using System.Data;
using System.Text.RegularExpressions;
namespace JdeScoping.DataSync.Etl.Transformers;
///
/// Specifies behavior when a regex pattern does not match the input value.
///
public enum NonMatchBehavior
{
/// Keep the original value unchanged.
KeepOriginal,
/// Return null/DBNull.
ReturnNull,
/// Return an empty string.
ReturnEmpty
}
///
/// A data transformer that applies regex transformations to string values in a column.
/// Supports two modes: Find & Replace (when replacement is provided) and Match & Extract
/// (when replacement is null, extracts first capture group).
///
public class RegexTransformer : DataTransformerBase
{
private readonly string _columnName;
private readonly string _pattern;
private readonly string? _replacement;
private readonly bool _ignoreCase;
private readonly NonMatchBehavior _nonMatchBehavior;
private Regex? _regex;
private int _columnOrdinal = -1;
///
public override string TransformerName => $"Regex:{_columnName}";
///
/// Creates a new RegexTransformer.
///
/// The column to transform.
/// The regex pattern.
/// Replacement string for Find & Replace mode, or null for Match & Extract mode.
/// Whether to use case-insensitive matching.
/// Behavior when pattern does not match.
public RegexTransformer(
string columnName,
string pattern,
string? replacement = null,
bool ignoreCase = false,
NonMatchBehavior nonMatchBehavior = NonMatchBehavior.KeepOriginal)
{
ArgumentException.ThrowIfNullOrWhiteSpace(columnName);
ArgumentException.ThrowIfNullOrWhiteSpace(pattern);
_columnName = columnName;
_pattern = pattern;
_replacement = replacement;
_ignoreCase = ignoreCase;
_nonMatchBehavior = nonMatchBehavior;
}
///
protected override void OnInitialize(IDataReader source)
{
_columnOrdinal = source.GetOrdinal(_columnName);
var options = RegexOptions.Compiled;
if (_ignoreCase)
options |= RegexOptions.IgnoreCase;
_regex = new Regex(_pattern, options);
}
///
public override object GetValue(int ordinal, IDataReader source)
{
var value = source.GetValue(ordinal);
// Only transform the target column
if (ordinal != _columnOrdinal)
return value;
// Pass through null/DBNull
if (value == null || value == DBNull.Value)
return DBNull.Value;
var stringValue = value.ToString() ?? string.Empty;
// Find & Replace mode (replacement is not null)
if (_replacement != null)
{
return _regex!.Replace(stringValue, _replacement);
}
// Match & Extract mode (replacement is null)
var match = _regex!.Match(stringValue);
if (match.Success && match.Groups.Count > 1)
{
return match.Groups[1].Value;
}
// No match - apply NonMatchBehavior
return _nonMatchBehavior switch
{
NonMatchBehavior.ReturnNull => DBNull.Value,
NonMatchBehavior.ReturnEmpty => string.Empty,
_ => value // KeepOriginal
};
}
///
public override Type GetFieldType(int ordinal, IDataReader source)
{
// Target column always returns string
if (ordinal == _columnOrdinal)
return typeof(string);
return source.GetFieldType(ordinal);
}
}