Files
llm-pii-poc/tests/PiiRedaction.Core.Tests/Integration/RealTamilPipelineTests.cs
Bilal Nazer Ali cf8f5a7232 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

107 lines
4.4 KiB
C#

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();
}
}