Upload app.py

app.py

@@ -121,6 +121,9 @@ def load_and_validate_excel(file_contents_list, file_names_list, keywords_hash):
     if dedup_cols:
         combined_df = combined_df.drop_duplicates(subset=dedup_cols, keep='first')
 
+    # Reset index to ensure sequential indices after deduplication
+    combined_df = combined_df.reset_index(drop=True)
+
     dedup_count = original_count - len(combined_df)
     return combined_df, original_count, dedup_count
 
@@ -345,43 +348,44 @@ with tab1:
                     )
                 ]
 
-            st.write(f"**Showing {len(filtered_df)} of {len(df)} entries**")
+            st.write(f"**{len(filtered_df)} of {len(df)} entries after filters**")
 
-            # Display filtered data
             if len(filtered_df) > 0:
-                # Show key columns
-                display_cols = ["Entry Number", "Description", "Tariff",
-                               "Primary 1", "Primary 2", "Primary 3",
-                               "Primary 4", "Primary 5", "Primary 6"]
-                display_cols = [c for c in display_cols if c in filtered_df.columns]
-
-                st.dataframe(
-                    filtered_df[display_cols].head(100),
-                    use_container_width=True
+                # Manual validation button
+                file_names_key = ",".join(sorted(file_names))
+
+                # Check if validation already done for these files
+                validation_done = (
+                    "cached_full_results" in st.session_state and
+                    st.session_state.get("cached_file_names") == file_names_key
                 )
 
-                if len(filtered_df) > 100:
-                    st.info("Showing first 100 rows.")
+                if validation_done:
+                    # Filter cached results based on current filters
+                    full_results_df = st.session_state.cached_full_results
+                    filtered_indices = filtered_df.index.tolist()
+                    filtered_results_df = full_results_df.iloc[filtered_indices].copy()
 
-                # Run validation ONCE on full dataset (cached), then filter results
-                file_names_key = ",".join(sorted(file_names))
-                if "cached_full_results" not in st.session_state or st.session_state.get("cached_file_namess") != file_names_key:
-                    with st.spinner("Validating all entries (one-time)..."):
-                        validator = get_validator()
-                        full_results = validate_dataframe(df, validator)
-                        full_results_df = results_to_dataframe(full_results)
-                        st.session_state.cached_full_results = full_results_df
-                        st.session_state.cached_file_namess = file_names_key
-
-                # Filter cached results based on current filters
-                full_results_df = st.session_state.cached_full_results
-                filtered_indices = filtered_df.index.tolist()
-                filtered_results_df = full_results_df.iloc[filtered_indices].copy()
-
-                st.session_state.validation_results = filtered_results_df
-                st.session_state.filtered_df = filtered_df
-
-                st.success(f"Showing {len(filtered_df)} entries. Go to 'Validation Results' tab to review.")
+                    st.session_state.validation_results = filtered_results_df
+                    st.session_state.filtered_df = filtered_df
+
+                    st.success(f"Validated {len(filtered_df)} entries. Go to 'Validation Results' tab to review.")
+                else:
+                    st.session_state.filtered_df = filtered_df
+
+                    if st.button("Validate", type="primary"):
+                        with st.spinner("Validating all entries..."):
+                            validator = get_validator()
+                            full_results = validate_dataframe(df, validator)
+                            full_results_df = results_to_dataframe(full_results)
+                            st.session_state.cached_full_results = full_results_df
+                            st.session_state.cached_file_names = file_names_key
+
+                            filtered_indices = filtered_df.index.tolist()
+                            filtered_results_df = full_results_df.iloc[filtered_indices].copy()
+                            st.session_state.validation_results = filtered_results_df
+
+                            st.rerun()
 
         except Exception as e:
             st.error(f"Error loading file: {str(e)}")