| .. |
|
__init__.py
|
d5dbed7325
目录重构
|
1 year ago |
|
citationmarker_remove.py
|
d5dbed7325
目录重构
|
1 year ago |
|
construct_paras.py
|
d5dbed7325
目录重构
|
1 year ago |
|
detect_equation.py
|
bc339320ab
增加了一个solve_line_alien.py,在detect_equation.py中修改了__solve_contain_bboxs函数,并在pdf_parse_by_model.py里增加了函数solve_line_alien.py的调用
|
1 year ago |
|
detect_footer_by_model.py
|
f62d1aa781
将模型和pymu坐标的转换逻辑抽象成方法
|
1 year ago |
|
detect_footer_header_by_statistics.py
|
d5dbed7325
目录重构
|
1 year ago |
|
detect_footnote.py
|
f62d1aa781
将模型和pymu坐标的转换逻辑抽象成方法
|
1 year ago |
|
detect_header.py
|
f62d1aa781
将模型和pymu坐标的转换逻辑抽象成方法
|
1 year ago |
|
detect_images.py
|
d5dbed7325
目录重构
|
1 year ago |
|
detect_page_number.py
|
f62d1aa781
将模型和pymu坐标的转换逻辑抽象成方法
|
1 year ago |
|
detect_tables.py
|
d5dbed7325
目录重构
|
1 year ago |
|
equations_replace.py
|
d5dbed7325
目录重构
|
1 year ago |
|
fix_image.py
|
d5dbed7325
目录重构
|
1 year ago |
|
fix_table.py
|
d5dbed7325
目录重构
|
1 year ago |
|
main_text_font.py
|
d5dbed7325
目录重构
|
1 year ago |
|
ocr_cut_image.py
|
ec1a6ef716
增加生成多模态markdown逻辑
|
1 year ago |
|
ocr_detect_layout.py
|
61a0c62c46
pdf_info_dict中间态结构调整
|
1 year ago |
|
ocr_dict_merge.py
|
5513e48ab8
add modify inline equation y axis
|
1 year ago |
|
ocr_remove_spans.py
|
0c279ffccd
更新remove_spans_by_bboxes中选择被删除的span的逻辑
|
1 year ago |
|
pdf_pre_filter.py
|
d5dbed7325
目录重构
|
1 year ago |
|
post_layout_split.py
|
d5dbed7325
目录重构
|
1 year ago |
|
remove_bbox_overlap.py
|
2611e85349
feat: complete self check
|
1 year ago |
|
remove_colored_strip_bbox.py
|
d5dbed7325
目录重构
|
1 year ago |
|
remove_footer_header.py
|
d5dbed7325
目录重构
|
1 year ago |
|
remove_rotate_bbox.py
|
d5dbed7325
目录重构
|
1 year ago |
|
resolve_bbox_conflict.py
|
d5dbed7325
目录重构
|
1 year ago |
|
solve_line_alien.py
|
bc339320ab
增加了一个solve_line_alien.py,在detect_equation.py中修改了__solve_contain_bboxs函数,并在pdf_parse_by_model.py里增加了函数solve_line_alien.py的调用
|
1 year ago |
|
statistics.py
|
d5dbed7325
目录重构
|
1 year ago |