{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<CENTER>\n",
    "    <h1>LegalTech HackZurich 2020</h1>\n",
    "    <br><hr></br>\n",
    "    <a href=\"http://universidad.ch/hackzurich/suite/\" class=\"icons\"><img src=\"https://hackzurich.com/media/pages/workshops/15-legaltech/4173366116-1599065131/legaltech-600x-copy-600x.png\" style=\"width:20%\"></a>\n",
    "</CENTER>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%html\n",
    "<style>\n",
    "div.input {\n",
    "    display:none;\n",
    "}\n",
    "</style>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "\n",
    "with open('text-eng.txt', 'r') as f:\n",
    "    sample = f.read()\n",
    "\n",
    "##\n",
    "sentences = nltk.sent_tokenize(sample)\n",
    "tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]\n",
    "tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]\n",
    "chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_entity_names(t):\n",
    "    entity_names = []\n",
    "\n",
    "    if hasattr(t, 'label') and t.label:\n",
    "        if t.label() == 'NE':\n",
    "            entity_names.append(' '.join([child[0] for child in t]))\n",
    "        else:\n",
    "            for child in t:\n",
    "                entity_names.extend(extract_entity_names(child))\n",
    "\n",
    "    return entity_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "entity_names = []\n",
    "for tree in chunked_sentences:\n",
    "    # Print results per sentence\n",
    "    # print extract_entity_names(tree)\n",
    "\n",
    "    entity_names.extend(extract_entity_names(tree))\n",
    "\n",
    "# Print all entity names\n",
    "#print entity_names\n",
    "\n",
    "# Print unique entity names\n",
    "print(entity_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file = open(\"names-extracted.txt\", \"w\")\n",
    "\n",
    "for element in entity_names:\n",
    "    print(f\"{element}\", file=file)\n",
    "file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.system('cat names-extracted.txt | sort | uniq > names-sorted-uniq-PDF.txt')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<CENTER>\n",
    "    <a href=\"http://universidad.ch/hackzurich/suite/\" class=\"icons\"><img src=\"http://universidad.ch/hackzurich/suite/logos/footer-hackathon.png\" style=\"width:90%\"></a>\n",
    "</CENTER>"
   ]
  }
 ],
 "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
}