import zipfile,os,re
import pandas as pd
from pathlib import Path


#设置工作目录, 要求工作目录中恰有一个.txt文件（或.tex文件)和一些.zip文件，其余不论
# 第一行用"#"开头的作业数据不会被读取
filepath = r"C:\Users\weiye\Documents\wwy sync\xiaoxian待导入"

#设置届别与接受的比例阈值
semester = 2023
# threshold = 0.5 #当班级提交人数超过该比例时数据有效

def getindex(string,pos = 2):
    para = string.split(".")
    return int(para[pos-1])

def stringcount(string,list):
    theitem = ""
    count = 0
    for item in list:
        if string in item:
            count += 1
            theitem = item
    return (count,theitem)


shiftdict = {"高一": 3, "高二": 2, "高三": 1}
patterns = [r"填空([\d\.]+)\((\d+)\)",r"单选([\d\.]+)\((\d+)\)",r"^([\d\.]+)第\d+(步)"]



#生成文件名tex_file和zip_file
files = [os.path.join(filepath,f) for f in os.listdir(filepath)]
tex_file = [f for f in files if ".tex" in f or ".txt" in f][0]
zip_files = [f for f in files if ".zip" in f]

#分割各次作业数据
with open(tex_file,"r",encoding = "utf8") as f:
    tex_data = f.read().strip()
tex_data = re.sub(r"\t+",r" ",tex_data)
tex_data = re.sub(r"\n{2,}","---split---",tex_data)
homeworklist = tex_data.split("---split---")

#读取各次作业首行（文件名）与次行（日期）并组织字典结构
homeworkdict = {}
for hwk in homeworklist:
    hwkdata = hwk.strip().split("\n")
    id = hwkdata.pop(0).replace(" ","")
    date = hwkdata.pop(0)
    if not id.startswith("#"):
        homeworkdict[id] = {}
        homeworkdict[id]["date"] = date
        homeworkdict[id]["usage_data"] = hwkdata

#测试是否每一项都有相应的zip文件与之对应
execflag = True
for id in homeworkdict:
    if stringcount(id,zip_files)[0] == 1:
        print("zip文件在文件夹中:",id)
    else:
        execflag = False
        print("!!!zip文件个数不对:",id)

if execflag:
    outputstr = "usages\n\n"
    for hid in homeworkdict:
        print("正在处理%s"%id)
        date = homeworkdict[hid]["date"]
        #在zip文件中找到包含正确率数据的文件
        zip_file = os.path.join(filepath,stringcount(hid,zip_files)[1])
        zf = zipfile.ZipFile(zip_file)
        # statfiles = [f.filename for f in zf.filelist if "试题分析" in f.filename]
        handinfiles = [f.filename for f in zf.filelist if "小题分_按学号" in f.filename]

        if "statsfile.xlsx" in os.listdir("临时文件"):
            os.remove("临时文件/statsfile.xlsx")
        extractedpath = Path(zf.extract(handinfiles[0]))
        extractedpath.rename("临时文件/statsfile.xlsx")
        df = pd.read_excel("临时文件/statsfile.xlsx",skiprows=2)
        indices = {}
        for col in df.columns:
            for pattern in patterns:
                res = re.findall(pattern,col)
                if len(res) > 0:
                    id,mark = res[0]
                    if not id in indices:
                        indices[id] = {}
                    if not "步" in mark:
                        indices[id][col] = int(mark)
                    else:
                        indices[id][col] = int(input(f"{hid}-{col}的满分:"))

        corresp_dict = {}
        homework = homeworkdict[hid]
        data = homework["date"]
        for rawline in homework["usage_data"]:
            line = re.sub(r"[\t\s]+"," ",rawline)
            a,b = line.split(" ")
            if a.strip() in indices:
                corresp_dict[b.strip()]=indices[a].copy()
        # print(corresp_dict)
        for excelfile in handinfiles:
            if "statsfile.xlsx" in os.listdir("临时文件"):
                os.remove("临时文件/statsfile.xlsx")
            extractedpath = Path(zf.extract(excelfile))
            extractedpath.rename("临时文件/statsfile.xlsx")
            df = pd.read_excel("临时文件/statsfile.xlsx",skiprows=2)[:-2]
            gradename = re.findall(r"高[一二三]",excelfile)[0]
            classname = str(semester+shiftdict[gradename])+"届"+gradename+re.findall(r"高[一二三]([\d]*?)班",excelfile)[0].zfill(2)+"班"
            for id in corresp_dict:
                colandmarks = corresp_dict[id]
                currentstring = f"{id}\n{date}\t{classname}"
                for col in colandmarks:
                    mark = colandmarks[col]
                    diff = df[col].mean()/mark
                    currentstring += f"\t{diff:.3f}"
                currentstring += "\n\n"
                outputstr += currentstring 

    with open("临时文件/自动转换结果.txt","w",encoding = "utf8") as f:
        f.write(outputstr)
    with open("文本文件/metadata.txt","w",encoding = "utf8") as f:
        f.write(outputstr)
    zf.close()