import sqlite3
from pandas import DataFrame
import re

class sql_method:
    ‘‘‘
    function: 可以实现对@R_301_457@的基本操作
    ‘‘‘
    def __init__(self,dbName,tableName,data,columns,COLUMNS,Read_All=True):
        ‘‘‘
        function: 初始化参数
        dbName: @R_301_457@文件名
        tableName: @R_301_457@中表的名称
        data: 从csv文件中读取且经过处理的数据
        columns: 用于创建@R_301_457@，为表的第一行
        COLUMNS: 用于数据的格式化输出，为输出的表头
        Read_All: 创建表之后是否读取出所有数据
        ‘‘‘
        self.dbName = dbName
        self.tableName = tableName
        self.data = data
        self.columns = columns
        self.COLUMNS = COLUMNS
        self.Read_All = Read_All

    def creatTable(self):
        ‘‘‘
        function: 创建@R_301_457@文件及相关的表
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 创建表
        connect.execute("CREATE TABLE {}({})".format(self.tableName,self.columns))
        # 提交事务
        connect.commit()
        # 断开连接
        connect.close()

    def destroyTable(self):
        ‘‘‘
        function: 删除@R_301_457@文件中的表
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 删除表
        connect.execute("DROP TABLE {}".format(self.tableName))
        # 提交事务
        connect.commit()
        # 断开连接
        connect.close()

    def insertDataS(self):
        ‘‘‘
        function: 向@R_301_457@文件中的表插入多条数据
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 插入多条数据
        connect.executemany("INSERT INTO {} VALUES(?,?,?)".format(self.tableName),self.data)
        #for i in range(len(self.data)):
        #    connect.execute("INSERT INTO university VALUES(?,?)",data[i])
        # 提交事务
        connect.commit()
        # 断开连接
        connect.close()

    def getAllData(self):
        ‘‘‘
        function: 得到@R_301_457@文件中的所有数据
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 创建游标对象
        cursor = connect.cursor()
        # 读取数据
        cursor.execute("SELECT * FROM {}".format(self.tableName))
        dataList = cursor.fetchall()
        # 断开连接
        connect.close()
        return dataList

    def searchData(self,conditions,IfPrint=True):
        ‘‘‘
        function: 查找特定的数据
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 创建游标
        cursor = connect.cursor()
        # 查找数据
        cursor.execute("SELECT * FROM {} WHERE {}".format(self.tableName,conditions))
        data = cursor.fetchall()
        # 关闭游标
        cursor.close()
        # 断开@R_301_457@连接
        connect.close()
        if IfPrint:
            self.printData(data)
        return data

    def deleteData(self,conditions):
        ‘‘‘
        function: 删除@R_301_457@中的数据
        ‘‘‘
        # 连接@R_301_457@
        connect = sqlite3.connect(self.dbName)
        # 插入多条数据
        connect.execute("DELETE FROM {} WHERE {}".format(self.tableName,conditions))
        # 提交事务
        connect.commit()
        # 断开连接
        connect.close()

    def printData(self,data):
        print("{1:{0}^3}{2:{0}<11}{3:{0}<4}{4:{0}<4}{5:{0}<5}{6:{0}<5}{7:{0}^5}{8:{0}^5}{9:{0}^5}{10:{0}^5}{11:{0}^5}{12:{0}^6}{13:{0}^5}".format(chr(12288),*self.COLUMNS))
        for i in range(len(data)):
            print("{1:{0}<4.0f}{2:{0}<10}{3:{0}<5}{4:{0}<6}{5:{0}<7}{6:{0}<8}{7:{0}<7.0f}{8:{0}<8}{9:{0}<7.0f}{10:{0}<6.0f}{11:{0}<9.0f}{12:{0}<6.0f}{13:{0}<6.0f}".format(chr(12288),*data[i]))

    def run(self):
        try:
            # 创建@R_301_457@文件
            self.creatTable()
            print(">>> @R_301_457@创建成功！")
            # 保存数据到@R_301_457@
            self.insertDataS()
            print(">>> 表创建、数据插入成功！")
        except:
            print(">>> @R_301_457@已创建！")
        # 读取所有数据
        if self.Read_All:
            self.printData(self.getAllData())

def get_data(fileName):
    ‘‘‘
    function: 读取获得大学排名的数据 并 将结果返回
    ‘‘‘
    data = []
    # 打开文件
    f = open(fileName,‘r‘,encoding=‘utf-8‘)
    # 按行读取文件
    for line in f.readlines():
        # 替换掉其中的换行符和百分号  替换百分号是为了方便之后的排序和运算
        line = line.replace(‘\n‘,‘‘)
        line = line.replace(‘%‘,‘‘)
        # 将字符串按照 ‘,‘ 分割为列表
        line = line.split(‘,‘)
       
        for i in range(len(line)):
            # 使用 异常处理 避开 出现中文无法转换 的错误
            try:
                # 将空值填充为 0
                if line[i] == ‘‘:
                    line[i] = ‘0‘
                # 将数字转换为数值
                line[i] = eval(line[i])
            except:
                continue
        data.append(tuple(line))
    # EN_columns、CH_columns 分别为 用于@R_301_457@创建、数据的格式化输出
    EN_columns = "Rank real,University text,Province text,Grade real,SourseQuality real,TrainingResult real,ResearchScale real,\
    ReserchQuality real,TopResult real,TopTalent real,TechnologyService real,Cooperation real,TransformationResults real"
    CH_columns =  ["排名","学校名称","省市","总分","生涯质量","培养结果(%)","科研规模","科研质量","顶尖成果","顶尖人才","科技服务","产学研合作","成果转化"]
    return data[1:],EN_columns,CH_columns

if __name__ == "__main__":
    # =================== 设置和得到基本数据 ===================
    fileName = "D:\\123.csv"
    data,CH_columns = get_data(fileName)
    dbName = "university.db"
    tableName = "university"

    # ================= 创建一个sql_method对象 ==================
    sql = sql_method(dbName,CH_columns,False)

    # =================== 创建@R_301_457@并保存数据 ===================
    sql.run()
   
    # =================== 在@R_301_457@中查找数据项 ===================
    # 查找记录并输出结果
    print(">>> 查找数据项（University = ‘广东工业大学‘） :")
    sql.searchData("University = ‘广东工业大学‘",True)

    # ================= 在@R_301_457@中筛选数据项并排序 ==================
    # 将选取广东省的数据 并 对科研规模大小排序
    print("\n>>> 筛选数据项并按照科研规模排序（Province = ‘广东省‘） :")
    sql.searchData("Province = ‘广东省‘ ORDER BY ResearchScale",True)

    # =============== 对@R_301_457@中的数据进行重新排序操作 ================
    # 定义权值
    Weight = [0.3,0.15,0.1,0.05,0.05]
    value,sum = [],0
    # 获取 Province = ‘广东省‘ 的所有数据
    sample = sql.searchData("Province = ‘广东省‘",False)
    # 按照权值求出各个大学的总得分
    for i in range(len(sample)):
        for j in range(len(Weight)):
            sum += sample[i][4+j] * Weight[j]
        value.append(sum)
        sum = 0
    # 将结果通过 pandas 的 DataFrame 方法组成一个二维序列
    university = [university[1] for university in sample]
    uv,tmp = [],[]
    for i in range(len(university)):
        tmp.append(university[i])
        tmp.append(value[i])
        uv.append(tmp)
        tmp = []
    df = DataFrame(uv,columns=list(("大学","总分")))
    df = df.sort_values(‘总分‘)
    df.index = [i for i in range(1,len(uv)+1)]
    # 输出结果
    print("\n>>> 筛选【广东省】的大学并通过权值运算后重排名的结果：\n",df)
   
    # ===================== 在@R_301_457@中删除数据项 =====================
    sql.deleteData("Province = ‘北京市‘")
    sql.deleteData("Province = ‘广东省‘")
    sql.deleteData("Province = ‘山东省‘")
    sql.deleteData("Province = ‘山西省‘")
    sql.deleteData("Province = ‘江西省‘")
    sql.deleteData("Province = ‘河南省‘")
    print("\n>>> 数据删除成功！")
    sql.printData(sql.getAllData())

    # ====================== 在@R_301_457@中删除表 ========================
    sql.destroyTable()
    print(">>> 表删除成功！")
    PrintTableList(data,10)   # 输出前10行数据
    saveAsCsv("D:\\123.csv",data)