terra-llm/Assets/LLM/source/extract_low_level.py

import argparse
import sys
import subprocess
import json
from pathlib import Path

# Add the utils directory to the Python path
utils_path = Path(__file__).parent / 'utils'
sys.path.append(str(utils_path))

from config_utils import load_config

def run_subprocess(script_name, input_dir, output_dir, indent=None, shrink=False, ignored_folders=None):
    """Helper function to run a parser subprocess."""
    script_path = Path(__file__).parent / "parsers" / script_name
    command = [
        sys.executable,
        str(script_path),
        "--input",
        str(input_dir),
        "--output",
        str(output_dir)
    ]
    
    # Pass indent and shrink arguments to subparsers.
    # This assumes the subparsers have been updated to accept them.
    if indent is not None:
        command.extend(["--indent", str(indent)])
    if shrink:
        command.append("--shrink-json")
    
    if ignored_folders:
        command.extend(["--ignored-folders", json.dumps(ignored_folders)])

    try:
        result = subprocess.run(command, check=True, text=True, capture_output=True, encoding='utf-8')
        if result.stdout:
            print(result.stdout)
        if result.stderr:
            print(result.stderr, file=sys.stderr)

    except subprocess.CalledProcessError as e:
        print(f"--- ERROR in {script_name} ---")
        print(e.stdout)
        print(e.stderr, file=sys.stderr)
        print(f"--- End of Error ---")
    except FileNotFoundError:
        print(f"--- ERROR: Script not found at {script_path} ---", file=sys.stderr)


def main():
    """
    Main function to orchestrate the low-level data extraction pipeline.
    """
    parser = argparse.ArgumentParser(
        description="Orchestrates a pipeline of parsers for a detailed data breakdown."
    )
    parser.add_argument("--input", type=str, required=True, help="The root directory of the target Unity project.")
    parser.add_argument("--output", type=str, required=True, help="The directory where the generated output folder will be saved.")
    args = parser.parse_args()

    # --- Load Configuration ---
    config = load_config()
    ignored_folders = config.get('ignored_folders', [])
    shrink_json = config.get('shrink_json', False)
    indent_level = config.get('indentation_level', 4)

    input_dir = Path(args.input).resolve()
    output_dir = Path(args.output).resolve()

    if not input_dir.is_dir():
        print(f"Error: Input path '{input_dir}' is not a valid directory.", file=sys.stderr)
        sys.exit(1)

    low_level_output_dir = output_dir / "LowLevel"
    low_level_output_dir.mkdir(parents=True, exist_ok=True)
    print(f"Output will be saved to: {low_level_output_dir}")

    # --- Run Extraction Pipeline ---
    # Pass all relevant config options to the subparsers.
    run_subprocess("copy_scripts.py", input_dir, low_level_output_dir, indent_level, shrink_json, ignored_folders)
    run_subprocess("copy_shaders.py", input_dir, low_level_output_dir, indent_level, shrink_json, ignored_folders)
    run_subprocess("parse_project_settings.py", input_dir, low_level_output_dir, indent_level, shrink_json, ignored_folders)
    run_subprocess("parse_generic_assets.py", input_dir, low_level_output_dir, indent_level, shrink_json, ignored_folders)
    run_subprocess("parse_scenes_and_prefabs.py", input_dir, low_level_output_dir, indent_level, shrink_json, ignored_folders)

    print("\nLow-level extraction pipeline complete.")

if __name__ == "__main__":
    main()