Benjamin Admin 5359a4cc2b fix: cache word_result in paddle_kombi/rapid_kombi for detect-structure
Both kombi OCR functions wrote word_result to DB but not to the
in-memory cache. When detect-structure ran next, it found no words
and passed an empty list to graphic detection, making all word-overlap
heuristics ineffective. This caused green text words to be wrongly
classified as graphic regions.

Also adds a fallback in detect-structure to use raw OCR word lists
if cell word_boxes are empty.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-18 07:29:02 +01:00
Description
No description provided
42 MiB
Languages
TypeScript 60.2%
Python 32.9%
Go 5.5%
C# 0.8%
CSS 0.2%
Other 0.3%