Function process_none_page_numbers

pageindex/page_index.py:656–691

(toc_items, page_list, start_index=1, model=None)

##check if needed to process none page numbers
def process_none_page_numbers(toc_items, page_list, start_index=1, model=None):
    for i, item in enumerate(toc_items):
        if "physical_index" not in item:
            # logger.info(f"fix item: {item}")
            # Find previous physical_index
            prev_physical_index = 0  # Default if no previous item exists
            for j in range(i - 1, -1, -1):
                if toc_items[j].get('physical_index') is not None:
                    prev_physical_index = toc_items[j]['physical_index']
                    break
            
            # Find next physical_index
            next_physical_index = -1  # Default if no next item exists
            for j in range(i + 1, len(toc_items)):
                if toc_items[j].get('physical_index') is not None:
                    next_physical_index = toc_items[j]['physical_index']
                    break

            page_contents = []
            for page_index in range(prev_physical_index, next_physical_index+1):
                # Add bounds checking to prevent IndexError
                list_index = page_index - start_index
                if list_index >= 0 and list_index < len(page_list):
                    page_text = f"<physical_index_{page_index}>\n{page_list[list_index][0]}\n<physical_index_{page_index}>\n\n"
                    page_contents.append(page_text)
                else:
                    continue

            item_copy = copy.deepcopy(item)
            del item_copy['page']
            result = add_page_number_to_toc(page_contents, item_copy, model)
            if isinstance(result[0]['physical_index'], str) and result[0]['physical_index'].startswith('<physical_index'):
                item['physical_index'] = int(result[0]['physical_index'].split('_')[-1].rstrip('>').strip())
                del item['page']
    
    return toc_items