ig last commit for this app

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from PyPDF2 import PdfReader
 import random
+import re
 
 # App Title
 st.set_page_config(page_title="Procurement Guide App", page_icon="📘", layout="wide")
@@ -20,17 +21,15 @@ procurement_type = st.sidebar.selectbox(
 st.markdown("### Upload Your Procurement Document")
 uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
 
-# Glossary Section
-st.sidebar.header("Glossary")
-glossary = {
-    "Procurement": "The process of acquiring goods or services.",
-    "End-user": "The person who ultimately uses or is intended to use a product or service.",
-    "Admin": "The person responsible for overseeing and managing operations.",
-    "Procurement Officer": "The individual responsible for purchasing and managing contracts."
-}
-st.sidebar.write("Here are some key terms in procurement:")
-for term, definition in glossary.items():
-    st.sidebar.markdown(f"**{term}**: {definition}")
+# Function to extract glossary terms
+def extract_glossary(text):
+    glossary_terms = re.findall(r"\b[A-Z][a-z]+\b", text)
+    return list(set(glossary_terms))
+
+# Function to extract checklist items
+def extract_checklist(text):
+    checklist_items = re.findall(r"(\d+\.\s.*|\•\s.*)", text)
+    return checklist_items
 
 if uploaded_file is not None:
     try:
@@ -38,6 +37,10 @@ if uploaded_file is not None:
         pdf_reader = PdfReader(uploaded_file)
         pdf_text = "".join(page.extract_text() for page in pdf_reader.pages)
 
+        # Extract glossary terms and checklist items
+        glossary = extract_glossary(pdf_text)
+        checklist = extract_checklist(pdf_text)
+
         # Display selected options
         st.markdown(f"### Selected Role: `{role}`")
         st.markdown(f"### Selected Procurement Type: `{procurement_type}`")
@@ -46,41 +49,52 @@ if uploaded_file is not None:
         st.markdown("### Document Content:")
         st.text_area("PDF Content", pdf_text, height=500)
 
-        # Generate Questions and Check Answers
-        st.markdown("### Generated Questions:")
-        sentences = pdf_text.split(".")
-        if len(sentences) >= 3:
-            questions = random.sample(sentences, 3)
-            for i, question in enumerate(questions, 1):
-                st.markdown(f"**Question {i}:** {question.strip()}?")
-                user_answer = st.text_input(f"Your Answer to Question {i}:", key=f"answer_{i}")
-
-                # Check correctness if answer is provided
-                if user_answer:
-                    correct_answer = question.strip()
-                    if user_answer.lower() == correct_answer.lower():
-                        st.success(f"Correct! Your answer matches the expected answer.")
-                    else:
-                        st.error(f"Incorrect. The correct answer is: {correct_answer}")
-        else:
-            st.warning("Not enough content to generate questions.")
+        # Selection box for content to display
+        content_choice = st.selectbox("Choose what to view:", ["Questions", "Glossary", "Checklist"])
+
+        if content_choice == "Questions":
+            # Generate Questions and Check Answers
+            st.markdown("### Generated Questions:")
+            sentences = pdf_text.split(".")
+            if len(sentences) >= 3:
+                questions = random.sample(sentences, 3)
+                for i, question in enumerate(questions, 1):
+                    st.markdown(f"**Question {i}:** {question.strip()}?")
+                    user_answer = st.text_input(f"Your Answer to Question {i}:", key=f"answer_{i}")
+
+                    # Check correctness if answer is provided
+                    if user_answer:
+                        correct_answer = question.strip()
+                        if user_answer.lower() == correct_answer.lower():
+                            st.success(f"Correct! Your answer matches the expected answer.")
+                        else:
+                            st.error(f"Incorrect. The correct answer is: {correct_answer}")
+            else:
+                st.warning("Not enough content to generate questions.")
+
+        elif content_choice == "Glossary":
+            # Display Glossary
+            st.markdown("### Glossary Terms Extracted:")
+            if glossary:
+                for term in glossary:
+                    st.markdown(f"- **{term}**")
+            else:
+                st.markdown("No glossary terms found.")
+
+        elif content_choice == "Checklist":
+            # Display Checklist
+            st.markdown("### Checklist Items Extracted:")
+            if checklist:
+                for item in checklist:
+                    st.markdown(f"- {item}")
+            else:
+                st.markdown("No checklist items found.")
 
     except Exception as e:
         st.error(f"Error reading the PDF: {e}")
 else:
     st.info("Please upload a PDF file to view its content.")
 
-# Checklist Section
-st.sidebar.header("Procurement Checklist")
-checklist = [
-    "Ensure the document is signed by the authorized person",
-    "Verify that the items are properly listed and described",
-    "Check for any required legal or compliance information",
-    "Confirm payment terms and conditions"
-]
-for item in checklist:
-    st.sidebar.checkbox(item)
-
 # Footer
 st.markdown("---")
-st.markdown("© 2025 Procurement Guide App - Powered by Streamlit")
+st.markdown("© 2025 Procurement Guide App - Powered by Streamlit")