{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Duplicate checker\n",
    "----\n",
    "\n",
    "This Python script checks for duplicate tags within text files (`.txt`) in a specified directory and its subdirectories. It reads each text file, splits its content into tags separated by commas, and identifies any duplicates. If duplicates are found, it prints out a message indicating the file where the duplicates were found and the duplicate tags themselves. Finally, the `check_tags_in_directory` function iterates through the directory and calls `check_duplicate_tags` for each text file found."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "def check_duplicate_tags(file_path):\n",
    "    with open(file_path, 'r') as file:\n",
    "        tags = file.read().split(', ')\n",
    "        duplicates = set()\n",
    "        unique_tags = set()\n",
    "        for tag in tags:\n",
    "            if tag in unique_tags:\n",
    "                duplicates.add(tag)\n",
    "            else:\n",
    "                unique_tags.add(tag)\n",
    "        if duplicates:\n",
    "            print(f\"Duplicate tags found in {file_path}: {', '.join(duplicates)}\")\n",
    "\n",
    "def check_tags_in_directory(directory):\n",
    "    for root, _, files in os.walk(directory):\n",
    "        for file_name in files:\n",
    "            if file_name.endswith('.txt'):\n",
    "                file_path = os.path.join(root, file_name)\n",
    "                check_duplicate_tags(file_path)\n",
    "\n",
    "if __name__ == \"__main__\":\n",
    "    directory_path = r'C:\\Users\\kade\\Desktop\\training_dir_staging'\n",
    "    check_tags_in_directory(directory_path)\n"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}