Update pdf_parse_union_core_v2.py

magic_pdf/pdf_parse_union_core_v2.py

@@ -381,7 +381,7 @@ def revert_group_blocks(blocks):
     return new_blocks
 
 
-def parse_page_core(ocr_status,config_path,local_image_dir,
+def parse_page_core(config_path,local_image_dir,
     page_doc: PageableData, magic_model, page_id, pdf_bytes_md5, imageWriter, parse_mode
 ):
     need_drop = False
@@ -428,7 +428,7 @@ def parse_page_core(ocr_status,config_path,local_image_dir,
     """删除重叠spans中较小的那些"""
     spans, dropped_spans_by_span_overlap = remove_overlaps_min_spans(spans)
     """对image和table截图"""
-    spans = ocr_cut_image_and_table(ocr_status,config_path,local_image_dir,
+    spans = ocr_cut_image_and_table(config_path,local_image_dir,
         spans, page_doc, page_id, pdf_bytes_md5, imageWriter
     )
 
@@ -524,7 +524,7 @@ def parse_page_core(ocr_status,config_path,local_image_dir,
     return page_info
 
 
-def pdf_parse_union(ocr_status,config_path,local_image_dir,
+def pdf_parse_union(config_path,local_image_dir,
     dataset: Dataset,
     model_list,
     imageWriter,
@@ -568,7 +568,7 @@ def pdf_parse_union(ocr_status,config_path,local_image_dir,
         """解析pdf中的每一页"""
         if start_page_id <= page_id <= end_page_id:
             page_info = parse_page_core(
-                ocr_status,config_path,local_image_dir,page, magic_model, page_id, pdf_bytes_md5, imageWriter, parse_mode
+                config_path,local_image_dir,page, magic_model, page_id, pdf_bytes_md5, imageWriter, parse_mode
             )
         else:
             page_info = page.get_page_info()