feat: complete catalog sensitivity enhancements

backend/test/catalog-sensitivity-classifier.test.ts

@@ -69,6 +69,32 @@ function source(scan: SensitivityTableScan): SensitivityValueSource {
   }) };
 }
 
+test("reports source-scan activity before a long table scan completes", async () => {
+  let releaseScan!: () => void;
+  const scanGate = new Promise<void>((resolve) => {
+    releaseScan = resolve;
+  });
+  const scanTable = vi.fn(async () => {
+    await scanGate;
+    return { kind: "complete" as const, observedValues: 0 };
+  });
+  const activity = vi.fn();
+  const analysis = new SensitivityClassifier({ scanTable }).assess(
+    [{ database, table, columns: [column()] }],
+    new AbortController().signal,
+    undefined,
+    activity,
+  );
+
+  await vi.waitFor(() => expect(scanTable).toHaveBeenCalledOnce());
+  releaseScan();
+  await analysis;
+
+  expect(activity).toHaveBeenCalledWith(
+    "Scanning source data: pass 1 of 3, table batch 1 of 1.",
+  );
+});
+
 test("one email hidden in a generically named column makes the whole column sensitive", async () => {
   const target = column();
   const values = source({
@@ -351,6 +377,98 @@ test("strong Italian PII metadata is sensitive even when the source column is em
   expect(values.scanTable).not.toHaveBeenCalled();
 });
 
+test("excludes bigint primary keys from content analysis as non-informative identifiers", async () => {
+  const target = column({
+    name: "id",
+    dataType: "bigint",
+    primaryKeyPosition: 1,
+    isPrimaryKey: true,
+  });
+  const values = source({
+    batches: [[{
+      columnId: target.id,
+      value: "3471234567",
+      characterLength: 10,
+    }]],
+    coverage: { kind: "complete", observedValues: 1 },
+  });
+
+  const [assessment] = await new SensitivityClassifier(values).assessTable(
+    { database, table, columns: [target] },
+    new AbortController().signal,
+  );
+
+  expect(assessment).toMatchObject({
+    assessment: "non_sensitive",
+    proposedSensitive: false,
+    evidence: [{
+      kind: "type",
+      ruleId: "type.bigint_primary_key_non_informative",
+      label: "non-informative bigint primary key",
+    }],
+    coverage: "metadata",
+  });
+  expect(values.scanTable).not.toHaveBeenCalled();
+});
+
+test("infers an undeclared bigint column named pk as a non-informative primary-key identifier", async () => {
+  const target = column({
+    name: "pk",
+    dataType: "bigint",
+    primaryKeyPosition: null,
+    isPrimaryKey: false,
+  });
+  const values = source({
+    batches: [[{
+      columnId: target.id,
+      value: "3471234567",
+      characterLength: 10,
+    }]],
+    coverage: { kind: "complete", observedValues: 1 },
+  });
+
+  const [assessment] = await new SensitivityClassifier(values).assessTable(
+    { database, table, columns: [target] },
+    new AbortController().signal,
+  );
+
+  expect(assessment).toMatchObject({
+    assessment: "non_sensitive",
+    proposedSensitive: false,
+    evidence: [{
+      kind: "metadata",
+      ruleId: "metadata.bigint_pk_identifier_non_informative",
+      label: "non-informative conventional bigint primary-key identifier",
+    }],
+    coverage: "metadata",
+  });
+  expect(values.scanTable).not.toHaveBeenCalled();
+});
+
+test("still inspects phone-like values in bigint columns that are not primary keys", async () => {
+  const target = column({ name: "id", dataType: "bigint" });
+  const values = source({
+    batches: [[{
+      columnId: target.id,
+      value: "3471234567",
+      characterLength: 10,
+    }]],
+    coverage: { kind: "complete", observedValues: 1 },
+  });
+
+  const [assessment] = await new SensitivityClassifier(values).assessTable(
+    { database, table, columns: [target] },
+    new AbortController().signal,
+  );
+
+  expect(assessment).toMatchObject({
+    assessment: "sensitive",
+    proposedSensitive: true,
+    evidence: [{ kind: "content", ruleId: "pii.phone_number" }],
+  });
+  expect(values.scanTable).toHaveBeenCalledOnce();
+});
+
 test.each([
   ["RSSMRA85T10A562S", "pii.italian_fiscal_code"],
   ["IT60 X054 2811 1010 0000 0123 456", "financial.iban"],