Update preprocessing.py

preprocessing.py

@@ -196,7 +196,7 @@ def read_file(file_path):
         reader = pypdf.PdfReader(file_path)
         raw_data = ""
         for idx in range(len(reader.pages)):
-            raw_data += book_preprocessing(reader.pages[idx].extract_text())
+            raw_data += reader.pages[idx].extract_text()
             if not is_meaningful(raw_data):
                 print("this text not supported")
                 raise ValueError("Unsupported file format.")