将对span的操作移动到ocr_span_list_modify，增加独占一行区块的位置调整逻辑

magic_pdf/pdf_parse_by_ocr.py

@@ -22,11 +22,11 @@ from magic_pdf.pre_proc.detect_page_number import parse_pageNos
 from magic_pdf.pre_proc.ocr_cut_image import cut_image_and_table
 from magic_pdf.pre_proc.ocr_detect_layout import layout_detect
 from magic_pdf.pre_proc.ocr_dict_merge import (
-    remove_overlaps_min_spans,
     merge_spans_to_line_by_layout,
     modify_y_axis
 )
-from magic_pdf.pre_proc.ocr_remove_spans import remove_spans_by_bboxes
+from magic_pdf.pre_proc.ocr_span_list_modify import remove_spans_by_bboxes, remove_overlaps_min_spans, \
+    adjust_bbox_for_standalone_block
 from magic_pdf.pre_proc.remove_bbox_overlap import remove_overlap_between_bbox
 
 
@@ -191,6 +191,8 @@ def parse_pdf_by_ocr(
         spans = remove_overlap_between_bbox(spans)
 
         # 对tpye=["displayed_equation", "image", "table"]进行额外处理,如果左边有字的话,将该span的bbox中y0调整至不高于文字的y0
+        spans = adjust_bbox_for_standalone_block(spans)
+
 
         # 从ocr_page_info中解析layout信息(按自然阅读方向排序,并修复重叠和交错的bad case)
         layout_bboxes, layout_tree = layout_detect(ocr_page_info['subfield_dets'], page, ocr_page_info)

magic_pdf/pre_proc/ocr_dict_merge.py

@@ -4,19 +4,6 @@ from magic_pdf.libs.boxbase import __is_overlaps_y_exceeds_threshold, get_minbox
     calculate_overlap_area_in_bbox1_area_ratio
 
 
-# 删除重叠spans中较小的那些
-def remove_overlaps_min_spans(spans):
-    for span1 in spans.copy():
-        for span2 in spans.copy():
-            if span1 != span2:
-                overlap_box = get_minbox_if_overlap_by_ratio(span1['bbox'], span2['bbox'], 0.65)
-                if overlap_box is not None:
-                    bbox_to_remove = next((span for span in spans if span['bbox'] == overlap_box), None)
-                    if bbox_to_remove is not None:
-                        spans.remove(bbox_to_remove)
-    return spans
-
-
 # 将每一个line中的span从左到右排序
 def line_sort_spans_by_left_to_right(lines):
     line_objects = []

magic_pdf/pre_proc/ocr_remove_spans.py

@@ -1,17 +0,0 @@
-from magic_pdf.libs.boxbase import calculate_overlap_area_in_bbox1_area_ratio
-
-
-def remove_spans_by_bboxes(spans, need_remove_spans_bboxes):
-    # 遍历spans, 判断是否在removed_span_block_bboxes中
-    # 如果是, 则删除该span 否则, 保留该span
-    need_remove_spans = []
-    for span in spans:
-        for removed_bbox in need_remove_spans_bboxes:
-            if calculate_overlap_area_in_bbox1_area_ratio(span['bbox'], removed_bbox) > 0.5:
-                need_remove_spans.append(span)
-                break
-
-    for span in need_remove_spans:
-        spans.remove(span)
-
-    return spans

magic_pdf/pre_proc/ocr_span_list_modify.py

@@ -0,0 +1,45 @@
+from magic_pdf.libs.boxbase import calculate_overlap_area_in_bbox1_area_ratio, get_minbox_if_overlap_by_ratio
+
+
+def remove_overlaps_min_spans(spans):
+    #  删除重叠spans中较小的那些
+    for span1 in spans.copy():
+        for span2 in spans.copy():
+            if span1 != span2:
+                overlap_box = get_minbox_if_overlap_by_ratio(span1['bbox'], span2['bbox'], 0.65)
+                if overlap_box is not None:
+                    bbox_to_remove = next((span for span in spans if span['bbox'] == overlap_box), None)
+                    if bbox_to_remove is not None:
+                        spans.remove(bbox_to_remove)
+    return spans
+
+
+def remove_spans_by_bboxes(spans, need_remove_spans_bboxes):
+    # 遍历spans, 判断是否在removed_span_block_bboxes中
+    # 如果是, 则删除该span 否则, 保留该span
+    need_remove_spans = []
+    for span in spans:
+        for removed_bbox in need_remove_spans_bboxes:
+            if calculate_overlap_area_in_bbox1_area_ratio(span['bbox'], removed_bbox) > 0.5:
+                need_remove_spans.append(span)
+                break
+
+    for span in need_remove_spans:
+        spans.remove(span)
+
+    return spans
+
+
+def adjust_bbox_for_standalone_block(spans):
+    # 对tpye=["displayed_equation", "image", "table"]进行额外处理,如果左边有字的话,将该span的bbox中y0调整至不高于文字的y0
+    for sb_span in spans:
+        if sb_span['type'] in ["displayed_equation", "image", "table"]:
+            for text_span in spans:
+                if text_span['type'] in ['text', 'inline_equation']:
+                    # 判断span2的纵向高度是否被span所覆盖
+                    if sb_span['bbox'][1] < text_span['bbox'][1] and sb_span['bbox'][3] > text_span['bbox'][3]:
+                        # 判断span2是否在span左边
+                        if text_span['bbox'][0] < sb_span['bbox'][0]:
+                            # 调整span的y0和span2的y0一致
+                            sb_span['bbox'][1] = text_span['bbox'][1]
+    return spans