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);
}
}

View File

@@ -8,6 +8,7 @@ namespace PiiRedaction.Core.Tests.Integration;
public sealed class GoldenPromptTests
{
[TestCaseSource(typeof(PromptScenarioCatalog), nameof(PromptScenarioCatalog.AllScenarios))]
[TestCaseSource(typeof(TamilPromptScenarioCatalog), nameof(TamilPromptScenarioCatalog.AllScenarios))]
public void Sanitize_PromptScenario_ProducesExpectedOutput(PromptScenario scenario)
{
var sanitizer = ProductionPipelineFactory.CreateForScenario(scenario);

View File

@@ -0,0 +1,106 @@
using FluentAssertions;
using PiiRedaction.Core.Abstractions;
using PiiRedaction.Core.Models;
using PiiRedaction.Core.Tests.TestSupport;
using PiiRedaction.Tests.Shared;
namespace PiiRedaction.Core.Tests.Integration;
/// <summary>
/// End-to-end pipeline proof using routed English + Tamil ONNX NER models.
/// </summary>
[TestFixture]
[Category("TamilNer")]
public sealed class RealTamilPipelineTests : RealRoutingNerModelFixture
{
private IPromptSanitizer _sanitizer = null!;
[OneTimeSetUp]
public void OneTimeSetUpPipeline()
{
_sanitizer = ProductionPipelineFactory.CreateWithRoutingRealModels(EnglishRunner, TamilRunner);
}
[Test]
public void Sanitize_TamilCustomerNameOnly_RedactsPerson()
{
const string prompt =
"வாடிக்கையாளர் ராஜேஷ் குமார் சேமிப்பு கணக்கில் அங்கீகரிக்கப்படாத பரிவர்த்தனைகளைப் புகாரளித்தார்.";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
result.SanitizedPrompt.Should().NotContain("ராஜேஷ்");
result.DetectedEntities.Should().Contain(entity =>
entity.Type == PiiEntityType.Person && entity.Source == PiiDetectionSource.Ner);
}
[Test]
public void Sanitize_TamilWithPhonePan_RedactsPersonPhoneAndPan()
{
const string prompt = "வாடிக்கையாளர் ராஜேஷ் குமார் தொலைபேசி 9876543210 PAN ABCDE1234F.";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
result.SanitizedPrompt.Should().Contain("<PHONE_1>");
result.SanitizedPrompt.Should().Contain("<PAN_1>");
result.SanitizedPrompt.Should().NotContainAny("ராஜேஷ்", "9876543210", "ABCDE1234F");
}
[Test]
public void Sanitize_TanglishCustomer_RedactsPersonAndPhone()
{
const string prompt = "Customer Senthil phone 9876543210 reported a failed UPI transfer.";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
result.SanitizedPrompt.Should().Contain("<PHONE_1>");
result.SanitizedPrompt.Should().NotContainAny("Senthil", "9876543210");
}
[Test]
public void Sanitize_MixedTamilEnglish_RedactsPersonAndPhone()
{
const string prompt = "வாடிக்கையாளர் Ravi Kumar phone 9876543210 disputed the charge.";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
result.SanitizedPrompt.Should().Contain("<PHONE_1>");
result.SanitizedPrompt.Should().NotContainAny("Ravi Kumar", "9876543210");
}
[Test]
public void Sanitize_TamilFullFinancial_RedactsAllPiiTypes()
{
const string prompt =
"வாடிக்கையாளர் ராஜேஷ் குமார் மின்னஞ்சல் ravi.kumar@gmail.com தொலைபேசி 9876543210 LoanNumber LN-456789 PAN ABCDE1234F. இந்த வாடிக்கையாளர் புகாரை சுருக்கமாக கூறுங்கள்.";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
result.SanitizedPrompt.Should().Contain("<EMAIL_1>");
result.SanitizedPrompt.Should().Contain("<PHONE_1>");
result.SanitizedPrompt.Should().Contain("<LOAN_NUMBER_1>");
result.SanitizedPrompt.Should().Contain("<PAN_1>");
result.SanitizedPrompt.Should().NotContainAny(
"ராஜேஷ்",
"ravi.kumar@gmail.com",
"9876543210",
"LN-456789",
"ABCDE1234F");
}
[Test]
public void Sanitize_CleanTamilQuestion_PassesThroughWithoutPersonRedaction()
{
const string prompt = "பணத்தை திரும்பப் பெறுவது எப்படி?";
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
result.SanitizedPrompt.Should().Be(prompt);
result.DetectedEntities.Should().BeEmpty();
}
}

View File

@@ -25,6 +25,9 @@
<ItemGroup>
<Compile Include="..\TestSupport.Shared\RealNerModelPaths.cs" Link="TestSupport.Shared\RealNerModelPaths.cs" />
<Compile Include="..\TestSupport.Shared\RealNerModelFixture.cs" Link="TestSupport.Shared\RealNerModelFixture.cs" />
<Compile Include="..\TestSupport.Shared\RealTamilNerModelPaths.cs" Link="TestSupport.Shared\RealTamilNerModelPaths.cs" />
<Compile Include="..\TestSupport.Shared\RealTamilNerModelFixture.cs" Link="TestSupport.Shared\RealTamilNerModelFixture.cs" />
<Compile Include="..\TestSupport.Shared\RealRoutingNerModelFixture.cs" Link="TestSupport.Shared\RealRoutingNerModelFixture.cs" />
</ItemGroup>
<ItemGroup>

View File

@@ -1,7 +1,10 @@
using Microsoft.Extensions.Options;
using PiiRedaction.Core.Abstractions;
using PiiRedaction.Core.Configuration;
using PiiRedaction.Core.Detection;
using PiiRedaction.Core.Redaction;
using PiiRedaction.Core.Sanitization;
using PiiRedaction.Infrastructure.Onnx;
namespace PiiRedaction.Core.Tests.TestSupport;
@@ -10,6 +13,15 @@ public static class ProductionPipelineFactory
public static IPromptSanitizer CreateWithRealModel(IOnnxNerModelRunner runner) =>
new PromptSanitizer(CreateCompositeDetector(runner), new PlaceholderPiiRedactor());
public static IPromptSanitizer CreateWithRoutingRealModels(
EnglishOnnxNerRunner englishRunner,
TamilOnnxNerRunner tamilRunner,
IOptions<PiiRedactionOptions>? options = null) =>
CreateWithRealModel(new RoutingOnnxNerModelRunner(
englishRunner,
tamilRunner,
options ?? Options.Create(new PiiRedactionOptions { EnableTamilNer = true })));
public static IPiiDetector CreateCompositeDetector(IOnnxNerModelRunner runner) =>
new CompositePiiDetector(
[

View File

@@ -0,0 +1,63 @@
using NUnit.Framework;
using PiiRedaction.Core.Models;
namespace PiiRedaction.Core.Tests.TestSupport;
/// <summary>
/// Golden end-to-end scenarios for Tamil script, Tanglish, and mixed-script prompts.
/// Uses fake NER spans for person names; regex and domain rules run for real.
/// </summary>
public static class TamilPromptScenarioCatalog
{
public static IEnumerable<TestCaseData> AllScenarios()
{
foreach (var scenario in BuildScenarios())
{
yield return new TestCaseData(scenario).SetName(scenario.Name);
}
}
private static IEnumerable<PromptScenario> BuildScenarios()
{
yield return TamilCustomerNameOnly();
yield return TamilWithPhonePan();
yield return TanglishCustomer();
yield return MixedTamilEnglish();
yield return TamilFullFinancial();
}
private static PromptScenario TamilCustomerNameOnly() => new(
"Tamil_CustomerNameOnly",
"வாடிக்கையாளர் ராஜேஷ் குமார் சேமிப்பு கணக்கில் அங்கீகரிக்கப்படாத பரிவர்த்தனைகளைப் புகாரளித்தார்.",
"வாடிக்கையாளர் <PERSON_1> சேமிப்பு கணக்கில் அங்கீகரிக்கப்படாத பரிவர்த்தனைகளைப் புகாரளித்தார்.",
[PiiEntityType.Person],
["ராஜேஷ் குமார்"]);
private static PromptScenario TamilWithPhonePan() => new(
"Tamil_WithPhonePan",
"வாடிக்கையாளர் ராஜேஷ் குமார் தொலைபேசி 9876543210 PAN ABCDE1234F.",
"வாடிக்கையாளர் <PERSON_1> தொலைபேசி <PHONE_1> PAN <PAN_1>.",
[PiiEntityType.Person, PiiEntityType.Phone, PiiEntityType.Pan],
["ராஜேஷ் குமார்", "9876543210", "ABCDE1234F"]);
private static PromptScenario TanglishCustomer() => new(
"Tanglish_CustomerPhone",
"Customer Senthil phone 9876543210 reported a failed UPI transfer.",
"Customer <PERSON_1> phone <PHONE_1> reported a failed UPI transfer.",
[PiiEntityType.Person, PiiEntityType.Phone],
["Senthil", "9876543210"]);
private static PromptScenario MixedTamilEnglish() => new(
"Mixed_TamilEnglish",
"வாடிக்கையாளர் Ravi Kumar phone 9876543210 disputed the charge.",
"வாடிக்கையாளர் <PERSON_1> phone <PHONE_1> disputed the charge.",
[PiiEntityType.Person, PiiEntityType.Phone],
["Ravi Kumar", "9876543210"]);
private static PromptScenario TamilFullFinancial() => new(
"Tamil_FullFinancial",
"வாடிக்கையாளர் ராஜேஷ் குமார் மின்னஞ்சல் ravi.kumar@gmail.com தொலைபேசி 9876543210 LoanNumber LN-456789 PAN ABCDE1234F. இந்த வாடிக்கையாளர் புகாரை சுருக்கமாக கூறுங்கள்.",
"வாடிக்கையாளர் <PERSON_1> மின்னஞ்சல் <EMAIL_1> தொலைபேசி <PHONE_1> LoanNumber <LOAN_NUMBER_1> PAN <PAN_1>. இந்த வாடிக்கையாளர் புகாரை சுருக்கமாக கூறுங்கள்.",
[PiiEntityType.Person, PiiEntityType.Email, PiiEntityType.Phone, PiiEntityType.LoanNumber, PiiEntityType.Pan],
["ராஜேஷ் குமார்", "ravi.kumar@gmail.com", "9876543210", "LN-456789", "ABCDE1234F"]);
}