修复了para_split内容丢失

opendatalab · Apr 23, 2024 · f4a7e0d · f4a7e0d
1 parent 1d16c31
commit f4a7e0d
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/magic_pdf/para/para_split_v2.py b/magic_pdf/para/para_split_v2.py
@@ -246,11 +246,11 @@ def __group_line_by_layout(blocks, layout_bboxes, lang="en"):
     for lyout in layout_bboxes:
         lines = [line for block in blocks if block["type"] == BlockType.Text and is_in_layout(block['bbox'], lyout['layout_bbox']) for line in
                  block['lines']]
-        blocks = [block for block in blocks if is_in_layout(block['bbox'], lyout['layout_bbox'])]
+        blocks_in_layout = [block for block in blocks if is_in_layout(block['bbox'], lyout['layout_bbox'])]
 
 
         lines_group.append(lines)
-        blocks_group.append(blocks)
+        blocks_group.append(blocks_in_layout)
     return lines_group, blocks_group