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.
This commit is contained in:
Bilal Nazer Ali
2026-07-07 17:12:38 +05:30
parent a707c6c9cf
commit cf8f5a7232
71 changed files with 4494 additions and 356 deletions

View File

@@ -0,0 +1,54 @@
using FluentAssertions;
using PiiRedaction.Core.Detection;
using PiiRedaction.Infrastructure.Onnx;
namespace PiiRedaction.Core.Tests.Detection;
[TestFixture]
public sealed class ScriptRouterTests
{
private readonly ScriptRouter _router = new();
[Test]
public void GetComposition_LatinOnly_ReturnsLatinOnly()
{
_router.GetComposition("Customer Ravi Kumar called about billing.")
.Should().Be(ScriptComposition.LatinOnly);
}
[Test]
public void GetComposition_TamilOnly_ReturnsTamilOnly()
{
_router.GetComposition("வாடிக்கையாளர் ராஜேஷ் தொலைபேசி 9876543210")
.Should().Be(ScriptComposition.TamilOnly);
}
[Test]
public void GetComposition_Mixed_ReturnsMixed()
{
_router.GetComposition("Rajesh மற்றும் Priya disputed the charge.")
.Should().Be(ScriptComposition.Mixed);
}
[Test]
public void GetComposition_MixedTamilEnglishSample_ReturnsMixed()
{
_router.GetComposition("வாடிக்கையாளர் Ravi Kumar phone 9876543210 disputed the charge.")
.Should().Be(ScriptComposition.Mixed);
}
[Test]
public void GetComposition_NoLetters_ReturnsNoLetters()
{
_router.GetComposition("9876543210 12345")
.Should().Be(ScriptComposition.NoLetters);
}
[Test]
public void GetComposition_TamilBoundaryChars_AreClassifiedAsTamil()
{
_router.GetComposition("\u0B80").Should().Be(ScriptComposition.TamilOnly);
_router.GetComposition("\u0BFF").Should().Be(ScriptComposition.TamilOnly);
_router.GetComposition("A").Should().Be(ScriptComposition.LatinOnly);
}
}