import json
with open("humaneval_new.json", "r", encoding="utf-8") as f:
    data = json.load(f)
line_counts=[17,17,17,17,17,15]
line_counts_I=line_counts[0]*0.01*164
line_counts_II=line_counts[1]*0.01*164
line_counts_III=line_counts[2]*0.01*164
line_counts_IV=line_counts[3]*0.01*164
line_counts_V=line_counts[4]*0.01*164
line_counts_VI=line_counts[5]*0.01*164

token_counts=[17,17,17,17,17,15]
token_counts_I=token_counts[0]*0.01*164
token_counts_II=token_counts[1]*0.01*164
token_counts_III=token_counts[2]*0.01*164
token_counts_IV=token_counts[3]*0.01*164
token_counts_V=token_counts[4]*0.01*164
token_counts_VI=token_counts[5]*0.01*164

cyclomatic_complexity=[17,17,17,17,17,15]
cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*164
cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*164
cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*164
cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*164
cyclomatic_complexity_V=cyclomatic_complexity[4]*0.01*164
cyclomatic_complexity_VI=cyclomatic_complexity[5]*0.01*164


data.sort(key=lambda x: x['line'])
for i, item in enumerate(data):
    if i < line_counts_I:
        item['line_diff'] = 0
    elif i <line_counts_I+line_counts_II:
        item['line_diff'] = 1
    elif i <line_counts_I+line_counts_II+line_counts_III:
        item['line_diff'] = 2
    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV:
        item['line_diff'] = 3
    elif i <line_counts_I+line_counts_II+line_counts_III+line_counts_IV+line_counts_V:
        item['line_diff'] = 4
    else:
        item['line_diff'] = 5

data.sort(key=lambda x: x['token'])
for i, item in enumerate(data):
    if i < token_counts_I:
        item['token_diff'] = 0
    elif i < token_counts_I + token_counts_II:
        item['token_diff'] = 1
    elif i < token_counts_I + token_counts_II+token_counts_III:
        item['token_diff'] = 2
    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV:
        item['token_diff'] = 3
    elif i < token_counts_I + token_counts_II+token_counts_III+token_counts_IV+token_counts_V:
        item['token_diff'] = 4

    else:
        item['token_diff'] = 5

data.sort(key=lambda x: x['cyclomatic_complexity'])
for i, item in enumerate(data):
    if i < cyclomatic_complexity_I:
        item['CC_diff'] = 0
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
        item['CC_diff'] = 1
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
        item['CC_diff'] = 2
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV:
        item['CC_diff'] = 3
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III+cyclomatic_complexity_IV+cyclomatic_complexity_V:
        item['CC_diff'] = 4
    else:
        item['CC_diff'] = 5


data.sort(key=lambda x: x['id'])
# 将更新后的数据写回JSON文件
with open('QS.json', 'w', encoding='utf-8') as file:
    json.dump(data, file, ensure_ascii=False, indent=4)