{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of Cantonese sentences:  58492\n"
     ]
    }
   ],
   "source": [
    "can_sents = []\n",
    "\n",
    "with open(\"../train/common_voice.can\", \"r\") as common_voice_file, open(\"../train/wordshk.can\", \"r\") as wordshk_file,\\\n",
    "    open(\"../train/novels.can\", \"r\") as novels_file,\\\n",
    "    open(\"../train/abc.can\", \"r\") as abc_file:\n",
    "    lines = common_voice_file.read().splitlines() + wordshk_file.read().splitlines() + novels_file.read().splitlines() + abc_file.read().splitlines()\n",
    "    for line in lines:\n",
    "        if len(line) >= 5:\n",
    "            can_sents.append(line)\n",
    "\n",
    "print(\"Number of Cantonese sentences: \", len(can_sents))\n",
    "\n",
    "with open(\"bing.can\", \"w\") as f:\n",
    "    for sent in can_sents:\n",
    "        f.write(sent + \"\\n\")\n",
    "    f.flush()\n"
   ]
  }
 ],
 "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": "3.10.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}