Update app.py

app.py

@@ -1,6 +1,6 @@
 
 import gradio as gr
-import fitz
+from PyPDF2 import PdfReader
 from sentence_transformers import SentenceTransformer, util
 import matplotlib.pyplot as plt
 import pandas as pd
@@ -10,11 +10,13 @@ model = SentenceTransformer("all-MiniLM-L6-v2")
 
 def extract_text_pdf(file_obj):
     try:
-        with fitz.open(stream=file_obj, filetype="pdf") as doc:
-            text = ""
-            for page in doc:
-                text += page.get_text()
-            return text if text.strip() else None
+        pdf_reader = PdfReader(file_obj)
+        text = ""
+        for page in pdf_reader.pages:
+            extracted = page.extract_text()
+            if extracted:
+                text += extracted + "\n"
+        return text if text.strip() else None
     except:
         return None
 
@@ -51,7 +53,11 @@ def compare_all(old_pdf, new_pdf, lo_file):
         summary += "🆕 Significant changes detected."
 
     # LO comparison
-    los = lo_file.read().decode("utf-8").splitlines()
+    los = lo_file.read().decode("utf-8", errors="ignore").splitlines()
+    los = [lo.strip() for lo in los if lo.strip()]
+    if not los:
+        return summary + "\n⚠️ No valid Learning Outcomes found.", None, None
+
     old_scores = compare_with_los(old_text, los)
     new_scores = compare_with_los(new_text, los)
     score_diff = [round(new - old, 2) for old, new in zip(old_scores, new_scores)]
@@ -92,8 +98,8 @@ iface = gr.Interface(
         gr.Plot(label="LO-wise Bar Chart"),
         gr.HTML(label="LO-wise Comparison Table")
     ],
-    title="📘 Semantic Handout Comparator with LO Alignment",
-    description="Compare course handouts for overall change and LO alignment using transformer models."
+    title="📘 Semantic Handout Comparator with LO Alignment (Fixed)",
+    description="Compare course handouts and learning outcomes using robust PDF reading and transformers."
 )
 
 iface.launch()