import os
import tempfile
import shutil
from git import Repo
from typing import List, Tuple
import hashlib
from urllib.parse import urlparse

class GitHubService:
    def __init__(self, github_token: str = ""):
        self.github_token = github_token
    
    def generate_repo_id(self, repo_url: str) -> str:
        """Generate a unique ID for the repository"""
        return hashlib.md5(repo_url.encode()).hexdigest()
    
    def parse_github_url(self, url: str) -> Tuple[str, str]:
        """Extract owner and repo name from GitHub URL"""
        parsed = urlparse(url)
        path_parts = parsed.path.strip('/').split('/')
        if len(path_parts) >= 2:
            return path_parts[0], path_parts[1]
        raise ValueError("Invalid GitHub URL format")
    
    async def clone_repository(self, repo_url: str, branch: str = "main") -> str:
        """Clone repository to temporary directory"""
        temp_dir = tempfile.mkdtemp()
        try:
            if self.github_token:
                # Use token for private repos or higher rate limits
                auth_url = repo_url.replace("https://", f"https://{self.github_token}@")
                Repo.clone_from(auth_url, temp_dir, branch=branch, depth=1)
            else:
                Repo.clone_from(repo_url, temp_dir, branch=branch, depth=1)
            return temp_dir
        except Exception as e:
            shutil.rmtree(temp_dir, ignore_errors=True)
            raise Exception(f"Failed to clone repository: {str(e)}")
    
    def cleanup_repo(self, repo_path: str):
        """Clean up cloned repository"""
        if os.path.exists(repo_path):
            shutil.rmtree(repo_path, ignore_errors=True)