Function toc_extractor

pageindex/page_index.py:222–238

(page_list, toc_page_list, model)

    return json_content['page_index_given_in_toc']

def toc_extractor(page_list, toc_page_list, model):
    def transform_dots_to_colon(text):
        text = re.sub(r'\.{5,}', ': ', text)
        # Handle dots separated by spaces
        text = re.sub(r'(?:\. ){5,}\.?', ': ', text)
        return text
    
    toc_content = ""
    for page_index in toc_page_list:
        toc_content += page_list[page_index][0]
    toc_content = transform_dots_to_colon(toc_content)
    has_page_index = detect_page_index(toc_content, model=model)
    
    return {
        "toc_content": toc_content,
        "page_index_given_in_toc": has_page_index
    }