# coding=utf-8

import re
import mysql_pool
from pymysql.converters import escape_string
import cosin_similarity
import pandas as pd
import glm_utils
import os
import json

wdys1 = {
    "项目名称": "xmmc",
    "现状问题": "xzwt",
    "系统基础": "xtjc",
    "项目目标": "xmmb",
    "预期绩效": "yqjx",
    "建设需求": "jsxq",
    "数据需求": "sjxq",
    "安全需求": "aqxq",
    "业务领域": "ywly",
    "核心业务": "hxyw",
    "业务需求": "ywxq",
    "业务协同": "ywxt",
    "建设层级": "jscj",
    "用户范围": "yhfw",
    "目标群体": "mbqt",
    "建设内容": "jsnr",
    "功能模块": "gnmk",
    "数据共享": "sjgx",
    "智能要素": "znys",
    "申报单位": "sbdw",
    "所属地区": "ssdq",
    "预算年度": "ysnd"
}
wdys2 = {
    "xmmc": "项目名称",
    "xzwt": "现状问题",
    "xtjc": "系统基础",
    "xmmb": "项目目标",
    "yqjx": "预期绩效",
    "jsxq": "建设需求",
    "sjxq": "数据需求",
    "aqxq": "安全需求",
    "ywly": "业务领域",
    "hxyw": "核心业务",
    "ywxq": "业务需求",
    "ywxt": "业务协同",
    "jscj": "建设层级",
    "yhfw": "用户范围",
    "mbqt": "目标群体",
    "jsnr": "建设内容",
    "gnmk": "功能模块",
    "sjgx": "数据共享",
    "znys": "智能要素",
    "sbdw": "申报单位",
    "ssdq": "所属地区",
    "ysnd": "预算年度"
}
gnmkys = {
    "gnmc": "功能名称",
    "gnms": "功能描述"
}


def getFlag():
    data_dict = {}
    df = pd.read_excel("0825-丽水系统查重维度.xlsx")
    data = df.values
    data = list(pd.Series(data[:, 1]).dropna())
    for d in data:
        try:
            wd = re.search("(.*?)（.*?%）", d).group(1).strip()
            wdc = wdys1.get(wd)
            if wdc:
                qz = re.search(".*?（(.*?%)）", d).group(1)
                data_dict[wdc] = qz
        except:
            pass
    return data_dict

# getFlag()

def gong_neng_mo_kuai(xmmc, mysql, dl, data, er_title, line):
    # 将excel文件中的所有第三维度内容进行拼接
    str_dict = {}
    for et in er_title:
        for d in data:
            if d[1] == et:
                if str_dict.get(et):
                    str_dict[et] = str_dict.get(et) + d[3]
                else:
                    str_dict[et] = d[3]
    for k, v in str_dict.items():
        mysql.sql_change_msg("""insert into user_history_module_data(xmmc,gnmc,gnms,line, remark) value("%s", "%s", "%s", "%s", "%s")""" % (
            escape_string(xmmc), escape_string(k), escape_string(v), line, ""))
        #
        similarity = cosin_similarity.CosineSimilarity(v, v)
        similarity, keywords_x, keywords_y = similarity.main()
        mysql.sql_change_msg("""insert into user_history_module_keywords (xmmc,gnmc,gnms,line) value("%s" ,"%s", "%s", "%s")""" % (
            xmmc, escape_string(k), str(keywords_y)[1:-1], line))


def project_check(data_list, line):
    mysql = mysql_pool.ConnMysql()
    # 读取维度和权重
    # get_data_dict = getFlag()
    # 遍历excel存储路径
    for dl in data_list:
        # path = "0825-丽水系统查重维度1.xlsx"
        # 读取路径下的excel
        print(dl)
        df = pd.read_excel(dl[1])
        xmmc = df.keys()
        # print(type(xmmc[dup_file_test]))
        xmmc=xmmc[1]
        # print(type(xmmc))
        # xmmc1=''

        if "可研报告"or "可研性报告"or "可行性研究报告" in xmmc:
            xmmc=xmmc.replace('可研报告','')
            xmmc=xmmc.replace('可研性报告','')
            xmmc=xmmc.replace('可行性研究报告','')
        # print(xmmc)
        data = df.values
        # 将excel文件中的所有维度内容进行拼接
        join_str = ""
        str_dict = {}
        title = ""
        er_title = set()
        # for d in data:
        #     # print(d)
        #     if pd.notnull(d[0]):
        #         title = d[0]
        #         if title == "功能模块":
        #             er_title.add(d[dup_file_test])
        #         join_str = ""
        #         for i in d[dup_file_test:]:
        #             if pd.notnull(i):
        #                 join_str += i
        #         str_dict[wdys1.get(title)] = join_str
        #     else:
        #         if title == "功能模块":
        #             er_title.add(d[dup_file_test])
        #         for i in d[dup_file_test:]:
        #             if pd.notnull(i):
        #                 join_str += i
        #         str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str
        # print(str_dict)
        gnmk_str = []
        # print(data)
        for d in data:
            if pd.notnull(d[0]):
                title = d[0]
                if title == "功能模块":
                    er_title.add(d[1])
                join_str = ""
                for i in d[1:]:
                    # print(type(i))
                    # i=str(i)
                    if pd.notnull(i):
                        join_str += str(i)
                        if title == "功能模块":
                            # for j in d[3:]:
                            if i == '功能描述':
                                continue
                            else:
                                gnmk_str.append(i)
                str_dict[wdys1.get(title)] = join_str
                # print(str_dict.get(wdys1.get(title)))
            else:
                if title == "功能模块":
                    er_title.add(d[1])
                for i in d[3:]:
                    if pd.notnull(i):
                        join_str += str(i)
                        if title == "功能模块":
                            gnmk_str.append(i)
                str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str
                # gnmk="".join(gnmk_str)
                # str_dict['gnmk']=gnmk
        gnmk = ",".join(gnmk_str)
        str_dict['gnmk'] = gnmk
        # print(str_dict)
        # print(str_dict.get("xzwt")if str_dict.get("xzwt") else None)
        # print(str_dict.get('gnmk')if str_dict.get('gnmk')else None)
        mysql.sql_change_msg(
            """insert into user_history_data (xmmc, xzwt, xtjc, xmmb, yqjx, jsxq, sjxq, aqxq, ywly, hxyw, ywxq, ywxt, jscj, yhfw, mbqt, jsnr, gnmk, sjgx, znys,sbdw,ssdq,ysnd,line,remark) value ("%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s","%s","%s","%s","%s","%s")"""
            % (escape_string(xmmc),
               escape_string(str_dict.get("xzwt")) if str_dict.get("xzwt") else None,
               escape_string(str_dict.get("xtjc")) if str_dict.get("xtjc") else None,
               escape_string(str_dict.get("xmmb")) if str_dict.get("xmmb") else None,
               escape_string(str_dict.get("yqjx")) if str_dict.get("yqjx") else None,
               escape_string(str_dict.get("jsxq")) if str_dict.get("jsxq") else None,
               escape_string(str_dict.get("sjxq")) if str_dict.get("sjxq") else None,
               escape_string(str_dict.get("aqxq")) if str_dict.get("aqxq") else None,
               escape_string(str_dict.get("ywly")) if str_dict.get("ywly") else None,
               escape_string(str_dict.get("hxyw")) if str_dict.get("hxyw") else None,
               escape_string(str_dict.get("ywxq")) if str_dict.get("ywxq") else None,
               escape_string(str_dict.get("ywxt")) if str_dict.get("ywxt") else None,
               escape_string(str_dict.get("jscj")) if str_dict.get("jscj") else None,
               escape_string(str_dict.get("yhfw")) if str_dict.get("yhfw") else None,
               escape_string(str_dict.get("mbqt")) if str_dict.get("mbqt") else None,
               escape_string(str_dict.get("jsnr")) if str_dict.get("jsnr") else None,
               escape_string(str_dict.get("gnmk")) if str_dict.get("gnmk") else None,
               escape_string(str_dict.get("sjgx")) if str_dict.get("sjgx") else None,
               escape_string(str_dict.get("znys")) if str_dict.get("znys") else None,
               escape_string(str_dict.get("sbdw")) if str_dict.get("sbdw") else None,
               escape_string(str_dict.get("ssdq")) if str_dict.get("ssdq") else None,
               escape_string(str_dict.get("ysnd")) if str_dict.get("ysnd") else None,
               line, ""))
        project_gjc = {}
        for w in wdys2.keys():
            content_x = str_dict.get(w)
            content_y = str_dict.get(w)
            if content_x and content_y:
                # 循环遍历每一个维度
                similarity = cosin_similarity.CosineSimilarity(content_x, content_y)
                # 相似度  关键词
                similarity, keywords_x, keywords_y = similarity.main()
                project_gjc[w] = keywords_y
        mysql.sql_change_msg(
            """insert into user_history_keywords (xmmc, xzwt, xtjc, xmmb, yqjx, jsxq, sjxq, aqxq, ywly, hxyw, ywxq, ywxt, jscj, yhfw, mbqt, jsnr, gnmk, sjgx, znys, line) value ("%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s")"""
            % (xmmc, str(project_gjc.get("xzwt"))[1:-1] if project_gjc.get("xzwt") else None,
               str(project_gjc.get("xtjc"))[1:-1] if project_gjc.get("xtjc") else None,
               str(project_gjc.get("xmmb"))[1:-1] if project_gjc.get("xmmb") else None,
               str(project_gjc.get("yqjx"))[1:-1] if project_gjc.get("yqjx") else None,
               str(project_gjc.get("jsxq"))[1:-1] if project_gjc.get("jsxq") else None,
               str(project_gjc.get("sjxq"))[1:-1] if project_gjc.get("sjxq") else None,
               str(project_gjc.get("aqxq"))[1:-1] if project_gjc.get("aqxq") else None,
               str(project_gjc.get("ywly"))[1:-1] if project_gjc.get("ywly") else None,
               str(project_gjc.get("hxyw"))[1:-1] if project_gjc.get("hxyw") else None,
               str(project_gjc.get("ywxq"))[1:-1] if project_gjc.get("ywxq") else None,
               str(project_gjc.get("ywxt"))[1:-1] if project_gjc.get("ywxt") else None,
               str(project_gjc.get("jscj"))[1:-1] if project_gjc.get("jscj") else None,
               str(project_gjc.get("yhfw"))[1:-1] if project_gjc.get("yhfw") else None,
               str(project_gjc.get("mbqt"))[1:-1] if project_gjc.get("mbqt") else None,
               str(project_gjc.get("jsnr"))[1:-1] if project_gjc.get("jsnr") else None,
               str(project_gjc.get("gnmk"))[1:-1] if project_gjc.get("gnmk") else None,
               str(project_gjc.get("sjgx"))[1:-1] if project_gjc.get("sjgx") else None,
               str(project_gjc.get("znys"))[1:-1] if project_gjc.get("znys") else None,
               line))

        gong_neng_mo_kuai(xmmc, mysql, dl, data, er_title, line)



def update_desc():
    mysql = mysql_pool.ConnMysql()
    module_list = mysql.sql_select_many("""select id, gnms from user_history_module_data where xmmc = '丽水市城市管理指挥中心信息系统（一期）项目'""")
    for module in module_list:
        # 通过chatglm进行提取信息
        gnms = module.get("gnms")
        content = glm_utils.CallContentResultNew(gnms)

        mysql.sql_change_msg(
            """UPDATE user_history_module_data SET glm_desc = "%s" WHERE id = %d""" % (
                content if content else None,
                module.get("id")))
        print(content)


def update_desc1():
    mysql = mysql_pool.ConnMysql()
    module_list = mysql.sql_select_many("""select id, gnms from gnms_gml where xmmc = '丽水花园云（城市大脑）数字驾驶舱项目'""")
    for module in module_list:
        # 通过chatglm进行提取信息
        gnms = module.get("gnms")
        content = glm_utils.CallContentResultNew(gnms)

        mysql.sql_change_msg(
            """UPDATE gnms_gml SET glm_desc = "%s" WHERE id = %d""" % (
                content if content else None,
                module.get("id")))
        print(content)


def info_word_project():
    mysql = mysql_pool.ConnMysql()
    module_list1 = mysql.sql_select_many(
        """select jsnr from user_history_data where xmmc = '2023年丽水市云和县数字法治门户建设项目' """)
    module_list2 = mysql.sql_select_many(
        """select jsnr from user_history_data where xmmc IN ('浙江省第二监狱重点罪犯管控模型项目',
            '浙江省农村水电站管理数字化应用',
            '浙江省河湖库保护数字化应用建设项目',
            '浙江省环境遥感监测业务智治',
            '平台项目',
            '浙江林业智媒平台项目',
            '未来e家应用建设方案',
            '浙江省智慧林业云平台升级改造项目建设方案',
            '为侨服务“全球通”平台二期建设项目')""")
    json_objects = []
    for module_info1 in module_list1:
        for jsnr1Ele in module_info1["jsnr"].split('-----》'):
            for module_info2 in module_list2:
                for jsnr2Ele in module_info2["jsnr"].split('-----》'):
                    str = "A：%s\nB：%s" % (jsnr1Ele, jsnr2Ele)
                    data = {
                        "instruction": "现在你是一个政府提案的查重检查人员，给定两段话A和B：让我们一步步思考并判断是否相似。请以相似度从高、中、低三个等级进行评价，并给出理由。",
                        "input": str,
                        "output": ""
                    }
                    json_objects.append(data)

    with open('其他-建设内容.json', 'w') as f:
        for json_obj in json_objects:
            json_str = json.dumps(json_obj, ensure_ascii=False)  # 将JSON对象转换为字符串
            f.write(json_str + '\n')  # 写入字符串，并添加换行符



def info_word1():
    mysql = mysql_pool.ConnMysql()
    # module_list1 = mysql.sql_select_many("""select gnms from user_history_module_data where xmmc = '莲智社区' """)
    # module_list2 = mysql.sql_select_many("""select gnms from user_history_module_data where xmmc IN ('古堰画乡智慧客厅项目—未来社区智慧服务平台', '未来e家')""")
    module_list1 = mysql.sql_select_many("""select gnms from user_history_module_data where xmmc = '丽水市遂昌县政法委数字法治综合应用' """)
    module_list2 = mysql.sql_select_many("""select gnms from user_history_module_data where xmmc IN ('浙江省第二监狱重点罪犯管控模型项目',
            '浙江省农村水电站管理数字化应用',
            '浙江省河湖库保护数字化应用建设项目',
            '浙江省环境遥感监测业务智治',
            '平台项目',
            '浙江林业智媒平台项目',
            '未来e家应用建设方案',
            '浙江省智慧林业云平台升级改造项目建设方案',
            '为侨服务“全球通”平台二期建设项目')""")

    json_objects = []
    for module_info1 in module_list1:
        for module_info2 in module_list2:
            str = "A：%s\nB：%s" % (module_info1["gnms"], module_info2["gnms"])
            data = {
                "instruction": "现在你是一个政府提案的查重检查人员，给定两段话A和B：让我们一步步思考并判断是否相似。请以相似度从高、中、低三个等级进行评价，并给出理由。",
                "input": str,
                "output": ""
            }
            json_objects.append(data)

    with open('其他-功能模块对比.json', 'w') as f:
        for json_obj in json_objects:
            json_str = json.dumps(json_obj, ensure_ascii=False)  # 将JSON对象转换为字符串
            f.write(json_str + '\n')  # 写入字符串，并添加换行符


def info_word_project_yw():
    mysql = mysql_pool.ConnMysql()
    module_list1 = mysql.sql_select_many(
        """select jsnr from user_history_data where xmmc = '2023年丽水市云和县数字法治门户建设项目' """)
    module_list2 = mysql.sql_select_many(
        """select jsnr from user_history_data where xmmc IN ('2023年丽水市云和县数字法治门户建设项目', '浙江省司法厅全域数字法治监督应用系统（一期）', '丽水市遂昌县政法委数字法治综合应用', '丽水市龙泉市政法委法治龙泉门户', '庆元县数字法治综合门户')""")
    json_objects = []
    for module_info1 in module_list1:
        for jsnr1Ele in module_info1["jsnr"].split('-----》'):
            for module_info2 in module_list2:
                for jsnr2Ele in module_info2["jsnr"].split('-----》'):
                    str = "A：%s\nB：%s" % (jsnr1Ele, jsnr2Ele)
                    data = {
                        "instruction": "现在你是一个政府提案的查重检查人员，给定两段话A和B：让我们一步步思考并判断是否相似。请以相似度从高、中、低三个等级进行评价，并给出理由。",
                        "input": str,
                        "output": ""
                    }
                    json_objects.append(data)

    with open('其他-建设内容.json', 'w') as f:
        for json_obj in json_objects:
            json_str = json.dumps(json_obj, ensure_ascii=False)  # 将JSON对象转换为字符串
            f.write(json_str + '\n')  # 写入字符串，并添加换行符


if __name__ == "__main__":
    info_word1()
    print("ok.......")
    path = r"/Users/kebobo/Downloads/丽水/未来社区"
    data_list = os.listdir(path)
    for file in data_list:
        if file != '.DS_Store':
            data_list = [(0, path + '/' + file, "")]
            project_check(data_list, "2024-07-27-数字法治")
            print("已存入************************************* %s" % file)

"""
建设目标，业务功能

gnmk_str = []
for d in data:
    if pd.notnull(d[0]):
        title = d[0]
        if title == "功能模块":
            er_title.add(d[dup_file_test])
        join_str = ""
        for i in d[dup_file_test:]:
            if pd.notnull(i):
                join_str += i
                if title == "功能模块":
                    gnmk_str.append(i)
        str_dict[wdys1.get(title)] = join_str
    else:
        if title == "功能模块":
            er_title.add(d[dup_file_test])
        for i in d[dup_file_test:]:
            if pd.notnull(i):
                join_str += i
                if title == "功能模块":
                    gnmk_str.append(i)
        str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str
gnmk = "".join(gnmk_str)


"""