Update app.py

app.py

@@ -99,6 +99,8 @@ def load_css():
         padding: 0.8rem;
         margin: 0.5rem 0;
         border-left: 1px solid #e0e0e0;
+        font-family: 'Courier New', monospace;
+        font-size: 1rem;
     }
     
     .rendered-citation {
@@ -106,22 +108,30 @@ def load_css():
         font-size: 1.4rem;
     }
     
-    .citations-table {
+    .citation-table {
         margin: 1rem 0;
         width: 100%;
         border-collapse: collapse;
     }
     
-    .citations-table th, .citations-table td {
+    .citation-table th, .citation-table td {
         border: 1px solid #e0e0e0;
         padding: 0.5rem;
         text-align: left;
     }
     
-    .citations-table th {
+    .citation-table th {
         background: #f8f8f8;
         font-weight: bold;
     }
+    
+    .citation-table th:nth-child(7), .citation-table td:nth-child(7) { /* Annotated Text column */
+        width: 30%; /* Match SCC Index width */
+    }
+    
+    .citation-table th:nth-child(6), .citation-table td:nth-child(6) { /* SCC Index column */
+        width: 30%;
+    }
     </style>
     """, unsafe_allow_html=True)
 
@@ -163,6 +173,13 @@ def format_citation_html(url, fragment_text, author, year, scc_hash):
     full_url = f"{url}#:~:text={encoded_fragment}"
     return f'<a href="{full_url}" data-hash="{scc_hash}">{author} ({year})</a>'
 
+def format_citation_end_html(url, fragment_text, author, year, scc_hash):
+    # Select the longest segment for the text fragment to avoid breaking the link
+    selected_fragment = select_longest_segment(fragment_text)
+    encoded_fragment = encode_text_fragment(selected_fragment)
+    full_url = f"{url}#:~:text={encoded_fragment}"
+    return f'<a href="{full_url}" data-hash="{scc_hash}">({author}, {year})</a>'
+
 def format_metadata_html(url, author, year, scc_hash, username, task_name, current_date, current_time):
     # Use original task_name with em dashes for text fragment URL
     metadata = f"{username}—{task_name}—{current_date}—{current_time}"
@@ -233,7 +250,7 @@ def get_excel_download_link(df, filename="citation_data.xlsx"):
 
         for col_idx, col in enumerate(headers):
             value = row[col]
-            if col in ["Citation", "SCC Index"]:
+            if col in ["Citation (Start of Text)", "Citation (End of Text)", "SCC Index"]:
                 # Extract URL and display text from HTML anchor tag
                 match = re.search(r'<a href="([^"]+)"[^>]*>([^<]+)</a>', str(value))
                 if match:
@@ -261,39 +278,6 @@ def get_excel_download_link(df, filename="citation_data.xlsx"):
     href = f'<a href="data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{b64}" download="{filename}">Download citation data as Excel</a>'
     return href
 
-# --- Live Clock JavaScript ---
-def live_clock():
-    return """
-    <div class="datetime-display">
-        <span id="live_datetime"></span>
-    </div>
-    <script>
-        function updateClock() {
-            const options = {
-                timeZone: 'Australia/Melbourne',
-                year: 'numeric',
-                month: '2-digit',
-                day: '2-digit',
-                hour: '2-digit',
-                minute: '2-digit',
-                second: '2-digit',
-                hour12: false
-            };
-            const formatter = new Intl.DateTimeFormat('en-AU', options);
-            const now = new Date();
-            const parts = formatter.formatToParts(now);
-            const date = `${parts[4].value}-${parts[2].value}-${parts[0].value}`;
-            const time = `${parts[6].value}:${parts[8].value}:${parts[10].value}`;
-            const datetimeElement = document.getElementById('live_datetime');
-            if (datetimeElement) {
-                datetimeElement.innerText = `${date} ${time}`;
-            }
-        }
-        updateClock();
-        setInterval(updateClock, 1000);
-    </script>
-    """
-
 # --- Streamlit App ---
 st.set_page_config(layout="wide", page_title="Smart Context Citation Tool")
 
@@ -360,7 +344,7 @@ with st.expander("SCC Style Guidelines"):
                     <li><strong>Author(s) Name:</strong> The author(s) of the source (e.g., Abuseif et al.).</li>
                     <li><strong>Publication Year:</strong> The year of publication (e.g., 2023).</li>
                     <li><strong>Source URL:</strong> The full URL of the source, without text fragments (e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046).</li>
-                    <li><strong>Annotated Text:</strong> The sentence or paragraph containing the information you are referencing from the source (e.g., A proposed design framework for green roof settings in general and trees on buildings in particular).</li>
+                    <li><strong>Annotated Text:</strong> The sentence or paragraph containing the information you are referencing from the source (e.g., A proposed design framework for green roof settings in general and trees on buildings in particular). Limited to 100 words to ensure reasonable processing.</li>
                 </ul>
             </li>
             <li><strong>Generate Citation:</strong> Click the &quot;Generate Citation&quot; button.</li>
@@ -377,228 +361,355 @@ with st.expander("SCC Style Guidelines"):
         <ol>
             <li>Paste the reference directly in the appropriate place within your document.</li>
             <li>Create an SCC Index (instead of a traditional reference list), and paste the corresponding SCC Index entry for each reference you’ve used.</li>
+            <li>You can download the citation table to facilitate reference tracking for your study and research. You may also submit it as an appendix with your work.</li>
         </ol>
         <h4>Verifying Citations (for Markers and Reviewers)</h4>
         <ol>
-            <li><strong>Access the Tool:</strong> Open the &quot;Verify Citation&quot; tab.</li>
-            <li><strong>Enter Citation Information:</strong>
-                <ul>
-                    <li><strong>Citation Text:</strong> Paste the citation text (e.g., Abuseif et al. (2023) or (Abuseif et al., 2023)).</li>
-                    <li><strong>Citation URL:</strong> Paste the hyperlink URL from the citation (right-click and select &quot;Copy Link Address&quot;).</li>
-                </ul>
-            </li>
-            <li><strong>Enter SCC Index Information:</strong>
+            <li><strong>Access the Tool:</strong> Open the &quot;Verify Citation&quot; tab, which provides two options for verification: Manual Verification or Excel Upload Verification (automated using the citation table).</li>
+            <li><strong>Manual Verification:</strong>
                 <ul>
-                    <li><strong>SCC Index Text:</strong> Paste the index text (e.g., Abuseif et al. (2023). cda7ba19e51e430107e58696758fdf79b8f016d8f27e8f8691ad713e7c8bc668).</li>
-                    <li><strong>SCC Index URL:</strong> Paste the hyperlink URL from the index (right-click and select &quot;Copy Link Address&quot;).</li>
+                    <li><strong>Enter Citation Information:</strong>
+                        <ul>
+                            <li><strong>Citation Text:</strong> Paste the citation text (e.g., Abuseif et al. (2023) or (Abuseif et al., 2023)).</li>
+                            <li><strong>Citation URL:</strong> Paste the hyperlink URL from the citation (right-click and select &quot;Copy Link Address&quot;).</li>
+                        </ul>
+                    </li>
+                    <li><strong>Enter SCC Index Information:</strong>
+                        <ul>
+                            <li><strong>SCC Index Text:</strong> Paste the index text (e.g., Abuseif et al. (2023). cda7ba19e51e430107e58696758fdf79b8f016d8f27e8f8691ad713e7c8bc668).</li>
+                            <li><strong>SCC Index URL:</strong> Paste the hyperlink URL from the index (right-click and select &quot;Copy Link Address&quot;).</li>
+                        </ul>
+                    </li>
+                    <li><strong>Verify Citation:</strong> Click the &quot;Verify Citation&quot; button in the Manual Verification tab.</li>
+                    <li><strong>Review Result:</strong>
+                        <ul>
+                            <li><strong>Authentic Citation:</strong> Displayed in green if the hash matches, confirming integrity.</li>
+                            <li><strong>Unauthentic Citation:</strong> Displayed in red if the hash does not match, indicating potential tampering.</li>
+                        </ul>
+                    </li>
                 </ul>
             </li>
-            <li><strong>Verify Citation:</strong> Click the &quot;Verify Citation&quot; button.</li>
-            <li><strong>Review Result:</strong>
+            <li><strong>Automated Verification Using Citation Table:</strong>
                 <ul>
-                    <li><strong>Authentic Citation:</strong> Displayed in green if the hash matches, confirming integrity.</li>
-                    <li><strong>Unauthentic Citation:</strong> Displayed in red if the hash does not match, indicating potential tampering.</li>
+                    <li><strong>Upload Excel File:</strong> In the Excel Upload Verification tab, upload the Excel file generated from the Citation Generator tab.</li>
+                    <li><strong>Verify Citations:</strong> Click the &quot;Verify Citations from Excel&quot; button.</li>
+                    <li><strong>Review Results:</strong> View the verification results in a table, with each citation marked as:
+                        <ul>
+                            <li><strong>Authenticated:</strong> If the hash matches, confirming integrity.</li>
+                            <li><strong>Unauthenticated:</strong> If the hash does not match, indicating potential issues.</li>
+                        </ul>
+                    </li>
                 </ul>
             </li>
         </ol>
     </div>
     """, unsafe_allow_html=True)
 
+# Tabs for Citation Generator and Verify Citation
 tabs = st.tabs(["Citation Generator", "Verify Citation"])
 
+# --- Citation Generator Tab ---
 with tabs[0]:
     st.markdown('<div class="tab-content">', unsafe_allow_html=True)
-
-    # User Information Section
+    
+    # User Information
     st.subheader("User Information")
-    col1, col2 = st.columns(2)
-    with col1:
-        username = st.text_input("Username", help="Your username for tracking purposes", placeholder="e.g., Majed")
-    with col2:
-        task_name = st.text_input("Task Name", help="The name of the task or project", placeholder="e.g., Design Strategies for Trees on Buildings")
-
-    # Citation Info Section
-    st.subheader("Citation Info")
-    col3, col4 = st.columns(2)
-    with col3:
-        author_name = st.text_input("Author(s) Name", help="The author(s) of the source", placeholder="e.g., Abuseif et al.")
-    with col4:
-        publication_year = st.text_input("Publication Year", help="The year of publication", placeholder="e.g., 2023")
+    col_user1, col_user2 = st.columns(2)
+    with col_user1:
+        username = st.text_input("Username", help="Enter your username", placeholder="e.g., Majed")
+    with col_user2:
+        task_name = st.text_input("Task Name", help="Enter the project or assignment name", placeholder="e.g., Design Strategies for Trees on Buildings")
     
-    col5, col6 = st.columns(2)
-    with col5:
-        source_url = st.text_input("Source URL", help="The full URL of the source", placeholder="https://www.sciencedirect.com/science/article/pii/S2772411523000046")
-    with col6:
-        annotated_text = st.text_input("Annotated Text", help="The sentence or paragraph containing the information you are referencing from the source", placeholder="e.g., A proposed design framework for green roof settings...")
-
-    # Live date and time display
-    st.markdown("### Current Date and Time (AEST)")
-    st.components.v1.html(live_clock(), height=50)
-
-    # Get current date and time in Melbourne timezone for hash generation
-    melbourne_tz = pytz.timezone(MELBOURNE_TIMEZONE)
-    current_datetime_melbourne = datetime.now(melbourne_tz)
-    current_date = current_datetime_melbourne.strftime("%Y-%m-%d")
-    current_time = current_datetime_melbourne.strftime("%H:%M:%S")
-
+    # Citation Information
+    st.subheader("Citation Information")
+    col_citation1, col_citation2 = st.columns(2)
+    with col_citation1:
+        author_name = st.text_input("Author(s) Name", help="Enter the author(s) name", placeholder="e.g., Abuseif et al.")
+        publication_year = st.text_input("Publication Year", help="Enter the publication year", placeholder="e.g., 2023")
+        source_url = st.text_input("Source URL", help="Enter the full URL of the source (without text fragments)", placeholder="e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046")
+    with col_citation2:
+        annotated_text = st.text_area("Annotated Text", help="Enter the sentence or paragraph containing the referenced information (maximum 100 words)", placeholder="e.g., A proposed design framework for green roof settings...", height=150)
+    
+    # Generate Citation Button
     generate_button = st.button("Generate Citation", type="primary", use_container_width=True)
-
+    
     if generate_button:
+        # Validate inputs
         if not all([username, task_name, author_name, publication_year, source_url, annotated_text]):
             st.error("Please fill in all fields before generating a citation.")
+        elif not re.match(r'https?://[^\s]+', source_url):
+            st.error("Please enter a valid URL starting with http:// or https://")
+        elif not re.match(r'^\d{4}$', publication_year):
+            st.error("Please enter a valid 4-digit publication year.")
         elif check_for_fragment(source_url):
-            st.markdown("""
-            <div class="warning-box">
-                <strong>Warning:</strong> Your URL already contains a text fragment, which suggests you may have used AI assistance in your research. Please revisit the source, review the context carefully, and copy the source link again—ensuring it does not include any existing fragments.
-            </div>
-            """, unsafe_allow_html=True)
+            st.error("The source URL should not contain a text fragment (e.g., #:~:text=).")
         else:
-            # Generate hash using normalized inputs
-            scc_hash = generate_citation_hash(author_name, publication_year, source_url, annotated_text, annotated_text, username, task_name, current_date, current_time)
-            citation_link_start = format_citation_html(source_url, annotated_text, author_name, publication_year, scc_hash)
-            # Use the longest segment for the end-of-text citation link
-            selected_fragment = select_longest_segment(annotated_text)
-            citation_link_end = f'<a href="{source_url}#:~:text={encode_text_fragment(selected_fragment)}" data-hash="{scc_hash}">({author_name}, {publication_year})</a>'
-            metadata_link = format_metadata_html(source_url, author_name, publication_year, scc_hash, username, task_name, current_date, current_time)
-
-            # --- Persistent Table with Clickable SCC Hash ---
-
-            # First, ensure session state is initialized for the citation DataFrame
-            if 'citation_df' not in st.session_state:
-                st.session_state.citation_df = pd.DataFrame(columns=[
-                    "Username", "Task Name", "Time", "Date",
-                    "Citation", "SCC Index", "Annotated Text"
-                ])
-    
-            # Create clickable HTML for SCC Index (full metadata link)
-            clickable_index = metadata_link
-    
-            # Create new row data
-            new_row = {
-                "Username": username,
-                "Task Name": task_name,
-                "Time": current_time,
-                "Date": current_date,
-                "Citation": citation_link_start,
-                "SCC Index": clickable_index,
-                "Annotated Text": annotated_text
-            }
-    
-            # Append the new row to the session state DataFrame
-            new_df = pd.DataFrame([new_row])
-            st.session_state.citation_df = pd.concat([st.session_state.citation_df, new_df], ignore_index=True)
-    
-            # Get the accumulated DataFrame for display and download
-            df = st.session_state.citation_df
-    
-            col_html1, col_html2 = st.columns(2)
-    
-            # HTML Citation - Start of Text
-            with col_html1:
-                st.markdown("### Citation (Start of Text)")
-                st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
-                st.markdown(citation_link_start, unsafe_allow_html=True)
-                st.markdown('</div>', unsafe_allow_html=True)
-    
-            # HTML Citation - End of Text
-            with col_html2:
-                st.markdown("### Citation (End of Text)")
-                st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
-                st.markdown(citation_link_end, unsafe_allow_html=True)
-                st.markdown('</div>', unsafe_allow_html=True)
-    
-            # SCC Index
-            st.markdown("### SCC Index")
-            st.markdown(metadata_link, unsafe_allow_html=True)
-    
-            # Display table after SCC Index
-            st.markdown("### Citations Table")
-            st.markdown(get_excel_download_link(df), unsafe_allow_html=True, help="New feature to help you track your citations data. Please make sure to click on the 'Enable Editing' message at the top of the file when you open it in Excel to be able to click and copy the hyperlinked citations correctly.")
-            st.markdown(df.to_html(classes="citations-table", index=False, escape=False), unsafe_allow_html=True)
-    
-        st.markdown('</div>', unsafe_allow_html=True)
-
+            # Check word count for Annotated Text
+            word_count = len(annotated_text.split())
+            if word_count > 100:
+                st.error("Annotated Text exceeds the maximum limit of 100 words. Please reduce the text.")
+            else:
+                # Get current date and time in Melbourne timezone
+                melbourne_tz = pytz.timezone(MELBOURNE_TIMEZONE)
+                current_time = datetime.now(melbourne_tz).strftime("%H:%M:%S")
+                current_date = datetime.now(melbourne_tz).strftime("%Y-%m-%d")
+                
+                # Generate citation hash
+                scc_hash = generate_citation_hash(
+                    author_name, publication_year, source_url, annotated_text, annotated_text,
+                    username, task_name, current_date, current_time
+                )
+                
+                # Generate HTML citations
+                citation_link_start = format_citation_html(source_url, annotated_text, author_name, publication_year, scc_hash)
+                citation_link_end = format_citation_end_html(source_url, annotated_text, author_name, publication_year, scc_hash)
+                metadata_link = format_metadata_html(source_url, author_name, publication_year, scc_hash, username, task_name, current_date, current_time)
+                
+                # --- Persistent Table with Clickable SCC Hash ---
+                
+                # First, ensure session state is initialized for the citation DataFrame
+                if 'citation_df' not in st.session_state:
+                    st.session_state.citation_df = pd.DataFrame(columns=[
+                        "Username", "Task Name", "Time", "Date", "URL",
+                        "Citation (Start of Text)", "Citation (End of Text)", "SCC Index", "Annotated Text"
+                    ])
+                
+                # Create clickable HTML for SCC Index (full metadata link)
+                clickable_index = metadata_link
+                
+                # Create new row data
+                new_row = {
+                    "Username": username,
+                    "Task Name": task_name,
+                    "Time": current_time,
+                    "Date": current_date,
+                    "URL": source_url,
+                    "Citation (Start of Text)": citation_link_start,
+                    "Citation (End of Text)": citation_link_end,
+                    "SCC Index": clickable_index,
+                    "Annotated Text": annotated_text
+                }
+                
+                # Append the new row to the session state DataFrame
+                new_df = pd.DataFrame([new_row])
+                st.session_state.citation_df = pd.concat([st.session_state.citation_df, new_df], ignore_index=True)
+                
+                # Get the accumulated DataFrame for display and download
+                df = st.session_state.citation_df
+                
+                col_html1, col_html2 = st.columns(2)
+                
+                # HTML Citation - Start of Text
+                with col_html1:
+                    st.markdown("### Citation (Start of Text)")
+                    st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
+                    st.markdown(citation_link_start, unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                
+                # HTML Citation - End of Text
+                with col_html2:
+                    st.markdown("### Citation (End of Text)")
+                    st.markdown('<div class="rendered-citation">', unsafe_allow_html=True)
+                    st.markdown(citation_link_end, unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                
+                # SCC Index
+                st.markdown("### SCC Index")
+                st.markdown(metadata_link, unsafe_allow_html=True)
+                
+                # Display table after SCC Index
+                st.markdown("### Citation Table")
+                st.markdown(get_excel_download_link(df, "citation_data.xlsx"), unsafe_allow_html=True, help="New feature to help you track your citations data. Please make sure to click on the 'Enable Editing' message at the top of the file when you open it in Excel to be able to click and copy the hyperlinked citations correctly.")
+                # Display table with original columns
+                display_df = df[["Username", "Task Name", "Time", "Date", "Citation (Start of Text)", "SCC Index", "Annotated Text"]]
+                st.markdown(display_df.to_html(classes="citation-table", index=False, escape=False), unsafe_allow_html=True)
+            
+            st.markdown('</div>', unsafe_allow_html=True)
+
+# --- Verify Citation Tab ---
 with tabs[1]:
     st.markdown('<div class="tab-content">', unsafe_allow_html=True)
-    st.subheader("Citation Information")
-    citation_text = st.text_input("Citation Text", help="Paste the citation text, e.g., 'Abuseif et al. (2023)' or '(Abuseif et al., 2023)'", placeholder="e.g., Abuseif et al. (2023)")
-    citation_url = st.text_input("Citation URL", help="Paste the hyperlink URL from the citation, e.g., 'https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=fragment'", placeholder="e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=fragment")
-
-    st.subheader("SCC Index")
-    hash_text = st.text_input("SCC Index Text", help="Paste the index text, e.g., 'Abuseif et al. (2023). <hash>'", placeholder="e.g., Abuseif et al. (2023). <hash>")
-    hash_url = st.text_input("SCC Index URL", help="Paste the hyperlink URL from the index, e.g., 'https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=metadata'", placeholder="e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=metadata")
-
-    verify_button = st.button("Verify Citation", type="primary", use_container_width=True)
-
-    if verify_button:
-        if not all([citation_text, citation_url, hash_text, hash_url]):
-            st.error("Please provide all fields (citation text, citation URL, SCC index text, SCC index URL) before verifying.")
-        else:
-            # Parse citation text
-            author, year = parse_citation_text(citation_text)
-            # Parse citation URL
-            citation_base_url, citation_fragment = parse_url(citation_url)
-            # Parse hash text
-            scc_hash = parse_hash_text(hash_text)
-            # Parse hash URL
-            hash_base_url, hash_fragment = parse_url(hash_url)
-            # Parse metadata from hash URL fragment
-            username, task_name, date, time = parse_metadata(hash_fragment)
+    verify_tabs = st.tabs(["Manual Verification", "Excel Upload Verification"])
     
-            if not all([author, year, citation_base_url, citation_fragment, scc_hash, hash_base_url, username, task_name, date, time]):
-                st.error("Invalid input format. Ensure the citation text, URLs, and SCC index text are correctly pasted from the generated output.")
-            elif citation_base_url != hash_base_url:
-                st.error("The citation URL and SCC index URL must point to the same base URL.")
+    with verify_tabs[0]:
+        st.subheader("Citation Information")
+        citation_text = st.text_input("Citation Text", help="Paste the citation text, e.g., 'Abuseif et al. (2023)' or '(Abuseif et al., 2023)'", placeholder="e.g., Abuseif et al. (2023)", key="manual_citation_text")
+        citation_url = st.text_input("Citation URL", help="Paste the hyperlink URL from the citation, e.g., 'https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=fragment'", placeholder="e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=fragment", key="manual_citation_url")
+        
+        st.subheader("SCC Index")
+        hash_text = st.text_input("SCC Index Text", help="Paste the index text, e.g., 'Abuseif et al. (2023). <hash>'", placeholder="e.g., Abuseif et al. (2023). <hash>", key="manual_hash_text")
+        hash_url = st.text_input("SCC Index URL", help="Paste the hyperlink URL from the index, e.g., 'https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=metadata'", placeholder="e.g., https://www.sciencedirect.com/science/article/pii/S2772411523000046#:~:text=metadata", key="manual_hash_url")
+        
+        verify_button = st.button("Verify Citation", type="primary", use_container_width=True, key="manual_verify_button")
+        
+        if verify_button:
+            if not all([citation_text, citation_url, hash_text, hash_url]):
+                st.error("Please provide all fields (citation text, citation URL, SCC index text, SCC index URL) before verifying.")
             else:
-                # Normalize inputs by stripping whitespace
-                citation_fragment = citation_fragment.strip()
-                task_name = task_name.strip()
-                # Check for potential truncation
-                if len(citation_fragment) < 20:
-                    st.markdown("""
-                    <div class="warning-box">
-                        <strong>Warning:</strong> The citation text fragment may be truncated, which could cause verification to fail.
-                    </div>
-                    """, unsafe_allow_html=True)
-                selected_citation_fragment = select_longest_segment(citation_fragment)
-                # Recompute hash
-                recomputed_hash = generate_citation_hash(
-                    author, year, citation_base_url, selected_citation_fragment, selected_citation_fragment, username, task_name, date, time
-                )
-    
-                if recomputed_hash == scc_hash:
-                    st.markdown("""
-                    <div class="success-box">
-                        <strong>Authentic citation!</strong>
-                    </div>
-                    """, unsafe_allow_html=True)
-                    
-                    # Create DataFrame for citation details
-                    citation_data = {
-                        "Username": [username],
-                        "Task Name": [task_name],
-                        "Time": [time],
-                        "Date": [date],
-                        "URL": [citation_base_url],
-                        "Author(s) Name": [author],
-                        "Year": [year],
-                        "Annotated Text": [citation_fragment]
-                    }
-                    df = pd.DataFrame(citation_data)
-                    
-                    # Display table
-                    st.markdown("### Citations Details")
-                    st.markdown(df.to_html(classes="citations-table", index=False), unsafe_allow_html=True)
-                    
-                    # Provide download link
-                    st.markdown(get_table_download_link(df), unsafe_allow_html=True)
+                # Parse citation text
+                author, year = parse_citation_text(citation_text)
+                # Parse citation URL
+                citation_base_url, citation_fragment = parse_url(citation_url)
+                # Parse hash text
+                scc_hash = parse_hash_text(hash_text)
+                # Parse hash URL
+                hash_base_url, hash_fragment = parse_url(hash_url)
+                # Parse metadata from hash URL fragment
+                username, task_name, date, time = parse_metadata(hash_fragment)
+                
+                if not all([author, year, citation_base_url, citation_fragment, scc_hash, hash_base_url, username, task_name, date, time]):
+                    st.error("Invalid input format. Ensure the citation text, URLs, and SCC index text are correctly pasted from the generated output.")
+                elif citation_base_url != hash_base_url:
+                    st.error("The citation URL and SCC index URL must point to the same base URL.")
                 else:
-                    st.markdown("""
-                    <div class="warning-box">
-                        <strong>Unauthentic citation</strong>
-                    </div>
-                    """, unsafe_allow_html=True)
-
+                    # Normalize inputs by stripping whitespace
+                    citation_fragment = citation_fragment.strip()
+                    task_name = task_name.strip()
+                    # Check for potential truncation
+                    if len(citation_fragment) < 20:
+                        st.markdown("""
+                        <div class="warning-box">
+                            <strong>Warning:</strong> The citation text fragment may be truncated, which could cause verification to fail.
+                        </div>
+                        """, unsafe_allow_html=True)
+                    selected_citation_fragment = select_longest_segment(citation_fragment)
+                    # Recompute hash
+                    recomputed_hash = generate_citation_hash(
+                        author, year, citation_base_url, selected_citation_fragment, selected_citation_fragment,
+                        username, task_name, date, time
+                    )
+                    
+                    if recomputed_hash == scc_hash:
+                        st.markdown("""
+                        <div class="success-box">
+                            <strong>Authentic citation!</strong>
+                        </div>
+                        """, unsafe_allow_html=True)
+                            
+                        # Create DataFrame for citation details
+                        citation_data = {
+                            "Username": [username],
+                            "Task Name": [task_name],
+                            "Time": [time],
+                            "Date": [date],
+                            "URL": [citation_base_url],
+                            "Author(s) Name": [author],
+                            "Year": [year],
+                            "Annotated Text": [citation_fragment]
+                        }
+                        df = pd.DataFrame(citation_data)
+                            
+                        # Display table
+                        st.markdown("### Citations Details")
+                        st.markdown(df.to_html(classes="citations-table", index=False), unsafe_allow_html=True)
+                            
+                        # Provide download link
+                        st.markdown(get_table_download_link(df), unsafe_allow_html=True)
+                    else:
+                        st.markdown("""
+                        <div class="warning-box">
+                            <strong>Unauthentic citation</strong>
+                        </div>
+                        """, unsafe_allow_html=True)
+    
+    with verify_tabs[1]:
+        st.subheader("Upload Excel File")
+        uploaded_file = st.file_uploader("Choose an Excel file", type=["xlsx"], help="Upload the Excel file containing citation data (generated from the Citation Generator tab).")
+        
+        verify_excel_button = st.button("Verify Citations from Excel", type="primary", use_container_width=True, key="excel_verify_button")
+        
+        if verify_excel_button:
+            if not uploaded_file:
+                st.error("Please upload an Excel file before verifying.")
+            else:
+                try:
+                    # Read Excel file with pandas
+                    df = pd.read_excel(uploaded_file)
+                    expected_columns = ["Username", "Task Name", "Time", "Date", "URL", "Citation (Start of Text)", "Citation (End of Text)", "SCC Index", "Annotated Text"]
+                    if not all(col in df.columns for col in expected_columns):
+                        st.error("The uploaded Excel file does not contain the required columns: " + ", ".join(expected_columns))
+                    else:
+                        results = []
+                        # Iterate over rows with data
+                        for row_idx in range(len(df)):
+                            row = df.iloc[row_idx]
+                            # Extract text data directly
+                            username = str(row["Username"]) if pd.notna(row["Username"]) else ""
+                            task_name = str(row["Task Name"]) if pd.notna(row["Task Name"]) else ""
+                            time = str(row["Time"]) if pd.notna(row["Time"]) else ""
+                            date = str(row["Date"]) if pd.notna(row["Date"]) else ""
+                            base_url = str(row["URL"]) if pd.notna(row["URL"]) else ""
+                            annotated_text = str(row["Annotated Text"]) if pd.notna(row["Annotated Text"]) else ""
+                            citation_start_text = str(row["Citation (Start of Text)"]) if pd.notna(row["Citation (Start of Text)"]) else ""
+                            citation_end_text = str(row["Citation (End of Text)"]) if pd.notna(row["Citation (End of Text)"]) else ""
+                            hash_text = str(row["SCC Index"]) if pd.notna(row["SCC Index"]) else ""
+                            
+                            # Initialize variables for verification
+                            status = "Unauthenticated"
+                            author = year = scc_hash = None
+                            
+                            # Perform verification using either Citation (Start of Text) or Citation (End of Text)
+                            citation_text = citation_start_text or citation_end_text
+                            
+                            if all([citation_text, hash_text, base_url, annotated_text, username, task_name, date, time]):
+                                # Parse citation text for author and year
+                                author, year = parse_citation_text(citation_text)
+                                # Parse hash from SCC Index text
+                                scc_hash = parse_hash_text(hash_text)
+                                
+                                if all([author, year, scc_hash]):
+                                    # Use Annotated Text as citation fragment
+                                    citation_fragment = annotated_text.strip()
+                                    # Check for potential truncation
+                                    if len(citation_fragment) < 20:
+                                        st.markdown("""
+                                        <div class="warning-box">
+                                            <strong>Warning:</strong> The citation text fragment in row {} may be truncated, which could cause verification to fail.
+                                        </div>
+                                        """.format(row_idx + 2), unsafe_allow_html=True)
+                                    selected_citation_fragment = select_longest_segment(citation_fragment)
+                                    # Recompute hash using text data
+                                    recomputed_hash = generate_citation_hash(
+                                        author, year, base_url, selected_citation_fragment, selected_citation_fragment,
+                                        username, task_name, date, time
+                                    )
+                                    if recomputed_hash == scc_hash:
+                                        status = "Authenticated"
+                            
+                            # Store result for this row
+                            results.append({
+                                "Username": username,
+                                "Task Name": task_name,
+                                "Time": time,
+                                "Date": date,
+                                "URL": base_url if base_url else "N/A",
+                                "Author(s) Name": author if author else "N/A",
+                                "Year": year if year else "N/A",
+                                "Annotated Text": annotated_text,
+                                "Status": status
+                            })
+                        
+                        # Create results DataFrame
+                        results_df = pd.DataFrame(results)
+                        
+                        # Display results
+                        st.markdown("### Citation Verification Results")
+                        st.markdown(results_df.to_html(classes="citations-table", index=False), unsafe_allow_html=True)
+                        st.markdown(get_table_download_link(results_df, "verified_citation_data.csv"), unsafe_allow_html=True)
+                        
+                        # Display success message
+                        if results:
+                            st.markdown("""
+                            <div class="success-box">
+                                <strong>Citations processed successfully!</strong>
+                            </div>
+                            """, unsafe_allow_html=True)
+                        else:
+                            st.error("No valid data found in the Excel file.")
+                
+                except Exception as e:
+                    st.error(f"Error processing Excel file: {str(e)}")
+    
     st.markdown('</div>', unsafe_allow_html=True)
 
 # Footer