Function process_and_check_item

pageindex/page_index.py:768–835

(incorrect_item)

    incorrect_results_and_range_logs = []
    # Helper function to process and check a single incorrect item
    async def process_and_check_item(incorrect_item):
        list_index = incorrect_item['list_index']
        
        # Check if list_index is valid
        if list_index < 0 or list_index >= len(toc_with_page_number):
            # Return an invalid result for out-of-bounds indices
            return {
                'list_index': list_index,
                'title': incorrect_item['title'],
                'physical_index': incorrect_item.get('physical_index'),
                'is_valid': False
            }
        
        # Find the previous correct item
        prev_correct = None
        for i in range(list_index-1, -1, -1):
            if i not in incorrect_indices and i >= 0 and i < len(toc_with_page_number):
                physical_index = toc_with_page_number[i].get('physical_index')
                if physical_index is not None:
                    prev_correct = physical_index
                    break
        # If no previous correct item found, use start_index
        if prev_correct is None:
            prev_correct = start_index - 1
        
        # Find the next correct item
        next_correct = None
        for i in range(list_index+1, len(toc_with_page_number)):
            if i not in incorrect_indices and i >= 0 and i < len(toc_with_page_number):
                physical_index = toc_with_page_number[i].get('physical_index')
                if physical_index is not None:
                    next_correct = physical_index
                    break
        # If no next correct item found, use end_index
        if next_correct is None:
            next_correct = end_index
        
        incorrect_results_and_range_logs.append({
            'list_index': list_index,
            'title': incorrect_item['title'],
            'prev_correct': prev_correct,
            'next_correct': next_correct
        })

        page_contents=[]
        for page_index in range(prev_correct, next_correct+1):
            # Add bounds checking to prevent IndexError
            page_list_idx = page_index - start_index
            if page_list_idx >= 0 and page_list_idx < len(page_list):
                page_text = f"<physical_index_{page_index}>\n{page_list[page_list_idx][0]}\n<physical_index_{page_index}>\n\n"
                page_contents.append(page_text)
            else:
                continue
        content_range = ''.join(page_contents)
        
        physical_index_int = await single_toc_item_index_fixer(incorrect_item['title'], content_range, model)
        
        # Check if the result is correct