This repository has been archived on 2024-06-23. You can view files and clone it, but cannot push or open issues or pull requests.
mathdeptv2/工具/全局未标注相同题目检测.py

102 lines
2.9 KiB
Python

import os,re,difflib,Levenshtein,time,json
# 相同题目的阈值
threshold = 0.99
outputfile = r"临时文件/相同题目列表.txt"
#生成数码列表, 逗号分隔每个区块, 区块内部用:表示整数闭区间
def generate_number_set(string):
string = re.sub(r"[\n\s]","",string)
string_list = string.split(",")
numbers_list = []
for s in string_list:
if not ":" in s:
numbers_list.append(s.zfill(6))
else:
start,end = s.split(":")
for ind in range(int(start),int(end)+1):
numbers_list.append(str(ind).zfill(6))
return numbers_list
#字符串预处理
def pre_treating(string):
string = re.sub(r"\\begin\{center\}[\s\S]*?\\end\{center\}","",string)
string = re.sub(r"(bracket\{\d+\})|(blank\{\d+\})|(fourch)|(twoch)|(onech)","",string)
string = re.sub(r"[\s\\\{\}\$\(\)\[\]]","",string)
string = re.sub(r"[\n\t]","",string)
string = re.sub(r"(displaystyle)|(overrightarrow)","",string)
string = re.sub(r"[,\.:;?]","",string)
return string
#difflab字符串比较
def difflab_get_equal_rate(str1, str2):
# str1 = pre_treating(str1)
# str2 = pre_treating(str2)
return difflib.SequenceMatcher(None, str1, str2).ratio()
#Levenshtein jaro字符串比较
def jaro_get_equal_rate(str1,str2):
# str1 = pre_treating(str1)
# str2 = pre_treating(str2)
return Levenshtein.jaro(str1,str2)
#Levenshtein 字符串比较
def Lev_get_equal_rate(str1,str2):
# str1 = pre_treating(str1)
# str2 = pre_treating(str2)
return Levenshtein.ratio(str1,str2)
#指定对比方法
sim_test = jaro_get_equal_rate
#读入题库
with open(r"../题库0.3/Problems.json","r",encoding = "utf8") as f:
database = f.read()
pro_dict = json.loads(database)
pro_dict_treated = {}
for id in pro_dict:
pro_dict_treated[id] = pro_dict[id].copy()
pro_dict_treated[id]["content"] = pre_treating(pro_dict_treated[id]["content"])
print("题目数:",len(pro_dict))
#记录起始时间
starttime = time.time()
alike_problems = ""
count = 0
keys = list(pro_dict_treated.keys())
while len(keys) >= 2:
count += 1
if count % 500 == 0:
print(count)
currentid = keys.pop(0)
content1 = pro_dict_treated[currentid]["content"]
same = []
for id in keys:
if not id in pro_dict[currentid]["same"] and not id in pro_dict[currentid]["related"]:
content2 = pro_dict_treated[id]["content"]
if sim_test(content1,content2)>threshold:
same.append(id)
if len(same) >= 1:
# print(currentid)
alike_problems += currentid + ","
for i in same:
# print(i)
keys.pop(keys.index(i))
alike_problems += ",".join(same)
alike_problems += "\n\n"
endtime = time.time()
print("耗时: %.3f" %(endtime-starttime))
with open(outputfile,"w",encoding = "u8") as f:
f.write(alike_problems)