diff --git a/.jules/bolt.md b/.jules/bolt.md index 8ce7ce8f7..a5bc227c2 100644 --- a/.jules/bolt.md +++ b/.jules/bolt.md @@ -77,3 +77,7 @@ ## 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. + +## 2024-11-20 - Optimizing string deduplication with dict.fromkeys() +**Learning:** While `dict.fromkeys()` is excellent for string deduplication, using it with a generator expression inside incurs generator overhead. +**Action:** When optimizing string deduplication in Python hot paths, prefer explicit `for` loops updating a local dictionary (`seen[key] = None`) over generator comprehensions passed to `dict.fromkeys()`. This avoids generator overhead while preserving element insertion order. diff --git a/appguardrail_core/rules.py b/appguardrail_core/rules.py index c06ea203a..84cc7d2ea 100644 --- a/appguardrail_core/rules.py +++ b/appguardrail_core/rules.py @@ -106,12 +106,12 @@ def as_dict(self) -> dict[str, Any]: def extract_public_references(message: str) -> tuple[str, ...]: """Extract OWASP, CWE, and CVE references already embedded in rule copy.""" - return tuple( - dict.fromkeys( - " ".join(match.group(1).split()) - for match in REFERENCE_RE.finditer(message or "") - ) - ) + # ⚡ Bolt: Use an explicit loop updating a local dict instead of dict.fromkeys() + # with a generator comprehension to avoid generator overhead while preserving order. + seen: dict[str, None] = {} + for match in REFERENCE_RE.finditer(message or ""): + seen[" ".join(match.group(1).split())] = None + return tuple(seen) def _category_for_references(references: tuple[str, ...], fallback: str) -> str: @@ -175,7 +175,5 @@ def validate_rule_metadata(metadata: RuleMetadata | dict[str, Any]) -> list[str] def _merge_references(*groups: tuple[str, ...]) -> tuple[str, ...]: return tuple( - dict.fromkeys( - reference for group in groups for reference in group if reference - ) + dict.fromkeys(reference for group in groups for reference in group if reference) )