dfc81dea28
Implements detect-redact-sanitize pipeline with regex, domain rules, and ONNX NER before the LLM boundary, plus NUnit tests and Xenovex push documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
128 lines
2.5 KiB
C#
128 lines
2.5 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 the real ONNX NER model (no fakes).
|
|
|
|
/// </summary>
|
|
|
|
[TestFixture]
|
|
|
|
[Category("RealModel")]
|
|
|
|
public sealed class RealNerPipelineTests : RealNerModelFixture
|
|
|
|
{
|
|
|
|
private IPromptSanitizer _sanitizer = null!;
|
|
|
|
|
|
|
|
[OneTimeSetUp]
|
|
|
|
public void OneTimeSetUpPipeline()
|
|
|
|
{
|
|
|
|
_sanitizer = ProductionPipelineFactory.CreateWithRealModel(Runner);
|
|
|
|
}
|
|
|
|
|
|
|
|
[Test]
|
|
|
|
public void Sanitize_FullFinancialWithCustomer_RedactsAllPiiTypes()
|
|
|
|
{
|
|
|
|
const string prompt =
|
|
|
|
"Customer Ravi Kumar with email ravi.kumar@gmail.com and phone 9876543210 has LoanNumber LN-456789 and PAN ABCDE1234F. Please summarize this customer issue.";
|
|
|
|
|
|
|
|
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
|
|
|
|
|
|
|
|
result.SanitizedPrompt.Should().Be(
|
|
|
|
"Customer <PERSON_1> with email <EMAIL_1> and phone <PHONE_1> has LoanNumber <LOAN_NUMBER_1> and PAN <PAN_1>. Please summarize this customer issue.");
|
|
|
|
|
|
|
|
result.SanitizedPrompt.Should().NotContainAny("Ravi Kumar", "ravi.kumar@gmail.com", "9876543210", "LN-456789", "ABCDE1234F");
|
|
|
|
result.DetectedEntities.Should().Contain(entity =>
|
|
|
|
entity.Type == PiiEntityType.Person && entity.Source == PiiDetectionSource.Ner);
|
|
|
|
}
|
|
|
|
|
|
|
|
[Test]
|
|
|
|
public void Sanitize_TwoCustomersInOnePrompt_RedactsBothPeople()
|
|
|
|
{
|
|
|
|
const string prompt = "Customer Ravi Kumar and Customer Priya Nair disputed the same charge.";
|
|
|
|
|
|
|
|
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
|
|
|
|
|
|
|
|
result.SanitizedPrompt.Should().Contain("<PERSON_1>");
|
|
|
|
result.SanitizedPrompt.Should().Contain("<PERSON_2>");
|
|
|
|
result.SanitizedPrompt.Should().NotContainAny("Ravi Kumar", "Priya Nair");
|
|
|
|
result.DetectedEntities.Count(entity => entity.Type == PiiEntityType.Person).Should().BeGreaterThanOrEqualTo(2);
|
|
|
|
}
|
|
|
|
|
|
|
|
[Test]
|
|
|
|
public void Sanitize_NoPiiCleanTicket_PassesThroughUnchanged()
|
|
|
|
{
|
|
|
|
const string prompt = "What is the status of ticket TKT-99887 and when will the API maintenance end?";
|
|
|
|
|
|
|
|
var result = _sanitizer.Sanitize(new SanitizationRequest(prompt));
|
|
|
|
|
|
|
|
result.SanitizedPrompt.Should().Be(prompt);
|
|
|
|
result.DetectedEntities.Should().BeEmpty();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|