You can now have output redaction boxes in grey according to an environment variable. Review files are now saved every time page is changed.

app.py

@@ -13,7 +13,7 @@ from gradio_image_annotation.image_annotator import AnnotatedImageData
 from tools.helper_functions import ensure_output_folder_exists, add_folder_to_path, put_columns_in_df, get_connection_params, output_folder, get_or_create_env_var, reveal_feedback_buttons, custom_regex_load, reset_state_vars, load_in_default_allow_list, tesseract_ocr_option, text_ocr_option, textract_option, local_pii_detector, aws_pii_detector
 from tools.aws_functions import upload_file_to_s3, download_file_from_s3, RUN_AWS_FUNCTIONS, bucket_name
 from tools.file_redaction import choose_and_run_redactor
-from tools.file_conversion import prepare_image_or_pdf, get_input_file_names
+from tools.file_conversion import prepare_image_or_pdf, get_input_file_names, CUSTOM_BOX_COLOUR
 from tools.redaction_review import apply_redactions, modify_existing_page_redactions, decrease_page, increase_page, update_annotator, update_zoom, update_entities_df, df_select_callback
 from tools.data_anonymise import anonymise_data_files
 from tools.auth import authenticate_user
@@ -41,6 +41,8 @@ full_entity_list = ["TITLES", "PERSON", "PHONE_NUMBER", "EMAIL_ADDRESS", "STREET
 
 language = 'en'
 
+
+
 host_name = socket.gethostname()
 feedback_logs_folder = 'feedback/' + today_rev + '/' + host_name + '/'
 access_logs_folder = 'logs/' + today_rev + '/' + host_name + '/'
@@ -84,6 +86,8 @@ with app:
     log_files_output_list_state = gr.State([])
 
     review_file_state = gr.State(pd.DataFrame())
+
+    do_not_save_pdf_state = gr.State(False)
     
     # Logging state
     log_file_name = 'log.csv'
@@ -197,7 +201,7 @@ with app:
     # Object annotation
     with gr.Tab("Review redactions", id="tab_object_annotation"):
 
-        with gr.Accordion(label = "Review redaction file", open=False):
+        with gr.Accordion(label = "Review redaction file", open=True):
             output_review_files = gr.File(label="Review output files", file_count='multiple', height=file_input_height)
             upload_previous_review_file_btn = gr.Button("Review previously created redaction file (upload original PDF and ...review_file.csv)")
 
@@ -344,14 +348,18 @@ with app:
     # Page controls at top
     annotate_current_page.submit(
         modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])
     
     annotation_last_page_button.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom]).\
         then(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])    
+
     annotation_next_page_button.click(fn=increase_page, inputs=[annotate_current_page, all_image_annotations_state], outputs=[annotate_current_page, annotate_current_page_bottom]).\
         then(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])
     
     # Zoom in and out on annotator
     annotate_zoom_in.click(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
@@ -368,18 +376,23 @@ with app:
     #annotation_button_get.click(get_boxes_json, annotator, json_boxes)
     annotation_button_apply.click(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output], scroll_to_output=True)
 
+    do_not_save_pdf_state
+
     # Page controls at bottom
     annotate_current_page_bottom.submit(
         modify_existing_page_redactions, inputs = [annotator, annotate_current_page_bottom, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])
 
     annotation_last_page_button_bottom.click(fn=decrease_page, inputs=[annotate_current_page], outputs=[annotate_current_page, annotate_current_page_bottom]).\
         then(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])
     
     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]).\
         then(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs = [all_image_annotations_state, annotate_previous_page, annotate_current_page_bottom, recogniser_entity_dropdown, recogniser_entity_dataframe_base]).\
-        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base])
+        then(update_annotator, inputs=[all_image_annotations_state, annotate_current_page, recogniser_entity_dropdown, recogniser_entity_dataframe_base, annotator_zoom_number], outputs = [annotator, annotate_current_page, annotate_current_page_bottom, annotate_previous_page, recogniser_entity_dropdown, recogniser_entity_dataframe, recogniser_entity_dataframe_base]).\
+        then(apply_redactions, inputs=[annotator, doc_full_file_name_textbox, pdf_doc_state, all_image_annotations_state, annotate_current_page, review_file_state, do_not_save_pdf_state], outputs=[pdf_doc_state, all_image_annotations_state, output_review_files, log_files_output])
     
     # Review side bar controls
     recogniser_entity_dropdown.select(update_entities_df, inputs=[recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs=[recogniser_entity_dataframe])

tools/auth.py

@@ -7,13 +7,13 @@ import base64
 from tools.helper_functions import get_or_create_env_var
 
 client_id = get_or_create_env_var('AWS_CLIENT_ID', '')
-print(f'The value of AWS_CLIENT_ID is {client_id}')
+#print(f'The value of AWS_CLIENT_ID is {client_id}')
 
 client_secret = get_or_create_env_var('AWS_CLIENT_SECRET', '')
-print(f'The value of AWS_CLIENT_SECRET is {client_secret}')
+#print(f'The value of AWS_CLIENT_SECRET is {client_secret}')
 
 user_pool_id = get_or_create_env_var('AWS_USER_POOL_ID', '')
-print(f'The value of AWS_USER_POOL_ID is {user_pool_id}')
+#print(f'The value of AWS_USER_POOL_ID is {user_pool_id}')
 
 def calculate_secret_hash(client_id, client_secret, username):
     message = username + client_id

tools/file_conversion.py

@@ -1,5 +1,5 @@
 from pdf2image import convert_from_path, pdfinfo_from_path
-from tools.helper_functions import get_file_path_end, output_folder, tesseract_ocr_option, text_ocr_option, textract_option, local_pii_detector, aws_pii_detector, read_file
+from tools.helper_functions import get_file_path_end, output_folder, tesseract_ocr_option, text_ocr_option, textract_option, read_file, get_or_create_env_var
 from PIL import Image, ImageFile
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 import os
@@ -48,7 +48,8 @@ def is_pdf(filename):
 # %%
 ## Convert pdf to image if necessary
 
-
+CUSTOM_BOX_COLOUR = get_or_create_env_var("CUSTOM_BOX_COLOUR", "")
+print(f'The value of CUSTOM_BOX_COLOUR is {CUSTOM_BOX_COLOUR}')
 
 def process_single_page(pdf_path: str, page_num: int, image_dpi: float, output_dir: str = 'input') -> tuple[int, str]:
     try:
@@ -261,7 +262,10 @@ def redact_single_box(pymupdf_page:Page, pymupdf_rect:Rect, img_annotation_box:d
         else:
             out_colour = img_annotation_box["color"]
     else:
-        out_colour = (0,0,0)
+        if CUSTOM_BOX_COLOUR == "grey":
+            out_colour = (0.5, 0.5, 0.5)        
+        else:
+            out_colour = (0,0,0)
 
     shape.finish(color=out_colour, fill=out_colour)  # Black fill for the rectangle
     #shape.finish(color=(0, 0, 0))  # Black fill for the rectangle

tools/redaction_review.py

@@ -55,12 +55,6 @@ def update_annotator(image_annotator_object:AnnotatedImageData, page_num:int, re
     '''
     recogniser_entities = []
     recogniser_dataframe = pd.DataFrame()
-    #recogniser_entities_drop = gr.Dropdown(value="ALL", allow_custom_value=True)
-    #recogniser_dataframe_gr = gr.Dataframe(pd.DataFrame(data={"page":[""], "label":[""]}))
-
-    #print("recogniser_dataframe_gr", recogniser_dataframe_gr)
-    #print("recogniser_dataframe_gr shape", recogniser_dataframe_gr.shape)
-    #print("recogniser_dataframe_gr.iloc[0,0]:",  recogniser_dataframe_gr.iloc[0,0])
 
     if recogniser_dataframe_gr.iloc[0,0] == "":
         try:
@@ -228,7 +222,7 @@ def modify_existing_page_redactions(image_annotated:AnnotatedImageData, current_
 
     return all_image_annotations, current_page, current_page, recogniser_entities_drop, recogniser_dataframe_out
 
-def apply_redactions(image_annotated:AnnotatedImageData, file_paths:List[str], doc:Document, all_image_annotations:List[AnnotatedImageData], current_page:int, review_file_state, progress=gr.Progress(track_tqdm=True)):
+def apply_redactions(image_annotated:AnnotatedImageData, file_paths:List[str], doc:Document, all_image_annotations:List[AnnotatedImageData], current_page:int, review_file_state, save_pdf:bool=True, progress=gr.Progress(track_tqdm=True)):
     '''
     Apply modified redactions to a pymupdf and export review files
     '''
@@ -251,75 +245,76 @@ def apply_redactions(image_annotated:AnnotatedImageData, file_paths:List[str], d
         file_paths = [file_paths]
 
     for file_path in file_paths:
-        print("file_path:", file_path)
+        #print("file_path:", file_path)
         file_base = get_file_path_end(file_path)
 
         file_extension = os.path.splitext(file_path)[1].lower()
         
-        # If working with image docs
-        if (is_pdf(file_path) == False) & (file_extension not in '.csv'):
-            image = Image.open(file_paths[-1])
+        if save_pdf == True:
+            # If working with image docs
+            if (is_pdf(file_path) == False) & (file_extension not in '.csv'):
+                image = Image.open(file_paths[-1])
 
-            #image = pdf_doc
+                #image = pdf_doc
 
-            draw = ImageDraw.Draw(image)
+                draw = ImageDraw.Draw(image)
 
-            for img_annotation_box in image_annotated['boxes']:
-                coords = [img_annotation_box["xmin"],
-                img_annotation_box["ymin"],
-                img_annotation_box["xmax"],
-                img_annotation_box["ymax"]]
+                for img_annotation_box in image_annotated['boxes']:
+                    coords = [img_annotation_box["xmin"],
+                    img_annotation_box["ymin"],
+                    img_annotation_box["xmax"],
+                    img_annotation_box["ymax"]]
 
-                fill = img_annotation_box["color"]
+                    fill = img_annotation_box["color"]
 
-                draw.rectangle(coords, fill=fill)
+                    draw.rectangle(coords, fill=fill)
 
-                image.save(output_folder + file_base + "_redacted.png")
+                    image.save(output_folder + file_base + "_redacted.png")
 
-            doc = [image]
+                doc = [image]
 
-        elif file_extension in '.csv':
-            print("This is a csv")
-            pdf_doc = []
+            elif file_extension in '.csv':
+                print("This is a csv")
+                pdf_doc = []
 
-        # If working with pdfs
-        elif is_pdf(file_path) == True:
-            pdf_doc = pymupdf.open(file_path)
+            # If working with pdfs
+            elif is_pdf(file_path) == True:
+                pdf_doc = pymupdf.open(file_path)
 
-            number_of_pages = pdf_doc.page_count
+                number_of_pages = pdf_doc.page_count
 
-            print("Saving pages to file.")
+                print("Saving pages to file.")
 
-            for i in progress.tqdm(range(0, number_of_pages), desc="Saving redactions to file", unit = "pages"):
+                for i in progress.tqdm(range(0, number_of_pages), desc="Saving redactions to file", unit = "pages"):
 
-                #print("Saving page", str(i))
-                
-                image_loc = all_image_annotations[i]['image']
-                #print("Image location:", image_loc)
+                    #print("Saving page", str(i))
+                    
+                    image_loc = all_image_annotations[i]['image']
+                    #print("Image location:", image_loc)
 
-                # Load in image object
-                if isinstance(image_loc, np.ndarray):
-                    image = Image.fromarray(image_loc.astype('uint8'))
-                    #all_image_annotations[i]['image'] = image_loc.tolist()
-                elif isinstance(image_loc, Image.Image):
-                    image = image_loc
-                    #image_out_folder = output_folder + file_base + "_page_" + str(i) + ".png"
-                    #image_loc.save(image_out_folder)
-                    #all_image_annotations[i]['image'] = image_out_folder
-                elif isinstance(image_loc, str):
-                    image = Image.open(image_loc)
+                    # Load in image object
+                    if isinstance(image_loc, np.ndarray):
+                        image = Image.fromarray(image_loc.astype('uint8'))
+                        #all_image_annotations[i]['image'] = image_loc.tolist()
+                    elif isinstance(image_loc, Image.Image):
+                        image = image_loc
+                        #image_out_folder = output_folder + file_base + "_page_" + str(i) + ".png"
+                        #image_loc.save(image_out_folder)
+                        #all_image_annotations[i]['image'] = image_out_folder
+                    elif isinstance(image_loc, str):
+                        image = Image.open(image_loc)
 
-                pymupdf_page = pdf_doc.load_page(i) #doc.load_page(current_page -1)
-                pymupdf_page = redact_page_with_pymupdf(pymupdf_page, all_image_annotations[i], image)
+                    pymupdf_page = pdf_doc.load_page(i) #doc.load_page(current_page -1)
+                    pymupdf_page = redact_page_with_pymupdf(pymupdf_page, all_image_annotations[i], image)
 
-        else:
-            print("File type not recognised.")
-                
-        #try:
-        if pdf_doc:
-            out_pdf_file_path = output_folder + file_base + "_redacted.pdf"
-            pdf_doc.save(out_pdf_file_path)
-            output_files.append(out_pdf_file_path)
+            else:
+                print("File type not recognised.")
+                    
+            #try:
+            if pdf_doc:
+                out_pdf_file_path = output_folder + file_base + "_redacted.pdf"
+                pdf_doc.save(out_pdf_file_path)
+                output_files.append(out_pdf_file_path)
 
         try:
             print("Saving annotations to JSON")
@@ -331,7 +326,7 @@ def apply_redactions(image_annotated:AnnotatedImageData, file_paths:List[str], d
 
             print("Saving annotations to CSV review file")
 
-            print("review_file_state:", review_file_state)
+            #print("review_file_state:", review_file_state)
 
             # Convert json to csv and also save this
             review_df = convert_review_json_to_pandas_df(all_image_annotations, review_file_state)