fix(end_page_id):Fix the issue where end_page_id is corrected to len-1 when its input is 0. (#518)

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -111,7 +111,8 @@ def doc_analyze(pdf_bytes: bytes, ocr: bool = False, show_log: bool = False,
 
     images = load_images_from_pdf(pdf_bytes)
 
-    end_page_id = end_page_id if end_page_id else len(images) - 1
+    # end_page_id = end_page_id if end_page_id else len(images) - 1
+    end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(images) - 1
 
     if end_page_id > len(images) - 1:
         logger.warning("end_page_id is out of range, use images length")

magic_pdf/pdf_parse_union_core.py

@@ -225,7 +225,8 @@ def pdf_parse_union(pdf_bytes,
     magic_model = MagicModel(model_list, pdf_docs)
 
     '''根据输入的起始范围解析pdf'''
-    end_page_id = end_page_id if end_page_id else len(pdf_docs) - 1
+    # end_page_id = end_page_id if end_page_id else len(pdf_docs) - 1
+    end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(pdf_docs) - 1
 
     if end_page_id > len(pdf_docs) - 1:
         logger.warning("end_page_id is out of range, use pdf_docs length")