{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "smooth-consumption",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Import the requisite library\n",
    "import spacy\n",
    "\n",
    "#Sample text\n",
    "text = \"This is a sample number (555) 555-5555.\"\n",
    "\n",
    "#Build upon the spaCy Small Model\n",
    "nlp = spacy.blank(\"en\")\n",
    "\n",
    "#Create the Ruler and Add it\n",
    "ruler = nlp.add_pipe(\"entity_ruler\")\n",
    "\n",
    "#List of Entities and Patterns (source: https://spacy.io/usage/rule-based-matching)\n",
    "patterns = [\n",
    "                {\n",
    "                    \"label\": \"PHONE_NUMBER\",\n",
    "                    \"pattern\":\n",
    "                    [{\"TEXT\":\n",
    "                      {\"REGEX\": \"((\\d){3}-(\\d){4})\"}}\n",
    "                                                        ]\n",
    "                }\n",
    "            ]\n",
    "#add patterns to ruler\n",
    "ruler.add_patterns(patterns)\n",
    "\n",
    "\n",
    "#create the doc\n",
    "doc = nlp(text)\n",
    "\n",
    "#extract entities\n",
    "for ent in doc.ents:\n",
    "    print (ent.text, ent.label_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "statewide-insider",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5555555 PHONE_NUMBER\n"
     ]
    }
   ],
   "source": [
    "#Import the requisite library\n",
    "import spacy\n",
    "\n",
    "#Sample text\n",
    "text = \"This is a sample number 5555555.\"\n",
    "#Build upon the spaCy Small Model\n",
    "nlp = spacy.blank(\"en\")\n",
    "\n",
    "#Create the Ruler and Add it\n",
    "ruler = nlp.add_pipe(\"entity_ruler\")\n",
    "\n",
    "#List of Entities and Patterns (source: https://spacy.io/usage/rule-based-matching)\n",
    "patterns = [\n",
    "                {\n",
    "                    \"label\": \"PHONE_NUMBER\",\n",
    "                    \"pattern\":\n",
    "                    [{\"TEXT\":\n",
    "                      {\"REGEX\": \"((\\d){5})\"}}\n",
    "                                                        ]\n",
    "                }\n",
    "            ]\n",
    "#add patterns to ruler\n",
    "ruler.add_patterns(patterns)\n",
    "\n",
    "\n",
    "#create the doc\n",
    "doc = nlp(text)\n",
    "\n",
    "#extract entities\n",
    "for ent in doc.ents:\n",
    "    print (ent.text, ent.label_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "difficult-landing",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "polished-gothic",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.9.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}