Update app.py

app.py

@@ -1,92 +1,112 @@
 import gradio as gr
-from PyPDF2 import PdfReader
+import fitz  # PyMuPDF
+import docx
+import io
+import re
+from sklearn.feature_extraction.text import TfidfVectorizer
 from sentence_transformers import SentenceTransformer, util
 import matplotlib.pyplot as plt
-import pandas as pd
 import numpy as np
-from io import BytesIO
-from tempfile import NamedTemporaryFile
+from difflib import SequenceMatcher
 
-model = SentenceTransformer("all-MiniLM-L6-v2")
+model = SentenceTransformer('all-MiniLM-L6-v2')
 
-def extract_text_from_pdf(pdf_bytes):
+def extract_text_from_pdf(pdf_file):
     try:
-        reader = PdfReader(BytesIO(pdf_bytes))
-        return "\n".join([page.extract_text() or "" for page in reader.pages])
-    except Exception:
+        pdf_reader = fitz.open(stream=pdf_file, filetype="pdf")
+        text = ""
+        for page in pdf_reader:
+            text += page.get_text()
+        pdf_reader.close()
+        return text.strip()
+    except Exception as e:
         return ""
 
-def semantic_match(lo_texts, content):
+def normalize_text(text):
+    return re.sub(r'\s+', ' ', text.strip().lower())
+
+def extract_text_from_docx(file_binary):
+    try:
+        doc = docx.Document(io.BytesIO(file_binary))
+        return [para.text.strip() for para in doc.paragraphs if para.text.strip()]
+    except Exception as e:
+        return []
+
+def semantic_match(lo_list, content):
     scores = []
-    for lo in lo_texts:
-        emb1 = model.encode(lo, convert_to_tensor=True)
-        emb2 = model.encode(content, convert_to_tensor=True)
-        score = util.pytorch_cos_sim(emb1, emb2).item()
-        scores.append(score)
+    for lo in lo_list:
+        try:
+            lo_embed = model.encode(lo, convert_to_tensor=True)
+            content_embed = model.encode(content, convert_to_tensor=True)
+            sim = util.pytorch_cos_sim(lo_embed, content_embed).item()
+            scores.append(round(sim, 2))
+        except:
+            scores.append(0.0)
     return scores
 
+def content_change_score(text1, text2):
+    try:
+        sim = SequenceMatcher(None, normalize_text(text1), normalize_text(text2)).ratio()
+        return round((1 - sim) * 100, 2)
+    except:
+        return 100.0
+
 def compare_handouts(old_pdf, new_pdf, lo_file):
     old_text = extract_text_from_pdf(old_pdf)
     new_text = extract_text_from_pdf(new_pdf)
 
-    if not old_text.strip() or not new_text.strip():
-        return "❌ Could not extract text from one or both PDFs.", None, None
+    if len(old_text.strip()) < 200 or len(new_text.strip()) < 200:
+        return "⚠️ Could not extract meaningful content from one or both PDFs.", None
 
-    lo_doc = lo_file.decode("utf-8")
-    lo_list = [line.strip() for line in lo_doc.splitlines() if line.strip()]
+    lo_list = extract_text_from_docx(lo_file)
+    if not lo_list:
+        return "⚠️ No learning outcomes detected in .docx file.", None
 
     old_scores = semantic_match(lo_list, old_text)
     new_scores = semantic_match(lo_list, new_text)
 
-    improvement = np.array(new_scores) - np.array(old_scores)
-    df = pd.DataFrame({
-        "Learning Outcome": lo_list,
-        "Old Match Score": old_scores,
-        "New Match Score": new_scores,
-        "Improvement": improvement
-    })
+    change_percent = content_change_score(old_text, new_text)
+    improved_count = sum([n > o for n, o in zip(new_scores, old_scores)])
+    matched_los = sum([n >= o for n, o in zip(new_scores, old_scores)])
+
+    summary = f"📈 Content Change Estimate: {change_percent}%\n"
+    summary += f"🧠 LO Alignment: {matched_los} of {len(lo_list)} learning outcomes matched\n"
+    if improved_count > 0:
+        summary += "🟢 Summary: New handout has improved structure and added clarity."
+    else:
+        summary += "⚠️ Summary: No significant improvement in LO alignment."
 
-    fig, ax = plt.subplots(figsize=(10, 4))
     x = np.arange(len(lo_list))
-    ax.bar(x - 0.2, old_scores, width=0.4, label="Old")
-    ax.bar(x + 0.2, new_scores, width=0.4, label="New")
+    width = 0.35
+    fig, ax = plt.subplots()
+    ax.bar(x - width/2, old_scores, width, label='Old')
+    ax.bar(x + width/2, new_scores, width, label='New')
+    ax.set_ylabel('Match Score (0-1)')
+    ax.set_title('LO-wise Match Score: Old vs New')
     ax.set_xticks(x)
-    ax.set_xticklabels([f"LO{i+1}" for i in range(len(lo_list))])
-    ax.set_ylim(0, 1)
-    ax.set_ylabel("Semantic Similarity")
-    ax.set_title("LO Match Comparison")
+    ax.set_xticklabels([f"LO{i+1}" for i in range(len(lo_list))], rotation=45)
     ax.legend()
     plt.tight_layout()
 
-    content_change = (1 - (util.pytorch_cos_sim(model.encode(old_text, convert_to_tensor=True),
-                                                model.encode(new_text, convert_to_tensor=True)).item())) * 100
-    matched = sum(1 for o, n in zip(old_scores, new_scores) if n >= 0.6)
-    summary = f"📈 Content Change Estimate: {content_change:.2f}%\n"
-    summary += f"🧠 LO Alignment: {matched} of {len(lo_list)} learning outcomes matched\n"
-    summary += "🟢 Summary: New handout has improved structure and added clarity."
-
-    # Save to a temporary file
-    temp_file = NamedTemporaryFile(delete=False, suffix=".xlsx")
-    excel_path = Path(temp_file.name)
-    df.to_excel(excel_path, index=False)
-
-    return summary, fig, excel_path
-
-iface = gr.Interface(
-    fn=compare_handouts,
-    inputs=[
-        gr.File(label="📄 Upload OLD Handout PDF", type="binary"),
-        gr.File(label="📄 Upload NEW Handout PDF", type="binary"),
-        gr.File(label="📄 Upload Learning Outcomes (TXT)", type="binary")
-    ],
-    outputs=[
-        gr.Textbox(label="📋 Summary & Insights"),
-        gr.Plot(label="📊 Learning Outcome Match Chart"),
-        gr.File(label="📥 Download Excel Report")
-    ],
-    title="📚 Handout Comparator with LO Analysis",
-    description="Upload old & new handouts + a list of learning outcomes to get content change %, alignment, and a downloadable report."
-)
-
-if __name__ == "__main__":
-    iface.launch()
+    return summary, fig
+
+with gr.Blocks() as demo:
+    gr.Markdown("📘 **Educational Content Comparator**")
+    gr.Markdown("Upload 2 handouts and a .docx file of Learning Outcomes to compare changes and alignment.")
+
+    with gr.Row():
+        old_pdf = gr.File(label="📂 Upload Old PDF", file_types=[".pdf"], type="binary")
+        new_pdf = gr.File(label="📂 Upload New PDF", file_types=[".pdf"], type="binary")
+        lo_file = gr.File(label="📂 Upload Learning Outcomes (.docx)", file_types=[".docx"], type="binary")
+
+    with gr.Row():
+        btn = gr.Button("Submit")
+        clear_btn = gr.Button("Clear")
+
+    output_text = gr.Textbox(label="📋 Summary", lines=5, interactive=False)
+    output_plot = gr.Plot(label="📊 LO Match Chart")
+
+    btn.click(fn=compare_handouts, inputs=[old_pdf, new_pdf, lo_file], outputs=[output_text, output_plot])
+    clear_btn.click(fn=lambda: ("", None), inputs=[], outputs=[output_text, output_plot])
+
+demo.launch()