121 lines
4.7 KiB
Python
121 lines
4.7 KiB
Python
import os,re,json
|
|
|
|
"""---设置关键字, 同一field下不同选项为or关系, 同一字典中不同字段间为and关系, 不同字典间为or关系, _not表示列表中的关键字都不含, 同一字典中的数字用来供应同一字段不同的条件之间的and---"""
|
|
keywords_dict_table = [
|
|
{
|
|
"id":[""], #题号
|
|
"content":[""], #题面内容
|
|
"objs":[""], #目标代码
|
|
"tags":[""], #标签, 如["第二单元"]等
|
|
"genre":[""], #题目类型, 填空题, 选择题, 解答题
|
|
"ans":[""], #答案
|
|
"solution":[""], #解答与提示
|
|
"duration":[""], #解题时间(目前未设置)
|
|
"usages":[""], #使用记录, 数据库中格式为 <日期>\t<届别><班别>\t正确率[\t正确率]... 例如"20230301\t2023届01班\t0.985\t0.211
|
|
"origin":["高二下学期期末"], #题目来源
|
|
"edit":[""], #导入者及编辑者
|
|
"same":[""], #相同题目题号
|
|
"related":[""], #关联题目题号
|
|
"remark":[""], #备注, 注记
|
|
"space":[""], #解答题下的空间(em)表示一个m的宽度
|
|
"unrelated":[""], #无关题目题号
|
|
# "content2":["双曲线"], #在字段名中加入数字表示这个字段的另一个必要条件
|
|
# "content_not":["焦"], #加_not表示不能出现该样式的词
|
|
"content_not":["OBSOLETE"], #这一项不要更改, 是排除错构题目的标志
|
|
|
|
},
|
|
]
|
|
"""---关键字设置完毕---"""
|
|
# 示例： keywords_dict_table = [
|
|
# {"tags": ["第三单元"], "content1": [r"[\d]\alpha","2x"], "content2": ["sin"], "content3": ["cos"],"content4": ["cot"], "content5": ["tan"]},
|
|
# ]
|
|
# 实例2: keywords_dict_table = [
|
|
# {"tags":["第三单元"],"content":["f\(","y=","函数"],"usages":[r"0\.9",r"0\.8[3-9]"],"usages_not":[r"0\.[0-7]",r"0\.8[0-2]"],"usages1":["2023届"]},
|
|
# {"tags":["第五单元"],"usages":[r"0\.9"],"usages_not":[r"0\.[0-7]",r"0\.8[0-2]"],"usages1":["2023届"]}
|
|
# ]
|
|
# 实例3:
|
|
# keywords_dict_table = [
|
|
# {"usages":[r"2023届高三02班"],"usages2":[r"202209",r"20221[012]"],"usages3":[r"0\.[678][\d]{2}"],"usages_not":[r"2023届高三02班[^\n]*0\.[0-59][\d]{2}"]}
|
|
|
|
# ]
|
|
|
|
|
|
"""---设置输出文件名---"""
|
|
filename = "文本文件/题号筛选.txt"
|
|
"""---文件名设置完毕---"""
|
|
|
|
|
|
def match_condition(problem,condition_dict):
|
|
match = True
|
|
for field1 in [c for c in condition_dict if not "_not" in c and not condition_dict[c] == [""]]:
|
|
cond_list = condition_dict[field1]
|
|
field = re.sub("\d","",field1)
|
|
if type(problem[field]) == list:
|
|
string = "\n".join((problem[field]))
|
|
else:
|
|
string = str(problem[field])
|
|
current_match = False
|
|
for cond in cond_list:
|
|
if len(re.findall(cond,string)) > 0:
|
|
current_match = True
|
|
if current_match == False:
|
|
match = False
|
|
for field1 in [c for c in condition_dict if "_not" in c and not condition_dict[c] == [""]]:
|
|
cond_list = condition_dict[field1]
|
|
field1 = field1.replace("_not","")
|
|
field = re.sub("\d","",field1)
|
|
if type(problem[field]) == list:
|
|
string = "\n".join((problem[field]))
|
|
else:
|
|
string = str(problem[field])
|
|
current_match = True
|
|
for cond in cond_list:
|
|
if len(re.findall(cond,string)) > 0:
|
|
current_match = False
|
|
if current_match == False:
|
|
match = False
|
|
|
|
return match
|
|
|
|
def generate_exp(id_list):
|
|
if not len(id_list) == 0:
|
|
exp_list = []
|
|
start = id_list[0]
|
|
current = start
|
|
end = start
|
|
for id in id_list[1:]:
|
|
# print(id,current)
|
|
if int(id)-1 == int(current):
|
|
current = id
|
|
end = id
|
|
else:
|
|
if not start == end:
|
|
exp_list.append('"'+start+":"+end+'"')
|
|
else:
|
|
exp_list.append('"'+start+'"')
|
|
start = id
|
|
current = id
|
|
end = id
|
|
if not start == end:
|
|
exp_list.append('"'+start+":"+end+'"')
|
|
else:
|
|
exp_list.append('"'+start+'"')
|
|
return exp_list
|
|
|
|
#读取题库json文件并转化为字典
|
|
with open(r"../题库0.3/Problems.json","r",encoding = "utf8") as f:
|
|
database = f.read()
|
|
pro_dict = json.loads(database)
|
|
|
|
match_list = []
|
|
for condition in keywords_dict_table:
|
|
for id in pro_dict:
|
|
if match_condition(pro_dict[id],condition) and not id in match_list:
|
|
match_list.append(id)
|
|
|
|
match_list_exp = generate_exp(match_list)
|
|
|
|
with open(filename,"w",encoding="utf8") as f:
|
|
f.write((",".join(match_list_exp)).replace('"',''))
|
|
|
|
os.system("code "+filename) |