import dotenv

import os

import argparse

from flow import create_schema_flow

dotenv.load_dotenv()

DEFAULT_INCLUDE_PATTERNS = {

"*.py", "*.js", "*.jsx", "*.ts", "*.tsx", "*.go", "*.java", "*.pyi", "*.pyx",

"*.c", "*.cc", "*.cpp", "*.h", "*.sql", "*.ddl", "*.dml",

"*.md", "*.rst", "*Dockerfile", "*Makefile", "*.yaml", "*.yml",

"*migration*", "*schema*", "*model*", "*entity*", "*dao*", "*repository*"

}

DEFAULT_EXCLUDE_PATTERNS = {

"assets/*", "data/*", "images/*", "public/*", "static/*", "temp/*",

"*docs/*",

"*venv/*",

"*.venv/*",

"*test*",

"*tests/*",

"*examples/*",

"v1/*",

"*dist/*",

"*build/*",

"*experimental/*",

"*deprecated/*",

"*misc/*",

"*legacy/*",

".git/*", ".github/*", ".next/*", ".vscode/*",

"*obj/*",

"*bin/*",

"*node_modules/*",

"*.log"

}

def main():

parser = argparse.ArgumentParser(description="Generate a database schema for a GitHub codebase or local directory.")

source_group = parser.add_mutually_exclusive_group(required=True)

source_group.add_argument("--repo", help="URL of the public GitHub repository.")

source_group.add_argument("--dir", help="Path to local directory.")

parser.add_argument("-n", "--name", help="Project name (optional, derived from repo/directory if omitted).")

parser.add_argument("-t", "--token", help="GitHub personal access token (optional, reads from GITHUB_TOKEN env var if not provided).")

parser.add_argument("-o", "--output", default="output", help="Base directory for output (default: ./output).")

parser.add_argument("-i", "--include", nargs="+", help="Include file patterns (e.g. '*.py' '*.sql'). Defaults to common code and database files if not specified.")

parser.add_argument("-e", "--exclude", nargs="+", help="Exclude file patterns (e.g. 'tests/*' 'docs/*'). Defaults to test/build directories if not specified.")

parser.add_argument("-s", "--max-size", type=int, default=100000, help="Maximum file size in bytes (default: 100000, about 100KB).")

parser.add_argument("--no-cache", action="store_true", help="Disable LLM response caching (default: caching enabled)")

args = parser.parse_args()

github_token = None

if args.repo:

github_token = args.token or os.environ.get('GITHUB_TOKEN')

if not github_token:

print("Warning: No GitHub token provided. You might hit rate limits for public repositories.")

shared = {

"repo_url": args.repo,

"local_dir": args.dir,

"project_name": args.name,

"github_token": github_token,

"output_dir": args.output,

"include_patterns": set(args.include) if args.include else DEFAULT_INCLUDE_PATTERNS,

"exclude_patterns": set(args.exclude) if args.exclude else DEFAULT_EXCLUDE_PATTERNS,

"max_file_size": args.max_size,

"use_cache": not args.no_cache,

"files": [],

"tables": [],

"schema": [],

"final_output_dir": None,

}

print(f"Starting database schema generation for: {args.repo or args.dir}")

print(f"LLM caching: {'Disabled' if args.no_cache else 'Enabled'}")

schema_flow = create_schema_flow()

schema_flow.run(shared)

if __name__ == "__main__":

main()