From 769428ac6d36aa110a9fd2bf71329f7eb437eff0 Mon Sep 17 00:00:00 2001 From: wangweiye7840 Date: Fri, 7 Jun 2024 10:39:28 +0800 Subject: [PATCH] =?UTF-8?q?=E6=89=B9=E9=87=8F=E6=94=B6=E5=BD=95=E9=A2=98?= =?UTF-8?q?=E7=9B=AE=E5=8A=9F=E8=83=BD=E6=9B=B4=E6=96=B0=E5=AE=8C=E6=88=90?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- 工具v4/database_tools_2.py | 62 ++++++++++++++++++-------------------- 工具v4/批量收录新题.py | 7 +++-- 2 files changed, 34 insertions(+), 35 deletions(-) diff --git a/工具v4/database_tools_2.py b/工具v4/database_tools_2.py index bda66771..4b5ac898 100644 --- a/工具v4/database_tools_2.py +++ b/工具v4/database_tools_2.py @@ -393,6 +393,18 @@ def NextSpareID(num,database): #返回adict中下一个空闲的题号 mydb.close() return num +def NextSpareIDseries(num,cursor,length): #返回adict中以num起始, 连续长度至少为length的下一个空闲的题号 + cursor.execute("SELECT ID FROM problems;") + idlist = [ret[0] for ret in cursor.fetchall()] + idset = set(idlist) + num = int(num) + numset = set([str(num+i).zfill(6) for i in range(length)]) + while len(idset & numset) >= 1: + numset.remove(str(num).zfill(6)) + numset.add(str(num+length).zfill(6)) + num += 1 + return num + def NextSpareIDBlock(num,database): #返回adict中下一个空闲的题号块 mydb = connect(hostname = db_host, port = db_port, username=db_user, pwd=db_pwd, db = database) mycursor = mydb.cursor() @@ -433,15 +445,13 @@ def GenerateProblemListFromString(data): #从来自.tex文件的字符串生成 return problem_list #返回一个列表, 每一项是一个由 题目内容 和 题目来源前缀 组成的元组 -def GenerateProblemListFromString202406(data): #从data字符串生成题目列表, 每个item是一道题目, 题目后有色块的准关联题目的flushright块中的信息表示交互信息(如(003214rep)表示不添加, 用003214代替; (002521s)表示和002521相同, (000354r)表示和000354相关, 返回二元组(题目内容, 交互信息列表)的字典 +def GenerateNewProblemDataFromString2024(data): #从data字符串生成题目列表, 每个item是一道题目, 题目后有色块的准关联题目的flushright块中的信息表示交互信息(如(003214rep)表示不添加, 用003214代替; (002521s)表示和002521相同, (000354r)表示和000354相关, 返回三元组(题目内容, 中缀, 交互信息列表)的字典 try: data = re.findall(r"\\begin\{document\}([\s\S]*?)\\end\{document\}",data)[0] except: pass data = data + "\n\\end{enumerate}" data = re.sub(r"\n{2,}","\n",data) - # data = re.sub(r"\\definecolor[^\n]*\n","\n",data) - # data = re.sub(r"\\begin\{tcolorbox\}[\s\S]*?\\end\{tcolorbox\}","\n",data) data = re.sub(r"\\item",r"\\enditem\\item",data) data = re.sub(r"\\end\{enumerate\}",r"\\enditem",data) #切除无关信息, 保留关键信息 problempositions = [] @@ -450,39 +460,26 @@ def GenerateProblemListFromString202406(data): #从data字符串生成题目列 problem_list = [] for pos in problempositions: content_raw = data[pos[0]:pos[1]].strip() + meta = {"same":[],"related":[],"unrelated":[]} sim_problems = re.findall(r"\\definecolor[\s\S]*?\\end\{tcolorbox\}",content_raw) for sim_p in sim_problems: - #处理meta待修改 + metainfo = re.findall(r"相似度:[\s]*\d\.\d{3}[\\\s]*?(\d{6})\(([\s\S]*?)\)",sim_p) + if len(metainfo) == 1: + id,metatype = metainfo[0] + metatype = metatype.upper() + if metatype.startswith("REP"): + meta["rep"] = id.zfill(6) + elif metatype.startswith("S"): + meta["same"].append(id.zfill(6)) + elif metatype.startswith("R"): + meta["related"].append(id.zfill(6)) + elif metatype.startswith("U"): + meta["unrelated"].append(id.zfill(6)) content_raw = content_raw.replace(sim_p,"") content = content_raw.strip() - #以下待修改----20240607 - - content_raw = re.sub(r"\n\%[\s\S]*$","",content_raw) #题目内容 - content_raw = re.sub(r"\\\\$","",content_raw) # 删去题目最后一行处可能存在的\\ - content_raw = content_raw.strip() # 删去前后多余的空格 - meta = {} - if not content_raw[0] == "[": # 根据方括号内的内容生成交互信息, 这是无方括号的内容, 无meta - content = content_raw - else: - same_id_list = [] - related_id_list = [] - unrelated_id_list = [] - content = re.sub(r"^\[[A-Za-z\d,\s]*?\]","",content_raw).strip() - metaraw = re.findall(r"\[.*?\]",content_raw)[0] - metaraw = re.sub(r"[\[\]]","",metaraw) - metalist = metaraw.split(",") - for metaitem in metalist: - metaitem = metaitem.upper() - if metaitem.startswith("REP"): - meta = {"rep":metaitem[3:].zfill(6)} - elif metaitem.startswith("S"): - same_id_list.append(metaitem[1:].zfill(6)) - elif metaitem.startswith("R"): - related_id_list.append(metaitem[1:].zfill(6)) - elif metaitem.startswith("U"): - unrelated_id_list.append(metaitem[1:].zfill(6)) - if not "rep" in meta: - meta = {"same":same_id_list,"related":related_id_list,"unrelated":unrelated_id_list} + if "rep" in meta: + repid = meta["rep"] + meta = {"rep": id} subdata = data[:pos[0]] #开始寻找出处中缀 suflist = re.findall(r"\n(\%\s{0,}[\S]+)\n",subdata) if len(suflist) == 0: @@ -490,6 +487,7 @@ def GenerateProblemListFromString202406(data): #从data字符串生成题目列 else: suffix = suflist[-1].replace("%","").strip() problem_list.append((content,suffix,meta)) + # print(content,suffix,meta) return problem_list #返回一个列表, 每一项是一个由 题目内容 和 题目来源前缀 和 交互信息字典 组成的元组 diff --git a/工具v4/批量收录新题.py b/工具v4/批量收录新题.py index 8255c827..883a9fa5 100644 --- a/工具v4/批量收录新题.py +++ b/工具v4/批量收录新题.py @@ -65,7 +65,7 @@ class MyWindow_bdsl(QWidget,Ui_Form): output += "\n\\definecolor{mycolor}{rgb}"+colors output += "\n\\begin{tcolorbox}"+f"[colback = mycolor, opacityback = 0.25, colframe = orange!10!white, breakable]\n\n" output += "\\begin{flushright}\\begin{Large}\n" - output += f"相似度: {simrate:.3f} \\ {id}()\n" + output += f"相似度: {simrate:.3f} \\ {id}({'rep' if simrate == 1 else ''})\n" output += "\\end{Large}\\end{flushright}" content = pro_dict[id] output += f"\n{content}\n" @@ -89,11 +89,12 @@ class MyWindow_bdsl(QWidget,Ui_Form): else: Indexed = False idlistpath = "文本文件/新题收录列表.txt" - problems = GenerateProblemListFromString2024(data) #待修改（检测题目方式有变） + problems = GenerateNewProblemDataFromString2024(data) + problem_count = len(problems) # pro_dict = load_dict("../题库0.3/Problems.json") - nextspareid = NextSpareID(starting_id,self.database_name) #待修改（检测空白块数大小） self.db = connect(hostname = db_host, port= db_port, username= db_user, pwd = db_pwd, db= self.database_name) self.cursor = self.db.cursor() + nextspareid = NextSpareIDseries(starting_id,self.db.cursor(),problem_count) #待修改（检测空白块数大小） rolled_back = False idlist,newproblemlist = AddProblemstoDict2024nocommit(nextspareid,raworigin,problems,editor,Indexed,self.cursor) for p in newproblemlist: