Corrected large image reduction code

app.py

@@ -371,11 +371,8 @@ with app:
     clear_all_redactions_on_page_btn.click(modify_existing_page_redactions, inputs = [annotator, annotate_current_page, annotate_previous_page, all_image_annotations_state, recogniser_entity_dropdown, recogniser_entity_dataframe_base, clear_all_page_redactions], 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])
 
-    #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]).\
@@ -392,10 +389,10 @@ with app:
         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
+    # Review table controls
     recogniser_entity_dropdown.select(update_entities_df, inputs=[recogniser_entity_dropdown, recogniser_entity_dataframe_base], outputs=[recogniser_entity_dataframe])
 
-    recogniser_entity_dataframe.select(df_select_callback, inputs=[recogniser_entity_dataframe], outputs=annotate_current_page).\
+    recogniser_entity_dataframe.select(df_select_callback, inputs=[recogniser_entity_dataframe], outputs=[annotate_current_page]).\
     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])
     

tools/file_conversion.py

@@ -1,7 +1,6 @@
 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, read_file, get_or_create_env_var
 from PIL import Image, ImageFile
-ImageFile.LOAD_TRUNCATED_IMAGES = True
 import os
 import re
 import time
@@ -16,6 +15,7 @@ from typing import List, Optional
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 image_dpi = 300.0
+ImageFile.LOAD_TRUNCATED_IMAGES = True
 Image.MAX_IMAGE_PIXELS = None
 
 def is_pdf_or_image(filename):
@@ -75,7 +75,7 @@ def process_single_page(pdf_path: str, page_num: int, image_dpi: float, output_d
             image.save(out_path, format="PNG")
 
         # Check file size and resize if necessary
-        max_size = 5 * 1024 * 1024  # 5 MB in bytes # 5
+        max_size = 4.5 * 1024 * 1024  # 5 MB in bytes # 5
         file_size = os.path.getsize(out_path)        
 
         # Resize images if they are too big
@@ -83,7 +83,7 @@ def process_single_page(pdf_path: str, page_num: int, image_dpi: float, output_d
             # Start with the original image size
             width, height = image.size
 
-            print(f"Image size before {new_width}x{new_height}, original file_size: {file_size}")
+            print(f"Image size before {width}x{height}, original file_size: {file_size}")
 
             while file_size > max_size:
                 # Reduce the size by a factor (e.g., 50% of the current size)
@@ -107,9 +107,9 @@ def process_single_page(pdf_path: str, page_num: int, image_dpi: float, output_d
         print(f"Error processing page {page_num + 1}: {e}")
         return page_num, None
 
-def convert_pdf_to_images(pdf_path: str, prepare_for_review:bool=False, page_min: int = 0, image_dpi: float = 200, num_threads: int = 8, output_dir: str = '/input'):
+def convert_pdf_to_images(pdf_path: str, prepare_for_review:bool=False, page_min: int = 0, image_dpi: float = image_dpi, num_threads: int = 8, output_dir: str = '/input'):
 
-    # If preparing for review, just load the first page
+    # If preparing for review, just load the first page (not used)
     if prepare_for_review == True:
         page_count = pdfinfo_from_path(pdf_path)['Pages'] #1
     else:

tools/redaction_review.py

@@ -15,6 +15,8 @@ from fitz import Document
 from PIL import ImageDraw, Image
 from collections import defaultdict
 
+Image.MAX_IMAGE_PIXELS = None
+
 def decrease_page(number:int):
     '''
     Decrease page number for review redactions page.