From 91eaa6d8378d599613f41c95ec5f7343896eee48 Mon Sep 17 00:00:00 2001
From: dhgoal <153369624+dhgoal@users.noreply.github.com>
Date: Sun, 5 Jul 2026 15:30:51 +0900
Subject: [PATCH] test(enrichment): cover requirementTokens dedup, stopword,
 and alnum branches

The single existing test only exercised length-based drops. Adds the uncovered
branches: case-insensitive deduplication, a >=4-char word dropped by the
stopword set (not the length floor), and alphanumeric tokens split on
punctuation. Test-only.
---
 review-enrichment/test/history.test.ts | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/review-enrichment/test/history.test.ts b/review-enrichment/test/history.test.ts
index 38a16105f1..d7f377a5ad 100644
--- a/review-enrichment/test/history.test.ts
+++ b/review-enrichment/test/history.test.ts
@@ -322,6 +322,20 @@ test("requirementTokens drops short words and stopwords", () => {
   ]);
 });
 
+test("requirementTokens deduplicates case-insensitively", () => {
+  // Repeated words (any case) collapse to one token — the existing test has no repeats.
+  assert.deepEqual(requirementTokens("Cache cache CACHE storage"), ["cache", "storage"]);
+});
+
+test("requirementTokens drops a long-enough stopword via the stopword set, not the length floor", () => {
+  // `feature`/`should`/`support` are >= the 4-char floor, so they're dropped by the stopword check itself.
+  assert.deepEqual(requirementTokens("this feature should support caching"), ["caching"]);
+});
+
+test("requirementTokens keeps alphanumeric tokens and splits on punctuation", () => {
+  assert.deepEqual(requirementTokens("oauth2 retry-loop"), ["oauth2", "retry", "loop"]);
+});
+
 test("classifyCoverage thresholds", () => {
   assert.equal(classifyCoverage("history analyzer enrichment", "history analyzer enrichment"), "full");
   assert.equal(classifyCoverage("history analyzer enrichment", "history only"), "partial");