From 14e013134938efc6bd24eb32eb60e53264f05258 Mon Sep 17 00:00:00 2001
From: seonghobae <8172694+seonghobae@users.noreply.github.com>
Date: Mon, 5 Oct 2026 14:35:43 +0000
Subject: [PATCH] perf: optimize SARIF rule index lookup

---
 .jules/bolt.md             | 3 +++
 appguardrail_core/sarif.py | 5 ++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/.jules/bolt.md b/.jules/bolt.md
index 8ce7ce8f7..ce5215398 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -77,3 +77,6 @@
 ## 2024-11-20 - Optimize multiple tuple generation from a single collection
 **Learning:** `build_rule_metadata` derives exactly two collections, `owasp` and `cwe`, from the same references. Replacing its two generator traversals with one explicit loop reduces element visits from about 2N to N. Both versions remain O(N), so this is a constant-factor optimization rather than an asymptotic complexity improvement.
 **Action:** Combine repeated traversal when fixed derived collections share one source, while preserving ordering and classification semantics. Benchmark the production hot path before claiming a material wall-clock improvement.
+## 2025-02-12 - O(1) SARIF Rule Index Lookup Optimization
+**Learning:** In Python, calling `list(dict).index(key)` inside a loop over data items causes severe O(N^2) performance degradation because it creates a new list and performs a linear search on every iteration. This pattern was found in `appguardrail_core/sarif.py` during SARIF generation.
+**Action:** Always avoid `list(dict).index()` inside loops. Maintain a parallel index mapping dictionary (e.g., `indices[key] = len(indices)`) to achieve O(1) lookups and keep the overall loop bounded to O(N) time complexity.
diff --git a/appguardrail_core/sarif.py b/appguardrail_core/sarif.py
index ca4a9fb6b..43a74f7c8 100644
--- a/appguardrail_core/sarif.py
+++ b/appguardrail_core/sarif.py
@@ -39,12 +39,15 @@ def findings_to_sarif(
     normalized = normalize_findings(findings)
 
     rules: dict[str, dict[str, Any]] = {}
+    rule_indices: dict[str, int] = {}
     results: list[dict[str, Any]] = []
     for f in normalized:
         rule_id = f["rule_id"]
         severity = f["severity"]
         refs = f.get("references") or ()
         if rule_id not in rules:
+            # ⚡ Bolt: Maintain O(1) index lookup to avoid list(rules).index() O(N) overhead
+            rule_indices[rule_id] = len(rules)
             rule: dict[str, Any] = {
                 "id": rule_id,
                 "name": rule_id,
@@ -68,7 +71,7 @@ def findings_to_sarif(
         results.append(
             {
                 "ruleId": rule_id,
-                "ruleIndex": list(rules).index(rule_id),
+                "ruleIndex": rule_indices[rule_id],
                 "level": _LEVEL.get(severity, "note"),
                 "message": {"text": f["message"].strip()},
                 "locations": [