exam-segment-django/segment/ocr/split_topic_en.py

inf_words_dict = dict()
with open("./segment/ocr/type_config.txt", "r", encoding="utf-8") as f:
    for i, line in enumerate(f):
        if line.startswith("#"):
            continue
        line = line.strip().replace("：", ":").replace("，", ",")
        key, val = line.split(":")
        key = key.strip()
        val = val.split(",")
        val = tuple(v.strip() for v in val)
        inf_words_dict[val] = key

# 答案冒号 = "答案:"
# 解析冒号 = "解析:"


def could_skip_line(line):
    '''对于答案和解析行，不进行type_inf'''
    return line.startswith("答案:") or line.startswith("解析:")


def contains_all(s, words):
    return all([w in s for w in words])


def topic_type_line(line):
    if could_skip_line(line):
        return False
    for key, val in inf_words_dict.items():
        if contains_all(line, key):
            return True
    return False