Bilal-Nazer-Ali/llm-pii-poc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Surface NER routing provenance (ModelOrigin, NerModelsInvoked) through the pipeline and WPF harness so English/Tamil routing is observable during POC validation. Consolidate docs into solution-guide and add NER logs, topic filtering, and batch UI fixes in the test harness.

Browse Source
This commit is contained in:
Bilal Nazer Ali
2026-07-08 12:18:27 +05:30
parent cf8f5a7232
commit 81220c6ade
51 changed files with 1530 additions and 1463 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/PiiRedaction.Infrastructure.Tests/Onnx/RealTamilNerModelRunnerTests.cs
View File

@@ -21,15 +21,18 @@ public sealed class RealTamilNerModelRunnerTests : RealTamilNerModelFixture
string expectedNamePart,
string expectedValue)
{
var entities = Runner.PredictEntities(prompt);
var result = Runner.PredictEntities(prompt);
var entities = result.Entities;
entities.Should().Contain(entity =>
entity.Type == PiiEntityType.Person &&
entity.Source == PiiDetectionSource.Ner &&
entity.ModelOrigin == NerModelOrigin.Tamil &&
entity.Value.Contains(expectedNamePart, StringComparison.Ordinal) &&
prompt.AsSpan(entity.StartIndex, entity.Length).ToString() == entity.Value);
entities.Should().Contain(entity => entity.Value == expectedValue);
result.InvokedModels.Should().Equal(NerModelOrigin.Tamil);
}
[Test]
@@ -37,11 +40,12 @@ public sealed class RealTamilNerModelRunnerTests : RealTamilNerModelFixture
{
const string prompt = "வாடிக்கையாளர் ராஜேஷ் குமார் தொலைபேசி 9876543210";
var entities = Runner.PredictEntities(prompt);
var entities = Runner.PredictEntities(prompt).Entities;
entities.Should().Contain(entity =>
entity.Type == PiiEntityType.Person &&
entity.Source == PiiDetectionSource.Ner &&
entity.ModelOrigin == NerModelOrigin.Tamil &&
entity.Value.Contains("ராஜேஷ்", StringComparison.Ordinal));
entities.Should().NotContain(entity => entity.Type == PiiEntityType.Phone);
}
@@ -51,7 +55,7 @@ public sealed class RealTamilNerModelRunnerTests : RealTamilNerModelFixture
{
const string prompt = "பணத்தை திரும்பப் பெறுவது எப்படி?";
Runner.PredictEntities(prompt).Should().BeEmpty();
Runner.PredictEntities(prompt).Entities.Should().BeEmpty();
}
[TestCase("Customer Senthil phone 9876543210", "Senthil")]
@@ -61,7 +65,7 @@ public sealed class RealTamilNerModelRunnerTests : RealTamilNerModelFixture
{
// TamilOnnxNerRunner is script-scoped; Tanglish is handled by English routing in pipeline tests.
// Direct Tamil runner on Latin-only text should not emit person spans.
var entities = Runner.PredictEntities(prompt);
var entities = Runner.PredictEntities(prompt).Entities;
entities.Should().NotContain(entity =>
entity.Type == PiiEntityType.Person &&