From 62916ee574a9ffab7ef005d0ad725a0e54066325 Mon Sep 17 00:00:00 2001 From: un-pogaz <46523284+un-pogaz@users.noreply.github.com> Date: Sat, 9 Mar 2024 08:01:28 +0100 Subject: [PATCH] Full text search: imporve parsing when indexing books Following the spec of the tag, it's better to ignore only the sub-tags , and , because the root text inside the tag is what we want indexing. --- src/calibre/db/fts/text.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/db/fts/text.py b/src/calibre/db/fts/text.py index ea30acc39a..3e8938140f 100644 --- a/src/calibre/db/fts/text.py +++ b/src/calibre/db/fts/text.py @@ -20,7 +20,7 @@ class SimpleContainer(ContainerBase): tweak_mode = True -skipped_tags = frozenset({'style', 'title', 'script', 'head', 'img', 'svg', 'math', 'ruby'}) +skipped_tags = frozenset({'style', 'title', 'script', 'head', 'img', 'svg', 'math', 'rt', 'rp', 'rtc'}) def tag_to_text(tag):