Update app.py

app.py

@@ -151,11 +151,10 @@ The reporting period is from {start_date.strftime('%d %B %Y')} to {end_date.strf
 The currency is South African Rand (ZAR).
 The report must contain sections for Revenue, Operating Expenses, and Net Income or Loss. Each of these sections must be a clear table.
 The Revenue section must contain a single table showing only the 'Total Revenue'. Do NOT create a table that itemizes or lists individual income sources.
-The report must also include a "Key Highlights" section with bullet points and a final comprehensive "Summary" paragraph with insights.
+The report must also include a "Key Highlights" section with bullet points and a final "Summary" paragraph.
 Use the provided JSON data for all financial figures.
 For the Net Income or Loss table, if the net position is negative, display the amount in parentheses.
-Separate the major sections with a horizontal rule. 
-Your output should just be the report, no quips.
+Separate the major sections with a horizontal rule.
 """
     try:
         st.info("Sending request to Gemini for final report formatting...")
@@ -191,7 +190,6 @@ def create_pdf_report(report_text):
         
         for element in soup.find_all(True):
             if element.name in ['h1', 'h2', 'h3']:
-                # --- BUG FIX 1: Correctly extract the number from the tag ---
                 level = int(element.name[1])
                 font_size = {1: 16, 2: 14, 3: 12}.get(level, 11)
                 pdf.set_font('helvetica', 'B', font_size)
@@ -234,8 +232,7 @@ def create_pdf_report(report_text):
                     if is_total_row:
                         pdf.set_font('helvetica', 'B', 10)
 
-                    # --- BUG FIX 2: Correctly iterate through cells and widths ---
-                    if len(row) == len(col_widths): # Ensure row has the correct number of cells
+                    if len(row) == len(col_widths):
                         pdf.cell(col_widths[0], 7, row[0], border=1)
                         pdf.cell(col_widths[1], 7, row[1], border=1, align='R')
                         pdf.ln()
@@ -294,14 +291,31 @@ def main():
 
     if st.session_state['transactions']:
         df = pd.DataFrame(st.session_state['transactions'])
+        # Clean and validate data
         df['Date'] = pd.to_datetime(df['Date'], errors='coerce', dayfirst=True)
         df.dropna(subset=['Date'], inplace=True)
+        
+        # Perform the same robust cleaning for Amount as in the aggregation function
+        if 'Amount' in df.columns:
+            df['Amount'] = df['Amount'].astype(str).str.replace(r'[^\d.]', '', regex=True)
+            df['Amount'] = pd.to_numeric(df['Amount'], errors='coerce').fillna(0)
+
         if not df.empty:
             st.session_state['min_date'] = df['Date'].min().date()
             st.session_state['max_date'] = df['Date'].max().date()
+        
         st.write("### Extracted Transactions")
         st.dataframe(df.astype(str))
 
+        # --- NEW FEATURE: Download Processed CSV Button ---
+        st.download_button(
+            label="Download Processed CSV",
+            data=df.to_csv(index=False).encode('utf-8'),
+            file_name='processed_transactions.csv',
+            mime='text/csv',
+        )
+        # --- END OF NEW FEATURE ---
+
     st.write("### Generate Financial Report")
     col1, col2 = st.columns(2)
     with col1:
@@ -314,10 +328,12 @@ def main():
         if not st.session_state['transactions']:
             st.error("No transactions available to generate report. Please upload files first.")
         else:
-            df = pd.DataFrame(st.session_state['transactions'])
-            df['Date'] = pd.to_datetime(df['Date'], errors='coerce', dayfirst=True)
-            mask = (df['Date'] >= pd.to_datetime(start_date)) & (df['Date'] <= pd.to_datetime(end_date))
-            filtered_df = df.loc[mask]
+            # Re-create dataframe from session state to ensure it's fresh for filtering
+            df_report = pd.DataFrame(st.session_state['transactions'])
+            df_report['Date'] = pd.to_datetime(df_report['Date'], errors='coerce', dayfirst=True)
+            
+            mask = (df_report['Date'] >= pd.to_datetime(start_date)) & (df_report['Date'] <= pd.to_datetime(end_date))
+            filtered_df = df_report.loc[mask]
 
             if filtered_df.empty:
                 st.warning("No transactions found within the selected date range.")