wangweiye
/
mathdeptv2
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

单元挂钩 迁移到工具v3 完成

This commit is contained in:
wangweiye7840 2024-04-16 14:38:49 +08:00
parent dd753c09c5
commit 918d1108f9
2 changed files with 56 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
工具v3/database_tools_2.py
View File

@ -100,11 +100,13 @@ def pre_treating(string): #删除字符串中对比较无用的字符, 以供比
string = re.sub(r"[,\.:;?]","",string)
return string #返回处理后的字符串
def findsame(id,same_list): #在same_list中寻找与id相同的题号
set1 = set([pair[1] for pair in same_list if pair[0] == id])
set2 = set([pair[0] for pair in same_list if pair[1] == id])
def findsru(id,alist): #在same_list中寻找与id相同的题号
set1 = set([pair[1] for pair in alist if pair[0] == id])
set2 = set([pair[0] for pair in alist if pair[1] == id])
return sorted(list(set1 | set2))
def findsameinDB(id): #在数据库中寻找与id相同的题号
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
@ -129,18 +131,54 @@ def findrelatedinDB(id): #在数据库中寻找与id关联的题号
set2 = set([ret[0] for ret in mycursor.fetchall()])
return sorted(list(set1 | set2))
def get_unit_tags(id):
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
sql = "SELECT tagname FROM tagcorresp WHERE ID = (%s);"
val = (id,)
mycursor.execute(sql,val)
unittags = [ret[0] for ret in mycursor.fetchall() if "单元" in ret[0]]
mydb.close()
return unittags
def get_problem_content(id):
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
sql = "SELECT content FROM problems WHERE ID = (%s);"
val = (id,)
mycursor.execute(sql,val)
content = mycursor.fetchall()[0][0]
mydb.close()
return content
def generate_same_list():
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
mycursor.execute("SELECT ID,SAME_ID FROM same;")
same_list = [(ret[0],ret[1]) for ret in mycursor.fetchall()]
mydb.close()
return same_list.copy()
def generate_related_list():
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
mycursor.execute("SELECT ID,RELATED_ID FROM related;")
related_list = [(ret[0],ret[1]) for ret in mycursor.fetchall()]
mydb.close()
return related_list.copy()
def treat_dict(): #对整个题库字典中的内容部分进行预处理，删除无用字符
treated_dict = {}
mydb = connect(hostname = "wwylss.synology.me", port = "13306", username="tikuuser", pwd="Kjmathds_2024", db = "tikutest")
mycursor = mydb.cursor()
mycursor.execute("SELECT ID,content FROM problems;")
p_dict = {id:content for id,content in mycursor.fetchall()}
mycursor.execute("SELECT ID,SAME_ID FROM same;")
same_list = [(ret[0],ret[1]) for ret in mycursor.fetchall()]
# mycursor.execute("SELECT ID,SAME_ID FROM same;")
# same_list = [(ret[0],ret[1]) for ret in mycursor.fetchall()]
for id in p_dict:
treated_dict[id] = {}
treated_dict[id]["content"] = pre_treating(p_dict[id])
treated_dict[id]["same"] = findsame(id,same_list).copy()
treated_dict[id] = pre_treating(p_dict[id])
mydb.close()
return treated_dict #返回处理后的字典, 含内容字段及相同题目字段
@ -2195,26 +2233,26 @@ def unUnitted(idexp): #返回adict中未赋单元的id列表
return ununittedids
def AutoAssignTagNotoLaTeX(newlist): #根据题库中已有的单元挂钩和字符串相似比对, 给newlist中的每一个ID在可能的情况下自动适配单元号码, 可能有误, 需人工审核, 返回(LaTeX代码的body(从\begin{enumerate}到\end{enumerate}的部分),题号和单元号码的对应)组成的二元tuple
def AutoAssignTagNotoLaTeX(newlist,allsamelist,allrelatedlist):
output = "\\begin{enumerate}\n\n"
tagrecord = ""
print("正在生成简化题目的字典...")
treateddict = treat_dict()
print("简化题目字典生成完毕.")
for id in newlist:
samelist = findsameinDB(id)
relatedlist = findrelatedinDB(id)
samelist = findsru(id,allsamelist)
relatedlist = findsru(id,allrelatedlist)
if not samelist == []:
unittags = [i for i in adict[samelist[0]]["tags"] if "单元" in i]
unittags = get_unit_tags(samelist[0])
elif not relatedlist == []:
unittags = [i for i in adict[relatedlist[0]]["tags"] if "单元" in i]
unittags = get_unit_tags(relatedlist[0])
else:
simgroup = stringmaxsim(treateddict[id]["content"],treateddict,10)
simgroup = stringmaxsim(treateddict[id],treateddict,10)
unittags_raw = {}
for g in simgroup:
rid,sim = g
if not rid == id and sim > 0.75:
for t in [i for i in adict[rid]["tags"] if "单元" in i]:
for t in get_unit_tags(rid):
if t in unittags_raw:
unittags_raw[t] += 1
else:
@ -2226,7 +2264,7 @@ def AutoAssignTagNotoLaTeX(newlist): #根据题库中已有的单元挂钩和字
tagnumbers = ""
for u in unittags:
tagnumbers += str(getUnitNumber(u))
output += f"\\item ({id})[{tagnumbers}] {adict[id]['content']}\n\n"
output += f"\\item ({id})[{tagnumbers}] {get_problem_content(id)}\n\n"
tagrecord += f"{id}\t{tagnumbers}\n"
output += "\\end{enumerate}\n\n"
return (output,tagrecord)

4
工具v3/单元挂钩.py
View File

@ -14,13 +14,15 @@ class MyWindow(QWidget,Ui_Form):
def exec(self):
# pro_dict = load_dict("../题库0.3/Problems.json")
allids = getAllIDsExp()
all_same_list = generate_same_list()
all_related_list = generate_related_list()
if self.radioButton_phase1.isChecked():
idexp = self.lineEdit_ids.text()
if idexp.strip() == "":
idlist = unUnitted(allids)
else:
idlist = generate_number_set(idexp)
latex_body,tagrec = AutoAssignTagNotoLaTeX(idlist,pro_dict)
latex_body,tagrec = AutoAssignTagNotoLaTeX(idlist,all_same_list,all_related_list)
latex_raw = ReadTextFile("模板文件/讲义模板.txt")
latex_data = StringSubstitute(r"<<[\s\S]*?待替换[\s\S]*?>>",latex_raw,("待检查单元",latex_body))
SaveTextFile(tagrec,"临时文件/单元对应.txt")