Skip to content

P
pdf-miner
Commit f4a7e0d7 authored by liukaiwen's avatar liukaiwen
Browse files
Options

修复了para_split内容丢失

parent 1d16c319
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
magic_pdf/para/para_split_v2.py
View file @ f4a7e0d7
...@@ -246,11 +246,11 @@ def __group_line_by_layout(blocks, layout_bboxes, lang="en"): ...@@ -246,11 +246,11 @@ def __group_line_by_layout(blocks, layout_bboxes, lang="en"):
for lyout in layout_bboxes: 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 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']] 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) lines_group.append(lines)
blocks_group.append(blocks) blocks_group.append(blocks_in_layout)
return lines_group, blocks_group return lines_group, blocks_group
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment