spelling_checker.py 文件源码

def get_valid_bigram_words(self, words):
        _words = []
        for i in nltk.bigrams(words):
            if (len(i[0]) >= self.min_len) and (len(i[1]) >= self.min_len):
                if (not self.exclude_stopwords) or ((i[0] not in config.STOP_WORDS) and (i[1] not in config.STOP_WORDS)):
                    if (not self.skip_digit) or ((len(re.findall(re.compile("\d+"), i[0])) == 0) and (len(re.findall(re.compile("\d+"), i[1])) == 0)):
                        _words.append(" ".join(i))
        return _words