Merge pull request #36 from seanpedrick-case/remove_from_single_row_select

app.py

@@ -9,7 +9,7 @@ from tools.helper_functions import put_columns_in_df, get_connection_params, rev
 from tools.aws_functions import upload_file_to_s3, download_file_from_s3, upload_log_file_to_s3
 from tools.file_redaction import choose_and_run_redactor
 from tools.file_conversion import prepare_image_or_pdf, get_input_file_names
-from tools.redaction_review import apply_redactions_to_review_df_and_files, update_all_page_annotation_object_based_on_previous_page, decrease_page, increase_page, update_annotator_object_and_filter_df, update_entities_df_recogniser_entities, update_entities_df_page, update_entities_df_text, df_select_callback, convert_df_to_xfdf, convert_xfdf_to_dataframe, reset_dropdowns, exclude_selected_items_from_redaction, undo_last_removal, update_selected_review_df_row_colour, update_all_entity_df_dropdowns, df_select_callback_cost, update_other_annotator_number_from_current, update_annotator_page_from_review_df, df_select_callback_ocr, df_select_callback_textract_api
+from tools.redaction_review import apply_redactions_to_review_df_and_files, update_all_page_annotation_object_based_on_previous_page, decrease_page, increase_page, update_annotator_object_and_filter_df, update_entities_df_recogniser_entities, update_entities_df_page, update_entities_df_text, df_select_callback_dataframe_row, convert_df_to_xfdf, convert_xfdf_to_dataframe, reset_dropdowns, exclude_selected_items_from_redaction, undo_last_removal, update_selected_review_df_row_colour, update_all_entity_df_dropdowns, df_select_callback_cost, update_other_annotator_number_from_current, update_annotator_page_from_review_df, df_select_callback_ocr, df_select_callback_textract_api, get_all_rows_with_same_text
 from tools.data_anonymise import anonymise_data_files
 from tools.auth import authenticate_user
 from tools.load_spacy_model_custom_recognisers import custom_entities
@@ -190,6 +190,14 @@ with app:
     all_line_level_ocr_results_df_placeholder = gr.Dataframe(visible=False)
     cost_code_dataframe_base = gr.Dataframe(value=pd.DataFrame(), row_count = (0, "dynamic"), label="Cost codes", type="pandas", interactive=True, show_fullscreen_button=True, show_copy_button=True, show_search='filter', wrap=True, max_height=200, visible=False)
 
+    # Placeholder for selected entity dataframe row
+    selected_entity_id = gr.Textbox(value="", label="selected_entity_id", visible=False)
+    selected_entity_colour = gr.Textbox(value="", label="selected_entity_colour", visible=False)
+    selected_entity_dataframe_row_text = gr.Textbox(value="", label="selected_entity_dataframe_row_text", visible=False)
+
+    # This is an invisible dataframe that holds all items from the redaction outputs that have the same text as the selected row
+    recogniser_entity_dataframe_same_text = gr.Dataframe(pd.DataFrame(data={"page":[], "label":[], "text":[], "id":[]}), col_count=(4,"fixed"), type="pandas", label="Click table row to select and go to page", headers=["page", "label", "text", "id"], show_fullscreen_button=True, wrap=True, max_height=400, static_columns=[0,1,2,3], visible=False)
+
     # Duplicate page detection
     in_duplicate_pages_text = gr.Textbox(label="in_duplicate_pages_text", visible=False)
     duplicate_pages_df = gr.Dataframe(value=pd.DataFrame(), headers=None, col_count=0, row_count = (0, "dynamic"), label="duplicate_pages_df", visible=False, type="pandas", wrap=True)
@@ -319,7 +327,7 @@ with app:
 
         with gr.Accordion(label = "Review PDF redactions", open=True):
             output_review_files = gr.File(label="Upload original PDF and 'review_file' csv here to review suggested redactions. The 'ocr_output' file can also be optionally provided for text search.", file_count='multiple', height=file_input_height)
-            upload_previous_review_file_btn = gr.Button("Review PDF and 'review file' csv provided above", variant="secondary")                   
+            upload_previous_review_file_btn = gr.Button("Review redactions based on original PDF and 'review_file' csv provided above ('ocr_output' csv  optional)", variant="secondary")                   
         with gr.Row():
             annotate_zoom_in = gr.Button("Zoom in", visible=False)
             annotate_zoom_out = gr.Button("Zoom out", visible=False)        
@@ -368,19 +376,20 @@ with app:
                         recogniser_entity_dropdown = gr.Dropdown(label="Redaction category", value="ALL", allow_custom_value=True)
                         page_entity_dropdown = gr.Dropdown(label="Page", value="ALL", allow_custom_value=True)                    
                     text_entity_dropdown = gr.Dropdown(label="Text", value="ALL", allow_custom_value=True)
-                    recogniser_entity_dataframe = gr.Dataframe(pd.DataFrame(data={"page":[], "label":[], "text":[], "id":[]}), col_count=(4,"fixed"), type="pandas", label="Search results. Click to go to page", headers=["page", "label", "text", "id"], show_fullscreen_button=True, wrap=True, max_height=400, static_columns=[0,1,2,3])
+                    recogniser_entity_dataframe = gr.Dataframe(pd.DataFrame(data={"page":[], "label":[], "text":[], "id":[]}), col_count=(4,"fixed"), type="pandas", label="Click table row to select and go to page", headers=["page", "label", "text", "id"], show_fullscreen_button=True, wrap=True, max_height=400, static_columns=[0,1,2,3])
+
+                    with gr.Row(equal_height=True):                        
+                        exclude_selected_btn = gr.Button(value="Exclude all redactions in table")                    
+                    
+                    with gr.Accordion("Selected redaction row", open=True):
+                        selected_entity_dataframe_row = gr.Dataframe(pd.DataFrame(data={"page":[], "label":[], "text":[], "id":[]}), col_count=4, type="pandas", visible=True, headers=["page", "label", "text", "id"], show_fullscreen_button=True, wrap=True)
+                        exclude_selected_row_btn = gr.Button(value="Exclude specific redaction row")
+                        exclude_text_with_same_as_selected_row_btn = gr.Button(value="Exclude all redactions with same text as selected row")                         
 
-                    with gr.Row(equal_height=True):
-                        exclude_selected_row_btn = gr.Button(value="Exclude specific row from redactions")
-                        exclude_selected_btn = gr.Button(value="Exclude all items in table from redactions")
                     with gr.Row(equal_height=True):
                         reset_dropdowns_btn = gr.Button(value="Reset filters")
                         
                     undo_last_removal_btn = gr.Button(value="Undo last element removal")
-                    
-                    selected_entity_dataframe_row = gr.Dataframe(pd.DataFrame(data={"page":[], "label":[], "text":[], "id":[]}), col_count=4, type="pandas", visible=False, label="selected_entity_dataframe_row", headers=["page", "label", "text", "id"], show_fullscreen_button=True, wrap=True)
-                    selected_entity_id = gr.Textbox(value="", label="selected_entity_id", visible=False)
-                    selected_entity_colour = gr.Textbox(value="", label="selected_entity_colour", visible=False)
 
                 with gr.Accordion("Search all extracted text", open=True):                    
                     all_line_level_ocr_results_df = gr.Dataframe(value=pd.DataFrame(), headers=["page", "text"], col_count=(2, 'fixed'), row_count = (0, "dynamic"),  label="All OCR results", visible=True, type="pandas", wrap=True, show_fullscreen_button=True, show_search='filter', show_label=False, show_copy_button=True, max_height=400)
@@ -478,8 +487,6 @@ with app:
                 aws_access_key_textbox = gr.Textbox(value='', label="AWS access key for account with permissions for AWS Textract and Comprehend", visible=True, type="password")
                 aws_secret_key_textbox = gr.Textbox(value='', label="AWS secret key for account with permissions for AWS Textract and Comprehend", visible=True, type="password")
 
-
-            
         with gr.Accordion("Log file outputs", open = False):
             log_files_output = gr.File(label="Log file output", interactive=False)
 
@@ -492,7 +499,7 @@ with app:
             all_output_files = gr.File(label="All files in output folder", file_count='multiple', file_types=['.csv'], interactive=False)
 
     ###
-    ### UI INTERACTION ###
+    # UI INTERACTION
     ###
 
     ###
@@ -565,7 +572,6 @@ with app:
 
     textract_job_detail_df.select(df_select_callback_textract_api, inputs=[textract_output_found_checkbox], outputs=[job_id_textbox, job_type_dropdown, selected_job_id_row])
 
-
     convert_textract_outputs_to_ocr_results.click(replace_existing_pdf_input_for_whole_document_outputs, inputs = [s3_whole_document_textract_input_subfolder, doc_file_name_no_extension_textbox, output_folder_textbox, s3_whole_document_textract_default_bucket, in_doc_files, input_folder_textbox], outputs = [in_doc_files, doc_file_name_no_extension_textbox, doc_file_name_with_extension_textbox, doc_full_file_name_textbox, doc_file_name_textbox_list, total_pdf_page_count]).\
         success(fn = prepare_image_or_pdf, inputs=[in_doc_files, text_extract_method_radio, latest_file_completed_text, redaction_output_summary_textbox, first_loop_state, annotate_max_pages, all_image_annotations_state, prepare_for_review_bool_false, in_fully_redacted_list_state, output_folder_textbox, input_folder_textbox, prepare_images_bool_false], outputs=[redaction_output_summary_textbox, prepared_pdf_state, images_pdf_state, annotate_max_pages, annotate_max_pages_bottom, pdf_doc_state, all_image_annotations_state, review_file_state, document_cropboxes, page_sizes, textract_output_found_checkbox, all_img_details_state, all_line_level_ocr_results_df_base, local_ocr_output_found_checkbox]).\
         success(fn=check_for_existing_textract_file, inputs=[doc_file_name_no_extension_textbox, output_folder_textbox], outputs=[textract_output_found_checkbox]).\
@@ -587,17 +593,34 @@ with app:
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state])
 
     # Page number controls
-    annotate_current_page.change(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+    annotate_current_page.submit(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
         success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
     
-    annotation_last_page_button.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom])
-    annotation_next_page_button.click(fn=increase_page, inputs=[annotate_current_page, all_image_annotations_state], outputs=[annotate_current_page, annotate_current_page_bottom])        
+    annotation_last_page_button.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom]).\
+        success(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
+
+    annotation_next_page_button.click(fn=increase_page, inputs=[annotate_current_page, all_image_annotations_state], outputs=[annotate_current_page, annotate_current_page_bottom]).\
+        success(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])        
+
+    annotation_last_page_button_bottom.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom]).\
+        success(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
 
-    annotation_last_page_button_bottom.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom])    
-    annotation_next_page_button_bottom.click(fn=increase_page, inputs=[annotate_current_page, all_image_annotations_state], outputs=[annotate_current_page, annotate_current_page_bottom])
+    annotation_next_page_button_bottom.click(fn=increase_page, inputs=[annotate_current_page, all_image_annotations_state], outputs=[annotate_current_page, annotate_current_page_bottom]).\
+        success(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
 
-    annotate_current_page_bottom.submit(update_other_annotator_number_from_current, inputs=[annotate_current_page_bottom], outputs=[annotate_current_page])
+    annotate_current_page_bottom.submit(update_other_annotator_number_from_current, inputs=[annotate_current_page_bottom], outputs=[annotate_current_page]).\
+        success(update_all_page_annotation_object_based_on_previous_page, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, page_sizes], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
 
     # Apply page redactions
     annotation_button_apply.click(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state], scroll_to_output=True)
@@ -613,7 +636,7 @@ with app:
     text_entity_dropdown.select(update_entities_df_text, inputs=[text_entity_dropdown, recogniser_entity_dataframe_base, recogniser_entity_dropdown, page_entity_dropdown], outputs=[recogniser_entity_dataframe, recogniser_entity_dropdown, page_entity_dropdown])
 
     # Clicking on a cell in the recogniser entity dataframe will take you to that page, and also highlight the target redaction box in blue
-    recogniser_entity_dataframe.select(df_select_callback, inputs=[recogniser_entity_dataframe], outputs=[selected_entity_dataframe_row]).\
+    recogniser_entity_dataframe.select(df_select_callback_dataframe_row, inputs=[recogniser_entity_dataframe], outputs=[selected_entity_dataframe_row, selected_entity_dataframe_row_text]).\
         success(update_selected_review_df_row_colour, inputs=[selected_entity_dataframe_row, review_file_state, selected_entity_id, selected_entity_colour], outputs=[review_file_state, selected_entity_id, selected_entity_colour]).\
         success(update_annotator_page_from_review_df, inputs=[review_file_state, images_pdf_state, page_sizes, all_image_annotations_state, annotator, selected_entity_dataframe_row, input_folder_textbox, doc_full_file_name_textbox], outputs=[annotator, all_image_annotations_state, annotate_current_page, page_sizes, review_file_state, annotate_previous_page])
    
@@ -621,25 +644,32 @@ with app:
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state])
     
     # Exclude current selection from annotator and outputs
-    # Exclude only row
+    # Exclude only selected row
     exclude_selected_row_btn.click(exclude_selected_items_from_redaction, inputs=[review_file_state, selected_entity_dataframe_row, images_pdf_state, page_sizes, all_image_annotations_state, recogniser_entity_dataframe_base], outputs=[review_file_state, all_image_annotations_state, recogniser_entity_dataframe_base, backup_review_state, backup_image_annotations_state, backup_recogniser_entity_dataframe_base]).\
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
         success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state]).\
         success(update_all_entity_df_dropdowns, inputs=[recogniser_entity_dataframe_base, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown], outputs=[recogniser_entity_dropdown, text_entity_dropdown, page_entity_dropdown])
     
+    # Exclude all items with same text as selected row
+    exclude_text_with_same_as_selected_row_btn.click(get_all_rows_with_same_text, inputs=[recogniser_entity_dataframe_base, selected_entity_dataframe_row_text], outputs=[recogniser_entity_dataframe_same_text]).\
+    success(exclude_selected_items_from_redaction, inputs=[review_file_state, recogniser_entity_dataframe_same_text, images_pdf_state, page_sizes, all_image_annotations_state, recogniser_entity_dataframe_base], outputs=[review_file_state, all_image_annotations_state, recogniser_entity_dataframe_base, backup_review_state, backup_image_annotations_state, backup_recogniser_entity_dataframe_base]).\
+        success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
+        success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state]).\
+        success(update_all_entity_df_dropdowns, inputs=[recogniser_entity_dataframe_base, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown], outputs=[recogniser_entity_dropdown, text_entity_dropdown, page_entity_dropdown])
+    
     # Exclude everything visible in table
     exclude_selected_btn.click(exclude_selected_items_from_redaction, inputs=[review_file_state, recogniser_entity_dataframe, images_pdf_state, page_sizes, all_image_annotations_state, recogniser_entity_dataframe_base], outputs=[review_file_state, all_image_annotations_state, recogniser_entity_dataframe_base, backup_review_state, backup_image_annotations_state, backup_recogniser_entity_dataframe_base]).\
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
         success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state]).\
         success(update_all_entity_df_dropdowns, inputs=[recogniser_entity_dataframe_base, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown], outputs=[recogniser_entity_dropdown, text_entity_dropdown, page_entity_dropdown])
+    
+    
 
     undo_last_removal_btn.click(undo_last_removal, inputs=[backup_review_state, backup_image_annotations_state, backup_recogniser_entity_dataframe_base], outputs=[review_file_state, all_image_annotations_state, recogniser_entity_dataframe_base]).\
         success(update_annotator_object_and_filter_df, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, page_entity_dropdown, text_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number, review_file_state, page_sizes, doc_full_file_name_textbox, input_folder_textbox], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base, text_entity_dropdown, page_entity_dropdown, page_sizes, all_image_annotations_state]).\
         success(apply_redactions_to_review_df_and_files, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, output_folder_textbox, do_not_save_pdf_state, page_sizes], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output, review_file_state])
-    
-
-    
-    # Review OCR text buttom
+        
+    # Review OCR text button
     all_line_level_ocr_results_df.select(df_select_callback_ocr, inputs=[all_line_level_ocr_results_df], outputs=[annotate_current_page, selected_entity_dataframe_row])
     reset_all_ocr_results_btn.click(reset_ocr_base_dataframe, inputs=[all_line_level_ocr_results_df_base], outputs=[all_line_level_ocr_results_df])
     

tools/redaction_review.py

@@ -1040,7 +1040,7 @@ def reset_dropdowns(df:pd.DataFrame):
 
     return recogniser_entities_drop, text_entities_drop, page_entities_drop
     
-def df_select_callback(df: pd.DataFrame, evt: gr.SelectData):
+def df_select_callback_dataframe_row(df: pd.DataFrame, evt: gr.SelectData):
 
         row_value_page = evt.row_value[0] # This is the page number value
         row_value_label = evt.row_value[1] # This is the label number value
@@ -1049,7 +1049,7 @@ def df_select_callback(df: pd.DataFrame, evt: gr.SelectData):
 
         row_value_df = pd.DataFrame(data={"page":[row_value_page], "label":[row_value_label], "text":[row_value_text], "id":[row_value_id]})
 
-        return row_value_df
+        return row_value_df, row_value_text
 
 def df_select_callback_textract_api(df: pd.DataFrame, evt: gr.SelectData):
 
@@ -1079,6 +1079,16 @@ def df_select_callback_ocr(df: pd.DataFrame, evt: gr.SelectData):
 
         return row_value_page, row_value_df
 
+def get_all_rows_with_same_text(df: pd.DataFrame, text: str):
+    '''
+    Get all rows with the same text as the selected row
+    '''
+    if text:
+        # Get all rows with the same text as the selected row
+        return df[df["text"] == text]
+    else:
+        return pd.DataFrame(columns=["page", "label", "text", "id"])
+
 def update_selected_review_df_row_colour(
     redaction_row_selection: pd.DataFrame,
     review_df: pd.DataFrame,