Summarize git repositories

inspect_git_repos.py

# script to provide a summary of the repositories by only listing each one's name
# along with its status (public, public with changes, or private)

import os
import subprocess
import json
from concurrent.futures import ThreadPoolExecutor, as_completed

def execute_command(command, cwd):
    """Executes a shell command in a specified directory and returns the output."""
    result = subprocess.run(command, cwd=cwd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, shell=True)
    if result.returncode != 0:
        return None
    return result.stdout.strip()

def is_git_repo(path):
    """Check if a directory is a git repository."""
    return execute_command("git rev-parse --is-inside-work-tree", cwd=path) is not None

def get_remote_urls(path):
    """Retrieve all remote URLs of the git repository."""
    return execute_command("git remote -v", cwd=path)

def is_public(url):
    """Determine if the git repository URL suggests it is public."""
    private_indicators = ["gitlab.mycompany.com", "github-private.com"]
    return not any(private in url for private in private_indicators)

def check_for_local_changes(path):
    """Check for local branch changes not pushed to remote."""
    local_branches = execute_command("git branch -vv", cwd=path)
    return "ahead" in local_branches if local_branches else False

def analyze_repository(repo_path):
    """Analyze a single repository to determine its status and return detailed info."""
    if is_git_repo(repo_path):
        urls = get_remote_urls(repo_path)
        if urls:
            if is_public(urls):
                has_changes = check_for_local_changes(repo_path)
                status = 'Public + Changes' if has_changes else 'Public'
            else:
                status = 'Private'
            return {'path': repo_path, 'status': status}
    return None

def main():
    root_dir = input("Enter the directory path containing git repositories: ")
    repo_details = []

    # Collect top-level directory paths within the specified root
    top_level_repos = [os.path.join(root_dir, d) for d in os.listdir(root_dir) if os.path.isdir(os.path.join(root_dir, d))]

    # Use ThreadPoolExecutor to process repositories in parallel
    with ThreadPoolExecutor(max_workers=10) as executor:
        futures = [executor.submit(analyze_repository, repo_path) for repo_path in top_level_repos if is_git_repo(repo_path)]
        for future in as_completed(futures):
            result = future.result()
            if result:
                repo_details.append(result)

    # Save results to JSON
    with open('repository_summary.json', 'w') as json_file:
        json.dump(repo_details, json_file, indent=4)

    print("\nDetailed repository status has been saved to 'repository_summary.json'.")

if __name__ == "__main__":
    main()

jq '.[] | select(.status == "Public + Changes")' repository_summary.json

echo "Review the directories to be deleted:" && jq -r '.[] | select(.status == "Public" and (.identifier | contains("specific-owner") | not)) | .path' repository_summary.json && echo "Are you sure you want to delete these directories? (y/n)" && read confirm && [[ "$confirm" =~ ^[Yy]$ ]] && jq -r '.[] | select(.status == "Public" and (.identifier | contains("specific-owner") | not)) | .path' repository_summary.json | xargs rm -rf || echo "Deletion cancelled."