import json
import os
from collections import defaultdict
from typing import Dict, Tuple, Any, List, Set

def is_repository_valid(repo_name: str) -> Tuple[bool, str, Dict[str, Any]]:
    """
    Checks if a GitHub repository is valid and accessible.
    
    Args:
        repo_name: The name of the repository
        
    Returns:
        Tuple of (is_valid, error_message, library_info)
    """
    # Basic format validation
    if not repo_name:
        return False, "Repository name is required", {}
    return True, "", {}

def get_library_info(repo_data: Dict[str, Any]) -> Dict[str, Any]:
    """
    Extracts relevant information from GitHub repository data.
    
    Args:
        repo_data: GitHub API response for a repository
        
    Returns:
        Dictionary with library metadata
    """
    library_info = {
        "name": repo_data.get("name", ""),
        "full_name": repo_data.get("full_name", ""),
        "description": repo_data.get("description", ""),
        "stars": repo_data.get("stargazers_count", 0),
        "forks": repo_data.get("forks_count", 0),
        "license": repo_data.get("license", {}).get("name", "Unknown"),
        "created_at": repo_data.get("created_at", ""),
        "updated_at": repo_data.get("updated_at", ""),
        "open_issues": repo_data.get("open_issues_count", 0),
        "default_branch": repo_data.get("default_branch", "main"),
        "is_archived": repo_data.get("archived", False),
    }
    
    return library_info

def already_submitted_libraries(requested_libraries_dir: str) -> Tuple[Set[str], Dict[str, List[str]]]:
    """
    Gathers a list of already submitted libraries to avoid duplicates.
    
    Args:
        requested_libraries_dir: Directory with library assessment requests
        
    Returns:
        Tuple of (set of library identifiers, dict mapping orgs to submission dates)
    """
    depth = 1
    library_ids = []
    orgs_to_submission_dates = defaultdict(list)

    for root, _, files in os.walk(requested_libraries_dir):
        current_depth = root.count(os.sep) - requested_libraries_dir.count(os.sep)
        if current_depth == depth:
            for file in files:
                if not file.endswith(".json"):
                    continue
                with open(os.path.join(root, file), "r") as f:
                    info = json.load(f)
                    library_ids.append(f"{info['library']}_{info['version']}")

                    # Select organisation
                    if info["library"].count("/") == 0 or "submitted_time" not in info:
                        continue
                    organisation, _ = info["library"].split("/")
                    orgs_to_submission_dates[organisation].append(info["submitted_time"])

    return set(library_ids), orgs_to_submission_dates