fix(remove_overlaps_min_spans): optimize overlap detection in OCR span list modification

- Improve logic to skip dropped spans in overlap detection
- Enhance efficiency by avoiding unnecessary comparisons

magic_pdf/pre_proc/ocr_span_list_modify.py

@@ -38,6 +38,10 @@ def remove_overlaps_min_spans(spans):
     for span1 in spans:
         for span2 in spans:
             if span1 != span2:
+                # span1 或 span2 任何一个都不应该在 dropped_spans 中
+                if span1 in dropped_spans or span2 in dropped_spans:
+                    continue
+                else:
                     overlap_box = get_minbox_if_overlap_by_ratio(span1['bbox'], span2['bbox'], 0.65)
                     if overlap_box is not None:
                         span_need_remove = next((span for span in spans if span['bbox'] == overlap_box), None)