feat(ebook): add junk tokens for improved phrase matching

2026-07-16 13:09:34 -04:00
parent 6c5fcbd0fc
commit d6d90489db
3 changed files with 74 additions and 0 deletions
@@ -4,6 +4,7 @@ from python.ebook_search.protected_phrases.config.lib import (
    get_bad_ends,
    get_bad_starts,
    get_ignored_phrases,
+    get_junk_tokens,
    get_most_common_words,
 )

@@ -11,5 +12,6 @@ __all__ = [
    "get_bad_ends",
    "get_bad_starts",
    "get_ignored_phrases",
+    "get_junk_tokens",
    "get_most_common_words",
 ]