Merge pull request #55 from myhloli/master

v2pipeline在分段区域增加异常捕获
opendatalab · Apr 23, 2024 · 61267ed · 61267ed
2 parents 179ab59 + fa6e305
commit 61267ed
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 2 deletions.
diff --git a/magic_pdf/pdf_parse_by_ocr_v2.py b/magic_pdf/pdf_parse_by_ocr_v2.py
@@ -92,7 +92,11 @@ def parse_pdf_by_ocr(pdf_bytes,
         pdf_info_dict[f"page_{page_id}"] = page_info
 
     """分段"""
-    para_split(pdf_info_dict, debug_mode=debug_mode)
+    try:
+        para_split(pdf_info_dict, debug_mode=debug_mode)
+    except Exception as e:
+        logger.exception(e)
+        raise e
 
     """dict转list"""
     pdf_info_list = dict_to_list(pdf_info_dict)

diff --git a/magic_pdf/pdf_parse_by_txt_v2.py b/magic_pdf/pdf_parse_by_txt_v2.py
@@ -171,7 +171,11 @@ def parse_pdf_by_txt(
         pdf_info_dict[f"page_{page_id}"] = page_info
 
     """分段"""
-    para_split(pdf_info_dict, debug_mode=debug_mode)
+    try:
+        para_split(pdf_info_dict, debug_mode=debug_mode)
+    except Exception as e:
+        logger.exception(e)
+        raise e
 
     """dict转list"""
     pdf_info_list = dict_to_list(pdf_info_dict)