data_dictionary_shared.py 文件源码

def extract(text, paper=None, logger=logger):

    search_any = functools.partial(re_util.search_any, logger=logger)
    if not text and paper:
        try:
            text, _ = paper.get_text()
        except pdfutil.pdfutil.MalformedPDF as e:
            return None
    filters = [r'data documentation.*?shared']
    for sentence in nltk.sent_tokenize(text):
        match = search_any(filters, sentence)
        if match:
            source_type = "extracted"
            source_detail = "nltk search v1"
            value_text = sentence
            value_result = "Yes"
            return (value_text, value_result, source_type, source_detail)
    #if no match found:
    source_type = "extracted"
    source_detail = "nltk search v1"
    value_text = "Not Found"
    value_result = "No"
    return (value_text, value_result, source_type, source_detail)