{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xml.etree.ElementTree as ET\n",
    "import os\n",
    "import csv\n",
    "from collections import OrderedDict\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/var/folders/_n/1ldwyw1s547dcpvn3485fr7r0000gn/T/ipykernel_18830/2994982029.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     34\u001b[0m         \u001b[0mn_iperlemma\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'n_iperlemma'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     35\u001b[0m         \u001b[0mcommento\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'commento'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 36\u001b[0;31m         \u001b[0mid\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetIdAspo\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msigla_ovi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     37\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     38\u001b[0m         \u001b[0mline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msigla_ovi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/var/folders/_n/1ldwyw1s547dcpvn3485fr7r0000gn/T/ipykernel_18830/2994982029.py\u001b[0m in \u001b[0;36mgetIdAspo\u001b[0;34m(sigla_ovi)\u001b[0m\n\u001b[1;32m     17\u001b[0m         \u001b[0mlink_file\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/SIGLA-IDASPO.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     18\u001b[0m         \u001b[0mreader\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcsv\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDictReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlink_file\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m         \u001b[0;32mfor\u001b[0m \u001b[0mrow\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mreader\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     20\u001b[0m                 \u001b[0msigla_aspo\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrow\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'sigla'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     21\u001b[0m                 \u001b[0msa\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msigla_ovi\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/csv.py\u001b[0m in \u001b[0;36m__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    109\u001b[0m             \u001b[0;31m# Used only for its side effect.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    110\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfieldnames\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 111\u001b[0;31m         \u001b[0mrow\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreader\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    112\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mline_num\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mline_num\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    113\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import csv\n",
    "import codecs\n",
    "import pandas as pd\n",
    "import re\n",
    "import os\n",
    "import io\n",
    "import tokenize\n",
    "\n",
    "confronto_data = open('data_lemmi_iperlemmi_codice', 'w')\n",
    "csvwriter = csv.writer(confronto_data)\n",
    "\n",
    "params = ['sigla', 'n_lemma', 'lemma', 'pos', 'iperlemma', 'n_iperlemma', 'commento', 'id']\n",
    "\n",
    "csvwriter.writerow(params)\n",
    "\n",
    "def getIdAspo(sigla_ovi):\n",
    "        link_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/SIGLA-IDASPO.csv')\n",
    "        reader = csv.DictReader(link_file)\n",
    "        for row in reader:\n",
    "                sigla_aspo = row['sigla']\n",
    "                sa = sigla_ovi\n",
    "                if (sigla_aspo == sa):\n",
    "                        return row['id']\n",
    "merge_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/LEMMI.csv')\n",
    "reader = csv.DictReader(merge_file)\n",
    "\n",
    "for row in reader:\n",
    "        line = []\n",
    "        sigla_ovi = row['sigla']\n",
    "        n_lemma = row['n_lemma']\n",
    "        lemma = row['lemma']\n",
    "        pos = row['pos']\n",
    "        iperlemma = row['iperlemma']\n",
    "        n_iperlemma = row['n_iperlemma']\n",
    "        commento = row['commento']\n",
    "        id = getIdAspo(sigla_ovi)\n",
    "        line.append(sigla_ovi)\n",
    "        line.append(n_lemma)\n",
    "        line.append(lemma)\n",
    "        line.append(pos)\n",
    "        line.append(iperlemma)\n",
    "        line.append(n_iperlemma)\n",
    "        line.append(commento)\n",
    "\n",
    "        if id is not None:\n",
    "                line.append(id)\n",
    "        else:\n",
    "                line.append(\"\")\n",
    "\n",
    "        csvwriter.writerow(line)\n",
    "\n",
    "confronto_data.close()"
   ]
  }
 ],
 "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": "3.9.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}