Optimize entity detection with regex caching and pre-compilation

- Use functools.lru_cache to cache compiled patterns for entity names.
- Pre-compile static pronoun patterns into a single regex.
- Remove redundant .lower() calls in score_entity loop.

Co-authored-by: igorls <4753812+igorls@users.noreply.github.com>

mempalace/entity_detector.py

@@ -17,6 +17,7 @@ Usage:
 
 import re
 import os
+import functools
 from pathlib import Path
 from collections import defaultdict
 
@@ -60,6 +61,8 @@ PRONOUN_PATTERNS = [
     r"\btheir\b",
 ]
 
+PRONOUN_RE = re.compile("|".join(PRONOUN_PATTERNS), re.IGNORECASE)
+
 # Person signals — dialogue markers
 DIALOGUE_PATTERNS = [
     r"^>\s*{name}[:\s]",  # > Speaker: ...
@@ -466,6 +469,7 @@ def extract_candidates(text: str) -> dict:
 # ==================== SIGNAL SCORING ====================
 
 
+@functools.lru_cache(maxsize=128)
 def _build_patterns(name: str) -> dict:
     """Pre-compile all regex patterns for a single entity name."""
     n = re.escape(name)
@@ -515,11 +519,9 @@ def score_entity(name: str, text: str, lines: list) -> dict:
     name_line_indices = [i for i, line in enumerate(lines) if name_lower in line.lower()]
     pronoun_hits = 0
     for idx in name_line_indices:
-        window_text = " ".join(lines[max(0, idx - 2) : idx + 3]).lower()
+        window_text = " ".join(lines[max(0, idx - 2) : idx + 3])
-        for pronoun_pattern in PRONOUN_PATTERNS:
+        if PRONOUN_RE.search(window_text):
-            if re.search(pronoun_pattern, window_text):
+            pronoun_hits += 1
-                pronoun_hits += 1
-                break
     if pronoun_hits > 0:
         person_score += pronoun_hits * 2
         person_signals.append(f"pronoun nearby ({pronoun_hits}x)")