Merge pull request #2251 from myhloli/dev

feat(pdf_parse): add footnote block handling in layout split

Author: myhloli

Diff for: magic_pdf/pdf_parse_union_core_v2.py

@@ -490,7 +490,7 @@ def insert_lines_into_block(block_bbox, line_height, page_w, page_h):
         return [[x0, y0, x1, y1]]
 
 
-def sort_lines_by_model(fix_blocks, page_w, page_h, line_height):
+def sort_lines_by_model(fix_blocks, page_w, page_h, line_height, footnote_blocks):
     page_line_list = []
 
     def add_lines_to_block(b):
@@ -519,6 +519,10 @@ def add_lines_to_block(b):
             block['real_lines'] = copy.deepcopy(block['lines'])
             add_lines_to_block(block)
 
+    for block in footnote_blocks:
+        footnote_block = {'bbox': block[:4]}
+        add_lines_to_block(footnote_block)
+
     if len(page_line_list) > 200:  # layoutreader最高支持512line
         return None
 
@@ -779,7 +783,7 @@ def merge_two_blocks(b1, b2):
     # interline_equation_blocks参数不够准，后面切换到interline_equations上
     interline_equation_blocks = []
     if len(interline_equation_blocks) > 0:
-        all_bboxes, all_discarded_blocks = ocr_prepare_bboxes_for_layout_split_v2(
+        all_bboxes, all_discarded_blocks, footnote_blocks = ocr_prepare_bboxes_for_layout_split_v2(
             img_body_blocks, img_caption_blocks, img_footnote_blocks,
             table_body_blocks, table_caption_blocks, table_footnote_blocks,
             discarded_blocks,
@@ -790,7 +794,7 @@ def merge_two_blocks(b1, b2):
             page_h,
         )
     else:
-        all_bboxes, all_discarded_blocks = ocr_prepare_bboxes_for_layout_split_v2(
+        all_bboxes, all_discarded_blocks, footnote_blocks = ocr_prepare_bboxes_for_layout_split_v2(
             img_body_blocks, img_caption_blocks, img_footnote_blocks,
             table_body_blocks, table_caption_blocks, table_footnote_blocks,
             discarded_blocks,
@@ -866,7 +870,7 @@ def merge_two_blocks(b1, b2):
     line_height = get_line_height(fix_blocks)
 
     """获取所有line并对line排序"""
-    sorted_bboxes = sort_lines_by_model(fix_blocks, page_w, page_h, line_height)
+    sorted_bboxes = sort_lines_by_model(fix_blocks, page_w, page_h, line_height, footnote_blocks)
 
     """根据line的中位数算block的序列关系"""
     fix_blocks = cal_block_index(fix_blocks, sorted_bboxes)

Diff for: magic_pdf/pre_proc/ocr_detect_all_bboxes.py

@@ -119,7 +119,7 @@ def ocr_prepare_bboxes_for_layout_split_v2(
     """将剩余的bbox做分离处理，防止后面分layout时出错"""
     # all_bboxes, drop_reasons = remove_overlap_between_bbox_for_block(all_bboxes)
     all_bboxes.sort(key=lambda x: x[0]+x[1])
-    return all_bboxes, all_discarded_blocks
+    return all_bboxes, all_discarded_blocks, footnote_blocks
 
 
 def find_blocks_under_footnote(all_bboxes, footnote_blocks):