{
 "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": [],
   "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_thing_id', 'w')\n",
    "csvwriter = csv.writer(confronto_data)\n",
    "\n",
    "params = ['thing', 'sigla', 'lemma', 'n_lemma', 'iperlemma', 'n_iperlemma', 'pos', 'commento', 'id']\n",
    "\n",
    "csvwriter.writerow(params)\n",
    "\n",
    "def getIdLemma(lemma_unique):\n",
    "        link_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/OVI_lemmi_iperlemmi - JOIN LEMMI-IPERLEMMI UNIQUE.csv')\n",
    "        reader = csv.DictReader(link_file)\n",
    "        for row in reader:\n",
    "                if (row['pos'] != 'antr.' and row['pos'] != 'n.g.'):\n",
    "                        lemma_all = row['lemma']\n",
    "                        iperlemma_all = row['iperlemma']\n",
    "                        #id = row['id']\n",
    "                        all1 = lemma_unique\n",
    "                        all2 = iperlemma_unique\n",
    "                        if (lemma_all == all1):\n",
    "                                return row['thing']\n",
    "merge_file = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/OVI/CSV/OVI_lemmi_iperlemmi_idaspo - data_lemmi_iperlemmi_OVI_IDASPO.csv')\n",
    "reader = csv.DictReader(merge_file)\n",
    "\n",
    "for row in reader:\n",
    "        if (row['pos'] != 'antr.' and row['pos'] != 'n.g.'):\n",
    "                line = []\n",
    "                lemma_unique = row['lemma']\n",
    "                n_lemma = row['n_lemma']\n",
    "                sigla = row['sigla']\n",
    "                pos = row['pos']\n",
    "                iperlemma_unique = row['iperlemma']\n",
    "                n_iperlemma = row['n_iperlemma']\n",
    "                commento = row['commento']\n",
    "                #thing = row['thing']\n",
    "                id = row['id']\n",
    "                corresp = getIdLemma(lemma_unique)\n",
    "                #line.append(thing)\n",
    "                line.append(sigla)\n",
    "                line.append(lemma_unique)\n",
    "                line.append(n_lemma)\n",
    "                line.append(iperlemma_unique)\n",
    "                line.append(n_iperlemma)\n",
    "                line.append(pos)\n",
    "                line.append(commento)\n",
    "                line.append(id)\n",
    "                if corresp is not None:\n",
    "                        line.append(corresp)\n",
    "                else:\n",
    "                        line.append(\"\")\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
}