",
    "            \"Pr.\": u\"Praça\",\n",
    "            \"PR.\": u\"Praça\",\n",
    "            \"Complexo viário\": u\"Complexo Viário\",\n",
    "            \"Complexo viario\": u\"Complexo Viário\"\n",
    "          }\n",
    "\n",
    "def audit_street_type(street_types, street_name):\n",
    "    \"\"\"     Utiliza expressão regular para verificar o ínicio do campo \"addr:street\" identificando assim o Tipo de \n",
    "    Via (Rua, Alamenda, etc)\n",
    "    \"\"\"\n",
    "    #print street_name\n",
    "    m = street_type_re.search(street_name)\n",
    "    if m:\n",
    "        street_type = m.group()\n",
    "        #print street_type \n",
    "        if street_type not in expected:\n",
    "            street_types[street_type].add(street_name)\n",
    "            \n",
    "def is_street_name(elem):\n",
    "    \"\"\"     Verifica se o tag é um atributo de endereço de via (addr:street). Retorna um Boolean (True se atributo\n",
    "    de endereço de via)           \n",
    "    \"\"\"\n",
    "    return (elem.attrib['k'] == \"addr:street\")\n",
    "\n",
    "def audit():\n",
    "    \"\"\"     Realiza análise baseada no evento \"tag de ínicio\"; quando este ocorre o elemento em questão é \n",
    "    identificado e se for do tipo \"way\", o método \"iter\" é chamado; este método realiza uma iteração de todas as \n",
    "    subtags (tags aninhadas) do tipo \"tag\".\n",
    "    \"\"\"\n",
    "    for event, elem in ET.iterparse(osm_file, events=(\"start\",)):\n",
    "        if elem.tag == \"way\":\n",
    "            for tag in elem.iter(\"tag\"):\n",
    "                if is_street_name(tag):\n",
    "                    audit_street_type(street_types, tag.attrib['v'])\n",
    "    #pprint.pprint(dict(street_types))\n",
    "    return street_types\n",
    "\n",
    "def update_name(name, mapping):\n",
    "    #print name\n",
    "    m = street_type_re.search(name)\n",
    "    other_street_types=[]\n",
    "    if m:\n",
    "        street_type = m.group()\n",
    "        if street_type in mapping.keys():\n",
    "            name = re.sub(street_type_re, mapping[street_type], name)\n",
    "        else:\n",
    "            other_street_types.append(street_type)\n",
    "        return name\n",
    "\n",
    "def test():\n",
    "    st_types = audit()\n",
    "    print (len(st_types.keys()))\n",
    "    #pprint.pprint(dict(st_types))\n",
    "    \n",
    "    for st_type, ways in st_types.iteritems():\n",
    "        for name in ways:\n",
    "            better_name = update_name(name, mapping)\n",
    "        if name != better_name:\n",
    "            print name, \"=>\", better_name\n",
    "            name= better_name\n",
    "              \n",
    "if __name__ == '__main__':\n",
    "    test()\n",
    "    osm_file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [default]",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}