CoffeeAtHome/scripts/csv_manager.py

#!/usr/bin/env python3
"""
CSV Management Script for CoffeeAtHomeFlutter
Usage: python csv_manager.py [command] [options]
"""

import csv
import json
import os
import sys
from datetime import datetime

CSV_DIR = "lib/database"
BACKUP_DIR = "csv_backups"

def backup_csv_files():
    """Create backup of all CSV files"""
    if not os.path.exists(BACKUP_DIR):
        os.makedirs(BACKUP_DIR)
    
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    backup_path = f"{BACKUP_DIR}/backup_{timestamp}"
    os.makedirs(backup_path)
    
    csv_files = ["Coffee_Beans.csv", "Coffee_Machines.csv", "Brew_Recipes.csv", "Origin_Countries.csv"]
    
    for csv_file in csv_files:
        src = f"{CSV_DIR}/{csv_file}"
        dst = f"{backup_path}/{csv_file}"
        if os.path.exists(src):
            # Use shutil.copy2 instead of os.system for better cross-platform compatibility
            import shutil
            shutil.copy2(src, dst)
            print(f"Backed up {csv_file}")
    
    print(f"Backup created: {backup_path}")

def add_bean(bean_data):
    """Add new bean to Coffee_Beans.csv"""
    csv_file = f"{CSV_DIR}/Coffee_Beans.csv"
    
    # Validate required fields
    required_fields = ["id", "name", "origin", "varietal"]
    for field in required_fields:
        if field not in bean_data:
            print(f"Error: Missing required field '{field}'")
            return False
    
    # Read existing CSV to check for duplicates
    existing_ids = set()
    try:
        with open(csv_file, 'r', newline='', encoding='utf-8') as f:
            reader = csv.DictReader(f)
            existing_ids = {row['id'] for row in reader}
    except FileNotFoundError:
        print(f"Error: CSV file not found: {csv_file}")
        return False
    
    if bean_data['id'] in existing_ids:
        print(f"Error: Bean ID '{bean_data['id']}' already exists")
        return False
    
    # Append new bean
    try:
        with open(csv_file, 'a', newline='', encoding='utf-8') as f:
            if os.path.getsize(csv_file) == 0:
                # File is empty, write header
                fieldnames = list(bean_data.keys())
                writer = csv.DictWriter(f, fieldnames=fieldnames)
                writer.writeheader()
            else:
                # Get fieldnames from existing file
                with open(csv_file, 'r', newline='', encoding='utf-8') as rf:
                    reader = csv.DictReader(rf)
                    fieldnames = reader.fieldnames
                writer = csv.DictWriter(f, fieldnames=fieldnames)
            
            writer.writerow(bean_data)
            print(f"Added bean: {bean_data['name']}")
            return True
    except Exception as e:
        print(f"Error adding bean: {e}")
        return False

def validate_csv_format():
    """Validate all CSV files for correct format"""
    csv_configs = {
        "Coffee_Beans.csv": {
            "required_columns": ["id", "name", "origin", "varietal", "roastLevel"],
            "unique_columns": ["id"]
        },
        "Coffee_Machines.csv": {
            "required_columns": ["id", "manufacturer", "model", "type"],
            "unique_columns": ["id"]
        },
        "Brew_Recipes.csv": {
            "required_columns": ["id", "name", "brewMethod", "grindSize"],
            "unique_columns": ["id"]
        }
    }
    
    all_valid = True
    
    for csv_file, config in csv_configs.items():
        file_path = f"{CSV_DIR}/{csv_file}"
        if not os.path.exists(file_path):
            print(f"❌ Missing file: {csv_file}")
            all_valid = False
            continue
        
        try:
            with open(file_path, 'r', newline='', encoding='utf-8') as f:
                reader = csv.DictReader(f)
                rows = list(reader)
                
                # Check required columns
                missing_cols = set(config["required_columns"]) - set(reader.fieldnames or [])
                if missing_cols:
                    print(f"❌ {csv_file}: Missing columns: {missing_cols}")
                    all_valid = False
                    continue
                
                # Check unique constraints
                for unique_col in config["unique_columns"]:
                    values = [row[unique_col] for row in rows if row[unique_col]]
                    duplicates = set([x for x in values if values.count(x) > 1])
                    if duplicates:
                        print(f"❌ {csv_file}: Duplicate {unique_col} values: {duplicates}")
                        all_valid = False
                
                print(f"✅ {csv_file}: Valid ({len(rows)} rows)")
                
        except Exception as e:
            print(f"❌ {csv_file}: Error reading file: {e}")
            all_valid = False
    
    return all_valid

def export_to_json():
    """Export all CSV data to JSON for easy inspection"""
    output_dir = "csv_exports"
    if not os.path.exists(output_dir):
        os.makedirs(output_dir)
    
    csv_files = ["Coffee_Beans.csv", "Coffee_Machines.csv", "Brew_Recipes.csv", "Origin_Countries.csv"]
    
    for csv_file in csv_files:
        file_path = f"{CSV_DIR}/{csv_file}"
        if not os.path.exists(file_path):
            continue
        
        try:
            with open(file_path, 'r', newline='', encoding='utf-8') as f:
                reader = csv.DictReader(f)
                data = list(reader)
            
            json_file = f"{output_dir}/{csv_file.replace('.csv', '.json')}"
            with open(json_file, 'w', encoding='utf-8') as f:
                json.dump(data, f, indent=2, ensure_ascii=False)
            
            print(f"Exported {csv_file} -> {json_file}")
        except Exception as e:
            print(f"Error exporting {csv_file}: {e}")

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python csv_manager.py [backup|validate|export|add_bean]")
        sys.exit(1)
    
    command = sys.argv[1]
    
    if command == "backup":
        backup_csv_files()
    elif command == "validate":
        if validate_csv_format():
            print("✅ All CSV files are valid")
        else:
            print("❌ Some CSV files have issues")
            sys.exit(1)
    elif command == "export":
        export_to_json()
    elif command == "add_bean":
        # Example: python csv_manager.py add_bean '{"id":"bean_new","name":"New Bean","origin":"Colombia","varietal":"Arabica","roastLevel":"Medium"}'
        if len(sys.argv) < 3:
            print("Usage: python csv_manager.py add_bean '{json_data}'")
            sys.exit(1)
        
        try:
            bean_data = json.loads(sys.argv[2])
            add_bean(bean_data)
        except json.JSONDecodeError:
            print("Error: Invalid JSON data")
            sys.exit(1)
    else:
        print(f"Unknown command: {command}")
        print("Available commands: backup, validate, export, add_bean")
        sys.exit(1)