Improved testing code

invoice-extractor/donut_cord/base_cord_v2.py

@@ -102,19 +102,19 @@ def is_pdf(data):
 
 # Testing block
 if __name__ == "__main__":
-    #pdf_file_path = "/content/ex_sa_inv.pdf"  # Replace with your PDF file path
-    image_file_path = "C:/Users/aksha/Desktop/temp_index/indexify-extractors/invoice-extractor/donut_cord/ex_inv_th.png"  # Replace with your image file path
+    pdf_file_path = "/content/sa_inv_lst.pdf"  # Replace with your PDF file path
+    image_file_path = "/content/ex_sa_inv.jpg"  # Replace with your image file path
 
     extractor = DonutBaseV2()
 
-    # with open(pdf_file_path, "rb") as file:
-    #     pdf_data = file.read()
-    #     pdf_content = Content(data=pdf_data)
-    #     pdf_results = extractor.extract([pdf_content], SimpleInvoiceParserInputParams())
-    #     print("PDF Extraction Results:", pdf_results)
+    with open(pdf_file_path, "rb") as file:
+        pdf_data = file.read()
+        pdf_content = Content(data=pdf_data)
+        pdf_results = extractor.extract([pdf_content], SimpleInvoiceParserInputParams())
+        print("PDF Extraction Results:", pdf_results)
 
     with open(image_file_path, "rb") as file:
         image_data = file.read()
-        image_content = Content(data=image_data, content_type='image/png')  # Include content_type here
+        image_content = Content(data=image_data) 
         image_results = extractor.extract([image_content], SimpleInvoiceParserInputParams())
         print("Image Extraction Results:", image_results)