feat(extraction): add cached YAKE extractor for improved performance

python/ebook_search/protected_phrases/extraction.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import logging
 import re
 from collections import defaultdict
+from functools import lru_cache
 from time import perf_counter
 from typing import TYPE_CHECKING, Protocol
 
@@ -176,6 +177,21 @@ def extract_raw_ngrams(text: str, config: EbookSearchConfig) -> dict[str, Phrase
     return out
 
 
+@lru_cache(maxsize=2)
+def get_yake_extractor(max_ngram: int, top_k: int) -> KeywordExtractor:
+    """Return a cached YAKE extractor for the given settings.
+
+    Constructing a ``KeywordExtractor`` loads the language's stopword list from disk, so it is
+    cached and reused across books rather than rebuilt on every call.
+
+    Args:
+        max_ngram (int): Maximum n-gram size to extract.
+        top_k (int): Maximum number of keyphrases to request.
+
+    Returns:
+        KeywordExtractor: A shared extractor instance for the given settings.
+    """
+    return KeywordExtractor(lan="en", n=max_ngram, dedupLim=0.85, top=top_k)
 
 
 def extract_yake_candidates(
@@ -193,7 +209,7 @@ def extract_yake_candidates(
     Returns:
         dict[str, PhraseCandidate]: Candidates keyed by normalized phrase, with YAKE scores.
     """
-    extractor = KeywordExtractor(lan="en", n=config.phrase_max_tokens, dedupLim=0.85, top=top_k)
+    extractor = get_yake_extractor(config.phrase_max_tokens, top_k)
     out: dict[str, PhraseCandidate] = {}
     for phrase_text, yake_score in extractor.extract_keywords(book_text):
         normalized = normalize_candidate_phrase(phrase_text, config)