Add Tamil NER routing and WPF test harness for POC validation.

Introduce dual-script ONNX NER routing (English/Tamil/mixed), Tamil console samples and integration tests, model download scripts, and a resizable WPF MVVM harness with click-to-load prompts, batch validation, and runtime-adjustable detection panels.
2026-07-07 17:12:38 +05:30
parent a707c6c9cf
commit cf8f5a7232
71 changed files with 4494 additions and 356 deletions
--- a/tests/PiiRedaction.Infrastructure.Tests/Onnx/RealTamilNerModelRunnerTests.cs
+++ b/tests/PiiRedaction.Infrastructure.Tests/Onnx/RealTamilNerModelRunnerTests.cs
@@ -0,0 +1,70 @@
+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 entities = Runner.PredictEntities(prompt);
+
+        entities.Should().Contain(entity =>
+            entity.Type == PiiEntityType.Person &&
+            entity.Source == PiiDetectionSource.Ner &&
+            entity.Value.Contains(expectedNamePart, StringComparison.Ordinal) &&
+            prompt.AsSpan(entity.StartIndex, entity.Length).ToString() == entity.Value);
+
+        entities.Should().Contain(entity => entity.Value == expectedValue);
+    }
+
+    [Test]
+    public void PredictEntities_TamilWithPhone_DetectsPersonAndLeavesPhoneToRegex()
+    {
+        const string prompt = "வாடிக்கையாளர் ராஜேஷ் குமார் தொலைபேசி 9876543210";
+
+        var entities = Runner.PredictEntities(prompt);
+
+        entities.Should().Contain(entity =>
+            entity.Type == PiiEntityType.Person &&
+            entity.Source == PiiDetectionSource.Ner &&
+            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).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.Should().NotContain(entity =>
+            entity.Type == PiiEntityType.Person &&
+            entity.Value.Contains(expectedNamePart, StringComparison.OrdinalIgnoreCase));
+    }
+}