Update app.py

app.py

@@ -6,7 +6,6 @@ import fitz  # PyMuPDF
 import docx
 import matplotlib.pyplot as plt
 import pandas as pd
-import tempfile
 
 def extract_text_from_pdf(file):
     text = ""
@@ -20,8 +19,7 @@ def extract_text_from_pdf(file):
 
 def extract_text_from_docx(file):
     doc = docx.Document(file)
-    return "
-".join([para.text for para in doc.paragraphs])
+    return "\n".join([para.text for para in doc.paragraphs])
 
 def semantic_match(lo_texts, content):
     vectorizer = TfidfVectorizer().fit_transform([content] + lo_texts)
@@ -40,8 +38,7 @@ def compare_handouts(old_pdf, new_pdf, lo_file):
 
     # Extract Learning Outcomes
     lo_text = extract_text_from_docx(lo_file)
-    lo_list = [line.strip() for line in lo_text.split("
-") if line.strip()]
+    lo_list = [line.strip() for line in lo_text.split("\n") if line.strip()]
     if not lo_list:
         return "No learning outcomes detected.", None, None