From adec13fbbba7feaba4d975e0ea9a06606624fc61 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Sat, 25 Jul 2026 17:33:01 +0000
Subject: [PATCH] Memoize context lexicon compilation to improve clinical span
 processing performance.

Co-authored-by: zrt219 <199104500+zrt219@users.noreply.github.com>
---
 .jules/bolt.md                      | 3 +++
 openmed/openmed/clinical/context.py | 7 +++++++
 2 files changed, 10 insertions(+)
 create mode 100644 .jules/bolt.md

diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 0000000..5290c47
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## 2024-07-25 - Context Lexicon Compilation Bottleneck
+**Learning:** Deterministic regex generation for clinical span lexicons (`_compiled_context_lexicon` in `openmed/clinical/context.py`) is expensive and is repeatedly invoked by various helpers (e.g. `is_negated`, `is_hypothetical`). Since the language argument is hashable, caching this generation avoids massive repetitive computation.
+**Action:** Always verify if computationally heavy dynamic regex generation based on statically loadable parameters (like a language code or fixed taxonomy) is being done per-span, and aggressively memoize these functions (`@functools.lru_cache`) to avoid re-compilation.
diff --git a/openmed/openmed/clinical/context.py b/openmed/openmed/clinical/context.py
index 9fd11df..7ae9812 100644
--- a/openmed/openmed/clinical/context.py
+++ b/openmed/openmed/clinical/context.py
@@ -39,6 +39,7 @@
 from collections.abc import Iterable, Iterator, Mapping, Sequence
 from dataclasses import dataclass, replace
 from datetime import date
+from functools import lru_cache
 from typing import Any, Literal
 
 from openmed.clinical.lexicons import (
@@ -154,7 +155,13 @@ class _CompiledContextLexicon:
     backward_context_cues: frozenset[str]
 
 
+@lru_cache(maxsize=16)
 def _compiled_context_lexicon(language: str | None = None) -> _CompiledContextLexicon:
+    """Returns regex matchers derived from the context cues lexicon.
+
+    Memoized as cue sets can be large to iterate and regexes are expensive
+    to compile across many invocations.
+    """
     lexicon = get_clinical_cue_lexicon(language)
     token_boundaries = lexicon.token_boundaries
     return _CompiledContextLexicon(