Skip to content

GitLab

Unverified Commit dd377537 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1948 from myhloli/dev 

refactor(ocr_mkcontent): improve title level handling and formatting
parents b3faee93 eae0e6d8
Show whitespace changes
Inline Side-by-side
Showing with 4 additions and 3 deletions
magic_pdf/dict2md/ocr_mkcontent.py
View file @ dd377537
...@@ -208,12 +208,13 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx, drop_reason ...@@ -208,12 +208,13 @@ def para_to_standard_format_v2(para_block, img_buket_path, page_idx, drop_reason
'text': merge_para_with_text(para_block), 'text': merge_para_with_text(para_block),
} }
elif para_type == BlockType.Title: elif para_type == BlockType.Title:
title_level = get_title_level(para_block)
para_content = { para_content = {
'type': 'text', 'type': 'text',
'text': merge_para_with_text(para_block), 'text': merge_para_with_text(para_block),
'text_level': title_level,
} }
title_level = get_title_level(para_block)
if title_level != 0:
para_content['text_level'] = title_level
elif para_type == BlockType.InterlineEquation: elif para_type == BlockType.InterlineEquation:
para_content = { para_content = {
'type': 'equation', 'type': 'equation',
...@@ -319,5 +320,5 @@ def get_title_level(block): ...@@ -319,5 +320,5 @@ def get_title_level(block):
if title_level > 4: if title_level > 4:
title_level = 4 title_level = 4
elif title_level < 1: elif title_level < 1:
title_level = 1 title_level = 0
return title_level return title_level
\ No newline at end of file
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