{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Replace underscores with spaces\n",
    "----\n",
    "\n",
    "Recursively replaces underscores with spaces in the content of text files in the specified directory and its subdirectories,\n",
    "excluding specified tags."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "excluded_tags = [\n",
    "    \"rating_safe\",\n",
    "    \"rating_explicit\",\n",
    "    \"rating_questionable\"\n",
    "]\n",
    "\n",
    "def replace_underscores_with_spaces(directory_path):\n",
    "    for root, dirs, files in os.walk(directory_path):\n",
    "        for filename in files:\n",
    "            if filename.endswith(\".txt\"):\n",
    "                file_path = os.path.join(root, filename)\n",
    "\n",
    "                # Read the content of the file\n",
    "                with open(file_path, 'r') as file:\n",
    "                    content = file.read()\n",
    "\n",
    "                # Replace underscores with spaces, excluding specific tags\n",
    "                for tag in excluded_tags:\n",
    "                    replacement = tag.replace('_', ' ')\n",
    "                    content = content.replace(replacement, tag)\n",
    "\n",
    "                # Write the modified content back to the file\n",
    "                with open(file_path, 'w') as file:\n",
    "                    file.write(content)\n",
    "\n",
    "# Specify the directory path\n",
    "directory_path = r'C:\\Users\\kade\\Desktop\\training_dir_staging'\n",
    "\n",
    "# Call the function to recursively replace underscores with spaces (excluding specified tags)\n",
    "replace_underscores_with_spaces(directory_path)"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}