refactor(ebook-search): simplify search and phrase matching

python/ebook_search/protected_phrases/extraction.py

@@ -64,40 +64,30 @@ def normalize_candidate_phrase(
     phrase_text: str,
     config: EbookSearchConfig,
     *,
-    min_tokens: int | None = None,
     max_tokens: int | None = None,
-    strip_leading_article: bool = False,
 ) -> tuple[str, str, int] | None:
     """Normalize a candidate phrase and validate token bounds.
 
     Args:
         phrase_text (str): Raw phrase text to normalize.
         config (EbookSearchConfig): Runtime phrase-tuning settings.
-        min_tokens (int | None): Minimum token count override; defaults to ``config.phrase_min_tokens``.
         max_tokens (int | None): Maximum token count override; defaults to ``config.phrase_max_tokens``.
-        strip_leading_article (bool): Whether to drop a single leading English article.
 
     Returns:
         tuple[str, str, int] | None: Display text, normalized phrase, and token count, or ``None``
         when the phrase falls outside the token bounds or is ignored.
     """
     normalized_tokens = tokenize_with_offsets(phrase_text)
-    start = 0
-    if strip_leading_article and normalized_tokens and normalized_tokens[0].text in {"the", "a", "an"}:
-        start = 1
-
-    selected_tokens = normalized_tokens[start:]
-    min_count = config.phrase_min_tokens if min_tokens is None else min_tokens
     max_count = config.phrase_max_tokens if max_tokens is None else max_tokens
-    if len(selected_tokens) < min_count or len(selected_tokens) > max_count:
+    if len(normalized_tokens) < config.phrase_min_tokens or len(normalized_tokens) > max_count:
         return None
 
-    phrase_norm = " ".join(token.text for token in selected_tokens)
+    phrase_norm = " ".join(token.text for token in normalized_tokens)
     if phrase_norm in get_ignored_phrases():
         return None
 
-    display_text = phrase_text[selected_tokens[0].start_char : selected_tokens[-1].end_char].strip()
-    return display_text or phrase_norm, phrase_norm, len(selected_tokens)
+    display_text = phrase_text[normalized_tokens[0].start_char : normalized_tokens[-1].end_char].strip()
+    return display_text or phrase_norm, phrase_norm, len(normalized_tokens)
 
 
 def count_raw_ngrams(tokens: Sequence[str], config: EbookSearchConfig) -> Counter[str]: