Skip to content

GitLab

Unverified Commit 2c8470b0 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1986 from myhloli/dev 

refactor(pdf_parse): adjust line calculation for block height
parents 26777d25 72e66c2d
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
magic_pdf/pdf_parse_union_core_v2.py
View file @ 2c8470b0
...@@ -457,7 +457,6 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h): ...@@ -457,7 +457,6 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h):
# 如果block的宽度超过0.4页面宽度，则将block分成3行(是一种复杂布局，图不能切的太细) # 如果block的宽度超过0.4页面宽度，则将block分成3行(是一种复杂布局，图不能切的太细)
if block_weight > page_w * 0.4: if block_weight > page_w * 0.4:
lines = 3 lines = 3
line_height = (y1 - y0) / lines
elif block_weight > page_w * 0.25: # （可能是三列结构，也切细点） elif block_weight > page_w * 0.25: # （可能是三列结构，也切细点）
lines = int(block_height / line_height) lines = int(block_height / line_height)
else: # 判断长宽比 else: # 判断长宽比
...@@ -465,6 +464,7 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h): ...@@ -465,6 +464,7 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h):
return [[x0, y0, x1, y1]] return [[x0, y0, x1, y1]]
else: # 不细长的还是分成两行 else: # 不细长的还是分成两行
lines = 2 lines = 2
line_height = (y1 - y0) / lines line_height = (y1 - y0) / lines
# 确定从哪个y位置开始绘制线条 # 确定从哪个y位置开始绘制线条
......
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