From b7d63f3dc193cf4ce683f1b8ca6af65e07e9db08 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Odin=20Dahlstr=C3=B6m?= <zerodind@gmail.com>
Date: Thu, 30 Jan 2025 17:49:06 +0100
Subject: [PATCH] Process ocr_caption lines

---
 src/ocrmypdf/hocrtransform/_hocr.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/ocrmypdf/hocrtransform/_hocr.py b/src/ocrmypdf/hocrtransform/_hocr.py
index 54da4f4e..38ebae7b 100644
--- a/src/ocrmypdf/hocrtransform/_hocr.py
+++ b/src/ocrmypdf/hocrtransform/_hocr.py
@@ -210,7 +210,7 @@ class HocrTransform:
                     for element in par.iterfind(self._child_xpath('span'))
                     if 'class' in element.attrib
                     and element.attrib['class']
-                    in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
+                    in {'ocr_header', 'ocr_line', 'ocr_textfloat', 'ocr_caption'}
                 ):
                     found_lines = True
                     direction = self._get_text_direction(par)