update_github_names.py

#!/usr/bin/env python3
"""
Script to update github_name values in repositories.json
- Remove sikatech- prefix
- Use gitlab_path as github_name
- Identify duplicates for user to choose names
"""

import json
import re
import sys
from collections import defaultdict

def normalize_name(name):
    """
    Normalize name for GitHub:
    - All lowercase
    - Replace underscores with hyphens
    - Remove special characters
    - Replace multiple hyphens with single hyphen
    - Remove leading/trailing hyphens
    """
    # Convert to lowercase
    normalized = name.lower()
    
    # Replace underscores with hyphens
    normalized = normalized.replace('_', '-')
    
    # Remove special characters (keep only alphanumeric and hyphens)
    normalized = re.sub(r'[^a-z0-9-]', '', normalized)
    
    # Replace multiple consecutive hyphens with single hyphen
    normalized = re.sub(r'-+', '-', normalized)
    
    # Remove leading/trailing hyphens
    normalized = normalized.strip('-')
    
    return normalized

def update_repositories_json(file_path):
    """Update github_name values in repositories.json"""
    # Read the JSON file
    with open(file_path, 'r', encoding='utf-8') as f:
        data = json.load(f)
    
    # Track names and duplicates
    name_to_repos = defaultdict(list)
    
    # First pass: normalize all names and find duplicates
    for repo in data.get('repositories', []):
        gitlab_path = repo.get('gitlab_path', '')
        if gitlab_path:
            normalized = normalize_name(gitlab_path)
            name_to_repos[normalized].append({
                'gitlab_id': repo.get('gitlab_id'),
                'gitlab_path': gitlab_path,
                'gitlab_full_path': repo.get('gitlab_full_path', ''),
                'old_github_name': repo.get('github_name', '')
            })
    
    # Find duplicates
    duplicates = {name: repos for name, repos in name_to_repos.items() if len(repos) > 1}
    
    # Print duplicates for user to review
    if duplicates:
        print("=" * 80)
        print("DUPLICATE REPOSITORY NAMES FOUND:")
        print("=" * 80)
        print("\nThe following normalized names would result in duplicates:")
        print("(You'll need to choose unique names for these)\n")
        
        for normalized_name, repos in sorted(duplicates.items()):
            print(f"\nNormalized name: '{normalized_name}'")
            print(f"  Found {len(repos)} repositories:")
            for i, repo in enumerate(repos, 1):
                print(f"    {i}. ID: {repo['gitlab_id']}")
                print(f"       Path: {repo['gitlab_path']}")
                print(f"       Full Path: {repo['gitlab_full_path']}")
                print(f"       Current GitHub Name: {repo['old_github_name']}")
        
        print("\n" + "=" * 80)
        print(f"Total duplicates found: {len(duplicates)} normalized names")
        print("=" * 80)
        
        # Ask user if they want to proceed with non-duplicates
        print("\nProceeding to update non-duplicate names...")
    else:
        print("No duplicates found! All names are unique.")
    
    # Second pass: update non-duplicate names
    updates = []
    skipped = []
    
    for repo in data.get('repositories', []):
        gitlab_path = repo.get('gitlab_path', '')
        if gitlab_path:
            normalized = normalize_name(gitlab_path)
            old_name = repo.get('github_name', '')
            
            # Check if this is a duplicate
            if normalized in duplicates:
                skipped.append({
                    'gitlab_id': repo.get('gitlab_id'),
                    'gitlab_path': gitlab_path,
                    'normalized_name': normalized,
                    'old_github_name': old_name
                })
            else:
                new_name = normalized
                if old_name != new_name:
                    updates.append({
                        'gitlab_id': repo.get('gitlab_id'),
                        'gitlab_path': gitlab_path,
                        'old_name': old_name,
                        'new_name': new_name
                    })
                    repo['github_name'] = new_name
    
    # Write back to file
    with open(file_path, 'w', encoding='utf-8') as f:
        json.dump(data, f, indent=2, ensure_ascii=False)
    
    # Print summary
    print(f"\nUpdated {len(updates)} repository names (non-duplicates):")
    for update in updates[:20]:  # Show first 20
        print(f"  {update['gitlab_path']}: {update['old_name']} -> {update['new_name']}")
    if len(updates) > 20:
        print(f"  ... and {len(updates) - 20} more")
    
    if skipped:
        print(f"\nSkipped {len(skipped)} repositories with duplicate names (see above for details)")
    
    return len(updates), len(duplicates), skipped

if __name__ == '__main__':
    file_path = 'repositories.json'
    if len(sys.argv) > 1:
        file_path = sys.argv[1]
    
    try:
        updates, dup_count, skipped = update_repositories_json(file_path)
        print(f"\nSummary:")
        print(f"  - Updated: {updates} repositories")
        print(f"  - Duplicates found: {dup_count} normalized names")
        print(f"  - Skipped: {len(skipped)} repositories")
        sys.exit(0)
    except Exception as e:
        print(f"Error: {e}", file=sys.stderr)
        import traceback
        traceback.print_exc()
        sys.exit(1)