Bits of .NET

🧹 LINQ = Data Validation

Data needs validation. LINQ helps validate and clean data efficiently.

📝 Data Validation

// Validation Rules
public class DataValidator
{
    private readonly List> _rules = new();

    public DataValidator AddRule(Func rule)
    {
        _rules.Add(rule);
        return this;
    }

    public bool Validate(T item)
    {
        return _rules.All(rule => rule(item));
    }

    public IEnumerable ValidateAll(IEnumerable data)
    {
        return data.Where(item => Validate(item));
    }

    public IEnumerable GetErrors(IEnumerable data)
    {
        return data
            .Select(item => new
            {
                Item = item,
                Errors = _rules
                    .Select((rule, index) => new { rule, index })
                    .Where(x => !x.rule(item))
                    .Select(x => x.index)
                    .ToList()
            })
            .Where(x => x.Errors.Any())
            .Select(x => new ValidationError
            {
                Item = x.Item,
                ErrorIndices = x.Errors
            });
    }
}

🎯 Data Cleaning

// Data Cleaning Pipeline
public class DataCleaner
{
    public IEnumerable Clean(IEnumerable data)
    {
        return data
            .Where(item => item != null)
            .Select(RemoveWhitespace)
            .Select(RemoveDuplicates)
            .Select(NormalizeData)
            .Where(IsValid);
    }

    private T RemoveWhitespace(T item)
    {
        // Remove whitespace from string properties
        return item;
    }

    private T RemoveDuplicates(T item)
    {
        // Remove duplicate data
        return item;
    }

    private T NormalizeData(T item)
    {
        // Normalize data formats
        return item;
    }

    private bool IsValid(T item)
    {
        // Validate final data
        return true;
    }
}

// Usage Example
var users = GetUsers();
var validator = new DataValidator()
    .AddRule(u => !string.IsNullOrEmpty(u.Name))
    .AddRule(u => u.Age >= 18)
    .AddRule(u => u.Email.Contains('@'));

var validUsers = validator.ValidateAll(users);
var errors = validator.GetErrors(users);

var cleaner = new DataCleaner();
var cleanUsers = cleaner.Clean(validUsers);

💡 Data Validation Tips

• Validate early in pipeline
• Use meaningful error messages
• Clean data consistently
• Log validation errors
• Test edge cases