graph_of_words.py 文件源码

def extract_terms_from_file(file_location, stopwords=None, lemmatize=None, stem=None, only_N_J=None):
    with open(file_location, 'r', encoding='iso-8859-1') as doc:
        terms = []
        for line in doc:
            terms.extend(re.compile('\w+').findall(line.lower()))

        # terms = re.compile('\w+').findall(doc
        #                                   .read()
        #                                   .replace('\n', '')
        #                                   .lower())
        return clean_terms(terms, stopwords, lemmatize, stem, only_N_J)