llm-pii-poc/tests/PiiRedaction.Infrastructure.Tests/Onnx/RealTamilNerModelRunnerTests.cs

using FluentAssertions;
using PiiRedaction.Core.Models;
using PiiRedaction.Infrastructure.Onnx;
using PiiRedaction.Tests.Shared;

namespace PiiRedaction.Infrastructure.Tests.Onnx;

[TestFixture]
[Category("TamilNer")]
public sealed class RealTamilNerModelRunnerTests : RealTamilNerModelFixture
{
    [Test]
    public void IsModelAvailable_LoadsOnnxAndTokenizer()
    {
        Runner.IsModelAvailable.Should().BeTrue();
    }

    [TestCase("வாடிக்கையாளர் ராஜேஷ் குமார் அழைத்தார்.", "ராஜேஷ்", "ராஜேஷ் குமார்")]
    public void PredictEntities_TamilScript_DetectsPersonEntity(
        string prompt,
        string expectedNamePart,
        string expectedValue)
    {
        var result = Runner.PredictEntities(prompt);
        var entities = result.Entities;

        entities.Should().Contain(entity =>
            entity.Type == PiiEntityType.Person &&
            entity.Source == PiiDetectionSource.Ner &&
            entity.ModelOrigin == NerModelOrigin.Tamil &&
            entity.Value.Contains(expectedNamePart, StringComparison.Ordinal) &&
            prompt.AsSpan(entity.StartIndex, entity.Length).ToString() == entity.Value);

        entities.Should().Contain(entity => entity.Value == expectedValue);
        result.InvokedModels.Should().Equal(NerModelOrigin.Tamil);
    }

    [Test]
    public void PredictEntities_TamilWithPhone_DetectsPersonAndLeavesPhoneToRegex()
    {
        const string prompt = "வாடிக்கையாளர் ராஜேஷ் குமார் தொலைபேசி 9876543210";

        var entities = Runner.PredictEntities(prompt).Entities;

        entities.Should().Contain(entity =>
            entity.Type == PiiEntityType.Person &&
            entity.Source == PiiDetectionSource.Ner &&
            entity.ModelOrigin == NerModelOrigin.Tamil &&
            entity.Value.Contains("ராஜேஷ்", StringComparison.Ordinal));
        entities.Should().NotContain(entity => entity.Type == PiiEntityType.Phone);
    }

    [Test]
    public void PredictEntities_CleanTamilQuestion_ReturnsNoEntities()
    {
        const string prompt = "பணத்தை திரும்பப் பெறுவது எப்படி?";

        Runner.PredictEntities(prompt).Entities.Should().BeEmpty();
    }

    [TestCase("Customer Senthil phone 9876543210", "Senthil")]
    public void PredictEntities_TanglishLatinScript_DoesNotInvokeTamilRunner(
        string prompt,
        string expectedNamePart)
    {
        // TamilOnnxNerRunner is script-scoped; Tanglish is handled by English routing in pipeline tests.
        // Direct Tamil runner on Latin-only text should not emit person spans.
        var entities = Runner.PredictEntities(prompt).Entities;

        entities.Should().NotContain(entity =>
            entity.Type == PiiEntityType.Person &&
            entity.Value.Contains(expectedNamePart, StringComparison.OrdinalIgnoreCase));
    }
}