get_indices.py 文件源码

def get_word(word):
    inst = re.search(r"_\(([A-Za-z0-9_]+)\)", word)

    if inst == None:
        length = len(word.split("_"))
        if length < 5:
            return True, word
    else:
        if inst.group(1) != "disambiguation":
            word2 = re.sub(r'_\(.+\)','',word)
            if len(word2.split(" ")) <5:
                return True, word

    return False,word

# Load the trained doc2vec and word2vec models.