{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "d06f1e82-1895-4e3e-b88d-b67f857ddb56",
   "metadata": {},
   "source": [
    "# Test/create feature 'unaccented' and 'transliteration'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c692f7e1-df4f-43bf-b80f-0b0e4fa1e329",
   "metadata": {},
   "source": [
    "This is a playground for the development of two new features.\n",
    "\n",
    "It depends on Python library:\n",
    "\n",
    "* unidecode  = ASCII transliteration of unicode text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ebc96637-30a9-4561-9c46-44f60330804a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "en arkhe en o logos, kai o logos en pros ton theon, kai theos en o logos.\n",
      "εν αρχη ην ο λογος, και ο λογος ην προς τον θεον, και θεος ην ο λογος.\n",
      "ἐν ἀρχῇ ἦν ὁ λόγος, καὶ ὁ λόγος ἦν πρὸς τὸν θεόν, καὶ θεὸς ἦν ὁ λόγος.\n"
     ]
    }
   ],
   "source": [
    "from unidecode import unidecode\n",
    "import unicodedata\n",
    "\n",
    "def make_transliteration(text):\n",
    "    return unidecode(text)\n",
    "\n",
    "def remove_accents(text):\n",
    "    return ''.join(c for c in unicodedata.normalize('NFD', text) if unicodedata.category(c) != 'Mn')\n",
    "\n",
    "# test with John 1:1\n",
    "\n",
    "greek_text_with_accents = \"ἐν ἀρχῇ ἦν ὁ λόγος, καὶ ὁ λόγος ἦν πρὸς τὸν θεόν, καὶ θεὸς ἦν ὁ λόγος.\"\n",
    "transliterated_text = make_transliteration(greek_text_with_accents)\n",
    "unaccented_text= remove_accents(greek_text_with_accents)\n",
    "\n",
    "print(transliterated_text)      # in TF>0.5 use with: fmt='text-transliterated'\n",
    "print(unaccented_text)          # in TF>0.5 use with: fmt='text-unaccented'\n",
    "print(greek_text_with_accents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91314721-c5d5-4899-bc6d-ab5d3ac7446e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}