get_words_for_CCIR.py 文件源码

def process_id(train_file_dir,train_file_name):
    # ???????????????????????????????query??????list??????????list
    # train_file_dir?????????train_file_name????????
    unable = open(os.path.join(train_file_dir, 'cannot_segment_query_id.txt'), 'r')
    lines = unable.readlines()
    unable_id = []
    for line in lines:
        a = line.replace("\n", "").split("  ")
        unable_id.append(string.atoi(a[0]))
    f = open(os.path.join(train_file_dir, train_file_name),'r')
    qaid = []
    for line in f:
        file_dict_temp = json.loads(line)
        temp_id = file_dict_temp['query_id']
        if temp_id in unable_id:
            continue
        qaid.append(temp_id)
    return qaid