Add PII redaction POC for secure LLM prompting.

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>
2026-07-07 13:05:07 +05:30
commit dfc81dea28
60 changed files with 3283 additions and 0 deletions
--- a/tests/PiiRedaction.Core.Tests/Redaction/PlaceholderPiiRedactorTests.cs
+++ b/tests/PiiRedaction.Core.Tests/Redaction/PlaceholderPiiRedactorTests.cs
@@ -0,0 +1,134 @@
+using FluentAssertions;
+using PiiRedaction.Core.Models;
+using PiiRedaction.Core.Redaction;
+
+namespace PiiRedaction.Core.Tests.Redaction;
+
+[TestFixture]
+public sealed class PlaceholderPiiRedactorTests
+{
+    private readonly PlaceholderPiiRedactor _redactor = new();
+
+    [Test]
+    public void Redact_NoEntities_ReturnsOriginalTextAndEmptyMap()
+    {
+        const string text = "No PII here.";
+        var result = _redactor.Redact(text, []);
+
+        result.SanitizedText.Should().Be(text);
+        result.PlaceholderMap.Should().BeEmpty();
+    }
+
+    [Test]
+    public void Redact_SingleEntity_ReplacesWithTypedPlaceholder()
+    {
+        const string text = "Email ravi@test.com end.";
+        var entities = new[] { Entity(PiiEntityType.Email, "ravi@test.com", 6) };
+
+        var result = _redactor.Redact(text, entities);
+
+        result.SanitizedText.Should().Be("Email <EMAIL_1> end.");
+        result.PlaceholderMap["<EMAIL_1>"].Should().Be("ravi@test.com");
+    }
+
+    [Test]
+    public void Redact_DuplicateSameTypeAndValue_ReusesPlaceholder()
+    {
+        const string text = "a@b.co and a@b.co";
+        var entities = new[]
+        {
+            Entity(PiiEntityType.Email, "a@b.co", 0),
+            Entity(PiiEntityType.Email, "a@b.co", 11)
+        };
+
+        var result = _redactor.Redact(text, entities);
+
+        result.SanitizedText.Should().Be("<EMAIL_1> and <EMAIL_1>");
+        result.PlaceholderMap.Should().HaveCount(1);
+    }
+
+    [Test]
+    public void Redact_MultipleTypes_AssignsIndependentCounters()
+    {
+        const string text = "9876543210 ravi@test.com";
+        var entities = new[]
+        {
+            Entity(PiiEntityType.Phone, "9876543210", 0),
+            Entity(PiiEntityType.Email, "ravi@test.com", 11)
+        };
+
+        var result = _redactor.Redact(text, entities);
+
+        result.SanitizedText.Should().Be("<PHONE_1> <EMAIL_1>");
+    }
+
+    [Test]
+    public void Redact_MultipleSameTypeDifferentValues_IncrementsCounter()
+    {
+        const string text = "Customer Ravi Kumar and Customer Priya Nair";
+        var entities = new[]
+        {
+            Entity(PiiEntityType.Person, "Ravi Kumar", 9),
+            Entity(PiiEntityType.Person, "Priya Nair", 33)
+        };
+
+        var result = _redactor.Redact(text, entities);
+
+        result.SanitizedText.Should().Be("Customer <PERSON_2> and Customer <PERSON_1>");
+        result.PlaceholderMap.Should().HaveCount(2);
+    }
+
+    [Test]
+    public void Redact_EntityTypes_UseTypedPlaceholderPrefixes()
+    {
+        (PiiEntityType Type, string Prefix)[] cases =
+        [
+            (PiiEntityType.Person, "PERSON"),
+            (PiiEntityType.Email, "EMAIL"),
+            (PiiEntityType.LoanNumber, "LOAN_NUMBER")
+        ];
+
+        foreach (var (type, prefix) in cases)
+        {
+            const string value = "VALUE";
+            var text = $"start {value} end";
+            var result = _redactor.Redact(text, [Entity(type, value, 6)]);
+            result.SanitizedText.Should().Contain($"<{prefix}_1>", because: type.ToString());
+        }
+    }
+
+    [Test]
+    public void Redact_RightToLeftReplacement_PreservesCorrectOutput()
+    {
+        const string text = "AA BB CC";
+        var entities = new[]
+        {
+            Entity(PiiEntityType.Phone, "AA", 0),
+            Entity(PiiEntityType.Email, "BB", 3),
+            Entity(PiiEntityType.Pan, "CC", 6)
+        };
+
+        var result = _redactor.Redact(text, entities);
+
+        result.SanitizedText.Should().Be("<PHONE_1> <EMAIL_1> <PAN_1>");
+    }
+
+    [TestCase(null)]
+    [TestCase("")]
+    [TestCase("   ")]
+    public void Redact_InvalidText_ThrowsArgumentException(string? text)
+    {
+        var action = () => _redactor.Redact(text!, []);
+        action.Should().Throw<ArgumentException>();
+    }
+
+    [Test]
+    public void Redact_NullEntities_ThrowsArgumentNullException()
+    {
+        var action = () => _redactor.Redact("text", null!);
+        action.Should().Throw<ArgumentNullException>();
+    }
+
+    private static PiiEntity Entity(PiiEntityType type, string value, int start) =>
+        new(type, value, start, value.Length, PiiDetectionSource.Regex);
+}