Skip to content

GitLab

Unverified Commit 78ed7867 authored by myhloli's avatar myhloli Committed by GitHub
Browse files

Merge pull request #115 from papayalove/master 

修复边界问题（修复list拼接和reference分行问题）
parents f8548a8e 4ff09a2f
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
magic_pdf/para/para_split_v2.py
View file @ 78ed7867
...@@ -106,6 +106,7 @@ def __detect_list_lines(lines, new_layout_bboxes, lang): ...@@ -106,6 +106,7 @@ def __detect_list_lines(lines, new_layout_bboxes, lang):
3. 如果非顶格，首字符大写，编码为2 3. 如果非顶格，首字符大写，编码为2
4. 如果非顶格，首字符非大写编码为3 4. 如果非顶格，首字符非大写编码为3
""" """
if len(lines) > 0:
x_map_tag_dict, min_x_tag = cluster_line_x(lines) x_map_tag_dict, min_x_tag = cluster_line_x(lines)
for l in lines: for l in lines:
span_text = __get_span_text(l['spans'][0]) span_text = __get_span_text(l['spans'][0])
......
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