llm-pii-poc/src/PiiRedaction.Infrastructure/Onnx/NerLabelConfig.cs

namespace PiiRedaction.Infrastructure.Onnx;

public sealed class NerLabelConfig
{
    private readonly Func<string, bool> _isPersonLabel;

    private NerLabelConfig(Func<string, bool> isPersonLabel) => _isPersonLabel = isPersonLabel;

    public static NerLabelConfig English { get; } = new(IsEnglishPersonLabel);

    public static NerLabelConfig Tamil { get; } = new(IsTamilPersonLabel);

    public bool IsPersonLabel(string label) => _isPersonLabel(label);

    public bool IsBeginLabel(string label) => label.StartsWith("B-", StringComparison.Ordinal);

    public bool IsInsideLabel(string label) => label.StartsWith("I-", StringComparison.Ordinal);

    private static bool IsEnglishPersonLabel(string label) =>
        label is "B-PER" or "I-PER" or "B-PERSON" or "I-PERSON"
        || (label.EndsWith("-PER", StringComparison.Ordinal) &&
            (label.StartsWith("B-", StringComparison.Ordinal) || label.StartsWith("I-", StringComparison.Ordinal)));

    private static bool IsTamilPersonLabel(string label) =>
        label.Contains("person", StringComparison.OrdinalIgnoreCase);
}