{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pony2Seaart\n",
    "\n",
    "---\n",
    "\n",
    "This script converts Pony captions to Seaart."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import glob\n",
    "\n",
    "def pony2seaart(file_path):\n",
    "    if os.path.basename(file_path).endswith(\"sample-prompts.txt\"):\n",
    "        return\n",
    "    with open(file_path, \"r\") as file:\n",
    "        lines = file.readlines()\n",
    "        new_lines = []\n",
    "        for line in lines:\n",
    "            parts = line.strip().split(\", \")\n",
    "            tags = []\n",
    "            caption = \"\"\n",
    "            for part in parts:\n",
    "                if \".\" in part:\n",
    "                    if not caption:\n",
    "                        caption = part\n",
    "                    else:\n",
    "                        caption += \", \" + part\n",
    "                else:\n",
    "                    tag = part.replace(\" \", \"_\")\n",
    "                    if tag == \"rating_explicit\":\n",
    "                        tag = \"nsfw\"\n",
    "                    elif tag == \"rating_safe\":\n",
    "                        tag = \"safe\"\n",
    "                    elif tag == \"rating_questionable\":\n",
    "                        tag = \"questionable\"\n",
    "                    tags.append(tag)\n",
    "            new_line = \", \".join(tags) + (\", \" + caption if caption else \"\")\n",
    "            new_lines.append(new_line + \"\\n\")\n",
    "\n",
    "            new_file_name = os.path.splitext(os.path.basename(file_path))[0] + \".seaart\"\n",
    "            new_file_path = os.path.join(os.path.dirname(file_path), new_file_name)\n",
    "            with open(new_file_path, \"w\") as new_file:\n",
    "                new_file.writelines(new_lines)\n",
    "\n",
    "def process_directory(directory):\n",
    "    txt_files = glob.glob(os.path.join(directory, \"**\", \"*.txt\"), recursive=True)\n",
    "    for file_path in txt_files:\n",
    "        pony2seaart(file_path)\n",
    "\n",
    "if __name__ == \"__main__\":\n",
    "    input_dir = \"C:\\\\Users\\\\kade\\\\Desktop\\\\training_dir_staging\"\n",
    "    process_directory(input_dir)"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}