chapter-organizer/Core/Utility/CareerNormalizer.cs

using System.Text.RegularExpressions;

namespace Core.Utility;

public static class CareerNormalizer
{
	/// <summary>
	/// Normalizes career names from multiline text input.
	/// Strips bullet points, trims whitespace, and returns distinct normalized names.
	/// </summary>
	/// <param name="input">Multiline text input containing career names</param>
	/// <returns>Collection of normalized career names (trimmed, with bullets removed)</returns>
	public static IEnumerable<string> NormalizeCareerNames(string? input)
	{
		if (string.IsNullOrWhiteSpace(input))
		{
			return Enumerable.Empty<string>();
		}

		return input
			.Split(new[] { "\r\n", "\r", "\n" }, StringSplitOptions.None)
			.Select(line => NormalizeSingleCareerName(line))
			.Where(name => !string.IsNullOrWhiteSpace(name))
			.Distinct(StringComparer.OrdinalIgnoreCase)
			.ToList();
	}

	/// <summary>
	/// Normalizes a single career name by stripping bullet points and trimming whitespace.
	/// </summary>
	/// <param name="careerName">The career name to normalize</param>
	/// <returns>Normalized career name</returns>
	private static string NormalizeSingleCareerName(string careerName)
	{
		if (string.IsNullOrWhiteSpace(careerName))
		{
			return string.Empty;
		}

		// Remove common bullet point characters (•, -, *, etc.) and trim
		var normalized = Regex.Replace(careerName.Trim(), @"^[\u2022\u2023\u25E6\u2043\u2219\-\*\•]\s*", string.Empty, RegexOptions.Compiled);
		
		return normalized.Trim();
	}

	/// <summary>
	/// Finds or creates a career name for case-insensitive duplicate detection.
	/// Returns the normalized (lowercase) version for comparison.
	/// </summary>
	/// <param name="careerName">The career name to normalize for comparison</param>
	/// <returns>Lowercase normalized name for duplicate detection</returns>
	public static string GetNormalizedKey(string careerName)
	{
		return NormalizeSingleCareerName(careerName).ToLowerInvariant();
	}
}