BIDI_ML_INFO_EXTRACTION/BiddingKG/dl/interface/getAttributes.py

# from BiddingKG.dl.common.Utils import findAllIndex,debug,timeFormat,getCurrent_date,API_URL,uniform_package_name,money_process,getDigitsDic,isValidDate
from BiddingKG.dl.common.Utils import *
from BiddingKG.dl.interface.Entitys import PREM,Role,Entity
from decimal import Decimal
import re
import copy
import math
import pandas as pd
import os
from scipy.optimize import linear_sum_assignment
from BiddingKG.dl.interface.Entitys import Match
import numpy as np
import uuid
import time,calendar
from datetime import datetime

def getTheRole(entity,role_list):
    '''
    @summary:根据实体名称拿到index
    @param:
        entity:实体名称
        role_list:角色list
    @return:该实体所在下标
    '''
    for role_index in range(len(role_list)):
        if entity in role_list[role_index]:
            return role_index
    return None

dict_role_id = {"0":"tenderee",
                "1":"agency",
                "2":"win_tenderer",
                "3":"second_tenderer",
                "4":"third_tenderer"}

role2id_dict = {"tenderee":0,
                "agency":1,
                "win_tenderer":2,
                "second_tenderer":3,
                "third_tenderer":4}

def getPackage(packageList,sentence_index,begin_index,roleid,MAX_DIS=None,DIRECT=None):
    '''
    @param:
        packageList:文章的包的信息,包号-sent_index-词偏移-字偏移-[[前作用域句子,句内偏移],[后作用域句子,句内偏移]]-匹配集合
        sentence_index:实体所在的句子
        begin_index:实体所在句子的起始位置
    @return:公司实体所属的包
    @summary: 优化多标段，确定标段作用域之后，寻找作用域包含该实体的所有包，从前往后找到一个还没有该roleid的包返回，若找到的包都有roleid,则返回第一个，若没有找到包，返回None
    '''
    
    '''
    if len(packageList)==0:
        return None
    before_index = None
    after_index = None
    equal_index = None
    equal_count = 0
    
    
    for pack_index in range(len(packageList)):
        if packageList[pack_index][1]>sentence_index and after_index is None:
            after_index = pack_index
        if packageList[pack_index][1]<sentence_index:
            before_index = pack_index
        if packageList[pack_index][1]==sentence_index and equal_index is None:
            equal_index = pack_index
    #当前句子和之前句子未找到包
    if before_index is None and equal_index is None:
        return None
    else:
        if after_index is None:
            end_index = len(packageList)
        else:
            end_index = after_index
        #只在当前句子找到一个包号
        if end_index-max((before_index if before_index is not None else -1,equal_index if equal_index is not None else -1))==1:
            return packageList[end_index-1][0]
        else:
            for i in range(max((before_index if before_index is not None else -1,equal_index if equal_index is not None else -1)),end_index):
                if packageList[i][2]>int(begin_index):
                    if packageList[i-1][4]:
                        return packageList[i-1][0]
                    else:
                        if packageList[i][4]:
                            return packageList[i-1][0]
                        else:
                            return packageList[i][0]
            return packageList[end_index-1][0]
    '''
    if len(packageList)==0:
        return None,False
    list_legalPack = []
    for pack_index in range(len(packageList)):
        if DIRECT=="L" and (packageList[pack_index]["sentence_index"]>sentence_index or (packageList[pack_index]["sentence_index"]==sentence_index and packageList[pack_index]["offsetWords_begin"]>begin_index)):
            continue
        if DIRECT=="R" and (packageList[pack_index]["sentence_index"]<sentence_index or (packageList[pack_index]["sentence_index"]==sentence_index and packageList[pack_index]["offsetwords_begin"]<begin_index)):
            continue
        if (packageList[pack_index]["scope"][0][0]<sentence_index or (packageList[pack_index]["scope"][0][0]==sentence_index and packageList[pack_index]["scope"][0][1]<=begin_index))  and (packageList[pack_index]["scope"][1][0]>sentence_index or (packageList[pack_index]["scope"][1][0]==sentence_index and packageList[pack_index]["scope"][1][1]>=begin_index)):
            if MAX_DIS is not None:
                if abs(sentence_index-packageList[pack_index]["sentence_index"])<=MAX_DIS:
                    list_legalPack.append(pack_index)
            else:
                list_legalPack.append(pack_index)
    # if (packageList[pack_index]["scope"][0][0] < sentence_index
    #         or (packageList[pack_index]["scope"][0][0] == sentence_index
    #      and packageList[pack_index]["scope"][0][1] <= begin_index))
    #         and (packageList[pack_index]["scope"][1][0] > sentence_index
    #      or (packageList[pack_index]["scope"][1][0] == sentence_index
    #         and packageList[pack_index]["scope"][1][1] >= begin_index)):
    #     pass
    _flag = True
    for _index in list_legalPack:
        if roleid in packageList[_index]["hit"]:
            continue
        else:
            _flag = False
            packageList[_index]["hit"].add(roleid)
            return packageList[_index]["pointer"],_flag
    if len(list_legalPack)>0:
        return packageList[0]["pointer"],_flag
    return None,False

#生成合法的组合
def get_legal_comba(list_entity,dict_role_combination):
    
    #拿到一个包中所有合法的组合
    def circle_package(_dict_legal_combination):
        list_dict_role_first = []
        for _role in _dict_legal_combination:
            if len(list_dict_role_first)==0:
                for _entity in _dict_legal_combination[_role]:
                    if _entity !="":
                        list_dict_role_first.append({_role:_entity})
            else:
                list_dict_role_after = []
                _find_count = 0
                for _entity in _dict_legal_combination[_role]:
                    if _entity !="":
                        for _dict in list_dict_role_first:
                            _flag = True
                            for _key1 in _dict:
                                if _entity==_dict[_key1]:
                                    #修改为招标人和代理人可以为同一个
                                    if str(_key1) in ["0","1"] and str(_role) in ["0","1"]:
                                        _flag = True
                                    else:
                                        _flag = False
                            if _flag:
                                _find_count += 1
                                _new_dict = copy.copy(_dict)
                                _new_dict[_role] = _entity
                                if len(list_dict_role_after)>100000:
                                    break
                                list_dict_role_after.append(_new_dict)
                            else:
                                # 2021/5/25 update,同一实体（entity_text）不同角色
                                if len(list_dict_role_after) > 100000:
                                    break
                                for _dict in list_dict_role_first:
                                    for _key1 in _dict:
                                        if _entity == _dict[_key1]:
                                            _new_dict = copy.copy(_dict)
                                            _new_dict.pop(_key1)
                                            _new_dict[_role] = _entity
                                            list_dict_role_after.append({_role:_entity})
                if len(list_dict_role_after)==0:
                    pass
                else:
                    list_dict_role_first.extend(list_dict_role_after)

        return list_dict_role_first



    def recursive_package(_dict_legal_combination,set_legal_entity,dict_one_selution,list_all_selution):
        last_layer = False
        #若是空组合则放回空
        if len(_dict_legal_combination.keys())==0:
            return []
        #递归到最后一层则修改状态
        if len(_dict_legal_combination.keys())==1:
            last_layer = True
        #取一个角色开始进行遍历
        _key_role = list(_dict_legal_combination.keys())[0]
        for item in _dict_legal_combination[_key_role]:
            copy_dict_one_selution = copy.copy(dict_one_selution)
            copy_dict_legal_combination = {}
            copy_set_legal_entity = copy.copy(set_legal_entity)
            
            #复制余下的所有角色，进行下一轮递归
            for _key in _dict_legal_combination.keys():
                if _key!=_key_role:
                    copy_dict_legal_combination[_key] = _dict_legal_combination[_key]

            #修改为招标人和代理人可以为同一个
            if item !="":
                _flag = True
                if str(_key_role) in ["0","1"]:
                    for _key_flag in copy_dict_one_selution:
                        if _key_flag not in ["0","1"] and copy_dict_one_selution[_key_flag]==item:
                            _flag = False
                else:
                    for _key_flag in copy_dict_one_selution:
                        if copy_dict_one_selution[_key_flag]==item:
                            _flag = False
                if _flag:
                    copy_dict_one_selution[_key_role] = item
                    
            '''
            if item not in copy_set_legal_entity:
                if item !="":
                    copy_dict_one_selution[_key_role] = item
            '''
            copy_set_legal_entity.add(item)
            if last_layer:
                list_all_selution.append(copy_dict_one_selution)
            else:
                recursive_package(copy_dict_legal_combination,copy_set_legal_entity,copy_dict_one_selution,list_all_selution)
    

    #递归匹配各个包的结果        
    def recursive_packages(_dict_legal_combination,dict_one_selution,list_all_selution):
        last_layer = False
        if len(_dict_legal_combination.keys())==0:
            return []
        if len(_dict_legal_combination.keys())==1:
            last_layer = True
        _key_pack = list(_dict_legal_combination.keys())[0]
        for item in _dict_legal_combination[_key_pack]:
            copy_dict_one_selution = copy.copy(dict_one_selution)
            copy_dict_legal_combination = {}
            for _key in _dict_legal_combination.keys():
                if _key!=_key_pack:
                    copy_dict_legal_combination[_key] = _dict_legal_combination[_key]
            for _key_role in item.keys():
                copy_dict_one_selution[_key_pack+"$$"+_key_role] = item[_key_role]
            if last_layer:
                list_all_selution.append(copy_dict_one_selution)
            else:
                recursive_packages(copy_dict_legal_combination,copy_dict_one_selution,list_all_selution)
        return list_all_selution
    
    #循环获取所有包组合
    def circle_pageages(_dict_legal_combination):
        list_all_selution = []
        for _key_pack in _dict_legal_combination.keys():
            list_key_selution = []
            for item in _dict_legal_combination[_key_pack]:
                _dict = dict()
                for _key_role in item.keys():
                    _dict[_key_pack+"$$"+_key_role] = item[_key_role]
                list_key_selution.append(_dict)
            if len(list_all_selution)==0:
                list_all_selution = list_key_selution
            else:
                _list_all_selution = []
                for item_1 in list_all_selution:
                    for item_2 in list_key_selution:
                        _list_all_selution.append(dict(item_1,**item_2))
                list_all_selution = _list_all_selution
        return list_all_selution
                      
    #拿到各个包解析之后的结果
    _dict_legal_combination = {}
    for packageName in dict_role_combination.keys():
        _list_all_selution = []

        # recursive_package(dict_role_combination[packageName], set(), {}, _list_all_selution)
        _list_all_selution = circle_package(dict_role_combination[packageName])
        '''
        # print("===1")
        # print(packageName)
        for item in _list_all_selution:
            # print(item)
        # print("===2")
        '''
        #去除包含子集
        list_all_selution_simple = []
        _list_set_all_selution = []
        for item_selution in _list_all_selution:
            item_set_selution = set()
            for _key in item_selution.keys():
                item_set_selution.add((_key,item_selution[_key]))
            _list_set_all_selution.append(item_set_selution)
        if len(_list_set_all_selution)>1000:
            _dict_legal_combination[packageName] = _list_all_selution
            continue
        for i in range(len(_list_set_all_selution)):
            
            be_included = False
            for j in range(len(_list_set_all_selution)):
                if i!=j:
                    if len(set(_list_set_all_selution[i])&set(_list_set_all_selution[j]))==len(_list_set_all_selution[i]) and len(_list_set_all_selution[i])!=len(_list_set_all_selution[j]):
                        be_included = True
            if not be_included:
                list_all_selution_simple.append(_list_all_selution[i])
        _dict_legal_combination[packageName] = list_all_selution_simple
    _list_final_comba = []
    #对各个包的结果进行排列组合
    _comba_count = 1
    for _key in _dict_legal_combination.keys():
        _comba_count *= len(_dict_legal_combination[_key])
    #如果过大，则每个包只取概率最大的那个
    dict_pack_entity_prob = get_dict_entity_prob(list_entity)
    if _comba_count>250:
        new_dict_legal_combination = dict()
        for _key_pack in _dict_legal_combination.keys():
            MAX_PROB = -1000
            _MAX_PROB_COMBA = None
            for item in _dict_legal_combination[_key_pack]:
                # print(_key_pack,item)
                _dict = dict()
                for _key in item.keys():
                    _dict[str(_key_pack)+"$$"+str(_key)] = item[_key]
                _prob = getSumExpectation(dict_pack_entity_prob, _dict)
                if _prob>MAX_PROB:
                    MAX_PROB = _prob
                    _MAX_PROB_COMBA = [item]
            if _MAX_PROB_COMBA is not None:
                new_dict_legal_combination[_key_pack] = _MAX_PROB_COMBA
        _dict_legal_combination = new_dict_legal_combination
    #recursive_packages(_dict_legal_combination, {}, _list_final_comba)
    _list_final_comba = circle_pageages(_dict_legal_combination)
    #除了Project包(招标人和代理人)，其他包是不会有冲突的
    #查看是否有一个实体出现在了Project包和其他包中，如有，要进行裁剪
    _list_real_comba = []
    for dict_item in _list_final_comba:
        set_project = set()
        set_other = set()
        for _key in list(dict_item.keys()):
            if _key.split("$$")[0]=="Project":
                set_project.add(dict_item[_key])
            else:
                set_other.add(dict_item[_key])
        set_common = set_project&set_other
        if len(set_common)>0:
            dict_project = {}
            dict_not_project = {}
            for _key in list(dict_item.keys()):
                if dict_item[_key] in set_common:
                    if str(_key.split("$$")[0])=="Project":
                        dict_project[_key] = dict_item[_key]
                    else:
                        dict_not_project[_key] = dict_item[_key]
                else:
                    dict_project[_key] = dict_item[_key]
                    dict_not_project[_key] = dict_item[_key]
            
            _list_real_comba.append(dict_project)
            _list_real_comba.append(dict_not_project)
        else:
            _list_real_comba.append(dict_item)

    return _list_real_comba

def get_dict_entity_prob(list_entity,on_value=0.5):
    dict_pack_entity_prob = {}
    for in_attachment in [False,True]:
        identified_role = []
        if in_attachment==True:
            identified_role = [value[0] for value in dict_pack_entity_prob.values()]
        for entity in list_entity:
            if entity.entity_type in ['org','company'] and entity.in_attachment==in_attachment:
                values = entity.values
                role_prob = float(values[int(entity.label)])
                _key = entity.packageName+"$$"+str(entity.label)
                if role_prob>=on_value and str(entity.label)!="5":
                    _key_prob = _key+"$text$"+entity.entity_text
                    if in_attachment == True:
                        role_prob = 0.8 if role_prob>0.8 else role_prob   #附件的概率修改低点
                        # if entity.entity_text in identified_role: # 2023/7/3 注释掉，选取概率最大的作为连接概率
                        #     continue
                    if _key_prob in dict_pack_entity_prob:
                        # new_prob = role_prob+dict_pack_entity_prob[_key_prob][1] if role_prob>0.9 else max(role_prob, dict_pack_entity_prob[_key_prob][1])
                        # dict_pack_entity_prob[_key_prob] = [entity.entity_text, new_prob] #公司同角色多次出现概率累计
                        if role_prob>dict_pack_entity_prob[_key_prob][1]:
                            dict_pack_entity_prob[_key_prob] = [entity.entity_text,role_prob]
                    else:
                        dict_pack_entity_prob[_key_prob] = [entity.entity_text,role_prob]
    return dict_pack_entity_prob


#计算合计期望            
def getSumExpectation(dict_pack_entity_prob,combination,on_value=0.5):
    '''
    expect = 0
    for entity in list_entity:
        if entity.entity_type in ['org','company']:
            values = entity.values
            role_prob = float(values[int(entity.label)])
            _key = entity.packageName+"$$"+str(entity.label)
            if role_prob>on_value and str(entity.label)!="5":
                if _key in combination.keys() and combination[_key]==entity.entity_text:
                    expect += math.pow(role_prob,4)
                else:
                    expect -= math.pow(role_prob,4)
    '''
    #修改为同一个实体只取对应包-角色的最大的概率值
    expect = 0
    dict_entity_prob = {}
    for _key_pack_entity in dict_pack_entity_prob:
        _key_pack = _key_pack_entity.split("$text$")[0]
        role_prob = dict_pack_entity_prob[_key_pack_entity][1]
        if _key_pack in combination.keys() and combination[_key_pack]==dict_pack_entity_prob[_key_pack_entity][0]:
            if _key_pack_entity in dict_entity_prob.keys():
                if dict_entity_prob[_key_pack_entity]<role_prob:
                    dict_entity_prob[_key_pack_entity] = role_prob
            else:
                dict_entity_prob[_key_pack_entity] = role_prob
        else:
            if _key_pack_entity in dict_entity_prob.keys():
                if dict_entity_prob[_key_pack_entity]>-role_prob:
                    dict_entity_prob[_key_pack_entity] = -role_prob
            else:
                dict_entity_prob[_key_pack_entity] = -role_prob
    # for entity in list_entity:
    #     if entity.entity_type in ['org','company']:
    #         values = entity.values
    #         role_prob = float(values[int(entity.label)])
    #         _key = entity.packageName+"$$"+str(entity.label)
    #         if role_prob>=on_value and str(entity.label)!="5":
    #             if _key in combination.keys() and combination[_key]==entity.entity_text:
    #                 _key_prob = _key+entity.entity_text
    #                 if _key_prob in dict_entity_prob.keys():
    #                     if dict_entity_prob[_key_prob]<role_prob:
    #                         dict_entity_prob[_key_prob] = role_prob
    #                 else:
    #                     dict_entity_prob[_key_prob] = role_prob
    #             else:
    #                 _key_prob = _key+entity.entity_text
    #                 if _key_prob in dict_entity_prob.keys():
    #                     if dict_entity_prob[_key_prob]>-role_prob:
    #                         dict_entity_prob[_key_prob] = -role_prob
    #                 else:
    #                     dict_entity_prob[_key_prob] = -role_prob
    for _key in dict_entity_prob.keys():
        symbol = 1 if dict_entity_prob[_key]>0 else -1 
        expect += symbol*math.pow(dict_entity_prob[_key],2)
    return expect


def getRoleList(list_sentence,list_entity,on_value = 0.5):
    '''
    @summary: 搜索树，得到所有不矛盾的角色组合，取合计期望值最大的作为结果返回
    @param:
        list_sentence:文章所有的sentence
        list_entity:文章所有的实体
        on_value:概率阈值
    @return:文章的角色list
    '''

    pack = getPackagesFromArticle(list_sentence,list_entity)
    if pack is None:
        return None
    # PackageList,PackageSet,dict_PackageCode = pack
    PackageList,PackageSet,dict_PackageCode,main_body_pack = pack

    #拿到所有可能的情况
    dict_role_combination = {}
    tenderee_or_agency_set = set() # 记录所有预测为招标或代理的实体集合
    win_tenderer_set = set() # 记录所有预测为中标的实体集合
  # print(PackageList)
    #拿到各个实体的packageName,packageCode
    for entity in list_entity:
        if entity.entity_type in ['org','company']:
            #限制附件里角色values[label]最大概率prob
            max_prob = 0.85
            if str(entity.label)!="5" and entity.in_attachment:
                if entity.values[entity.label]>max_prob:
                    entity.values[entity.label] = max_prob
            #过滤掉字数小于3个的实体
            if len(entity.entity_text)<=3:
                continue
            values = entity.values
            role_prob = float(values[int(entity.label)])
            if role_prob>=on_value and str(entity.label)!="5":
                if str(entity.label) in ["0","1"]:
                    packageName = "Project"
                else:
                    if len(PackageSet)>0:
                        packagePointer,_ = getPackage(PackageList,entity.sentence_index,entity.begin_index,"role-"+str(entity.label))
                        if packagePointer is None:
                            #continue
                            packageName = "Project"
                          # print(entity.entity_text, packageName,entity.sentence_index,entity.begin_index)
                        else:
                            #add pointer_pack
                            entity.pointer_pack = packagePointer
                            packageName = packagePointer.entity_text
                          # print(entity.entity_text, packageName)
                    else:
                        packageName = "Project"
                    find_flag = False

                    if packageName in dict_PackageCode.keys():
                        packageCode = dict_PackageCode[packageName]
                    else:
                        packageCode = ""
                    entity.packageCode = packageCode
                role_name = dict_role_id.get(str(entity.label))
                entity.roleName = role_name
                entity.packageName = packageName
                if entity.packageName in dict_role_combination.keys():
                    if str(entity.label) in dict_role_combination[entity.packageName].keys():
                        dict_role_combination[entity.packageName][str(entity.label)].add(entity.entity_text)
                    else:
                        dict_role_combination[entity.packageName][str(entity.label)] = set([entity.entity_text])
                else:
                    dict_role_combination[entity.packageName] = {}
                    #初始化空值
                    roleIds = [0,1,2,3,4]
                    for _roleId in roleIds:
                        dict_role_combination[entity.packageName][str(_roleId)] = set([""])
                    dict_role_combination[entity.packageName][str(entity.label)].add(entity.entity_text)
    list_real_comba = get_legal_comba(list_entity,dict_role_combination)
    # print("===role_combination",dict_role_combination)
    # print("== real_comba",list_real_comba)
    #拿到最大期望值的组合
    max_index = 0
    max_expect = -100
    _index = 0
    dict_pack_entity_prob = get_dict_entity_prob(list_entity)
    for item_combination in list_real_comba:
        expect = getSumExpectation(dict_pack_entity_prob, item_combination)
        if expect>max_expect:
            max_index = _index
            max_expect = expect
        _index += 1
    RoleList = []
    RoleSet = set()
    if len(list_real_comba)>0:
        for _key in list_real_comba[max_index].keys():
            packageName = _key.split("$$")[0]
            label = _key.split("$$")[1]
            role_name = dict_role_id.get(str(label))
            entity_text = list_real_comba[max_index][_key]
            entity_prob = dict_pack_entity_prob.get(_key+'$text$'+entity_text, ['',0])[1]
            # entity_text = list_real_comba[max_index][_key][0]
            # entity_prob = list_real_comba[max_index][_key][1]
            if packageName in dict_PackageCode.keys():
                packagecode = dict_PackageCode.get(packageName)
            else:
                packagecode = ""
            RoleList.append(PREM(packageName,packagecode,role_name,entity_text,entity_prob,0,0.0,[]))
            if str(label) in ["0", "1"]:
                tenderee_or_agency_set.add(entity_text)
            elif str(label) in ["2"] and entity_prob > 0.8:
                win_tenderer_set.add(entity_text)

            if len(list_real_comba) > 1 and label == '2':
                multi_winner = []
                for comba in list_real_comba:
                    tmp_ent = comba.get(_key, '')
                    tmp_prob = dict_pack_entity_prob.get(_key+'$text$'+tmp_ent, ['',0])[1]
                    if tmp_ent !='' and tmp_prob>0.8:
                        multi_winner.append(comba[_key])
                if len(set(multi_winner)) > 1:
                    RoleList[-1].multi_winner = multi_winner
            # print('RoleList: ', RoleList)
            RoleSet.add(entity_text)

    #根据最优树来修正list_entity中角色对包的连接
    for _entity in list_entity:
        if _entity.pointer_pack is not None:
            _pack_name = _entity.pointer_pack.entity_text
            _find_flag = False
            for _prem in RoleList:
                if _prem.packageName==_pack_name and _prem.entity_text==_entity.entity_text:
                    _find_flag = True
            if not _find_flag:
                _entity.pointer_pack = None
    return RoleList,RoleSet,PackageList,PackageSet,win_tenderer_set,tenderee_or_agency_set,main_body_pack

def getPackageScopePattern():
    '''
    @summary: 获取包的作用域关键词
    '''
    df = pd.read_excel(os.path.dirname(__file__)+"/end.xls")
    pattern = "("
    for item in df["list_word"]:
        item = str(item).replace("(","\(").replace(")","\)").replace(".","\.").replace("[","\[").replace("]","\]").replace("-","\-")
        pattern += item+"|"
    pattern = pattern[:-1]+")[:：是为]|业绩.{,30}标段[0-9A-Za-z一二三四五六七八九十]{0,3}"
    return pattern
        
pattern_packageScope = getPackageScopePattern()   

def getPackagesFromArticle(list_sentence, list_entity):
    '''
    @param:
        list_sentence:文章的句子list
    @summary: 将包的信息插入list_entity中
    @return: type:list if [包号,句子index,词偏移,标段号] meaning:文章的包/标段信息
    '''

    if len(list_sentence) == 0:
        return None
    list_sentence.sort(key=lambda x: x.sentence_index)

    PackageList = []
    PackageList_scope = []
    PackageSet = set()
    dict_packageCode = dict()
    main_body_pack = set()  # 2024/04/28 保存正文包号

    # package_number_pattern =  re.compile(
    # '((施工|监理|监测|勘察|设计|劳务)(标段)?[0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦa-zA-Z]{,4}(标段?|包))|(([a-zA-Z]包[：）]?)?第?[0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦa-zA-Z]{1,4}标[段包]?)|((标[段号的包项]|([标分子]|合同|项目|采购|（)包|包[组件号])[0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦA-Za-z]{1,4})|(([，；。、：（]|第)[0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ]{1,4}分?包)|([a-zA-Z][0-9]{,3}分?[包标])|.{,1}((包组|包件|包号|分?包|标[段号的包]|子项目)编?号?[:：]?[a-zA-Z0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ-]+)|[，；。、：（]包[0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ]{1，4}[^\w]')  # 标号

#     package_number_pattern = re.compile(
#         '((施工|监理|监测|勘察|设计|劳务)(标段)?：?第?([一二三四五六七八九十]{1,3}|[ⅠⅡⅢⅣⅤⅥⅦ]{1,3}|[a-zA-Z0-9]{1,9}\-?[a-zA-Z0-9-]{,9})?[分子]?(标[段包项]?|包[组件标]?|合同[包段]))\
# |(([a-zA-Z]包[：（）]?)?第?([一二三四五六七八九十]{1,3}|[ⅠⅡⅢⅣⅤⅥⅦ]{1,3}|[a-zA-Z0-9]{1,9}\-?[a-zA-Z0-9-]{,9})[分子]?(标[段包项]?|合同[包段]))\
# |(([，；。、：（]|第)?([一二三四五六七八九十]{1,3}|[ⅠⅡⅢⅣⅤⅥⅦ]{1,3}|[a-zA-Z0-9]{1,9}\-?[a-zA-Z0-9-]{,9})[分子]?(标[段包项]?|包[组件标]?|合同[包段]))\
# |((标[段包项]|标段（包）|包[组件标]|[标分子（]包)(\[|【)?：?([一二三四五六七八九十]{1,3}|[ⅠⅡⅢⅣⅤⅥⅦ]{1,3}|[a-zA-Z0-9]{1,9}\-?[a-zA-Z0-9-]{,9}))\
# |[，；。、：（](标的?|项目|子项目?)(\[|【)?：?([一二三四五六七八九十]+|[0-9]{1,9})\
# |((([标分子（]|合同|项目|采购)包|[，。]标的|子项目|[分子]标|标[段包项]|包[组件标]?)编?号[:：]?[a-zA-Z0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ-]{1,9})\
# |[，；。、：（]?(合同|分|子)?包：?([一二三四五六七八九十]{1,3}|[ⅠⅡⅢⅣⅤⅥⅦ]{1,3}|[a-zA-Z0-9]{1,9}\-?[a-zA-Z0-9-]{,9})')

    other_package_pattern = re.compile(
        '((项目|物资|设备|场次|标段|标的|产品)(名称)?)[:：]([^，。]{2,50}?)[，。]')  # # 2020/11/23 大网站规则 调整  package_N_name_pattern， package_N_name_pattern 中的项目 改为 子项目
    win_tenderer_pattern = re.compile('(中标候?选?人|供应商)(名称)?[:：](.{2,25})[，。]')  # 2020/11/23 大网站规则 调整
    model_pattern = re.compile('(型号|序号)[:：]([^，。]{2,20})[，。]')  # 2020/11/23 大网站规则 调整
    number_pattern = re.compile("[0-9A-Za-z一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ]{1,4}")

    package_code_pattern = re.compile("(?:编号[:：]?\s*)([-\dA-Za-z\(\)]{1,20})")
    # 纯数字类型的包号统一，例如：'01','1'
    re_digital = re.compile("^\d+$")

    def changeIndexFromWordToWords(tokens, word_index):
        '''
        @summary:转换某个字的字偏移为词偏移
        '''
        before_index = 0
        after_index = 0
        for i in range(len(tokens)):
            after_index = after_index + len(tokens[i])
            if before_index <= word_index and after_index >= word_index:
                return i
            before_index = after_index

    package_names = []

    def extractPackageCode(tokens, word_index, size=20, pattern=package_code_pattern):
        '''
        @summary:抽取包附近的标段号
        @param:
            tokens:包所在句子的分词
            word_index:包所在字偏移
            size:左右各取多少个词
            pattern:提取标段号的正则
        @return: type:string,meaning:标段号
        '''
        index = changeIndexFromWordToWords(tokens, word_index)
        if index < size:
            begin = index
        else:
            begin = index - size
        if index + size > len(tokens):
            end = len(tokens)
        else:
            end = index + size
        # 拿到左右两边的词语组成短语
        text = "".join(tokens[begin:end])
        # 在短语中的字偏移
        new_word_index = word_index - len("".join(tokens[:begin]))
        min_distance = len(text)
        packageCode = None
        for the_iter in re.finditer(pattern, text):
            # 算出最小距离
            distance = min([abs(new_word_index - the_iter.span()[0]), abs(new_word_index - the_iter.span()[1])])
            if distance < min_distance:
                min_distance = distance
                packageCode = the_iter.group(1)
        return packageCode

    def get_package():
        PackageList_scope = []
        True_package = set()
        for i in range(len(list_sentence)):
            PackageList_item = []
            PackageList_item_scope = []
            content = list_sentence[i].sentence_text

#             content = content.replace('号，', '号：').replace(':', '：').replace('(', '（').replace(')', '）')
#             # .replace('-包',' 包').replace('包-', '包 ').replace('-标', ' 标').replace('标段-', '标段 ').replace('-合同包', ' 合同包') # 72760191 标段：№10
#             content = re.sub('[一二三四五六七八九十\d](标[段包项]|包[组件标])编号', ' 标段编号', content)
#
#             for it in re.finditer('CA标|(每个?|所有|相关|个|各|不分)[分子]?(标[段包项]?|包[组件标]?|合同包)|(质量|责任)三包|包[/每]|标段(划分|范围)|(承|压缩|软|皮|书|挂)包\
# |标[识注签贴配]|[商油]标号|第X包|第[一二三四五六七八九十]+至[一二三四五六七八九十]+(标[段包项]?|包[组件标]?|合同[包段])\
# |\.(docx|doc|pdf|xlsx|xls|jpg)|[一二三四五]次|五金|\d+[年月]|[\d.,]+万?元|\d+\.\d+', content):
#                 content = content.replace(it.group(0), ' ' * len(it.group(0)))
#             tokens = list_sentence[i].tokens
#             _names = []
#             for iter in re.finditer(package_number_pattern, content):
#                 if re.search('(业绩|信誉要求)：', content[:iter.start()]): # 前面有业绩或信誉的标段去掉
#                     continue
#                 # print('提取到标段：%s， 前后文：%s'%(iter.group(), content[iter.start()-5:iter.end()+5]))
#                 if re.match('\d', iter.group(0)) and re.search('\d\.$', content[:iter.start()]):  # 排除2.10标段3  5.4标段划分 这种情况
#                     # print('过滤掉错误包：', iter.group())
#                     continue
#                 if re.search('[承每书/]包|XX|xx', iter.group(0)) or re.search('\d包[/每]\w|一包[0-9一二三四五六七八九十]+', content[iter.start():iter.end()+3]) or re.search('[a-zA-Z0-9一二三四五六七八九十ⅠⅡⅢⅣⅤⅥⅦ-]{6,}', iter.group(0)):
#                     # print('过滤掉错误包：', iter.group())
#                     continue
#                 elif iter.end()+2 < len(content) and  re.search('标准|标的物|标志|包装|划分|标书', content[iter.start():iter.end()+2]):
#                     # print('过滤掉错误包：',iter.group())
#                     continue
#                 elif re.search('同一(标段?|包)', content[max(0, iter.start()-2):iter.end()]):  # 不得参加同一标段
#                     # print('过滤掉错误包：', iter.group())
#                     continue
#                 elif re.search('三包', content[max(0, iter.start()-2):iter.end()]) and re.search('第三包', content[max(0, iter.start()-2):iter.end()])==None:  # 规规章和“三包”规定
#                     # print('过滤掉错误包：', iter.group())
#                     continue
#                 elif re.search('[1-9]\d{2,}$|\d{4,}|^[1-9]\d{2,}|合同包[A-Za-z]{2,}', iter.group(0)):
#                     # print('过滤掉错误包号5：', iter.group(0))
#                     continue

            tokens = list_sentence[i].tokens
            _names = []
            for iter in find_package(content):
                temp_package_number = uniform_package_name(iter.group(0))
                True_package.add(temp_package_number)
                PackageList_item.append({"name": temp_package_number, "sentence_index": list_sentence[i].sentence_index,
                                         "offsetWords_begin": changeIndexFromWordToWords(tokens, iter.span()[0]),
                                         "offsetWord_begin": iter.span()[0], "offsetWord_end": iter.span()[1]})
                # PackageList_item.append([temp_package_number,i,changeIndexFromWordToWords(tokens,iter.span()[0]),iter.span()[0],iter.span()[1]])
                code = extractPackageCode(tokens, iter.span()[0])
                if code is not None:
                    dict_packageCode[temp_package_number] = code
                PackageSet.add(temp_package_number)
                if not list_sentence[i].in_attachment: # 保存不在附件的包号
                    main_body_pack.add(temp_package_number)

            # 识别packageScope
            for iter in re.finditer(pattern_packageScope, content):
                PackageList_item_scope.append({"name": "", "sentence_index": list_sentence[i].sentence_index,
                                               "offsetWords_begin": changeIndexFromWordToWords(tokens, iter.span()[0]),
                                               "offsetWord_begin": iter.span()[0], "offsetWord_end": iter.span()[1]})
                # PackageList_item_scope.append(["",i,changeIndexFromWordToWords(tokens,iter.span()[0]),iter.span()[0],iter.span()[1]])
            PackageList_item_scope = PackageList_item + PackageList_item_scope
            PackageList_item_scope.sort(key=lambda x: x["offsetWord_begin"])
            PackageList_scope = PackageList_scope + PackageList_item_scope
            PackageList_item.sort(key=lambda x: x["sentence_index"])
        return PackageList_scope, True_package

    def get_win_project():
        '''获取多个项目多个中标人的项目'''
        PackageList_scope = []
        True_package = set()
        # 2020/11/23 大网站规则 调整
        if len(PackageSet) == 0 and len(
                set([it.entity_text for it in list_entity if
                     it.entity_type in ['org', 'company'] and it.label == 2])) > 1:
            for i in range(len(list_sentence)):
                PackageList_item = []
                PackageList_item_scope = []
                content = list_sentence[i].sentence_text
                tokens = list_sentence[i].tokens
                names = re.findall(other_package_pattern, content)
                N_names = re.findall(win_tenderer_pattern, content)
                if len(names) != 1 or len(N_names) != 1:
                    continue
                for iter in re.finditer(other_package_pattern, content):
                    temp_package_number = iter.group(4)
                    xinghao = re.search(model_pattern, content)
                    if xinghao:
                        temp_package_number = temp_package_number + '+' + xinghao.group(2)
                    # print('新正则采购包名补充',temp_package_number)
                    if re.search(re_digital, temp_package_number):
                        temp_package_number = str(int(temp_package_number))
                    True_package.add(temp_package_number)
                    PackageList_item.append(
                        {"name": temp_package_number, "sentence_index": list_sentence[i].sentence_index,
                         "offsetWords_begin": changeIndexFromWordToWords(tokens, iter.span()[0]),
                         "offsetWord_begin": iter.span()[0], "offsetWord_end": iter.span()[1]})
                    # PackageList_item.append([temp_package_number,i,changeIndexFromWordToWords(tokens,iter.span()[0]),iter.span()[0],iter.span()[1]])
                    code = extractPackageCode(tokens, iter.span()[0])
                    if code is not None:
                        dict_packageCode[temp_package_number] = code
                    PackageSet.add(temp_package_number)
                    if not list_sentence[i].in_attachment:  # 保存不在附件的包号
                        main_body_pack.add(temp_package_number)

                # 识别packageScope
                for iter in re.finditer(pattern_packageScope, content):
                    PackageList_item_scope.append({"name": "", "sentence_index": list_sentence[i].sentence_index,
                                                   "offsetWords_begin": changeIndexFromWordToWords(tokens,
                                                                                                   iter.span()[0]),
                                                   "offsetWord_begin": iter.span()[0],
                                                   "offsetWord_end": iter.span()[1]})
                    # PackageList_item_scope.append(["",i,changeIndexFromWordToWords(tokens,iter.span()[0]),iter.span()[0],iter.span()[1]])
                PackageList_item_scope = PackageList_item + PackageList_item_scope
                PackageList_item_scope.sort(key=lambda x: x["offsetWord_begin"])
                PackageList_scope = PackageList_scope + PackageList_item_scope
                PackageList_item.sort(key=lambda x: x["sentence_index"])
        return PackageList_scope, True_package

    def get_package_scope(PackageList_scope):
        PackageList = []
        pattern_punctuation = "[:：（）\(\),，。；;]"
        # print("===packageList_scope",PackageList_scope)
        for i in range(len(list_sentence)):
            for j in range(len(PackageList_scope)):
                if i == PackageList_scope[j]["sentence_index"] and PackageList_scope[j]["name"] != "":
                    _flag = False
                    left_str = list_sentence[i].sentence_text[
                               PackageList_scope[j]["offsetWord_begin"] - 30:PackageList_scope[j][
                                                                                 "offsetWord_begin"] + 1]
                    right_str = list_sentence[i].sentence_text[
                                PackageList_scope[j]["offsetWord_begin"]:PackageList_scope[j]["offsetWord_begin"] + 30]
                    _left_find = re.findall(pattern_punctuation, left_str)
                    _right_find = re.findall(pattern_punctuation, right_str)
                    # print(left_str)
                    if re.search("同", left_str[-1:]) is not None and PackageList_scope[j]["name"] == "一":
                        continue
                    if re.search("划分", right_str[:10]) is not None:
                        continue
                    if len(_left_find) > 0 and _left_find[-1] in [":", "："]:
                        _flag = True
                    if len(_right_find) > 0 and _right_find[0] in [":", "："]:
                        _flag = True
                    if _flag:
                        scope_begin = [PackageList_scope[j]["sentence_index"],
                                       PackageList_scope[j]["offsetWords_begin"]]
                    else:
                        if j == 0:
                            scope_begin = [0, 0]
                        else:
                            scope_begin = [PackageList_scope[j - 1]["sentence_index"],
                                           PackageList_scope[j - 1]["offsetWords_begin"]]
                    if j == len(PackageList_scope) - 1:
                        scope_end = [list_sentence[-1].sentence_index,
                                     changeIndexFromWordToWords(list_sentence[-1].tokens,
                                                                len(list_sentence[
                                                                        -1].sentence_text))]
                    else:
                        scope_end = [PackageList_scope[j + 1]["sentence_index"],
                                     PackageList_scope[j + 1]["offsetWords_begin"]]
                    if j>0 and PackageList_scope[j - 1]["sentence_index"] == PackageList_scope[j]["sentence_index"] and \
                            PackageList_scope[j - 1]["offsetWord_begin"] <= PackageList_scope[j]["offsetWord_begin"] and \
                            PackageList_scope[j - 1]["offsetWord_end"] >= PackageList_scope[j]["offsetWord_end"]:
                        continue

                    # add package to entity
                    _pack_entity = Entity(doc_id=list_sentence[0].doc_id, entity_id="%s_%s_%s_%s" % (
                        list_sentence[0].doc_id, i, PackageList_scope[j]["offsetWord_begin"],
                        PackageList_scope[j]["offsetWord_begin"]), entity_text=PackageList_scope[j]["name"],
                                          entity_type="package", sentence_index=PackageList_scope[j]["sentence_index"],
                                          begin_index=changeIndexFromWordToWords(list_sentence[i].tokens,
                                                                                 PackageList_scope[j][
                                                                                     "offsetWord_begin"]),
                                          end_index=changeIndexFromWordToWords(list_sentence[i].tokens,
                                                                               PackageList_scope[j]["offsetWord_end"]),
                                          wordOffset_begin=PackageList_scope[j]["offsetWord_begin"],
                                          wordOffset_end=PackageList_scope[j]["offsetWord_end"],
                                          in_attachment=list_sentence[i].in_attachment)
                    list_entity.append(_pack_entity)
                    copy_pack = copy.copy(PackageList_scope[j])
                    copy_pack["scope"] = [scope_begin, scope_end]
                    copy_pack["hit"] = set()
                    copy_pack["pointer"] = _pack_entity
                    PackageList.append(copy_pack)
        return PackageList

    PackageList_scope, True_package = get_package()
    # PackageList_scope2, True_package2 = get_win_project()  # 20240508 与表格提取重复，去掉
    # if len(True_package2) > 2: # 同时包含多标段及多中标人的
    #     PackageList_scope = PackageList_scope + PackageList_scope2
    PackageList = get_package_scope(PackageList_scope)
    # if len(PackageSet)<2: # 20230922只提取到一个包号的去掉，都放在默认包project 2024/02/02 注释掉，防止多标段每篇公告只公布一个标段的没法提取标段号
        # return [], set(), {}
    return PackageList, PackageSet, dict_packageCode, main_body_pack


# km配对方法
def dispatch(match_list):
    main_roles = list(set([match.main_role for match in match_list]))
    attributes = list(set([match.attribute for match in match_list]))

    label = np.zeros(shape=(len(main_roles), len(attributes)))
    for match in match_list:
        main_role = match.main_role
        attribute = match.attribute
        value = match.value
        label[main_roles.index(main_role), attributes.index(attribute)] = value + 10000
    # print(label)
    gragh = -label
    # km算法
    row, col = linear_sum_assignment(gragh)
    max_dispatch = [(i, j) for i, j, value in zip(row, col, gragh[row, col]) if value]
    # return [Match(main_roles[row], attributes[col]) for row, col in max_dispatch]
    return [(main_roles[row], attributes[col]) for row, col in max_dispatch]

from BiddingKG.dl.common.Utils import getUnifyMoney
from BiddingKG.dl.interface.modelFactory import Model_relation_extraction
relationExtraction_model = Model_relation_extraction()
def findAttributeAfterEntity(PackDict,roleSet,PackageList,PackageSet,list_sentence,list_entity,list_outline,on_value = 0.5,on_value_person=0.5,sentence_len=4):
    '''
    @param:
        PackDict:文章包dict
        roleSet:文章所有角色的公司名称
        PackageList:文章的包信息
        PackageSet:文章所有包的名称
        list_entity:文章所有经过模型处理的实体
        on_value:金额模型的阈值
        on_value_person:联系人模型的阈值
        sentence_len:公司和属性间隔句子的最大长度
    @return:添加了属性信息的角色list
    '''
    
    #根据roleid添加金额到rolelist中
    def addMoneyByRoleid(packDict,packageName,roleid,money,money_prob):
        for i in range(len(packDict[packageName]["roleList"])):
            if packDict[packageName]["roleList"][i].role_name==dict_role_id.get(str(roleid)):
                if money_prob>packDict[packageName]["roleList"][i].money_prob:
                    packDict[packageName]["roleList"][i].money = money
                    packDict[packageName]["roleList"][i].money_prob = money_prob
        return packDict
                    
    #根据实体名称添加金额到rolelist中
    def addMoneyByEntity(packDict,packageName,entity,money,money_prob):
        for i in range(len(packDict[packageName]["roleList"])):
            if packDict[packageName]["roleList"][i].entity_text==entity:
                # if money_prob>packDict[packageName]["roleList"][i].money_prob:
                #     packDict[packageName]["roleList"][i].money = money
                #     packDict[packageName]["roleList"][i].money_prob = money_prob
                if packDict[packageName]["roleList"][i].money_prob==0 :  # 2021/7/20第一次更新金额
                    packDict[packageName]["roleList"][i].money = money.entity_text
                    packDict[packageName]["roleList"][i].money_prob = money_prob
                    packDict[packageName]["roleList"][i].money_unit = money.money_unit
                elif money_prob>packDict[packageName]["roleList"][i].money_prob+0.2 or (money.notes in ['大写'] and money.in_attachment==False): # 2021/7/20改为优先选择大写金额,
                    # print('已连接金额概率：money_prob:',packDict[packageName]["roleList"][i].money_prob)
                    # print('链接金额备注 ',money.notes, money.entity_text, money.values)
                    packDict[packageName]["roleList"][i].money = money.entity_text
                    packDict[packageName]["roleList"][i].money_prob = money_prob
                    packDict[packageName]["roleList"][i].money_unit = money.money_unit
                # print('链接中的金额：{0}, 单位：{1}'.format(money.entity_text, money.money_unit))
        return packDict
    def addRatioByEntity(packDict,packageName,entity,ratio):
        for i in range(len(packDict[packageName]["roleList"])):
            if packDict[packageName]["roleList"][i].entity_text==entity:
                packDict[packageName]["roleList"][i].ratio = ratio.ratio_value
    def addServiceTimeByEntity(packDict,packageName,entity,serviceTime):
        for i in range(len(packDict[packageName]["roleList"])):
            if packDict[packageName]["roleList"][i].entity_text==entity:
                packDict[packageName]["roleList"][i].serviceTime = serviceTime.entity_text

    #根据实体名称得到角色
    def getRoleWithText(packDict,entity_text):
        for pack in packDict.keys():
            for i in range(len(packDict[pack]["roleList"])):
                if packDict[pack]["roleList"][i].entity_text==entity_text:
                    return packDict[pack]["roleList"][i].role_name
    
    def doesEntityOrLinkedEntity_inRoleSet(entity,RoleSet):
        _list_entitys = [entity]+entity.linked_entitys
        for _entity in _list_entitys:
            if _entity.entity_text in RoleSet:
                return True
    
    p_entity = 0

    # 2021/7/19 顺序比较金额，前面是后面的一万倍则把前面金额/10000
    # money_list = [it for it in list_entity if it.entity_type=="money"]
    # for i in range(len(money_list)-1):
    #     for j in range(1, len(money_list)):
    #         if (float(money_list[i].entity_text) > 5000000000 or money_list[j].notes=='大写') and \
    #                 Decimal(money_list[i].entity_text)/Decimal(money_list[j].entity_text)==10000:
    #             money_list[i].entity_text = str(Decimal(money_list[i].entity_text)/10000)
    #             # print('连接前修改大于50亿金额：前面是后面的一万倍则把前面金额/10000')

    '''同样金额同时有元及万元单位的，把万元的金额改为元'''
    wanyuan = []
    yuan = []
    for it in list_entity:
        if it.entity_type == "money" and float(it.entity_text)>1000000: # 20240523 修改为百万以上金额才对比万倍关系，其他又行业限额纠正避免有些万元单位提取不到从而被除一万 例：52435607 最高限价（万元）：22679.32 蜀冈招标控制价22679.32工程地点南路西侧（万元）
            if it.money_unit == '万元' or float(it.entity_text)>5000000000:
                wanyuan.append(it)
            if it.money_unit == '元' or float(it.entity_text)<5000000:
                yuan.append(it)
    if wanyuan != [] and yuan != []:
        for m1 in wanyuan:
            for m2 in yuan:
                if Decimal(m1.entity_text)/Decimal(m2.entity_text) == 10000:
                    m1.entity_text = m2.entity_text


    #遍历所有实体
    # while(p_entity<len(list_entity)):
    #     entity = list_entity[p_entity]
        '''
        #招标金额从后往前找
        if entity.entity_type=="money":
            if entity.values[entity.label]>=on_value:
                if str(entity.label)=="0":
                    packagePointer,_ = getPackage(PackageList,entity.sentence_index,entity.begin_index,"money-"+str(entity.label))
                    if packagePointer is None:
                        packageName = "Project"
                    else:
                        packageName = packagePointer.entity_text
                    addMoneyByRoleid(PackDict, packageName, "0", entity.entity_text, entity.values[entity.label])
        '''
        ''' # 2020/11/25 与下面的联系人连接步骤重复，取消
        if entity.entity_type=="person":
            if entity.values[entity.label]>=on_value_person:
                if str(entity.label)=="1":
                    for i in range(len(PackDict["Project"]["roleList"])):
                        if PackDict["Project"]["roleList"][i].role_name=="tenderee":
                            PackDict["Project"]["roleList"][i].linklist.append((entity.entity_text,entity.person_phone))
                        # add pointer_person
                        for _entity in list_entity:
                            if dict_role_id.get(str(_entity.label))=="tenderee":
                                for i in range(len(PackDict["Project"]["roleList"])):
                                    if PackDict["Project"]["roleList"][i].entity_text==_entity.entity_text and PackDict["Project"]["roleList"][i].role_name=="tenderee":
                                        _entity.pointer_person = entity
                elif str(entity.label)=="2":
                    for i in range(len(PackDict["Project"]["roleList"])):
                        if PackDict["Project"]["roleList"][i].role_name=="agency":
                            PackDict["Project"]["roleList"][i].linklist.append((entity.entity_text,entity.person_phone))
                    # add pointer_person
                    for _entity in list_entity:
                        if dict_role_id.get(str(_entity.label))=="agency":
                            for i in range(len(PackDict["Project"]["roleList"])):
                                if PackDict["Project"]["roleList"][i].entity_text==_entity.entity_text and PackDict["Project"]["roleList"][i].role_name=="agency":
                                    _entity.pointer_person = entity
    '''
        # #金额往前找实体
        # if entity.entity_type=="money":
        #     if entity.values[entity.label]>=on_value:
        #         p_entity_money= p_entity
        #         entity_money = list_entity[p_entity_money]
        #         if len(PackageSet)>0:
        #             packagePointer,_ = getPackage(PackageList,entity_money.sentence_index,entity_money.begin_index,"money-"+str(entity_money.entity_text)+"-"+str(entity_money.label))
        #             if packagePointer is None:
        #                 packageName_entity = "Project"
        #             else:
        #                 packageName_entity = packagePointer.entity_text
        #         else:
        #             packageName_entity = "Project"
        #         while(p_entity_money>0):
        #             entity_before = list_entity[p_entity_money]
        #             if entity_before.entity_type in ['org','company']:
        #                 if str(entity_before.label)=="1":
        #                     addMoneyByEntity(PackDict, packageName_entity, entity_before.entity_text, entity_money.entity_text, entity_money.values[entity_money.label])
        #                     #add pointer_money
        #                     entity_before.pointer_money = entity_money
        #                 break
        #             p_entity_money -= 1



        #如果实体属于角色集合，则往后找属性
        # if doesEntityOrLinkedEntity_inRoleSet(entity, roleSet):
        #
        #     p_entity += 1
        #     #循环查找符合的属性
        #     while(p_entity<len(list_entity)):
        #
        #         entity_after = list_entity[p_entity]
        #         if entity_after.sentence_index-entity.sentence_index>=sentence_len:
        #             p_entity -= 1
        #             break
        #         #若是遇到公司实体，则跳出循环
        #         if entity_after.entity_type in ['org','company']:
        #             p_entity -= 1
        #             break
        #         if entity_after.values is not None:
        #             if entity_after.entity_type=="money":
        #                 if entity_after.values[entity_after.label]>=on_value:
        #                     '''
        #                     #招标金额从后往前找
        #                     if str(entity_after.label)=="0":
        #                         packagePointer,_ = getPackage(PackageList,entity.sentence_index,entity.begin_index,"money-"+str(entity.label))
        #                         if packagePointer is None:
        #                             packageName = "Project"
        #                         else:
        #                             packageName = packagePointer.entity_text
        #                         addMoneyByRoleid(PackDict, packageName, "0", entity_after.entity_text, entity_after.values[entity_after.label])
        #                     '''
        #                     if str(entity_after.label)=="1":
        #                         #print(entity_after.entity_text,entity.entity_text)
        #                         _list_entitys = [entity]+entity.linked_entitys
        #                         if len(PackageSet)>0:
        #                             packagePointer,_ = getPackage(PackageList,entity_after.sentence_index,entity_after.begin_index,"money-"+str(entity_after.entity_text)+"-"+str(entity_after.label))
        #                             if packagePointer is None:
        #                                 packageName_entity = "Project"
        #                             else:
        #                                 packageName_entity = packagePointer.entity_text
        #                         else:
        #                             packageName_entity = "Project"
        #                         if str(entity.label) in ["2","3","4"]:
        #                             # addMoneyByEntity(PackDict, packageName_entity, entity.entity_text, entity_after.entity_text, entity_after.values[entity_after.label])
        #                             if entity_after.notes == '单价' or float(entity_after.entity_text)<5000: #2021/12/17 调整小金额阈值，避免203608823.html 两次金额一次万元没提取到的情况
        #                                 addMoneyByEntity(PackDict, packageName_entity, entity.entity_text, entity_after,
        #                                                  0.5)
        #                                 entity.pointer_money = entity_after
        #                                 # print('role zhao money', entity.entity_text, '中标金额：', entity_after.entity_text)
        #                             else:
        #                                 addMoneyByEntity(PackDict, packageName_entity, entity.entity_text, entity_after,
        #                                                  entity_after.values[entity_after.label])
        #                                 entity.pointer_money = entity_after
        #                                 # print('role zhao money', entity.entity_text, '中标金额：', entity_after.entity_text)
        #                                 if entity_after.values[entity_after.label]>0.6:
        #                                     break # 2021/7/16 新增，找到中标金额，非单价即停止，不再往后找金额
        #                             #add pointer_money
        #                             # entity.pointer_money = entity_after
        #                             # print('role zhao money', entity.entity_text, '中标金额：', entity_after.entity_text)
        #                             # if entity_after.notes!='单价':
        #                             #     break  # 2021/7/16 新增，找到中标金额即停止，不再往后找金额
        #                 '''
        #             if entity_after.entity_type=="person":
        #                 if entity_after.values[entity_after.label]>=on_value_person:
        #                     if str(entity_after.label)=="1":
        #                         for i in range(len(roleList)):
        #                             if roleList[i].role_name=="tenderee":
        #                                 roleList[i].linklist.append((entity_after.entity_text,entity_after.person_phone))
        #                     elif str(entity_after.label)=="2":
        #                         for i in range(len(roleList)):
        #                             if roleList[i].role_name=="agency":
        #                                 roleList[i].linklist.append((entity_after.entity_text,entity_after.person_phone))
        #                     elif str(entity_after.label)=="3":
        #                         _list_entitys = [entity]+entity.linked_entitys
        #                         for _entity in _list_entitys:
        #                             for i in range(len(roleList)):
        #                                 if roleList[i].entity_text==_entity.entity_text:
        #                                     if entity_after.sentence_index-_entity.sentence_index>1 and len(roleList[i].linklist)>0:
        #                                         break
        #                                     roleList[i].linklist.append((entity_after.entity_text,entity_after.person_phone))
        #             '''
        #
        #         p_entity += 1
        #
        # p_entity += 1
    # 记录每句的分词数量
    tokens_num_dict = dict()
    last_tokens_num = 0
    for sentence in list_sentence:
        _index = sentence.sentence_index
        if _index == 0:
            tokens_num_dict[_index] = 0
        else:
            tokens_num_dict[_index] = tokens_num_dict[_index - 1] + last_tokens_num
        last_tokens_num = len(sentence.tokens)
    attribute_type = ['money','serviceTime','ratio']# 'money'仅指“中投标金额”
    for link_attribute in attribute_type:
        temp_entity_list = []
        if link_attribute=="money":
            temp_entity_list = [ent for ent in list_entity if (ent.entity_type in ['org','company'] and ent.label in [2,3,4]) or
                                (ent.entity_type=='money' and ent.label==1 and ent.values[ent.label]>=0.5)]
            # 删除重复的‘中投标金额’，一般为大小写两种样式
            drop_tendererMoney = []
            for ent_idx in range(len(temp_entity_list)-1):
                entity = temp_entity_list[ent_idx]
                if entity.entity_type=='money':
                    next_entity = temp_entity_list[ent_idx+1]
                    if next_entity.entity_type=='money':
                        if getUnifyMoney(entity.entity_text)==getUnifyMoney(next_entity.entity_text):
                            if (tokens_num_dict[next_entity.sentence_index] + next_entity.begin_index) - (
                                               tokens_num_dict[entity.sentence_index] + entity.end_index) < 10:
                                drop_tendererMoney.append(next_entity)
            for _drop in drop_tendererMoney:
                temp_entity_list.remove(_drop)
        elif link_attribute=="serviceTime":
            temp_entity_list = [ent for ent in list_entity if (ent.entity_type in ['org','company'] and ent.label in [2,3,4]) or
                                ent.entity_type=='serviceTime']
        elif link_attribute=="ratio":
            temp_entity_list = [ent for ent in list_entity if (ent.entity_type in ['org','company'] and ent.label in [2,3,4]) or
                                ent.entity_type=='ratio']
        temp_entity_list = sorted(temp_entity_list,key=lambda x: (x.sentence_index, x.begin_index))
        temp_match_list = []
        for ent_idx in range(len(temp_entity_list)):
            entity = temp_entity_list[ent_idx]
            if entity.entity_type in ['org','company']:
                match_nums = 0
                tenderer_nums = 0 #经过其他中投标人的数量
                byNotTenderer_match_nums = 0 #跟在中投标人后面的属性
                for after_index in range(ent_idx + 1, min(len(temp_entity_list), ent_idx + 4)):
                    after_entity = temp_entity_list[after_index]
                    if entity.in_attachment != after_entity.in_attachment: # 正文与附件的不能相连
                        break
                    if after_entity.entity_type == link_attribute:
                        distance = (tokens_num_dict[after_entity.sentence_index] + after_entity.begin_index) - (
                                           tokens_num_dict[entity.sentence_index] + entity.end_index)
                        sentence_distance = after_entity.sentence_index - entity.sentence_index
                        value = (-1 / 2 * (distance ** 2)) / 10000
                        if link_attribute == "money":
                            if after_entity.notes == '单价':
                                value = value * 100
                        if sentence_distance == 0:
                            if distance < 100:
                                # value = (-1 / 2 * (distance ** 2)) / 10000
                                temp_match_list.append(Match(entity, after_entity, value))
                                match_nums += 1
                                if not tenderer_nums:
                                    byNotTenderer_match_nums += 1
                                else:
                                    break
                        else:
                            if distance < 60:
                                # value = (-1 / 2 * (distance ** 2)) / 10000
                                temp_match_list.append(Match(entity, after_entity, value))
                                match_nums += 1
                                if not tenderer_nums:
                                    byNotTenderer_match_nums += 1
                                else:
                                    break
                    else:
                        tenderer_nums += 1
                #前向查找属性
                if ent_idx!=0 and (not match_nums or not byNotTenderer_match_nums):
                    previous_entity = temp_entity_list[ent_idx - 1]
                    if previous_entity.entity_type == link_attribute:
                        # if previous_entity.sentence_index == entity.sentence_index:
                        distance = (tokens_num_dict[entity.sentence_index] + entity.begin_index) - (
                                tokens_num_dict[previous_entity.sentence_index] + previous_entity.end_index)
                        if distance < 40:
                            # 前向 没有 /10000
                            value = (-1 / 2 * (distance ** 2))
                            temp_match_list.append(Match(entity, previous_entity, value))
        # km算法分配求解
        dispatch_result = dispatch(temp_match_list)
        dispatch_result = sorted(dispatch_result, key=lambda x: (x[0].sentence_index,x[0].begin_index))
        for match in dispatch_result:
            _entity = match[0]
            _attribute = match[1]
            if link_attribute=='money':
                _entity.pointer_money = _attribute
                packagePointer, _ = getPackage(PackageList, _attribute.sentence_index, _attribute.begin_index,
                                               "money-" + str(_attribute.entity_text) + "-" + str(_attribute.label))
                # print(_entity.entity_text,_attribute.entity_text)
                if packagePointer is None:
                    packageName_entity = "Project"
                else:
                    packageName_entity = packagePointer.entity_text
                if _attribute.notes == '单价' or float(_attribute.entity_text) < 5000:  # 2021/12/17 调整小金额阈值，避免203608823.html 两次金额一次万元没提取到的情况
                    # print(packageName_entity,_attribute.entity_text, _attribute.values[_attribute.label])
                    addMoneyByEntity(PackDict, packageName_entity, _entity.entity_text, _attribute,0.5)
                else:
                    # print(packageName_entity,_attribute.entity_text, _attribute.values[_attribute.label])
                    addMoneyByEntity(PackDict, packageName_entity, _entity.entity_text, _attribute,
                                     _attribute.values[_attribute.label])
            elif link_attribute=='serviceTime':
                _entity.pointer_serviceTime = _attribute
                packagePointer, _ = getPackage(PackageList, _attribute.sentence_index, _attribute.begin_index,
                                               "serviceTime-" + str(_attribute.entity_text) + "-" + str(_attribute.label))
                if packagePointer is None:
                    packageName_entity = "Project"
                else:
                    packageName_entity = packagePointer.entity_text
                addServiceTimeByEntity(PackDict, packageName_entity, _entity.entity_text, _attribute)
            elif link_attribute=='ratio':
                _entity.pointer_ratio = _attribute
                packagePointer, _ = getPackage(PackageList, _attribute.sentence_index, _attribute.begin_index,
                                               "ratio-" + str(_attribute.entity_text) + "-" + str(_attribute.label))
                if packagePointer is None:
                    packageName_entity = "Project"
                else:
                    packageName_entity = packagePointer.entity_text
                addRatioByEntity(PackDict, packageName_entity, _entity.entity_text, _attribute)
    ''''''
    # 通过模型分类的招标/代理联系人
    list_sentence = sorted(list_sentence, key=lambda x: x.sentence_index)
    person_list = [entity for entity in list_entity if entity.entity_type == 'person' and entity.label in [1, 2]]
    tenderee_contact = set()
    tenderee_phone = set()
    agency_contact = set()
    agency_phone = set()
    winter_contact = set()
    for _person in person_list:
        if _person.label == 1:
            tenderee_contact.add(_person.entity_text)
        if _person.label == 2:
            agency_contact.add(_person.entity_text)
    # 正则匹配无 '主体/联系人' 的电话
    # 例："采购人联系方式：0833-5226788，"
    phone_pattern = '(1[3-9][0-9][-—－―]?\d{4}[-—－―]?\d{4}|' \
                    '\+86.?1[3-9]\d{9}|' \
                    '0[1-9]\d{1,2}[-—－―][2-9]\d{6,7}/[1-9]\d{6,10}|' \
                    '0[1-9]\d{1,2}[-—－―][2-9]\d{6}\d?.?转\d{1,4}|' \
                    '0[1-9]\d{1,2}[-—－―][2-9]\d{6}\d?[-—－―]\d{1,4}|' \
                    '0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?(?=1[3-9]\d{9})|' \
                   '0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?(?=0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?)|' \
                   '0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?(?=[2-9]\d{6,7})|' \
                   '0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?|' \
                   '[\（|\(]0[1-9]\d{1,2}[\）|\)]-?[2-9]\d{6}\d?-?\d{,4}|' \
                   '[2-9]\d{6,7})'
    re_tenderee_phone = re.compile(
        "(?:(?:(?:采购|招标|议价|议标|比选)(?:人|公司|单位|组织|部门)|建设(?:单位|业主)|(?:采购|招标|甲)方|询价单位|项目业主|业主)[^。]{0,5}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,7}?)"
        # 电话号码
        + phone_pattern)
    # 例："采购人地址和联系方式：峨边彝族自治县教育局，0833-5226788，"
    re_tenderee_phone2 = re.compile(
        "(?:(?:(?:采购|招标|议价|议标|比选)(?:人|公司|单位|组织|部门)|建设(?:单位|业主)|(?:采购|招标|甲)方|询价单位|项目业主|业主)[^。]{0,3}(?:地址)[^。]{0,3}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,20}?)"
        # 电话号码
        + phone_pattern)
    re_agent_phone = re.compile(
        "(?:(?:代理(?:人|机构|公司|单位|组织|方)|采购机构|集中采购机构|集采机构|招标机构)[^。]{0,5}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,7}?)"
        # 电话号码
        + phone_pattern)
    re_agent_phone2 = re.compile(
        "(?:(?:代理(?:人|机构|公司|单位|组织|方)|采购机构|集中采购机构|集采机构|招标机构)[^。]{0,3}(?:地址)[^。]{0,3}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,20}?)"
        # 电话号码
        + phone_pattern)
    content = ""
    for _sentence in list_sentence:
        content += "".join(_sentence.tokens)
    _content = copy.deepcopy(content)
    while re.search("(.)(，)([^0-9])|([^0-9])(，)(.)", content):
        content_words = list(content)
        for i in re.finditer("(.)(，)([^0-9])", content):
            content_words[i.span(2)[0]] = ""
        for i in re.finditer("([^0-9])(，)(.)", content):
            content_words[i.span(2)[0]] = ""
        content = "".join(content_words)
    content = re.sub("[:：]|[\(（]|[\)）]", "", content)
    _tenderee_phone = re.findall(re_tenderee_phone, content)
    # 更新正则确定的角色属性
    for i in range(len(PackDict["Project"]["roleList"])):
        if PackDict["Project"]["roleList"][i].role_name == "tenderee":
            _tenderee_phone = re.findall(re_tenderee_phone, content)
            if _tenderee_phone:
                for _phone in _tenderee_phone:
                    _phone = _phone.split("/") # 分割多个号码
                    for one_phone in _phone:
                        PackDict["Project"]["roleList"][i].linklist.append(("", one_phone))
                        tenderee_phone.add(one_phone)
            _tenderee_phone2 = re.findall(re_tenderee_phone2, content)
            if _tenderee_phone2:
                for _phone in _tenderee_phone2:
                    _phone = _phone.split("/")
                    for one_phone in _phone:
                        PackDict["Project"]["roleList"][i].linklist.append(("", one_phone))
                        tenderee_phone.add(one_phone)
        if PackDict["Project"]["roleList"][i].role_name == "agency":
            _agent_phone = re.findall(re_agent_phone, content)
            if _agent_phone:
                for _phone in _agent_phone:
                    _phone = _phone.split("/")
                    for one_phone in _phone:
                        PackDict["Project"]["roleList"][i].linklist.append(("", one_phone))
                        agency_phone.add(one_phone)
            _agent_phone2 = re.findall(re_agent_phone2, content)
            if _agent_phone2:
                for _phone in _agent_phone2:
                    _phone = _phone.split("/")
                    for one_phone in _phone:
                        PackDict["Project"]["roleList"][i].linklist.append(("", one_phone))
                        agency_phone.add(one_phone)
    # 正则提取电话号码实体
    # key_word = re.compile('((?:电话|联系方式|联系人).{0,4}?)([0-1]\d{6,11})')
    phone = re.compile('1[3-9][0-9][-—－―]?\d{4}[-—－―]?\d{4}|'
                       '\+86.?1[3-9]\d{9}|'
                       # '0[^0]\d{1,2}[-—－―][1-9]\d{6,7}/[1-9]\d{6,10}|'
                       '0[1-9]\d{1,2}[-—－―][2-9]\d{6}\d?[-—－―]\d{1,4}|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=1[3-9]\d{9})|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?)|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=[2-9]\d{6,7})|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?|'
                       '[\（|\(]0[1-9]\d{1,2}[\）|\)]-?[2-9]\d{6}\d?-?\d{,4}|'
                       '400\d{7}转\d{1,4}|'
                       '[2-9]\d{6,7}')
    url_pattern = re.compile("http[s]?://(?:[a-zA-Z]|[0-9]|[#$\-_@.&+=\?:/]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+")
    email_pattern = re.compile("[a-zA-Z0-9][a-zA-Z0-9_-]+(?:\.[a-zA-Z0-9_-]+)*@"
                            "[a-zA-Z0-9_-]+(?:\.[a-zA-Z0-9_-]+)*(?:\.[a-zA-Z]{2,})")
    phone_entitys = []
    code_entitys = [ent for ent in list_entity if ent.entity_type=='code']
    for _sentence in list_sentence:
        sentence_text = _sentence.sentence_text
        # 过长数字串直接过滤替换
        for _re in re.findall("\d{50,}",sentence_text):
            sentence_text = sentence_text.replace(_re,"#"*len(_re))
        in_attachment = _sentence.in_attachment
        list_tokenbegin = []
        begin = 0
        for i in range(0, len(_sentence.tokens)):
            list_tokenbegin.append(begin)
            begin += len(str(_sentence.tokens[i]))
        list_tokenbegin.append(begin + 1)
        # 排除网址、邮箱、项目编号实体
        error_list = []
        for i in re.finditer(url_pattern, sentence_text):
            error_list.append((i.start(), i.end()))
        for i in re.finditer(email_pattern, sentence_text):
            error_list.append((i.start(), i.end()))
        for code_ent in [ent for ent in code_entitys if ent.sentence_index==_sentence.sentence_index]:
            error_list.append((code_ent.wordOffset_begin,code_ent.wordOffset_end))
        res_set = set()
        for i in re.finditer(phone, sentence_text):
            is_continue = False
            for error_ent in error_list:
                if i.start()>=error_ent[0] and i.end()<=error_ent[1]:
                    is_continue = True
                    break
            if is_continue:
                continue
            res_set.add((i.group(), i.start(), i.end()))
        res_set = sorted(list(res_set),key=lambda x:x[1])
        # 限制数量，防止异常数据处理时间过长
        res_set = res_set[:200]
        last_phone_mask = True
        error_numStr_index = []
        sentence_phone_list = []
        for item_idx in range(len(res_set)):
            item = res_set[item_idx]
            phone_left = sentence_text[max(0, item[1] - 10):item[1]]
            phone_right = sentence_text[item[2]:item[2] + 10]
            phone_left_num = re.search("[\da-zA-Z\-—－―]+$",phone_left)
            numStr_left = item[1]
            if phone_left_num:
                numStr_left -= len(phone_left_num.group())
            phone_right_num = re.search("^[\da-zA-Z\-—－―]+",phone_right)
            numStr_right = item[2]
            if phone_right_num:
                numStr_right += len(phone_right_num.group())
            numStr_index = (numStr_left,numStr_right)

            if re.search("电话|手机|联系[人方]|联系方式",re.sub("，","",phone_left)):
                pass
            else:
                # 排除“传真号”和其它错误项
                if re.search("传，?真|信，?箱|邮，?[编箱件]|QQ|qq", phone_left):
                    if not re.search("电，?话", phone_left):
                        error_numStr_index.append(numStr_index)
                        last_phone_mask = False
                        continue
                if re.search("身份证号?码?|注册[证号]|帐号|编[号码]|报价|费率|标价|证号|价格|型号|附件|代码|列号|行号|税号|[\(\（]万?元[\)\）]|[a-zA-Z]+\d*$", re.sub("，","",phone_left)):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                if re.search("^\d{0,4}[.,]\d{2,}|^[0-9a-zA-Z\.]*@|^\d*[a-zA-Z]+|元", phone_right):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                # 号码含有0过多，不符合规则
                if re.search("0{6,}",item[0]):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                # 前后跟着字母
                if re.search("[a-zA-Z/]+$", phone_left) or re.search("^[a-zA-Z/]+", phone_right):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                # 时间日期类排除
                if re.search("时间|日期", phone_left):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                # 排除号码实体为时间格式 ，例如：20150515
                if re.search("^20(1[0-9]|2[0-5])(0[1-9]|1[012])(0[1-9]|[1-2][0-9]|3[01])$",item[0]):
                    error_numStr_index.append(numStr_index)
                    last_phone_mask = False
                    continue
                # 前后跟着长度小于一定值数字的正则排除
                if re.search("\d+[-—－―]?\d*$",phone_left) or re.search("^\d+[-—－―]?\d*",phone_right):
                    phone_left_number = re.search("\d+[-—－―]?\d*$",phone_left)
                    phone_right_number = re.search("^\d+[-—－―]?\d+",phone_right)
                    if phone_left_number:
                        if len(phone_left_number.group())<7:
                            error_numStr_index.append(numStr_index)
                            last_phone_mask = False
                            continue
                    if phone_right_number:
                        if len(phone_right_number.group())<7:
                            error_numStr_index.append(numStr_index)
                            last_phone_mask = False
                            continue
                left_context = re.search("[\da-zA-Z\-—－―]+$",sentence_text[:item[1]])
                if left_context:
                    if len(left_context.group()) != len("".join(re.findall(phone, left_context.group()))):
                    # if not re.search("(" + phone.pattern + ")$", left_context.group()):
                        error_numStr_index.append(numStr_index)
                        last_phone_mask = False
                        continue
                right_context = re.search("^[\da-zA-Z\-—－―]+", sentence_text[item[2]:])
                if right_context:
                    if len(right_context.group()) != len("".join(re.findall(phone, right_context.group()))):
                    # if not re.search("^(" + phone.pattern + ")", right_context.group()):
                        error_numStr_index.append(numStr_index)
                        last_phone_mask = False
                        continue
                # if:上一个phone实体不符合条件
                if not last_phone_mask:
                    item_start = item[1]
                    last_item_end = res_set[item_idx-1][2]
                    if item_start - last_item_end<=1 or re.search("^[\da-zA-Z\-—－―、]+$",sentence_text[last_item_end:item_start]):
                        error_numStr_index.append(numStr_index)
                        last_phone_mask = False
                        continue
            sentence_phone_list.append(item)
            last_phone_mask = True
        if error_numStr_index:
            drop_list = []
            for item in sentence_phone_list:
                for err_index in error_numStr_index:
                    if (item[1]>=err_index[0] and item[1]<=err_index[1]) or (item[2]>=err_index[0] and item[2]<=err_index[1]) or (item[1]<=err_index[0] and item[2]>=err_index[1]):
                        drop_list.append(item)
                        break
            for _drop_item in drop_list:
                sentence_phone_list.remove(_drop_item)
        for item in sentence_phone_list:
            for j in range(len(list_tokenbegin)):
                if list_tokenbegin[j] == item[1]:
                    begin_index = j
                    break
                elif list_tokenbegin[j] > item[1]:
                    begin_index = j - 1
                    break
            for j in range(begin_index, len(list_tokenbegin)):
                if list_tokenbegin[j] >= item[2]:
                    end_index = j - 1
                    break
            phone_text = re.sub("[-—－―]+","-",item[0]).replace("(","（").replace(")","）")
            _entity = Entity(_sentence.doc_id, None, phone_text, "phone", _sentence.sentence_index, begin_index, end_index, item[1],
                             item[2],in_attachment=in_attachment)
            phone_entitys.append(_entity)
    # print('phone_set:',set([ent.entity_text for ent in phone_entitys]))
    def is_company(entity,text):
        # 判断"公司"实体是否为地址地点
        if entity.label!=5 and entity.values[entity.label]>0.5:
            return True
        if ent.is_tail==True:
            return False
        entity_left = text[max(0,entity.wordOffset_begin-10):entity.wordOffset_begin]
        entity_left = re.sub("，（）\(\)","",entity_left)
        entity_left = entity_left[-5:]
        if re.search("地址|地点|银行[：:]",entity_left):
            return False
        else:
            return True
    pre_entity = []
    for ent in list_entity:
        if (ent.entity_type in ['company','org','phone'] and is_company(ent,list_sentence[ent.sentence_index].sentence_text)) or (ent.entity_type=='person' and ent.label in [1,2,3]) \
                or (ent.entity_type=='location' and len(ent.entity_text)>5):
            pre_entity.append(ent)
    text_data,pre_data = relationExtraction_model.encode(pre_entity + phone_entitys, list_sentence)
    # print(pre_data)
    maxlen = 512
    relation_list = []
    if 0<len(text_data)<=maxlen:
        relation_list = relationExtraction_model.predict(text_data, pre_data)
    else:
        # 公告大于maxlen时，分段预测
        start = 0
        # print("len(pre_data)",len(pre_data))
        temp_data = []
        deal_data = 0
        while start<len(pre_data):
            _pre_data = pre_data[start:start+maxlen]
            _text_data = text_data[start:start+maxlen]
            if relationExtraction_model.check_data(_pre_data):
                temp_data.append((_text_data,_pre_data))
            else:
                if temp_data:
                    deal_data += len(temp_data)
                    if deal_data>4:
                        break
                    for _text_data, _pre_data in temp_data:
                        relation_list.extend(relationExtraction_model.predict(_text_data,_pre_data))
                    temp_data = []
            start = start + maxlen - 120
        if temp_data:
            deal_data += len(temp_data)
            if deal_data <= 4:
                for _text_data, _pre_data in temp_data:
                    relation_list.extend(relationExtraction_model.predict(_text_data, _pre_data))
        # print("预测数据：",len(temp_data))
        # 去重结果
        relation_list = list(set(relation_list))
    # print([(rel[0].entity_text,rel[2].entity_text) for rel in relation_list])
    right_combination = [('org','person'),('company','person'),('company','location'),('org','location'),('person','phone')]
    linked_company = set()
    linked_person = set()
    linked_connetPerson = set()
    linked_phone = set()
    for predicate in ["rel_address","rel_phone","rel_person"]:
        _match_list = []
        _match_combo = []
        for relation in relation_list:
            _subject = relation[0]
            _object = relation[2]
            if isinstance(_subject,Entity) and isinstance(_object,Entity) and (_subject.entity_type,_object.entity_type) in right_combination:
                if _subject.in_attachment != _object.in_attachment:
                    continue
                if relation[1]==predicate:
                    distance = (tokens_num_dict[_object.sentence_index] + _object.begin_index) - (
                            tokens_num_dict[_subject.sentence_index] + _subject.end_index)
                    if predicate=="rel_person":
                        if (_subject.label==0 and _object.entity_text in agency_contact ) or (_subject.label==1 and _object.entity_text in tenderee_contact):
                            continue
                        # 角色为中标候选人，排除"质疑|投诉|监督|受理"相关的联系人
                        if _subject.label in [2,3,4] and re.search("质疑|投诉|监督|受理|项目(单位)?联系|^联系人|请.{0,4}联系",list_sentence[_object.sentence_index].sentence_text[max(0,_object.wordOffset_begin-10):_object.wordOffset_begin]):
                            continue
                        if _object.sentence_index!=0 and _object.wordOffset_begin<=10:
                            if _subject.label in [2, 3, 4] and re.search("请.{0,4}联系",
                                                                         list_sentence[_object.sentence_index-1].sentence_text[-10:]+
                                                                         list_sentence[_object.sentence_index].sentence_text[0:_object.wordOffset_begin]):
                                continue
                        # 角色为中标候选人，排除距离过远的联系人
                        if _subject.label in [2, 3, 4] and distance>=40:
                            continue
                    if distance>0:
                        value = (-1 / 2 * (distance ** 2))/10000
                    else:
                        distance = abs(distance)
                        value = (-1 / 2 * (distance ** 2))
                    _match_list.append(Match(_subject,_object,value))
                    _match_combo.append((_subject,_object))
        match_result = dispatch(_match_list)
        error_list = []
        for mat in list(set(_match_combo)-set(match_result)):
            for temp in match_result:
                if mat[1]==temp[1] and mat[0]!=temp[0]:
                    error_list.append(mat)
                    break
        result = list(set(_match_combo)-set(error_list))
        if predicate=='rel_person':
            # 从后往前更新状态，已近后向链接的属性不在前向链接（解决错误链接）
            result = sorted(result,key=lambda x:x[1].begin_index,reverse=True)
            for combo in result:
                is_continue = False
                if not combo[0].pointer_person:
                    combo[0].pointer_person = []
                if combo[1].begin_index<combo[0].begin_index:
                    if combo[0].pointer_person:
                        for temp in combo[0].pointer_person:
                            if temp.begin_index>combo[0].begin_index:
                                is_continue = True
                                break
                if is_continue:
                    continue
                combo[0].pointer_person.append(combo[1])
                linked_company.add(combo[0])
                linked_person.add(combo[1])
                # print(1,combo[0].entity_text,combo[1].entity_text)
        if predicate=='rel_address':
            result = sorted(result,key=lambda x:x[1].begin_index,reverse=True)
            for combo in result:
                if combo[0].pointer_address:
                    continue
                combo[0].pointer_address = combo[1]
                # print(2,combo[0].entity_text,combo[1].entity_text)
        if predicate=='rel_phone':
            result = sorted(result,key=lambda x:x[1].begin_index,reverse=True)
            for combo in result:
                is_continue = False
                if not combo[0].person_phone:
                    combo[0].person_phone = []
                if combo[1].begin_index<combo[0].begin_index:
                    if combo[0].person_phone:
                        for temp in combo[0].person_phone:
                            if temp.begin_index>combo[0].begin_index:
                                is_continue = True
                                break
                if is_continue: continue
                combo[0].person_phone.append(combo[1])
                linked_connetPerson.add(combo[0])
                linked_phone.add(combo[1])
                if combo[0].label in [1,2]:
                    if PackDict.get("Project"):
                        for i in range(len(PackDict["Project"]["roleList"])):
                            if (combo[0].label==1 and PackDict["Project"]["roleList"][i].role_name=='tenderee') \
                                    or (combo[0].label==2 and PackDict["Project"]["roleList"][i].role_name=='agency'):
                                PackDict["Project"]["roleList"][i].linklist.append((combo[0].entity_text,combo[1].entity_text))
                                break
                # print(3,combo[0].entity_text,combo[1].entity_text)

    # "公司——地址" 链接规则补充
    company_lacation_EntityList = [ent for ent in pre_entity if ent.entity_type in ['company', 'org', 'location']]
    # company_lacation_EntityList = [ent for ent in pre_entity if (ent.entity_type in ['company', 'org'] and ent.label!=5) or ent.entity_type=="location"]
    company_lacation_EntityList = sorted(company_lacation_EntityList, key=lambda x: (x.sentence_index, x.begin_index))
    t_match_list = []
    for ent_idx in range(len(company_lacation_EntityList)):
        entity = company_lacation_EntityList[ent_idx]
        if entity.entity_type in ['company', 'org'] and entity.label!=5:
            match_nums = 0
            company_nums = 0  # 经过其他公司的数量
            location_nums = 0  # 经过电话的数量
            for after_index in range(ent_idx + 1, min(len(company_lacation_EntityList), ent_idx + 5)):
                after_entity = company_lacation_EntityList[after_index]
                if after_entity.entity_type == "location":
                    distance = (tokens_num_dict[after_entity.sentence_index] + after_entity.begin_index) - (
                            tokens_num_dict[entity.sentence_index] + entity.end_index)
                    location_nums += 1
                    if distance > 100 or location_nums >= 3:
                        break
                    sentence_distance = after_entity.sentence_index - entity.sentence_index
                    value = (-1 / 2 * (distance ** 2)) / 10000
                    if sentence_distance == 0:
                        if distance < 80:
                            t_match_list.append(Match(entity, after_entity, value))
                            match_nums += 1
                            if company_nums:
                                break
                    else:
                        if distance < 50:
                            t_match_list.append(Match(entity, after_entity, value))
                            match_nums += 1
                            if company_nums:
                                break
                else:
                    # type:company/org
                    company_nums += 1
                    if entity.label in [2, 3, 4] and after_entity.label in [0, 1]:
                        break
                    if entity.label in [0, 1] and after_entity.label in [2, 3, 4]:
                        break
                    if entity.label in [0, 1] and after_entity.label not in [0, 1]:
                        break

    # km算法分配求解
    # for item in t_match_list:
    #     print("loc_rela",item.main_role.entity_text,item.attribute.entity_text)
    relate_location_result = dispatch(t_match_list)
    relate_location_result = sorted(relate_location_result, key=lambda x: (x[0].sentence_index, x[0].begin_index))
    for match in relate_location_result:
        _company = match[0]
        _relation = match[1]
        # print("loc_relation1", _company.entity_text, _relation.entity_text, )
        if not _company.pointer_address:
            # print('loc_relation2',_company.entity_text,_relation.entity_text)
            _company.pointer_address = _relation
    # "联系人——联系电话" 链接规则补充
    person_phone_EntityList = [ent for ent in pre_entity+ phone_entitys if ent.entity_type not in ['company','org','location']]
    person_phone_EntityList = sorted(person_phone_EntityList, key=lambda x: (x.sentence_index, x.begin_index))
    t_match_list = []
    for ent_idx in range(len(person_phone_EntityList)):
        entity = person_phone_EntityList[ent_idx]
        if entity.entity_type=="person":
            match_nums = 0
            person_nums = 0  # 经过其他中联系人的数量
            byNotPerson_match_nums = 0  # 跟在联系人后面的属性
            phone_nums = 0 # 经过电话的数量
            for after_index in range(ent_idx + 1, min(len(person_phone_EntityList), ent_idx + 8)):
                after_entity = person_phone_EntityList[after_index]
                if after_entity.entity_type == "phone":
                    distance = (tokens_num_dict[after_entity.sentence_index] + after_entity.begin_index) - (
                            tokens_num_dict[entity.sentence_index] + entity.end_index)
                    phone_nums += 1
                    if distance>100 or phone_nums>=4:
                        break
                    sentence_distance = after_entity.sentence_index - entity.sentence_index
                    value = (-1 / 2 * (distance ** 2)) / 10000
                    if sentence_distance == 0:
                        if distance < 70:
                            # value = (-1 / 2 * (distance ** 2)) / 10000
                            t_match_list.append(Match(entity, after_entity, value))
                            match_nums += 1
                            if not person_nums:
                                byNotPerson_match_nums += 1
                            else:
                                break
                    else:
                        if distance < 40:
                            # value = (-1 / 2 * (distance ** 2)) / 10000
                            t_match_list.append(Match(entity, after_entity, value))
                            match_nums += 1
                            if not person_nums:
                                byNotPerson_match_nums += 1
                            else:
                                break
                else:
                    person_nums += 1
            # 前向查找属性
            if ent_idx != 0 and (not match_nums or not byNotPerson_match_nums):
                previous_entity = person_phone_EntityList[ent_idx - 1]
                if previous_entity.entity_type == 'phone':
                    # if previous_entity.sentence_index == entity.sentence_index:
                    distance = (tokens_num_dict[entity.sentence_index] + entity.begin_index) - (
                            tokens_num_dict[previous_entity.sentence_index] + previous_entity.end_index)
                    if distance < 40:
                        # 前向 没有 /10000
                        value = (-1 / 2 * (distance ** 2))
                        t_match_list.append(Match(entity, previous_entity, value))
    # km算法分配求解(person-phone)
    t_match_list = [mat for mat in t_match_list if mat.main_role not in linked_connetPerson and mat.attribute not in linked_phone]
    personphone_result = dispatch(t_match_list)
    personphone_result = sorted(personphone_result, key=lambda x: (x[0].sentence_index, x[0].begin_index))
    for match in personphone_result:
        _person = match[0]
        _phone = match[1]
        if not _person.person_phone:
            _person.person_phone = []
        _person.person_phone.append(_phone)
    # 多个招标人/代理人或者别称
    for idx in range(1,len(pre_entity)):
        _pre_entity = pre_entity[idx]
        if _pre_entity in linked_company and _pre_entity.label==5:
            last_ent = pre_entity[idx-1]
            if last_ent.entity_type in ['company','org'] and last_ent.label in [0,1]:
                if last_ent.sentence_index==_pre_entity.sentence_index:
                    mid_text = list_sentence[_pre_entity.sentence_index].sentence_text[last_ent.wordOffset_end:_pre_entity.wordOffset_begin]
                    if len(mid_text)<=20 and "，" not in mid_text and re.search("[、\(（]",mid_text):
                        _pre_entity.label = last_ent.label
                        _pre_entity.values[last_ent.label] = 0.6
    # 2022/01/25 固定电话可连多个联系人
    temp_person_entitys = [entity for entity in pre_entity if entity.entity_type == 'person']
    temp_person_entitys2 = [] #和固定电话相连的联系人
    for entity in temp_person_entitys:
        if entity.person_phone:
            for _phone in entity.person_phone:
                if not re.search("^1[3-9]\d{9}$", _phone.entity_text):
                    temp_person_entitys2.append(entity)
                    break
    for index in range(len(temp_person_entitys)):
        entity = temp_person_entitys[index]
        if entity in temp_person_entitys2:
            last_person = entity
            for after_index in range(index + 1, min(len(temp_person_entitys), index + 5)):
                after_entity = temp_person_entitys[after_index]
                if after_entity.sentence_index == last_person.sentence_index and after_entity.begin_index - last_person.end_index < 3:
                    for _phone in entity.person_phone:
                        if not re.search("^1[3-9]\d{9}$", _phone.entity_text):
                            if _phone not in after_entity.person_phone:
                                after_entity.person_phone.append(_phone)
                    last_person = after_entity
                else:
                    break
            if index==0:
                continue
            last_person = entity
            for before_index in range(index-1, max(-1,index-5), -1):
                before_entity = temp_person_entitys[before_index]
                if before_entity.sentence_index == last_person.sentence_index and last_person.begin_index - before_entity.end_index < 3:
                    for _phone in entity.person_phone:
                        if not re.search("^1[3-9]\d{9}$", _phone.entity_text):
                            if _phone not in before_entity.person_phone:
                                before_entity.person_phone.append(_phone)
                    last_person = before_entity
                else:
                    break
    # 更新person为招标/代理联系人的联系方式
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            if PackDict[k]["roleList"][i].role_name == "tenderee":
                for _person in person_list:
                    if _person.label==1:#招标联系人
                        person_phone = [phone for phone in _person.person_phone] if _person.person_phone else []
                        for _p in person_phone:
                            PackDict[k]["roleList"][i].linklist.append((_person.entity_text, _p.entity_text))
                        if not person_phone:
                            PackDict[k]["roleList"][i].linklist.append((_person.entity_text,""))
            if PackDict[k]["roleList"][i].role_name == "agency":
                for _person in person_list:
                    if _person.label==2:#代理联系人
                        person_phone = [phone for phone in _person.person_phone] if _person.person_phone else []
                        for _p in person_phone:
                            PackDict[k]["roleList"][i].linklist.append((_person.entity_text, _p.entity_text))
                        if not person_phone:
                            PackDict[k]["roleList"][i].linklist.append((_person.entity_text,""))
    # 更新 PackDict
    not_sure_linked = []
    for link_p in list(linked_company):
        for k in PackDict.keys():
            for i in range(len(PackDict[k]["roleList"])):
                if PackDict[k]["roleList"][i].role_name == "tenderee":
                    if PackDict[k]["roleList"][i].entity_text != link_p.entity_text and link_p.label == 0:
                        not_sure_linked.append(link_p)
                        continue
                    if PackDict[k]["roleList"][i].entity_text == link_p.entity_text:
                        for per in link_p.pointer_person:
                            person_phone = [phone for phone in per.person_phone] if per.person_phone else []
                            if not person_phone:
                                if per.entity_text not in agency_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, ""))
                                    continue
                            for _p in person_phone:
                                if per.entity_text not in agency_contact and _p.entity_text not in agency_phone:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, _p.entity_text))
                elif PackDict[k]["roleList"][i].role_name == "agency":
                    if PackDict[k]["roleList"][i].entity_text != link_p.entity_text and link_p.label == 1:
                        not_sure_linked.append(link_p)
                        continue
                    if PackDict[k]["roleList"][i].entity_text == link_p.entity_text:
                        for per in link_p.pointer_person:
                            person_phone = [phone for phone in per.person_phone] if per.person_phone else []
                            if not person_phone:
                                if per.entity_text not in tenderee_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, ""))
                                    continue
                            for _p in person_phone:
                                if per.entity_text not in tenderee_contact and _p.entity_text not in tenderee_phone:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, _p.entity_text))
                else:
                    if PackDict[k]["roleList"][i].entity_text == link_p.entity_text:
                        for per in link_p.pointer_person:
                            person_phone = [phone for phone in per.person_phone] if per.person_phone else []
                            if not person_phone:
                                if per.entity_text not in tenderee_contact and per.entity_text not in agency_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, ""))
                                    winter_contact.add(per.entity_text)
                                    continue
                            for _p in person_phone:
                                if per.entity_text not in tenderee_contact and _p.entity_text not in tenderee_phone and \
                                        per.entity_text not in agency_contact and _p.entity_text not in agency_phone:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, _p.entity_text))
                                    winter_contact.add(per.entity_text)
    # 更新org/company实体label为0，1的链接
    for link_p in not_sure_linked:
        for k in PackDict.keys():
            for i in range(len(PackDict[k]["roleList"])):
                if PackDict[k]["roleList"][i].role_name == "tenderee":
                    if link_p.label == 0:
                        for per in link_p.pointer_person:
                            person_phone = [phone for phone in per.person_phone] if per.person_phone else []
                            if not person_phone:
                                if per.entity_text not in agency_contact and per.entity_text not in winter_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, ""))
                                    continue
                            for _p in person_phone:
                                if per.entity_text not in agency_contact and _p.entity_text not in agency_phone and per.entity_text not in winter_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, _p.entity_text))
                elif PackDict[k]["roleList"][i].role_name == "agency":
                    if link_p.label == 1:
                        for per in link_p.pointer_person:
                            person_phone = [phone for phone in per.person_phone] if per.person_phone else []
                            if not person_phone:
                                if per.entity_text not in tenderee_contact and per.entity_text not in winter_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, ""))
                                    continue
                            for _p in person_phone:
                                if per.entity_text not in tenderee_contact and _p.entity_text not in tenderee_phone and per.entity_text not in winter_contact:
                                    PackDict[k]["roleList"][i].linklist.append((per.entity_text, _p.entity_text))
    re_split = re.compile("[^\u4e00-\u9fa5、](十一|十二|十三|十四|十五|一|二|三|四|五|六|七|八|九|十)、")
    split_list = [0] * 16
    split_dict = {
        "一、": 1,
        "二、": 2,
        "三、": 3,
        "四、": 4,
        "五、": 5,
        "六、": 6,
        "七、": 7,
        "八、": 8,
        "九、": 9,
        "十、": 10,
        "十一、": 11,
        "十二、": 12,
        "十三、": 13,
        "十四、": 14,
        "十五、": 15
    }

    for item in re.finditer(re_split, _content):
        _index = split_dict.get(item.group()[1:])
        if not split_list[_index]:
            split_list[_index] = item.span()[0] + 1
    split_list = [i for i in split_list if i != 0]
    start = 0
    new_split_list = []
    for idx in split_list:
        new_split_list.append((start, idx))
        start = idx
    new_split_list.append((start, len(_content)))
    # 实体列表按照“公告分段”分组
    words_num_dict = dict()
    last_words_num = 0
    for sentence in list_sentence:
        _index = sentence.sentence_index
        if _index == 0:
            words_num_dict[_index] = 0
        else:
            words_num_dict[_index] = words_num_dict[_index - 1] + last_words_num
        last_words_num = len(sentence.sentence_text)

    # 公司-联系人连接（km算法）
    re_phone = re.compile('1[3-9][0-9][-—－―]?\d{4}[-—－―]?\d{4}|'
                       '\+86.?1[3-9]\d{9}|'
                       # '0[1-9]\d{1,2}[-—－―][1-9]\d{6,7}/[1-9]\d{6,10}|'
                       '0[1-9]\d{1,2}[-—－―][2-9]\d{6,7}[^\d]?转\d{1,4}|'
                       '0[1-9]\d{1,2}[-—－―][2-9]\d{6}\d?[-—－―]\d{1,4}|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=1[3-9]\d{9})|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=0[1-9]\d{1,2}[-—－―]?[2-9]\d{6}\d?)|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?(?=[2-9]\d{6,7})|'
                       '0[1-9]\d{1,2}[-—－―]{0,2}[2-9]\d{6}\d?|'
                       '[\（|\(]0[1-9]\d{1,2}[\）|\)]-?[2-9]\d{6,7}-?\d{,4}|'
                       '400\d{7}转\d{1,4}|'
                       '[2-9]\d{6,7}')
    key_phone = re.compile("联系方式|电话|联系人|负责人")
    temporary_list2 = []
    for entity in list_entity:
        # if entity.entity_type in ['org', 'company', 'person'] and entity.is_tail==False:
        if entity.entity_type in ['org', 'company', 'person']:
            temporary_list2.append(entity)
    temporary_list2 = sorted(temporary_list2, key=lambda x: (x.sentence_index, x.begin_index))
    new_temporary_list2 = []
    for _split in new_split_list:
        temp_list = []
        for _entity in temporary_list2:
            if words_num_dict[_entity.sentence_index] + _entity.wordOffset_begin >= _split[0] and words_num_dict[
                _entity.sentence_index] + _entity.wordOffset_end < _split[1]:
                temp_list.append(_entity)
            elif words_num_dict[_entity.sentence_index] + _entity.wordOffset_begin >= _split[1]:
                break
        new_temporary_list2.append(temp_list)
    # print(new_temporary_list2)
    match_list2 = []
    for split_index in range(len(new_temporary_list2)):
        split_entitys = new_temporary_list2[split_index]
        if len(split_entitys)<=1:
            continue
        is_skip = False
        for index in range(len(split_entitys)):
            entity = split_entitys[index]
            if is_skip:
                is_skip = False
                continue
            else:
                if entity.entity_type in ['org', 'company']:
                    if entity.label != 5 or entity.entity_text in roleSet:
                        match_nums = 0
                        for after_index in range(index + 1, min(len(split_entitys), index + 4)):
                            after_entity = split_entitys[after_index]
                            if entity.in_attachment != after_entity.in_attachment:
                                break
                            if after_entity.entity_type in ['person']:
                                distance = (tokens_num_dict[after_entity.sentence_index] + after_entity.begin_index) - (
                                                   tokens_num_dict[entity.sentence_index] + entity.end_index)
                                # 实体为中标人/候选人，联系人已确定类别【1，2】
                                if entity.label in [2, 3, 4] and after_entity.label in [1, 2]:
                                    break
                                if entity.label in [2, 3, 4] and distance>=20:
                                    break
                                # 角色为中标候选人，排除"质疑|投诉|监督|受理"相关的联系人
                                if entity.label in [2, 3, 4] and re.search("质疑|投诉|监督|受理|项目(单位)?联系", list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 10):after_entity.wordOffset_begin]):
                                    break
                                if after_entity.sentence_index != 0 and after_entity.wordOffset_begin <= 10:
                                    if entity.label in [2, 3, 4] and re.search("请.{0,5}联系",
                                                                                 list_sentence[after_entity.sentence_index - 1].sentence_text[-10:] +
                                                                                 list_sentence[after_entity.sentence_index].sentence_text[0:after_entity.wordOffset_begin]):
                                        continue
                                if after_entity.label in [1, 2, 3]:
                                    # distance = (tokens_num_dict[
                                    #                 after_entity.sentence_index] + after_entity.begin_index) - (
                                    #                        tokens_num_dict[entity.sentence_index] + entity.end_index)
                                    sentence_distance = after_entity.sentence_index - entity.sentence_index
                                    if sentence_distance == 0:
                                        if distance < 100:
                                            if entity.label in [2, 3, 4] and distance>40:
                                                break
                                            if (entity.label == 0 and after_entity.label == 1) or (
                                                    entity.label == 1 and after_entity.label == 2):
                                                distance = distance / 100
                                            value = (-1 / 2 * (distance ** 2)) / 10000
                                            match_list2.append(Match(entity, after_entity, value))
                                            match_nums += 1
                                    else:
                                        if distance < 60:
                                            if entity.label in [2, 3, 4] and distance>20:
                                                break
                                            if (entity.label == 0 and after_entity.label == 1) or (
                                                    entity.label == 1 and after_entity.label == 2):
                                                distance = distance / 100
                                            value = (-1 / 2 * (distance ** 2)) / 10000
                                            match_list2.append(Match(entity, after_entity, value))
                                            match_nums += 1
                            if after_entity.entity_type in ['org', 'company']:
                                if entity.label in [2, 3, 4] and after_entity.label in [0, 1]:
                                    break
                                # 解决在‘地址’中识别出org/company的问题
                                # if entity.label in [0,1] and after_index==index+1 and after_entity.label not in [0,1]:
                                if entity.label != 5 and after_index == index + 1 and (
                                        after_entity.label == entity.label or after_entity.label == 5):
                                    distance = (tokens_num_dict[
                                                    after_entity.sentence_index] + after_entity.begin_index) - (
                                                           tokens_num_dict[entity.sentence_index] + entity.end_index)
                                    if distance < 20:
                                        after_entity_left = list_sentence[after_entity.sentence_index].tokens[max(0,
                                                                                                                  after_entity.begin_index - 10):after_entity.begin_index]
                                        after_entity_right = list_sentence[after_entity.sentence_index].tokens[
                                                             after_entity.end_index + 1:after_entity.end_index + 6]
                                        after_entity_left = "".join(after_entity_left)
                                        if len(after_entity_left) > 20:
                                            after_entity_left = after_entity_left[-20:]
                                        after_entity_right = "".join(after_entity_right)[:10]
                                        if re.search("地，?址", after_entity_left):
                                            is_skip = True
                                            continue
                                        if re.search("\(|（", after_entity_left) and re.search("\)|）",after_entity_right):
                                            is_skip = True
                                            continue
                                if entity.label in [0, 1] and after_entity.label in [0, 1] and entity.label == after_entity.label:
                                    break
                                if entity.label in [0, 1] and after_entity.label in [0, 1] and split_entitys[
                                    index + 1].entity_type == "person":
                                    break
                                if entity.label in [0, 1 ,5] and after_entity.label in [2, 3, 4]:
                                    break
                                if entity.label in [2, 3, 4] and after_entity.label in [0, 1]:
                                    break
                        # 搜索没有联系人的电话
                        mid_tokens = []
                        is_same_sentence = False
                        if index == len(split_entitys) - 1:
                            for i in range(entity.sentence_index, len(list_sentence)):
                                mid_tokens += list_sentence[i].tokens
                            mid_tokens = mid_tokens[entity.end_index + 1:]
                            mid_sentence = "".join(mid_tokens)
                            have_phone = re.findall(re_phone, mid_sentence)
                            if have_phone:
                                if re.findall(re_phone, mid_sentence.split("。")[0]):
                                    is_same_sentence = True
                                _phone = have_phone[0]
                                if _phone in [ent.entity_text for ent in phone_entitys]:
                                    phone_begin = mid_sentence.find(_phone)
                                    if words_num_dict[entity.sentence_index] + entity.wordOffset_begin + phone_begin < \
                                            new_split_list[split_index][1]:
                                        mid_sentence = mid_sentence[max(0, phone_begin - 15):phone_begin].replace("，", "")
                                        if re.search(key_phone, mid_sentence):
                                            if entity.label in [2, 3, 4] and re.search("质疑|投诉|监督|受理|项目(单位)?联系",mid_sentence[-8:]):
                                                pass
                                            else:
                                                distance = 1
                                                if is_same_sentence:
                                                    if phone_begin <= 200:
                                                        if entity.label in [2,3,4] and phone_begin>80:
                                                            break
                                                        value = (-1 / 2 * (distance ** 2)) / 10000
                                                        match_list2.append(Match(entity, (entity, _phone), value))
                                                        match_nums += 1
                                                else:
                                                    if phone_begin <= 60:
                                                        if entity.label in [2,3,4] and phone_begin>40:
                                                            break
                                                        value = (-1 / 2 * (distance ** 2)) / 10000
                                                        match_list2.append(Match(entity, (entity, _phone), value))
                                                        match_nums += 1
                        else:
                            next_entity = split_entitys[index + 1]
                            if next_entity.entity_type in ["org","company"]:
                                _entity_left = list_sentence[next_entity.sentence_index].sentence_text[entity.wordOffset_end:next_entity.wordOffset_begin]
                                _entity_left2 = re.sub("，（）\(\):：", "", _entity_left)
                                _entity_left2 = _entity_left2[-5:]
                                if re.search("(地，?址|地，?点)[:：][^，。]*$", _entity_left) or re.search("地址|地点", _entity_left2):
                                    if index + 2<= len(split_entitys) - 1:
                                        next_entity = split_entitys[index + 2]
                                if len(_entity_left)<=2 and re.search("[、（\(]",_entity_left):
                                    if index + 2 <= len(split_entitys) - 1:
                                        next_entity = split_entitys[index + 2]
                            if entity.sentence_index == next_entity.sentence_index:
                                mid_tokens += list_sentence[entity.sentence_index].tokens[
                                              entity.end_index + 1:next_entity.begin_index]
                            else:
                                sentence_index = entity.sentence_index
                                while sentence_index <= next_entity.sentence_index:
                                    mid_tokens += list_sentence[sentence_index].tokens
                                    sentence_index += 1
                                mid_tokens = mid_tokens[entity.end_index + 1:-(len(
                                    list_sentence[next_entity.sentence_index].tokens) - next_entity.begin_index) + 1]
                            mid_sentence = "".join(mid_tokens)
                            have_phone = re.findall(re_phone, mid_sentence)
                            if have_phone:
                                if re.findall(re_phone, mid_sentence.split("。")[0]):
                                    is_same_sentence = True
                                _phone = have_phone[0]
                                if _phone in [ent.entity_text for ent in phone_entitys]:
                                    phone_begin = mid_sentence.find(_phone)
                                    mid_sentence = mid_sentence[max(0, phone_begin - 15):phone_begin].replace("，", "")
                                    if re.search(key_phone, mid_sentence):
                                        p_phone = [p.entity_text for p in next_entity.person_phone] if next_entity.person_phone else []
                                        if next_entity.entity_type == 'person' and _phone in p_phone:
                                            pass
                                        elif entity.label in [2, 3, 4] and re.search("质疑|投诉|监督|受理|项目(单位)?联系", mid_sentence[-8:]):
                                            pass
                                        else:
                                            distance = (tokens_num_dict[
                                                            next_entity.sentence_index] + next_entity.begin_index) - (
                                                               tokens_num_dict[entity.sentence_index] + entity.end_index)
                                            distance = distance / 2
                                            if is_same_sentence:
                                                if phone_begin <= 200:
                                                    value = (-1 / 2 * (distance ** 2)) / 10000
                                                    match_list2.append(Match(entity, (entity, _phone), value))
                                                    match_nums += 1
                                            else:
                                                if phone_begin <= 60:
                                                    value = (-1 / 2 * (distance ** 2)) / 10000
                                                    match_list2.append(Match(entity, (entity, _phone), value))
                                                    match_nums += 1
                        # 实体无匹配时，尝试前向查找匹配
                        if not match_nums:
                            if (entity.label != 5 or entity.entity_text in roleSet) and entity.values[entity.label] >= 0.5 and index != 0:
                                previous_entity = split_entitys[index - 1]
                                if previous_entity.entity_type == 'person' and previous_entity.label in [1, 2, 3]:
                                    if entity.label in [2, 3, 4] and previous_entity.label in [1, 2]:
                                        continue
                                    if previous_entity.sentence_index == entity.sentence_index:
                                        distance = (tokens_num_dict[entity.sentence_index] + entity.begin_index) - (
                                                tokens_num_dict[
                                                    previous_entity.sentence_index] + previous_entity.end_index)
                                        if distance < 20:
                                            # 距离相等时，前向添加处罚值
                                            # distance += 1
                                            # 前向 没有 /10000
                                            value = (-1 / 2 * (distance ** 2))
                                            match_list2.append(Match(entity, previous_entity, value))
    # print(match_list2)
    # print([(mat.main_role.entity_text,mat.attribute.entity_text if not isinstance(mat.attribute, tuple) else mat.attribute[1]) for mat in match_list2])
    match_list2 = [mat for mat in match_list2 if mat.main_role not in linked_company and mat.attribute not in linked_person]
    # print(match_list2)
    # print([(mat.main_role.entity_text,mat.attribute.entity_text if not isinstance(mat.attribute, tuple) else mat.attribute[1]) for mat in match_list2])

    # km算法分配求解
    result2 = dispatch(match_list2)
    # print(result2)
    for match in result2:
        entity = match[0]
        # print(entity.entity_text)
        # print(entity.label)
        # print(match.attribute)
        entity_index = list_entity.index(entity)
        is_update = False
        if isinstance(match[1], tuple):
            person_ = ''
            phone_ = match[1][1].split("/") # 分割多个号码
            # print(person_,phone_)
        else:
            person_ = match[1].entity_text
            phone_ = [i.entity_text for i in match[1].person_phone] if match[1].person_phone else []
        for k in PackDict.keys():
            for i in range(len(PackDict[k]["roleList"])):
                if PackDict[k]["roleList"][i].role_name == "tenderee":
                    # if not PackDict[k]["roleList"][i].linklist:
                        if PackDict[k]["roleList"][i].entity_text == entity.entity_text or entity.label == 0:
                            if person_ not in agency_contact and len(set(phone_)&set(agency_phone))==0 and person_ not in winter_contact:
                                if not phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, ""))
                                for p in phone_:
                                    # if not person_ and len()
                                    PackDict[k]["roleList"][i].linklist.append((person_, p))
                                is_update = True
                elif PackDict[k]["roleList"][i].role_name == "agency":
                    # if not PackDict[k]["roleList"][i].linklist:
                        if PackDict[k]["roleList"][i].entity_text == entity.entity_text or entity.label == 1 and person_ not in winter_contact:
                            if person_ not in tenderee_contact and len(set(phone_)&set(tenderee_phone))==0:
                                if not phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, ""))
                                for p in phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, p))
                                is_update = True
                else:
                    if PackDict[k]["roleList"][i].entity_text == entity.entity_text:
                        # if not PackDict[k]["roleList"][i].linklist:
                        if len([item for item in PackDict[k]["roleList"][i].linklist if item[1]])==0: # 有联系人但无联系方式（号码）
                            if person_ not in tenderee_contact and len(set(phone_)&set(tenderee_phone))==0 and \
                                    person_ not in agency_contact and len(set(phone_)&set(agency_phone))==0:
                                if not phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, ""))
                                for p in phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, p))
                                is_update = True
        if not person_:
            is_update = False
        if is_update:
            # 更新 list_entity
            if not list_entity[entity_index].pointer_person:
                list_entity[entity_index].pointer_person = []
            list_entity[entity_index].pointer_person.append(match[1])

    # print('tenderee_contact',tenderee_contact)
    # print('tenderee_phone',tenderee_phone)
    # print('agency_contact',agency_contact)
    # print('agency_phone',agency_phone)
    # print('PackDict')
    # for k in PackDict.keys():
    #     for i in range(len(PackDict[k]["roleList"])):
    #         print(PackDict[k]["roleList"][i].role_name)
    #         print(PackDict[k]["roleList"][i].entity_text)
    #         print(PackDict[k]["roleList"][i].linklist)

    linked_person = []
    linked_persons_with = []
    for company_entity in [entity for entity in list_entity if entity.entity_type in ['company','org']]:
        if company_entity.pointer_person:
            for _person in company_entity.pointer_person:
                linked_person.append(_person)
                linked_persons_with.append(company_entity)
    # 一个公司对应多个联系人的补充
    person_entitys = [entity for entity in list_entity if entity.entity_type=='person']
    person_entitys = person_entitys[::-1]
    for index in range(len(person_entitys)):
        entity = person_entitys[index]
        prepare_link = []
        if entity not in linked_person:
            prepare_link.append(entity)
            last_person = entity
            for after_index in range(index + 1, min(len(person_entitys), index + 5)):
                after_entity = person_entitys[after_index]
                if after_entity.sentence_index==last_person.sentence_index and last_person.begin_index-after_entity.end_index<5:
                    if after_entity in linked_person:
                        _index = linked_person.index(after_entity)
                        with_company = linked_persons_with[_index]
                        for i in range(len(PackDict["Project"]["roleList"])):
                            if PackDict["Project"]["roleList"][i].role_name == "tenderee":
                                if PackDict["Project"]["roleList"][i].entity_text == with_company.entity_text or with_company.label == 0:
                                    for item in prepare_link:
                                        person_phone = [p.entity_text for p in item.person_phone] if item.person_phone else []
                                        for _p in person_phone:
                                            PackDict["Project"]["roleList"][i].linklist.append((item.entity_text, _p))
                                        with_company.pointer_person.append(item)
                                        linked_person.append(item)
                            elif PackDict["Project"]["roleList"][i].role_name == "agency":
                                if PackDict["Project"]["roleList"][i].entity_text == with_company.entity_text or with_company.label == 1:
                                    for item in prepare_link:
                                        person_phone = [p.entity_text for p in item.person_phone] if item.person_phone else []
                                        for _p in person_phone:
                                            PackDict["Project"]["roleList"][i].linklist.append((item.entity_text, _p))
                                        with_company.pointer_person.append(item)
                                        linked_person.append(item)
                            else:
                                if PackDict["Project"]["roleList"][i].entity_text == with_company.entity_text:
                                    for item in prepare_link:
                                        person_phone = [p.entity_text for p in item.person_phone] if item.person_phone else []
                                        for _p in person_phone:
                                            PackDict["Project"]["roleList"][i].linklist.append((item.entity_text, _p))
                                        with_company.pointer_person.append(item)
                                        linked_person.append(item)
                        break
                    else:
                        prepare_link.append(after_entity)
                        last_person = after_entity
                        continue

    # 统一同类角色的属性
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            for _entity in list_entity:
                if _entity.entity_type in ['org','company']:
                    is_same = False
                    is_similar = False
                    # entity_text相同
                    if _entity.entity_text==PackDict[k]["roleList"][i].entity_text:
                        is_same = True
                    # entity.label为【0，1】
                    if _entity.label in [0,1] and dict_role_id[str(_entity.label)]==PackDict[k]["roleList"][i].role_name:
                        is_similar = True
                    if is_same:
                        linked_entitys = _entity.linked_entitys
                        if linked_entitys:
                            for linked_entity in linked_entitys:
                                pointer_person = linked_entity.pointer_person if linked_entity.pointer_person else []
                                for _pointer_person in pointer_person:
                                    _phone = [p.entity_text for p in _pointer_person.person_phone] if _pointer_person.person_phone else []
                                    for _p in _phone:
                                        if (_pointer_person.entity_text,_p) not in PackDict[k]["roleList"][i].linklist:
                                            PackDict[k]["roleList"][i].linklist.append((_pointer_person.entity_text,_p))
                    elif is_similar:
                        pointer_person = _entity.pointer_person if _entity.pointer_person else []
                        for _pointer_person in pointer_person:
                            _phone = [p.entity_text for p in _pointer_person.person_phone] if _pointer_person.person_phone else []
                            for _p in _phone:
                                if (_pointer_person.entity_text, _p) not in PackDict[k]["roleList"][i].linklist:
                                    PackDict[k]["roleList"][i].linklist.append(
                                        (_pointer_person.entity_text, _p))

    # "roleList"中联系人电话去重
    tenderee_agency_phone = []
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            if PackDict[k]["roleList"][i].role_name in ['agency','tenderee']:
                tenderee_agency_phone.extend([person_phone[1] for person_phone in PackDict[k]["roleList"][i].linklist if person_phone[1]])
            # 带有联系人的电话
            with_person = [person_phone[1] for person_phone in PackDict[k]["roleList"][i].linklist if person_phone[0]]
            # 带有电话的联系人
            with_phone = [person_phone[0] for person_phone in PackDict[k]["roleList"][i].linklist if person_phone[1]]
            remove_list = []
            for item in PackDict[k]["roleList"][i].linklist:
                if not item[0]:
                    if item[1] in with_person:
                        # 删除重复的无联系人电话
                        remove_list.append(item)
                elif not item[1]:
                    if item[0] in with_phone:
                        remove_list.append(item)
            for _item in remove_list:
                PackDict[k]["roleList"][i].linklist.remove(_item)
    # 中标候选人联系方式异常排除
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            if PackDict[k]["roleList"][i].role_name in ['win_tenderer', 'second_tenderer','third_tenderer']:
                if tenderee_agency_phone:
                    remove_list = []
                    for item in PackDict[k]["roleList"][i].linklist:
                        if item[1] and item[1] in tenderee_agency_phone:
                            remove_list.append(item)
                    for _item in remove_list:
                        PackDict[k]["roleList"][i].linklist.remove(_item)
                # else:
                #     # 公告中无招标代理联系方式时，可排除中标联系方式
                #     remove_list = []
                #     for _item in PackDict[k]["roleList"][i].linklist:
                #         # 有联系方式
                #         if _item[1]:
                #             remove_list.append(_item)
                #     for _item in remove_list:
                #         PackDict[k]["roleList"][i].linklist.remove(_item)
    # PackDict更新company/org地址
    last_role_prob = {}
    for ent in pre_entity:
        if ent.entity_type in ['company','org']:
            if ent.pointer_address:
                for k in PackDict.keys():
                    for i in range(len(PackDict[k]["roleList"])):
                        if PackDict[k]["roleList"][i].entity_text == ent.entity_text:
                            if not PackDict[k]["roleList"][i].address:
                                PackDict[k]["roleList"][i].address = ent.pointer_address.entity_text
                                last_role_prob[PackDict[k]["roleList"][i].role_name] = ent.values[role2id_dict[PackDict[k]["roleList"][i].role_name]]
                            else:
                                if PackDict[k]["roleList"][i].role_name in ['tenderee','agency']:
                                    # 角色为招标/代理人时，取其实体概率高的链接地址作为角色address
                                    if ent.values[role2id_dict[PackDict[k]["roleList"][i].role_name]] > last_role_prob[PackDict[k]["roleList"][i].role_name]:
                                        PackDict[k]["roleList"][i].address = ent.pointer_address.entity_text
                                        last_role_prob[PackDict[k]["roleList"][i].role_name] = ent.values[role2id_dict[PackDict[k]["roleList"][i].role_name]]
                                else:
                                    if len(ent.pointer_address.entity_text) > len(PackDict[k]["roleList"][i].address):
                                        PackDict[k]["roleList"][i].address = ent.pointer_address.entity_text

    # 联系人——电子邮箱链接
    temporary_list3 = [entity for entity in list_entity if entity.entity_type=='email' or (entity.entity_type=='person' and entity.label in [1,2,3])]
    temporary_list3 = sorted(temporary_list3, key=lambda x: (x.sentence_index, x.begin_index))
    new_temporary_list3 = []
    for _split in new_split_list:
        temp_list = []
        for _entity in temporary_list3:
            if words_num_dict[_entity.sentence_index] + _entity.wordOffset_begin >= _split[0] and words_num_dict[
                _entity.sentence_index] + _entity.wordOffset_end < _split[1]:
                temp_list.append(_entity)
            elif words_num_dict[_entity.sentence_index] + _entity.wordOffset_begin >= _split[1]:
                break
        new_temporary_list3.append(temp_list)
    # print(new_temporary_list3)
    match_list3 = []
    for split_index in range(len(new_temporary_list3)):
        split_entitys = new_temporary_list3[split_index]
        for index in range(len(split_entitys)):
            entity = split_entitys[index]
            if entity.entity_type == 'person':
                match_nums = 0
                for after_index in range(index + 1, min(len(split_entitys), index + 4)):
                    after_entity = split_entitys[after_index]
                    if match_nums > 2:
                        break
                    if after_entity.entity_type == 'email':
                        distance = (tokens_num_dict[after_entity.sentence_index] + after_entity.begin_index) - (
                                           tokens_num_dict[entity.sentence_index] + entity.end_index)
                        sentence_distance = after_entity.sentence_index - entity.sentence_index
                        if sentence_distance == 0:
                            if distance < 100:
                                if (entity.label == 0 and after_entity.label == 1) or (
                                        entity.label == 1 and after_entity.label == 2):
                                    distance = distance / 100
                                value = (-1 / 2 * (distance ** 2)) / 10000
                                match_list3.append(Match(entity, after_entity, value))
                                match_nums += 1
                        else:
                            if distance < 60:
                                if (entity.label == 0 and after_entity.label == 1) or (
                                        entity.label == 1 and after_entity.label == 2):
                                    distance = distance / 100
                                value = (-1 / 2 * (distance ** 2)) / 10000
                                match_list3.append(Match(entity, after_entity, value))
                                match_nums += 1
                # 前向查找匹配
                # if not match_nums:
                if index != 0:
                    previous_entity = split_entitys[index - 1]
                    if previous_entity.entity_type == 'email':
                        if previous_entity.sentence_index == entity.sentence_index:
                            distance = (tokens_num_dict[entity.sentence_index] + entity.begin_index) - (
                                    tokens_num_dict[
                                        previous_entity.sentence_index] + previous_entity.end_index)
                            if distance < 30:
                                # 距离相等时，前向添加处罚值
                                # distance += 1
                                # 前向 没有 /10000
                                value = (-1 / 2 * (distance ** 2))
                                match_list3.append(Match(entity, previous_entity, value))
    # print(match_list3)
    # km算法分配求解
    result3 = dispatch(match_list3)
    for match in result3:
        match_person = match[0]
        match_email = match[1]
        match_person.pointer_email = match_email

    # # 1）第一个公司实体的招标人，则看看下一个实体是否为代理人，如果是则联系人错位连接 。2）在同一句中往后找联系人。3）连接不上在整个文章找联系人。
    # temp_ent_list = []  # 临时列表，记录0,1角色及3联系人
    # other_person = []  # 阈值以上的联系人列表
    # link_person = []   # 有电话没联系上角色的person列表
    # other_ent = []
    # link_ent = []
    # found_person = False
    # ent_list = []
    # for entity in list_entity:
    #     if entity.entity_type in ['org','company','person']:
    #         ent_list.append(entity)
    # # ent_list = [entity for entity in list_entity if entity.entity_type in ['org','company','person']]
    # #for list_index in range(len(ent_list)):
    #     #if ent_list[list_index].entity_type in ['org','company'] and ent_list[list_index].label == 0 and list_index+2<len(ent_list) and \
    #        #ent_list[list_index+1].entity_type in ['org','company'] and ent_list[list_index+1].label == 1 and ent_list[list_index+2].entity_type in ['person']:
    #         #ent_list[list_index+1], ent_list[list_index+2] = ent_list[list_index+2], ent_list[list_index+1]
    # # 2020/11/25增加确定角色联系人判断
    # sure_person_set = set([entity.entity_text for entity in ent_list if entity.entity_type == 'person' and entity.label in [1, 2]])
    # # 招标/代理在同一句中交叉情况的处理
    # for index in range(len(ent_list)):
    #     entity = ent_list[index]
    #     if entity.entity_text in roleSet and entity.label in [0, 1] and index+3<len(ent_list):
    #         if entity.sentence_index==ent_list[index+1].sentence_index==ent_list[index+2].sentence_index==ent_list[index+3].sentence_index:
    #             if ent_list[index+1].begin_index - entity.end_index < 30:
    #                 if ent_list[index+1].entity_text in roleSet and ent_list[index+1].label in [0, 1] and entity.label!=ent_list[index+1].label:
    #                     if ent_list[index+2].entity_type=="person" and ent_list[index+3].entity_type=="person" and \
    #                             ent_list[index+2].label==3 and ent_list[index+3].label==3:
    #                         ent_list[index + 1], ent_list[index + 2] = ent_list[index + 2], ent_list[index + 1]
    #
    #
    # for index in range(len(ent_list)):
    #     entity = ent_list[index]
    #     if entity.entity_type=="person":
    #         if str(entity.label) == "0":  # 2020/11/25 非联系人直接跳过
    #             continue
    #         if entity.values[entity.label]>on_value_person:
    #             if str(entity.label)=="1":
    #                 for i in range(len(PackDict["Project"]["roleList"])):
    #                     if PackDict["Project"]["roleList"][i].role_name=="tenderee":
    #                         PackDict["Project"]["roleList"][i].linklist.append((entity.entity_text,entity.person_phone))
    #                         link_person.append(entity.entity_text)
    #                         link_ent.append(PackDict["Project"]["roleList"][i].entity_text)
    #                 # add pointer_person
    #                 for _entity in list_entity:
    #                     if dict_role_id.get(str(_entity.label))=="tenderee":
    #                         for i in range(len(PackDict["Project"]["roleList"])):
    #                             if PackDict["Project"]["roleList"][i].entity_text==_entity.entity_text and PackDict["Project"]["roleList"][i].role_name=="tenderee":
    #                                 _entity.pointer_person = entity
    #             elif str(entity.label)=="2":
    #                 for i in range(len(PackDict["Project"]["roleList"])):
    #                     if PackDict["Project"]["roleList"][i].role_name=="agency":
    #                         PackDict["Project"]["roleList"][i].linklist.append((entity.entity_text,entity.person_phone))
    #                         link_person.append(entity.entity_text)
    #                         link_ent.append(PackDict["Project"]["roleList"][i].entity_text)
    #                 # add pointer_person
    #                 for _entity in list_entity:
    #                     if dict_role_id.get(str(_entity.label))=="agency":
    #                         for i in range(len(PackDict["Project"]["roleList"])):
    #                             if PackDict["Project"]["roleList"][i].entity_text==_entity.entity_text and PackDict["Project"]["roleList"][i].role_name=="agency":
    #                                 _entity.pointer_person = entity
    #             elif str(entity.label)=="3":
    #                 if entity.entity_text in sure_person_set:  # 2020/11/25 排除已经确定角色的联系人
    #                     continue
    #                 #not_link_person.append((entity_after.entity_text,entity_after.person_phone))
    #                 other_person.append(entity.entity_text)
    #                 temp_ent_list.append((entity.entity_text,entity.person_phone,entity))
    #
    #     #if entity.entity_text in roleSet:
    #     if entity.entity_text in roleSet:
    #         if entity.label in [0,1]:
    #             other_ent.append(entity.entity_text)
    #             temp_ent_list.append((entity.entity_text, entity.label,entity))
    #         for behind_index in range(index+1, len(ent_list)):
    #             entity_after = ent_list[behind_index]
    #             if entity_after.sentence_index-entity.sentence_index>=1 or entity_after.entity_type in ['org','company']:   # 只在本句中找联系人
    #                 break
    #             if entity_after.values is not None:
    #                 if entity_after.entity_type=="person":
    #                     if str(entity_after.label) == "0": # 2020/11/25角色后面为非联系人 停止继续往后找
    #                         break
    #                     if entity_after.values[entity_after.label]>on_value_person:
    #                         if str(entity_after.label)=="1":
    #                             for i in range(len(PackDict["Project"]["roleList"])):
    #                                 if PackDict["Project"]["roleList"][i].role_name=="tenderee":
    #                                     PackDict["Project"]["roleList"][i].linklist.append((entity_after.entity_text,entity_after.person_phone))
    #                                     link_person.append(entity_after.entity_text)
    #                                     link_ent.append(PackDict["Project"]["roleList"][i].entity_text)
    #                         elif str(entity_after.label)=="2":
    #                             for i in range(len(PackDict["Project"]["roleList"])):
    #                                 if PackDict["Project"]["roleList"][i].role_name=="agency":
    #                                     PackDict["Project"]["roleList"][i].linklist.append((entity_after.entity_text,entity_after.person_phone))
    #                                     link_person.append(entity_after.entity_text)
    #                                     link_ent.append(PackDict["Project"]["roleList"][i].entity_text)
    #                         elif str(entity_after.label)=="3":
    #                             if entity_after.entity_text in sure_person_set: # 2020/11/25 如果姓名已经出现在确定角色联系人中则停止往后找
    #                                 break
    #                             elif entity_after.begin_index - entity.end_index > 30:#2020/10/25 如果角色实体与联系人实体间隔大于阈值停止
    #                                 break
    #                             for pack in PackDict.keys():
    #                                 for i in range(len(PackDict[pack]["roleList"])):
    #                                     if PackDict[pack]["roleList"][i].entity_text==entity.entity_text:
    #                                         #if entity_after.sentence_index-entity.sentence_index>1 and len(roleList[i].linklist)>0:
    #                                             #break
    #                                         PackDict[pack]["roleList"][i].linklist.append((entity_after.entity_text,entity_after.person_phone))
    #                                         link_person.append(entity_after.entity_text)
    #                                         #add pointer_person
    #                                         entity.pointer_person = entity_after
    #
    # not_link_person = [person for person in other_person if person not in link_person]
    # not_link_ent = [ent for ent in other_ent if ent not in link_ent]
    # if len(not_link_person) > 0 and len(not_link_ent) > 0 :
    #     item = temp_ent_list
    #     for i in range(len(item)):
    #         if item[i][0] in not_link_ent and item[i][1] == 0 and i+3 < len(item):
    #             if item[i+1][0] in other_ent and item[i+1][1] == 1 and item[i+2][0] in other_person and item[i+3][0] in other_person:
    #                 item[i+1], item[i+2] = item[i+2], item[i+1]
    #     for i in range(len(item)-1, -1, -1):
    #         if item[i][0] in not_link_ent:
    #             for pack in PackDict.keys():
    #                 for role in PackDict[pack]["roleList"]:
    #                     if role.entity_text == item[i][0] and len(role.linklist) < 1:
    #                         for j in range(i+1, len(item)):
    #                             if item[j][0] in not_link_person:
    #                                 role.linklist.append(item[j][:2])
    #                                 #add pointer_person
    #                                 item[i][2].pointer_person = item[j][2]
    #                                 break
    #                             else:
    #                                 break
    # # 电话没有联系人的处理
    # role_with_no_phone = []
    # for i in range(len(PackDict["Project"]["roleList"])):
    #     if PackDict["Project"]["roleList"][i].role_name in ["tenderee","agency"]:
    #         if len(PackDict["Project"]["roleList"][i].linklist)==0: # 找出没有联系人的招标/代理人
    #             role_with_no_phone.append(PackDict["Project"]["roleList"][i].entity_text)
    #         else:
    #             phone_nums = 0
    #             for link in PackDict["Project"]["roleList"][i].linklist:
    #                 if link[1]:
    #                     phone_nums += 1
    #                     break
    #             if not phone_nums:
    #                 role_with_no_phone.append(PackDict["Project"]["roleList"][i].entity_text)
    # if role_with_no_phone:
    #     phone_with_person = [entity.person_phone for entity in list_entity if entity.entity_type == "person"]
    #     # phone_with_person = [phone for phone in phone_with_person if phone]
    #
    #     dict_index_sentence = {}
    #     for _sentence in list_sentence:
    #         dict_index_sentence[_sentence.sentence_index] = _sentence
    #     new_entity_list = [entity for entity in list_entity if entity.entity_type in ['org','company','person']]
    #     for index in range(len(new_entity_list)):
    #         entity = new_entity_list[index]
    #         if entity.entity_text in role_with_no_phone:
    #             e_sentence = dict_index_sentence[entity.sentence_index]
    #             entity_right = e_sentence.tokens[entity.end_index:entity.end_index+40]
    #             entity_right = "".join(entity_right)
    #             if index+1<len(new_entity_list) and entity_right.find(new_entity_list[index+1].entity_text)>-1:
    #                 entity_right = entity_right[:entity_right.find(new_entity_list[index+1].entity_text)]
    #             have_phone = re.findall(phone,entity_right)
    #             if have_phone:
    #                 _phone = have_phone[0]
    #                 phone_begin = entity_right.find(_phone)
    #                 if _phone not in phone_with_person and re.search(key_phone,entity_right[:phone_begin]):
    #                     # entity.person_phone = _phone
    #                     for i in range(len(PackDict["Project"]["roleList"])):
    #                         if PackDict["Project"]["roleList"][i].entity_text == entity.entity_text:
    #                             PackDict["Project"]["roleList"][i].linklist.append(('', _phone))

    
    #寻找多标段招标金额
    p_entity = len(list_entity)-1

    set_tenderer_money = set()
    list_tenderer_money = []  #2021/7/16 新增列表，倒序保存所有中标金额
    unit_list = [] #2021/8/17 新增，保存金额单位

    #遍历所有实体
    max_prob = 0 # 保存招标金额最大概率
    while(p_entity>=0):
        entity = list_entity[p_entity]
        if entity.entity_type=="money":
            # 2021/12/03 添加成本警戒线、保证金
            if entity.notes in ['保证金', '成本警戒线']:
                packagePointer, _flag = getPackage(PackageList, entity.sentence_index, entity.begin_index,
                                                   "money-" + str(entity.label), MAX_DIS=2, DIRECT="L")
                if packagePointer is None:
                    packageName = "Project"
                else:
                    packageName = packagePointer.entity_text

                if packageName == "Project":
                    # if PackDict["Project"]["tendereeMoney"]<float(entity.entity_text):
                    #     PackDict["Project"]["tendereeMoney"] = str(Decimal(entity.entity_text))
                    if entity.notes=="保证金" and "bond" not in PackDict["Project"]:
                        PackDict["Project"]["bond"] = str(Decimal(entity.entity_text))
                    elif entity.notes=="成本警戒线" and "cost_warning" not in PackDict["Project"]:
                        PackDict["Project"]["cost_warning"] = str(Decimal(entity.entity_text))

                else:
                    if entity.notes == "保证金" and "bond" not in PackDict[packageName]:
                        PackDict[packageName]["bond"] = str(Decimal(entity.entity_text))
                    elif entity.notes == "成本警戒线" and "cost_warning" not in PackDict[packageName]:
                        PackDict[packageName]["cost_warning"] = str(Decimal(entity.entity_text))

            elif entity.values[entity.label]>=on_value:
                if str(entity.label)=="1":
                    set_tenderer_money.add(float(entity.entity_text))
                    list_tenderer_money.append(float(entity.entity_text))  # 2021/7/16 新增列表，倒序保存所有中标金额
                    unit_list.append(entity.money_unit)
                # if str(entity.label)=="0":
                if str(entity.label)=="0" and entity.notes!='总投资':
                    '''
                    if p_entity>0:
                        p_before = list_entity[p_entity-1]
                        if p_before.entity_type=="money" and p_before.label==entity.label and p_before.entity_text==entity.entity_text and abs(entity.begin_index-p_before.end_index)<=2:
                            p_entity -= 1
                            continue
                    '''
                    packagePointer,_flag = getPackage(PackageList,entity.sentence_index,entity.begin_index,"money-"+str(entity.label),MAX_DIS=2,DIRECT="L")
                    if packagePointer is None:
                        packageName = "Project"
                    else:
                        packageName = packagePointer.entity_text
                        
                    if packageName=="Project":
                        # if PackDict["Project"]["tendereeMoney"]<float(entity.entity_text):
                        #     PackDict["Project"]["tendereeMoney"] = str(Decimal(entity.entity_text))
                        # if entity.values[entity.label]>on_value:
                        if entity.values[entity.label]>max_prob-0.005: # 选择最大概率招标金额 2024/05/23 相差0.005尽量选前面的
                            PackDict["Project"]["tendereeMoney"] = str(Decimal(entity.entity_text))
                            PackDict["Project"]["tendereeMoneyUnit"] = entity.money_unit
                            max_prob = entity.values[entity.label]
                    else:
                        PackDict[packageName]["tendereeMoney"] = str(Decimal(entity.entity_text))
                        PackDict[packageName]["tendereeMoneyUnit"] = entity.money_unit
                        #add pointer_tendereeMoney
                        packagePointer.pointer_tendereeMoney = entity
        p_entity -= 1            
    
        
    #删除一个机构有多个角色的数据
    #删除重复人、概率不回传
    final_roleList = []
    list_pop = []
    set_tenderer_role = set()
    dict_pack_tenderer_money = dict()

    for pack in PackDict.keys():
        #删除无效包
        if PackDict[pack]["code"]=="" and PackDict[pack]["tendereeMoney"]==0 and len(PackDict[pack]["roleList"])==0:
            list_pop.append(pack)
        for i in range(len(PackDict[pack]["roleList"])):
            if PackDict[pack]["roleList"][i].role_name=="win_tenderer":
                if PackDict[pack]["roleList"][i].money==0:
                    set_tenderer_role.add(PackDict[pack]["roleList"][i])
                    dict_pack_tenderer_money[pack] = [PackDict[pack]["roleList"][i],set()]
    #找到包的中投标金额
    for _index in range(len(PackageList)):
        if "hit" in PackageList[_index]:
            for _hit in list(PackageList[_index]["hit"]):
                if len(_hit.split("-"))==3:
                    _money = float(_hit.split("-")[1]) if _hit.split("-")[0]=="money" else None
                # 补充金额前新增负号‘-’导致错误的规则
                elif len(_hit.split("-"))==4:
                    _money = float(_hit.split("-")[2]) if _hit.split("-")[0] == "money" else None
                else:
                    _money = None
                if PackageList[_index]["name"] in dict_pack_tenderer_money and _money is not None:
                    dict_pack_tenderer_money[PackageList[_index]["name"]][1].add(_money)
    #只找到一个中标人和中标金额
    if len(set_tenderer_money)==1 and len(set_tenderer_role)==1:
        list(set_tenderer_role)[0].money = list(set_tenderer_money)[0]
        list(set_tenderer_role)[0].money_unit = unit_list[0]
        # print('一个中标人一个金额：', list(set_tenderer_money)[0])
    #找到一个中标人和多个招标金额
    if len(set_tenderer_money)>1 and len(set_tenderer_role)==1:
        _maxMoney = list(set_tenderer_money)[0]
        _sumMoney = 0
        for _m in list(set_tenderer_money):
            _sumMoney += _m
            if _m>_maxMoney:
                _maxMoney = _m
        if _sumMoney/_maxMoney==2:
            list(set_tenderer_role)[0].money = _maxMoney
            # print('一人多金额分项合计 取最大金额：', _maxMoney)
        else:
            # list(set_tenderer_role)[0].money = _maxMoney
            if min(list_tenderer_money)>200000 and list_tenderer_money[-1]/min(list_tenderer_money)>9000:
                list(set_tenderer_role)[0].money = min(list_tenderer_money)
                list(set_tenderer_role)[0].money_unit = unit_list[list_tenderer_money.index(min(list_tenderer_money))]
                # print('一人多金额 且最小的大于20万第一个金额比最小金额大几千倍的最小中标金额：', min(list_tenderer_money))
            else:
                list(set_tenderer_role)[0].money = list_tenderer_money[-1]  # 2021/7/16 修改 不是单价合计方式取第一个中标金额
                list(set_tenderer_role)[0].money_unit = unit_list[-1] # 金额单位
                # print('一人多金额 取第一个中标金额：', list_tenderer_money[-1])
    #每个包都只找到一个金额
    _flag_pack_money = True
    for k,v in dict_pack_tenderer_money.items():
        if len(v[1])!=1:
            _flag_pack_money = False
    if _flag_pack_money and len(PackageSet)==len(dict_pack_tenderer_money.keys()):
        for k,v in dict_pack_tenderer_money.items():
            v[0].money = list(v[1])[0]
            # print('k,v in dict_pack_tenderer_money.items', k, v)
    # 2021/7/16 #增加判断中标金额是否远大于招标金额逻辑
    for pack in PackDict.keys():
        for i in range(len(PackDict[pack]["roleList"])):
            if float(PackDict[pack]["tendereeMoney"]) > 0:
                # print('金额数据类型：',type(PackDict[pack]["roleList"][i].money))
                if float(PackDict[pack]["roleList"][i].money) >10000000 and \
                        float(PackDict[pack]["roleList"][i].money)/float(PackDict[pack]["tendereeMoney"])>=1000:
                    PackDict[pack]["roleList"][i].money = float(PackDict[pack]["roleList"][i].money) / 10000
                    # print('招标金额校正中标金额')
    # 2022/04/01 #增加判断中标金额是否远小于招标金额逻辑，比例相差10000倍左右（中标金额“万”单位丢失或未识别）
    for pack in PackDict.keys():
        for i in range(len(PackDict[pack]["roleList"])):
            if float(PackDict[pack]["tendereeMoney"]) > 0 and float(PackDict[pack]["roleList"][i].money) > 0.:
                if float(PackDict[pack]["roleList"][i].money) < 1000 and \
                        float(PackDict[pack]["tendereeMoney"])/float(PackDict[pack]["roleList"][i].money)>=9995 and \
                        float(PackDict[pack]["tendereeMoney"])/float(PackDict[pack]["roleList"][i].money)<11000:
                    PackDict[pack]["roleList"][i].money = float(PackDict[pack]["roleList"][i].money) * 10000
    # 2021/7/19 #增加判断中标金额是否远大于第二三中标金额
    for pack in PackDict.keys():
        tmp_moneys = []
        for i in range(len(PackDict[pack]["roleList"])):
            if float(PackDict[pack]["roleList"][i].money) >100000:
                tmp_moneys.append(float(PackDict[pack]["roleList"][i].money))
        if len(tmp_moneys)>2 and max(tmp_moneys)/min(tmp_moneys)>1000:
            for i in range(len(PackDict[pack]["roleList"])):
                if float(PackDict[pack]["roleList"][i].money)/min(tmp_moneys)>1000:
                    PackDict[pack]["roleList"][i].money = float(PackDict[pack]["roleList"][i].money) / 10000
                    # print('通过其他中标人投标金额校正中标金额')
    for item in list_pop:
        PackDict.pop(item)
    # 公告中只有"招标人"且无"联系人"链接时
    if len(PackDict)==1:
        k = list(PackDict.keys())[0]
        tenderee_agency_role = [role for role in PackDict[k]["roleList"] if role.role_name in ['tenderee','agency']]
        if len(tenderee_agency_role)==1:
            exist_person = []
            exist_phone = []
            for role in PackDict[k]["roleList"]:
                for group in role.linklist:
                    if group[0]:
                        exist_person.append(group[0])
                    if group[1]:
                        exist_phone.append(group[1])

            if tenderee_agency_role[0].role_name == "tenderee":
                if not tenderee_agency_role[0].linklist:
                    get_contacts = False
                    if not get_contacts:
                        # 根据大纲Outline类召回联系人
                        for outline in list_outline:
                            if re.search("联系人|联系方|联系方式|联系电话|电话|负责人|与.{2,4}联系",outline.outline_summary):
                                for t_person in [p for p in temporary_list2 if p.entity_type=='person' and p.label==3]:
                                    if words_num_dict[t_person.sentence_index] + t_person.wordOffset_begin >= words_num_dict[outline.sentence_begin_index] + outline.wordOffset_begin and words_num_dict[
                                        t_person.sentence_index] + t_person.wordOffset_end < words_num_dict[outline.sentence_end_index] + outline.wordOffset_end:
                                        if t_person.person_phone:
                                            _phone = [p.entity_text for p in t_person.person_phone]
                                            for _p in _phone:
                                                if t_person.entity_text not in exist_person and _p not in exist_phone:
                                                    tenderee_agency_role[0].linklist.append((t_person.entity_text, _p))
                                                    get_contacts = True
                                            break
                                    elif words_num_dict[t_person.sentence_index] + t_person.wordOffset_begin >= \
                                            words_num_dict[outline.sentence_end_index] + outline.wordOffset_end:
                                        break
                                if not get_contacts:
                                    sentence_phone = phone.findall(outline.outline_text)
                                    if sentence_phone:
                                        if sentence_phone[0] not in exist_phone:
                                            tenderee_agency_role[0].linklist.append(("", sentence_phone[0]))
                                            get_contacts = True
                                            break
                    if not get_contacts:
                        # 直接取文中倒数第一个联系人
                        for _entity in temporary_list2[::-1]:
                            if _entity.entity_type=='person' and _entity.label==3:
                                if _entity.person_phone:
                                    _phone = [p.entity_text for p in _entity.person_phone]
                                    for _p in _phone:
                                        if _entity.entity_text not in exist_person and _p not in exist_phone:
                                            tenderee_agency_role[0].linklist.append((_entity.entity_text, _p))
                                            get_contacts = True
                                    break
                    if not get_contacts:
                        # 如果文中只有一个“phone”实体，则直接取为联系人电话
                        if len(phone_entitys) == 1:
                            if phone_entitys[0].entity_text not in exist_phone:
                                tenderee_agency_role[0].linklist.append(("", phone_entitys[0].entity_text))
                                get_contacts = True
                    if not get_contacts:
                        # 通过大纲Outline类直接取电话
                        if len(new_split_list) > 1:
                            for _start, _end in new_split_list:
                                temp_sentence = _content[_start:_end]
                                sentence_outline = temp_sentence.split("，:：")[0]
                                if re.search("联系人|联系方|联系方式|联系电话|电话|负责人|与.{2,4}联系", sentence_outline):
                                    sentence_phone = phone.findall(temp_sentence)
                                    if sentence_phone:
                                        if sentence_phone[0] in [ent.entity_text for ent in phone_entitys] and sentence_phone[0] not in exist_phone:
                                            tenderee_agency_role[0].linklist.append(("", sentence_phone[0]))
                                            get_contacts = True
                                            break
                    if not get_contacts:
                        # 通过正则提取句子段落进行提取电话
                        contacts_person = "(?:联系人|联系方|联系方式|负责人|电话|联系电话)[:：]?"
                        tenderee_pattern = "(?:(?:采购|招标|议价|议标|比选)(?:人|公司|单位|组织|部门)|建设(?:单位|业主)|(?:采购|招标|甲)方|询价单位|项目业主|业主|业主单位)[^。]{0,5}"
                        contact_pattern_list = [tenderee_pattern + contacts_person,
                                                "(?:采购[^。，]{0,2}项目|采购事项|招标)[^。，]{0,4}" + contacts_person,
                                                "(?:项目|采购)[^。，]{0,4}" + contacts_person,
                                                "(?:报名|报价|业务咨询|业务|投标咨询)[^。，]{0,4}" + contacts_person, ]
                        for _pattern in contact_pattern_list:
                            get_tenderee_contacts = False
                            for regular_match in re.finditer(_pattern, _content):
                                match_text = _content[regular_match.end():regular_match.end() + 40]
                                match_text = match_text.split("。")[0]
                                sentence_phone = phone.findall(match_text)
                                if sentence_phone:
                                    if sentence_phone[0] not in exist_phone:
                                        tenderee_agency_role[0].linklist.append(("", sentence_phone[0]))
                                        get_tenderee_contacts = True
                                        break
                            if get_tenderee_contacts:
                                break

    for pack in PackDict.keys():
        for i in range(len(PackDict[pack]["roleList"])):
            PackDict[pack]["roleList"][i] = PackDict[pack]["roleList"][i].getString()
    return PackDict

def initPackageAttr(RoleList,PackageSet,win_tenderer_set,tenderee_or_agency_set, main_body_pack):
    '''
    @summary: 根据拿到的roleList和packageSet初始化接口返回的数据
    '''   
    packDict = dict()
    packDict["Project"] = {"code":"","tendereeMoney":0,"roleList":[], 'tendereeMoneyUnit':''}
    for item in list(PackageSet):
        packDict[item] = {"code":"","tendereeMoney":0,"roleList":[], 'tendereeMoneyUnit':''}
        packDict[item]['in_attachment'] = False if item in main_body_pack else True
    for item in RoleList:
        if packDict[item.packageName]["code"] =="":
            packDict[item.packageName]["code"] = item.packageCode
        # packDict[item.packageName]["roleList"].append(Role(item.role_name,item.entity_text,0,0,0.0,[]))
        # packDict[item.packageName]["roleList"].append(Role(item.role_name,item.entity_text,0,0,0.0,[])) #Role(角色名称，实体名称，角色阈值，金额，金额阈值，连接列表，金额单位)
        packDict[item.packageName]["roleList"].append(Role(item.role_name,item.entity_text,item.role_prob,0,0.0,[],set(item.multi_winner)-win_tenderer_set-tenderee_or_agency_set)) #Role(角色名称，实体名称，角色阈值，金额，金额阈值，连接列表，多中标人)
    return packDict
                
def getPackageRoleMoney(list_sentence,list_entity,list_outline):
    '''
    @param:
        list_sentence:文章的句子list
        list_entity:文章的实体list
    @return: 拿到文章的包-标段号-角色-实体名称-金额-联系人-联系电话  
    '''
    # print("=1")
    theRole = getRoleList(list_sentence,list_entity)
    if not theRole:
        return []
    # RoleList,RoleSet,PackageList,PackageSet = theRole
    RoleList,RoleSet,PackageList,PackageSet,win_tenderer_set,tenderee_or_agency_set,main_body_pack = theRole
    '''
    for item in PackageList:
        # print(item)
    '''
    # PackDict = initPackageAttr(RoleList, PackageSet)
    PackDict = initPackageAttr(RoleList, PackageSet, win_tenderer_set,tenderee_or_agency_set,main_body_pack)

    PackDict = findAttributeAfterEntity(PackDict, RoleSet, PackageList, PackageSet, list_sentence, list_entity, list_outline)
    return PackDict

def turnBidWay(bidway):
    if bidway in ("邀请招标","采购方式：邀请"):
        return "邀请招标"
    elif bidway in ("询价","询单","询比","采购方式：询价"):
        return "询价"
    elif bidway in ("竞谈","竞争性谈判","公开竞谈"):
        return "竞争性谈判"
    elif bidway in ("竞争性磋商","磋商"):
        return "竞争性磋商"
    elif bidway in ("竞价","竞标","电子竞价","以电子竞价","电子书面竞投"):
        return "竞价"
    elif bidway in ("公开招标","网上电子投标","网上招标","采购方式：公开","招标为其他"):
        return "公开招标"
    elif bidway in ("单一来源"):
        return "单一来源"
    elif bidway in ("比选"):
        return "比选"
    else:
        return "其他"

def turnMoneySource(moneysource):
    result_list = []
    if re.search("自筹|业主筹集|筹资|自有",moneysource):
        result_list.append("自筹")
    if re.search("财政",moneysource) and not re.search("非财政",moneysource):
        result_list.append("财政资金")
    if re.search("拨款|补助|划拨|拨付|国拨|上级资金",moneysource):
        result_list.append("上级拨款")
    if re.search("社会资本|社会资金",moneysource):
        result_list.append("社会资本")
    if re.search("贷款|借款|借贷",moneysource):
        result_list.append("贷款资金")
    if re.search("债券|债|国债",moneysource):
        result_list.append("债券资金")
    if re.search("专项|项目资金",moneysource):
        result_list.append("项目专项资金")
    if re.search("配套",moneysource):
        result_list.append("配套资金")
    if re.search("外资",moneysource):
        result_list.append("外资")
    if re.search("国有资金|国企资金|国资|国家投资",moneysource):
        result_list.append("国有资金")
    if re.search("投资|融资",moneysource):
        result_list.append("投资资金")
    if re.search("预算(?<!外)|预算内",moneysource):
        result_list.append("预算内资金")
    if re.search("预算外",moneysource):
        result_list.append("预算外资金")

    result_list = sorted(result_list,key = lambda x:x)
    if len(result_list)>0 and len(result_list)<5:
        return ",".join(result_list)
    else:
        return "其他资金"

my_time_format_pattern = re.compile("((?P<year>20\d{2}|\d{2}|二[零〇0][零〇一二三四五六七八九0]{2})\s*[-/年.]\s*(?P<month>\d{1,2}|[一二三四五六七八九十]{1,3})\s*[-/月.]\s*(?P<day>\d{1,2}|[一二三四五六七八九十]{1,3}))")
from BiddingKG.dl.ratio.re_ratio import getUnifyNum
def my_timeFormat(_time,page_time):
    if page_time:
        current_year = time.strftime("%Y",time.localtime(int(datetime.strptime(page_time, '%Y-%m-%d').timestamp())))
    else:
        current_year = time.strftime("%Y",time.localtime())
    all_match = re.finditer(my_time_format_pattern,_time)
    time_list = []
    for _match in all_match:
        if len(_match.group())>0:
            legal = True
            year = ""
            month = ""
            day = ""
            for k,v in _match.groupdict().items():
                if k=="year":
                    year = v
                if k=="month":
                    month = v
                if k=="day":
                    day = v
            if year!="":
                if re.search("^\d+$", year):
                    if len(year) == 2:
                        year = "20" + year
                        if int(year) - int(current_year) > 5 or int(year) - int(current_year) < -1:
                            legal = False
                    else:
                        if int(year) - int(current_year)>10 or int(year) - int(current_year) < -1:
                            legal = False
                else:
                    _year = ""
                    for word in year:
                        if word == '0':
                            _year += word
                        else:
                            _year += str(getDigitsDic(word))
                    year = _year
            else:
                legal = False
            if month!="":
                if re.search("^\d+$", month):
                    if int(month) > 12:
                        legal = False
                else:
                    month = int(getUnifyNum(month))
                    if month >= 1 and month <= 12:
                        month = str(month)
                    else:
                        legal = False
            else:
                legal = False
            if day!="":
                if re.search("^\d+$", day):
                    if int(day) > 31:
                        legal = False
                else:
                    day = int(getUnifyNum(day))
                    if day >= 1 and day <= 31:
                        day = str(day)
                    else:
                        legal = False
            else:
                legal = False
            if not isValidDate(int(year),int(month),int(day)):
                legal = False
            if legal:
                # 数字字符格式化
                year = str(int(year))
                month = str(int(month))
                day = str(int(day))
                time_list.append("%s-%s-%s"%(year,month.rjust(2,"0"),day.rjust(2,"0")))
    return time_list

def getTimeAttributes(list_entity,list_sentence,page_time):
    # from BiddingKG.dl.interface.htmlparser import get_childs
    # document_tree = parse_document.tree
    # new_document_tree = []
    # _data_i = -1
    # while _data_i < len(document_tree) - 1:
    #     _data_i += 1
    #     _data = document_tree[_data_i]
    #     _type = _data["type"]
    #     if _type == "sentence":
    #         if _data["sentence_title"] is not None:
    #             new_document_tree.append(_data)
    # document_tree = new_document_tree


    time_entitys = [i for i in list_entity if i.entity_type=='time']
    time_entitys = sorted(time_entitys,key=lambda x:(x.sentence_index, x.begin_index))
    list_sentence = sorted(list_sentence,key=lambda x:x.sentence_index)
    dict_time = {
        "time_release": [], # 1 发布时间
        "time_bidopen": [], # 2 开标时间
        "time_bidclose": [], # 3 截标时间
        'time_bidstart': [],  # 12 投标（开始）时间、响应文件接收（开始）时间

        'time_publicityStart': [],  # 4 公示开始时间（公示时间、公示期）
        'time_publicityEnd': [],  # 5 公示截止时间
        'time_getFileStart': [],  # 6 文件获取开始时间（文件获取时间）
        'time_getFileEnd': [],  # 7 文件获取截止时间
        'time_registrationStart': [],  # 8 报名开始时间（报名时间）
        'time_registrationEnd': [],  # 9 报名截止时间
        'time_earnestMoneyStart': [], #10 保证金递交开始时间（保证金递交时间）
        'time_earnestMoneyEnd': [] , # 11 保证金递交截止时间
        'time_commencement':[] , #13 开工日期
        'time_completion': [],  # 14 竣工日期
        'time_listingStart': [],  # 15 挂牌开始日期（挂牌时间）
        'time_listingEnd': [],  # 16 挂牌结束日期、挂牌截止日期
        'time_signContract': [],  # 17 合同签订时间
        'time_contractStart': [],  # 18 合同开始时间
        'time_contractEnd': []  # 19 合同结束时间
    }

    dict_time2label = {
        "time_release": 1,  # 1 发布时间
        "time_bidopen": 2,  # 2 开标时间
        "time_bidclose": 3,  # 3 截标时间
        'time_bidstart': 12,  # 12 投标（开始）时间、响应文件接收（开始）时间

        'time_publicityStart': 4,  # 4 公示开始时间（公示时间、公示期）
        'time_publicityEnd': 5,  # 5 公示截止时间
        'time_getFileStart': 6,  # 6 文件获取开始时间（文件获取时间）
        'time_getFileEnd': 7,  # 7 文件获取截止时间
        'time_registrationStart': 8,  # 8 报名开始时间（报名时间）
        'time_registrationEnd': 9,  # 9 报名截止时间
        'time_earnestMoneyStart': 10,  # 10 保证金递交开始时间（保证金递交时间）
        'time_earnestMoneyEnd': 11,  # 11 保证金递交截止时间
        'time_commencement': 13,  # 13 开工日期
        'time_completion': 14,  # 14 竣工日期
        'time_listingStart': 15,  # 15 挂牌开始日期（挂牌时间）
        'time_listingEnd': 16,  # 16 挂牌结束日期、挂牌截止日期
        'time_signContract': 17,  # 17 合同签订时间
        'time_contractStart': 18,  # 18 合同开始时间
        'time_contractEnd': 19  # 19 合同结束时间
    }

    last_sentence_index = 0
    last_time_type = ""
    last_time_index = {
        'time_bidstart':"time_bidclose",
        'time_publicityStart':"time_publicityEnd",
        'time_getFileStart':"time_getFileEnd",
        'time_registrationStart':"time_registrationEnd",
        'time_earnestMoneyStart':"time_earnestMoneyEnd",
        'time_commencement':"time_completion",
        'time_listingStart':"time_listingEnd",
        'time_contractStart':"time_contractEnd"
    }
    time_entitys = [[_entity,my_timeFormat(_entity.entity_text,page_time)] for _entity in time_entitys]
    time_entitys = [item for item in time_entitys if item[1]]
    for entity_idx in range(len(time_entitys)):
        entity = time_entitys[entity_idx][0]
        extract_time = time_entitys[entity_idx][1]
        sentence_text = list_sentence[entity.sentence_index].sentence_text
        previous_entity = time_entitys[entity_idx-1][0] if entity_idx!=0 else None
        previous_extract_time = time_entitys[entity_idx-1][1] if entity_idx!=0 else None
        next_entity = time_entitys[entity_idx+1][0] if entity_idx!=len(time_entitys)-1 else None
        next_extract_time = time_entitys[entity_idx+1][1] if entity_idx!=len(time_entitys)-1 else None
        # 实体有效上下文
        entity_context_begin = previous_entity.wordOffset_end if previous_entity and previous_entity.sentence_index==entity.sentence_index else 0
        entity_context_end = next_entity.wordOffset_begin if next_entity and next_entity.sentence_index==entity.sentence_index else len(sentence_text)

        if entity.sentence_index!=last_sentence_index:
            # sentence_index 不同句子重置last_time_type
            last_time_type = ""
        entity_left = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 2):entity.wordOffset_begin]
        entity_left2 = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 10):entity.wordOffset_begin]
        entity_left3 = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 30):entity.wordOffset_begin]
        entity_right = sentence_text[entity.wordOffset_end:min(entity.wordOffset_end + 3,entity_context_end)]
        entity_right2 = sentence_text[entity.wordOffset_end:entity_context_end]
        entity_right2 = re.sub(r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+",'',entity_right2)[:60] # 去除网址
        # print(entity.entity_text,entity_right2)
        label_prob = entity.values[entity.label]
        entity_text = entity.entity_text
        in_attachment = entity.in_attachment
        # extract_time = my_timeFormat(entity_text,page_time)
        # print(entity_text,entity_left2)
        if extract_time:
            definite_time_list = []
            t = re.compile("(北京时间)?(?P<day>下午|上午|早上)?(?P<hour>\d{1,2})[:：时点](?P<half_hour>半)?(?P<minute>\d{1,2})?[:：分]?(?P<second>\d{2})?秒?")
            _entity_text = re.sub(" (?=[^\d])|(?<=[^\d]) ","",entity_text)
            _entity_text_len = len(_entity_text)
            _entity_text = _entity_text + sentence_text[entity.wordOffset_end:entity.wordOffset_end+20]
            t_in_word_num = len(re.findall(t,_entity_text))
            # t_out_of_word = re.search("^[^\d]{,2}"+t.pattern,re.sub(" (?=[^\d])|(?<=[^\d]) ","",sentence_text[entity.wordOffset_end:]))
            begin_index = 0
            for _num in range(t_in_word_num):
                if begin_index> _entity_text_len + 8:
                    break
                t_in_word = re.search(t, _entity_text[begin_index:])
                if t_in_word:
                    if _num==0 and t_in_word.start() > _entity_text_len + 8:
                        break
                    begin_index = t_in_word.end()
                    # print('t_in_word',entity_text,t_in_word.groupdict())
                    day = t_in_word.groupdict().get('day',"")
                    hour = t_in_word.groupdict().get('hour',"")
                    half_hour = t_in_word.groupdict().get('half_hour',"")
                    minute = t_in_word.groupdict().get('minute',"")
                    second = t_in_word.groupdict().get('second',"")
                    if hour:
                        if day=='下午' and int(hour)<12:
                            hour = str(int(hour)+12)
                        if int(hour)>24:
                            continue
                    else:
                        hour = "00"
                    if not minute:
                        if half_hour:
                            minute = "30"
                        else:
                            minute = "00"
                    if int(minute)>60:
                        continue
                    if not second:
                        second = "00"
                    if int(second)>60:
                        continue
                    definite_time = "%s:%s:%s"%(hour.rjust(2,"0"),minute.rjust(2,"0"),second.rjust(2,"0"))
                    # print(definite_time)
                    definite_time_list.append(definite_time)

            min_len = min(len(extract_time),len(definite_time_list))
            for i in range(min_len):
                if definite_time_list[i] == "24:00:00": # 修正不规范时间表述
                    definite_time_list[i] = "23:59:59"
                if definite_time_list[i] != "00:00:00":
                    extract_time[i] = extract_time[i] + " " + definite_time_list[i]

        if extract_time:
            # 时间变更prob优化
            if re.search("原",entity_left2):
                last_index = 0
                for item in re.finditer("原",entity_left2):
                    last_index = item.start() + 1
                label_prob = label_prob - 0.2 * last_index / len(entity_left2)
                # print('prob优化',label_prob,extract_time)
            elif re.search("改正|更正|修正|更改|延期",entity_left2):
                new_label = dict_time2label.get(last_time_type,None)
                if new_label and entity.label==0:
                    entity.label = new_label
                    label_prob = 1

            # 优化多个并列的时间，如：开标时间和截标时间，截标时间和报名结束时间
            if entity.label in [2,3,9]:
                if entity.label==2 and re.search("截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止|文件.{,2}([递提]交|接收)",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], label_prob-0.1, in_attachment))
                if entity.label==3 and re.search("开标|(评审|比选).{,2}(?:开始)?(时间|日期)|选取.{,2}(时间|日期)",entity_left3):
                    dict_time['time_bidopen'].append((extract_time[0], label_prob-0.1, in_attachment))
                if entity.label==3 and re.search("报名",entity_left3):
                    dict_time['time_registrationEnd'].append((extract_time[0], 0.5, in_attachment))
                if entity.label==9 and re.search("截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止|文件.{,2}([递提]交|接收)",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], label_prob-0.1, in_attachment))
            if entity.label in [11, 3]:
                if entity.label==11 and re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], 0.5, in_attachment))
                if entity.label==3 and re.search("保证金.{,2}(接受|收取)|(接受|收取).{,2}保证金",entity_left3):
                    dict_time['time_earnestMoneyEnd'].append((extract_time[0], 0.5, in_attachment))
            if entity.label in [6, 7]:
                if re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], 0.5, in_attachment))
            if entity.label==0:
                if re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], 0.45, in_attachment))
            if entity.label==6:
                # "文件获取时间"和"报名时间"并列
                if re.search("报名",entity_left3):
                    if len(extract_time)==1:
                        dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            # 获取文件/报名/报价 时间补充（上下文表达过长无法通过模型识别）
            # if entity.label == 0:
            #     if re.search("(获取|领取|售卖|出售|购买|下载).{,4}(招标|投标|采购)?(文件|标书)|(文件|标书).{,4}(获取|售卖|出售|发售|购买)", entity_left3):
            #         if len(extract_time)==2:
            #             dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_getFileEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if next_entity and next_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[entity.wordOffset_end:next_entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(next_extract_time)==1:
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_getFileEnd'].append((next_extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_getFileEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|在线|线下|线上|网上).{,2}报名|报名.{,2}(开始)?(时间|日期)", entity_left3):
            #         if len(extract_time)==2:
            #             dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if next_entity and next_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[entity.wordOffset_end:next_entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(next_extract_time)==1:
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_registrationEnd'].append((next_extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_registrationEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #
            #     if re.search("(获取|售卖|出售|购买).{,4}(招标|投标|采购)?(文件|标书)|(文件|标书).{,4}(获取|售卖|出售|发售|购买)", entity_right2):
            #         if len(extract_time)==2:
            #             dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_getFileEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if previous_entity and previous_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[previous_entity.wordOffset_end:entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(previous_extract_time)==1:
            #                     dict_time['time_getFileStart'].append((previous_extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_getFileEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|在线|线下).{,2}报名", entity_right2):
            #         if len(extract_time) == 2:
            #             dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if previous_entity and previous_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[previous_entity.wordOffset_end:entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(previous_extract_time)==1:
            #                     dict_time['time_registrationStart'].append((previous_extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_registrationEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|开始).{,4}(报价|投标|竞价)", entity_right2):
            #         if len(extract_time) == 2:
            #             dict_time['time_bidstart'].append((extract_time[0], 0.51, in_attachment))
            #             # dict_time['time_bidclose'].append((extract_time[1], 0.51, in_attachment))

            # 补充公告末尾处的发布时间
            if entity.label==0:
                if entity.is_tail:
                    entity.label = 1
                    entity.values[1] = 0.5
                    dict_time['time_release'].append((extract_time[0], 0.5, in_attachment))
            # 2022/12/12 新增挂牌时间正则
            if re.search("挂牌.{,4}(?:时间|日期)",entity_left2):
                if re.search("挂牌.{,4}(?:时间|日期)",entity_left2).end()>len(entity_left2)/2:
                    if len(extract_time) == 1:
                        if re.search("挂牌.?(开始|起始).?(?:时间|日期)",entity_left2):
                            dict_time['time_listingStart'].append((extract_time[0], 0.5, in_attachment))
                            last_time_type = 'time_listingStart'
                        elif re.search("挂牌.?(截[止至]|结束).?(?:时间|日期)",entity_left2):
                            dict_time['time_listingEnd'].append((extract_time[0], 0.5, in_attachment))
                            last_time_type = 'time_listingEnd'
                        elif re.search("挂牌.?(?:时间|日期)",entity_left2):
                            if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                                dict_time['time_listingEnd'].append((extract_time[0], 0.5, in_attachment))
                                last_time_type = 'time_listingEnd'
                            else:
                                dict_time['time_listingStart'].append((extract_time[0], 0.5, in_attachment))
                                last_time_type = 'time_listingStart'
                    else:
                        dict_time['time_listingStart'].append((extract_time[0], 0.5, in_attachment))
                        dict_time['time_listingEnd'].append((extract_time[1], 0.5, in_attachment))
                        last_time_type = ''
                    last_sentence_index = entity.sentence_index
                    continue

            # 2023/9/13 新增合同相关时间
            if re.search("合同|服务|履[约行]", entity_left3[-15:]):
                if len(extract_time) == 1:
                    if re.search("(合同.{,2}签[订定署].{,2}|签[订定署].{,2}合同.{,2})(?:时间|日期)|合同签[订定署].{,1}$", entity_left2):
                        dict_time['time_signContract'].append((extract_time[0], 0.5, in_attachment))
                        last_time_type = 'time_signContract'
                    elif re.search("(合同|服务|履约|(合同|服务)履行).{,4}(?:起始|开始)(?:时间|日期)", entity_left3[-15:]):
                        dict_time['time_contractStart'].append((extract_time[0], 0.55, in_attachment))
                        last_time_type = 'time_contractStart'
                    elif re.search("(合同|服务|履约).{,2}(?:完成|截止|结束)(?:时间|日期|时限)", entity_left2):
                        dict_time['time_contractEnd'].append((extract_time[0], 0.55, in_attachment))
                        last_time_type = 'time_contractEnd'
                    elif re.search("(?:合同|服务|履约|(合同|服务)履行)(?:期限?|有效期)|(?:服务|履约|(合同|服务)履行)(?:时间|日期|周期)|服务[时年]限|合同周期", entity_left2):
                        if re.search("到|至|截[至止]",entity_left) or re.search("前|止|截止",entity_right) or re.search("前",entity_text[-2:]):
                            dict_time['time_contractEnd'].append((extract_time[0], 0.5, in_attachment))
                            last_time_type = 'time_contractEnd'
                        else:
                            dict_time['time_contractStart'].append((extract_time[0], 0.5, in_attachment))
                            last_time_type = 'time_contractStart'
                    last_sentence_index = entity.sentence_index
                    continue
                else:
                    if re.search("(?:合同|服务|履约|(合同|服务)履行)(?:期限?|有效期)|(?:服务|履约|(合同|服务)履行)(?:时间|日期|周期)|服务[时年]限|合同周期", entity_left2):
                        # 排除开始和借宿时间一样的错误模板，例：“履约期限：2023年02月15日至2023年02月15日”
                        if extract_time[0]!=extract_time[1]:
                            dict_time['time_contractStart'].append((extract_time[0], 0.6, in_attachment))
                            dict_time['time_contractEnd'].append((extract_time[1], 0.6, in_attachment))
                            last_time_type = ''
                        last_sentence_index = entity.sentence_index
                        continue
            # 服务期限表达补充
            if entity.label==0:
                re_service = '合同期限|工期/交货期/服务期|工期\(交货期\)|合格工期|服务期限|工期' \
                    '|工期要求|项目周期|工期\(交货期\)|计划工期\(服务期限\)|服务时限|履行期限|服务周期|供货期限' \
                    '|合格工期|计划工期\(服务期\)|服务期|服务，期|交货\(完工\)(时间|日期)|交付\(服务、完工\)(时间|日期)' \
                    '|交货(时间|日期)|工期承诺|(服务|合同|施工|实施|工程|设计)的?(年限|期限|周期|期：)' \
                    '|服务期限为|计划工期|工期要求|服务期限|服务期' \
                    '|投标工期|设计工期|合格服务周期|总工期|服务(时间|日期)(范围)?|流转期限|维护期限|服务时限|交货期' \
                    '|完成(时间|日期)|服务期限|中标工期|项目周期|期限要求|供货期|合同履行日期|计划的?周期' \
                    '|履约期限|合同约定完成时限|合同完成日期|承诺完成日期' \
                    '|合同起始日起|合同履约期|履约截止日期|承包期限|合同完成日期' \
                    '|服务期间|服务履行期|委托(管理)?期限|履约期限、地点等简要信息'
                if len(extract_time)==2:
                    if re.search(re_service,entity_left2) or re.search("履约期限、地点等简要信息",entity_left3[-20:]):
                        dict_time['time_contractStart'].append((extract_time[0], 0.5, in_attachment))
                        dict_time['time_contractEnd'].append((extract_time[1], 0.5, in_attachment))
                        last_time_type = ''
            # 报价/投标时间补充(规则补充)
            if entity.label == 0:
                if re.search("[报竞]价.{,2}(开始|起始).{,2}(时间|日期)",entity_left2):
                    entity.label = 12
                    label_prob = 0.8
                elif re.search("[报竞]价.{,2}起止.{,2}(时间|日期)",entity_left2):
                    entity.label = 12
                    label_prob = 0.6
                elif re.search("响应.{,2}文件([递提]交|接收).{,2}(时间|日期)[：:]|([递提]交|接收).{,2}响应.{,2}文件.{,2}(时间|日期)[：:]",entity_left2):
                    entity.label = 3
                    label_prob = 0.501
                elif re.search("响应.{,2}文件([递提]交|接收).{,2}(时间|日期)|([递提]交|接收).{,2}响应.{,2}文件.{,2}(时间|日期)",entity_left2) and not re.search("截[止至]",entity_left2):
                    entity.label = 12
                    label_prob = 0.51
                elif re.search("[报竞]价.{,2}截[止至].{,2}(时间|日期)",entity_left2):
                    entity.label = 3
                    label_prob = 0.8
                elif re.search("(竞价|报价).?(时间|日期)",entity_left2):
                    entity.label = 12
                    label_prob = 0.51
                elif re.search("(竞价|报价).?(时间|日期)",entity_left3) and re.search("参与|报价|有意",entity_left2):
                    entity.label = 12
                    label_prob = 0.501
            # 文档结构补充
            # if entity.label == 0:
            #     re_registration = re.compile("报名|(文件|标书)[\u4e00-\u9fa5、]{,4}(获取|出售|售卖|购买|下载)|"
            #                                  "(获取|出售|售卖|购买|下载)[\u4e00-\u9fa5、]{,4}(文件|标书)")
            #     _data_i = -1
            #     while _data_i < len(document_tree) - 1:
            #         _data_i += 1
            #         _data = document_tree[_data_i]
            #         _type = _data["type"]
            #         _text = _data["text"].strip()
            #         childs = get_childs([_data])
            #         last_child = childs[-1]
            #         if entity.sentence_index>=_data.sentence_index and entity.wordOffset_begin>=_data.wordOffset_begin and
            #             ():
            #             if re.search(re_registration, re.split("[:：；;，]", _text)[0][:20]) is not None:
            #
            #                 content_text = ""
            #                 for c in childs:
            #                     content_text += c["text"] + ""
            #                 print('concat_text', content_text)

            if re.search("，(完成|截止|结束)(时间|日期)", entity_left2[-8:]) and entity.label==0:
                if entity.sentence_index == last_sentence_index:
                    time_type = last_time_index.get(last_time_type)
                    if time_type:
                        dict_time[time_type].append((extract_time[0], 0.5 + label_prob / 10,in_attachment))
                        last_time_type = ""
                        last_sentence_index = entity.sentence_index
                        continue

            if re.search("至|到|[日\d][-—]$|[～~]", entity_left):
                if entity.sentence_index == last_sentence_index:
                    time_type = last_time_index.get(last_time_type)
                    if time_type:
                        dict_time[time_type].append((extract_time[0], 0.5 + label_prob / 10,in_attachment))
                        last_time_type = ""
                        last_sentence_index = entity.sentence_index
                        continue
            if entity.label!=0:
                if entity.label==1 and label_prob>0.5:
                    dict_time['time_release'].append((extract_time[0],label_prob,in_attachment))
                    last_time_type = 'time_release'
                elif entity.label==2 and label_prob>0.5:
                    dict_time['time_bidopen'].append((extract_time[0],label_prob,in_attachment))
                    last_time_type = 'time_bidopen'
                elif entity.label==3 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_bidclose'].append((extract_time[0],label_prob,in_attachment))
                        last_time_type = 'time_bidclose'
                    elif len(extract_time)==2:
                        dict_time['time_bidstart'].append((extract_time[0], 0.6, in_attachment))
                        dict_time['time_bidclose'].append((extract_time[1], label_prob, in_attachment))
                        last_time_type = 'time_bidclose'
                elif entity.label==12 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_bidclose'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_bidclose'
                        else:
                            dict_time['time_bidstart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_bidstart'
                    else:
                        dict_time['time_bidstart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_bidclose'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==4 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_publicityEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_publicityEnd'
                        else:
                            dict_time['time_publicityStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_publicityStart'
                    else:
                        dict_time['time_publicityStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_publicityEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==5 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_publicityEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_publicityEnd'
                    else:
                        dict_time['time_publicityStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_publicityEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==6 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_getFileEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_getFileEnd'
                        else:
                            dict_time['time_getFileStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_getFileStart'
                    else:
                        dict_time['time_getFileStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_getFileEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==7 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_getFileEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_getFileEnd'
                    else:
                        dict_time['time_getFileStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_getFileEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==8 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_registrationEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_registrationEnd'
                        else:
                            dict_time['time_registrationStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_registrationStart'
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==9 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_registrationEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_registrationEnd'
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==10 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_earnestMoneyEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_earnestMoneyEnd'
                        else:
                            dict_time['time_earnestMoneyStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_earnestMoneyStart'
                    else:
                        dict_time['time_earnestMoneyStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_earnestMoneyEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==11 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_earnestMoneyEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_earnestMoneyEnd'
                    else:
                        dict_time['time_earnestMoneyStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_earnestMoneyEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==13 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_completion'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_completion'
                        else:
                            dict_time['time_commencement'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_commencement'
                    else:
                        dict_time['time_commencement'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_completion'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==14 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_completion'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_completion'
                    else:
                        dict_time['time_commencement'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_completion'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                else:
                    last_time_type = ""
            else:
                last_time_type = ""
        else:
            last_time_type = ""
        last_sentence_index = entity.sentence_index

    # 通过文档分析树形结构补充部分时间实体
    def add_time_by_parseDocument(dict_time,parse_document):
        from BiddingKG.dl.interface.htmlparser import get_childs
        document_tree = parse_document.tree
        # if not dict_time['time_getFileStart'] or not dict_time['time_getFileEnd']:
        # time_pattern = re.compile("")

        concat_text_list = []
        if not dict_time['time_registrationStart'] or not dict_time['time_registrationEnd']:
            re_registration = re.compile("报名|(文件|标书)[\u4e00-\u9fa5、]{,4}(获取|出售|售卖|购买|下载)|"
                                         "(获取|出售|售卖|购买|下载)[\u4e00-\u9fa5、]{,4}(文件|标书)")
            _data_i = -1
            while _data_i < len(document_tree) - 1:
                _data_i += 1
                _data = document_tree[_data_i]
                _type = _data["type"]
                _text = _data["text"].strip()
                # print(_data.keys())
                if _type == "sentence":
                    print('_text:',_text,_data["sentence_title"])
                    if _data["sentence_title"] is not None:
                        print("aptitude_pattern", _text)
                        print(_data['sentence_index'],_data['wordOffset_begin'],_data['wordOffset_end'])
                        if re.search(re_registration, re.split("[:：；;。]",_text)[0][:15]) is not None:
                            childs = get_childs([_data])
                            concat_text = ""
                            for c in childs:
                                concat_text += c["text"] + ""
                            print('concat_text',concat_text)
                            concat_text_list.append(concat_text)
                            _data_i += len(childs)-1
                # if _type == "table":
                #     list_table = _data["list_table"]
                #     parent_title = _data["parent_title"]
                #     if list_table is not None:
                #         for line in list_table[:2]:
                #             for cell_i in range(len(line)):
                #                 cell = line[cell_i]
                #                 cell_text = cell[0]
                #                 if len(cell_text) > 120 and re.search(re_registration, cell_text) is not None:
                #                     concat_text += cell_text + "\n"
        print('_text',concat_text_list)
        for text in concat_text_list:
            time_list = re.finditer(my_time_format_pattern,text)
            time_list = [(i,my_timeFormat(i.group(),page_time)) for i in time_list]
            for time_idx in range(len(time_list)):
                _time = time_list[time_idx][0]
                extract_time = time_list[time_idx][1]
                entity_left = text[:_time.start()]
                entity_left = re.split("[。；;!?？]",entity_left)[-1]
                # entity_left2 = sentence_text[
                #                max(entity_context_begin, entity.wordOffset_begin - 10):entity.wordOffset_begin]
                # entity_left3 = sentence_text[
                #                max(entity_context_begin, entity.wordOffset_begin - 30):entity.wordOffset_begin]
                entity_right = text[_time.end():]
                entity_right = re.split("[。；;!?？]",entity_right)[0]
                # entity_right2 = sentence_text[entity.wordOffset_end:entity_context_end]
                entity_right2 = re.sub(r"(http[s]?://)?(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F])){6,}",
                                       '', entity_right)[:60]  # 去除网址
                print('entity_right2',entity_right2)
                if re.search("(进行|在线|线下).{,2}报名", entity_right2):
                    print('报名text',entity_right2)
                    if len(extract_time) == 2:
                        dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
                    else:
                        if previous_entity and previous_entity.sentence_index==entity.sentence_index:
                            mid_text = sentence_text[previous_entity.wordOffset_end:entity.wordOffset_begin]
                            if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(previous_extract_time)==1:
                                dict_time['time_registrationStart'].append((previous_extract_time[0], 0.51, in_attachment))
                                dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
                        if not dict_time['time_registrationEnd']:
                            if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
                                dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
                            elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
                                dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))


        return dict_time

    # dict_time = add_time_by_parseDocument(dict_time,parse_document)

    # print(dict_time)
    result_dict = dict((key,"") for key in dict_time.keys())
    for time_type,value in dict_time.items():
        list_time = dict_time[time_type]
        if list_time:
            for in_attachment in [False,True]:
                _list_time  = [_time for _time in list_time if _time[2]==in_attachment]
                if _list_time:
                    _list_time.sort(key=lambda x:(x[1],len(x[0])),reverse=True) # sort_key: label_prob,时间文本长度(优先有具体时分秒的)
                    if in_attachment==True and len(result_dict[time_type])>0:
                        break
                    result_dict[time_type] = _list_time[0][0]
    # result_dict 纠错
    if not result_dict['time_bidclose']:
        if result_dict['time_bidstart']: # 无截标时间，投标开始和开标时间一样
            if result_dict['time_bidstart'][:10] in result_dict['time_bidopen']:
                result_dict['time_bidstart'] = ""
                result_dict['time_bidclose'] = result_dict['time_bidopen']
        if not result_dict['time_bidclose']:
            if result_dict['time_getFileEnd']:  # 无截标时间，获取文件截止时间和开标时间一样
                if result_dict['time_getFileEnd'][:10] in result_dict['time_bidopen']:
                    result_dict['time_bidclose'] = result_dict['time_bidopen']
    else:
        if result_dict['time_bidopen']: # 截标时间 和 开标时间 时分秒互补
            if len(result_dict['time_bidclose'])<len(result_dict['time_bidopen']) and result_dict['time_bidclose'] in result_dict['time_bidopen']:
                result_dict['time_bidclose'] = result_dict['time_bidopen']
            elif len(result_dict['time_bidclose'])>len(result_dict['time_bidopen']) and result_dict['time_bidopen'] in result_dict['time_bidclose']:
                result_dict['time_bidopen'] = result_dict['time_bidclose']

    return result_dict

def get_days_between(day1,day2,get_abs=0):
    '''
    :param day1: 较小日期
    :param day2: 较大日期
    :param get_abs: 是否取绝对值
    :return: 天数差
    '''
    # 将日期字符串转换为datetime对象
    date1 = datetime.strptime(day1, '%Y-%m-%d')
    date2 = datetime.strptime(day2, '%Y-%m-%d')
    # 计算日期差
    delta = date2 - date1
    # 获取天数差
    days_difference = delta.days
    if get_abs:
        return abs(days_difference)
    else:
        return days_difference

def extract_serviceTime(service_time,page_time):
    pattern1 = re.compile("\d{4}[年\-\./]\d{1,2}[月\-\./]\d{1,2}日?")
    pattern2 = re.compile("\d+(?:\.\d+)?[\(（]?个?[^\d]?[^\d]?(?:日|天|周年|整年|学?年|月|周|日历[天日]|工作[天日])")
    pattern3 = re.compile("\d{4}[年\-\./]\d{1,2}月?")
    pattern4 = re.compile("(?:日|天|周年|年|月|周|日历[天日]|工作[天日]|星期)[^\d]{1,3}\d+(?:\.\d+)?")
    DigitsDic = {"零":0, "壹":1, "贰":2, "叁":3, "肆":4, "伍":5, "陆":6, "柒":7, "捌":8, "玖":9,
                 "〇":0, "一":1, "二":2, "三":3, "四":4, "五":5, "六":6, "七":7, "八":8, "九":9,
                 "两":2, '貮': 2}

    def get_month_days(year, month):
        # calendar.monthrange(year, month)返回一个元组，其中第一个元素是月份的第一天是星期几（0-6为星期一到星期日），
        # 第二个元素是该月的天数。
        _, last_day = calendar.monthrange(year, month)
        return last_day
    def get_num(text):
        CN_UNIT = {'十': 10,'拾': 10,'百': 100,
            '佰': 100,'千': 1000,'仟': 1000}

        regex = re.compile(r'[〇一二三四五六七八九零壹贰叁肆伍陆柒捌玖貮两十拾百佰千仟]+')
        text = regex.search(text)
        if text:
            text = text.group()
        else:
            return ""
        result = 0
        result_list = []
        unit = 0
        control = 0
        for i, d in enumerate(text):
            if d in '零百佰千仟' and i == 0:
                return ""
            if d in DigitsDic:
                result += DigitsDic[d]
            elif d in CN_UNIT:
                if unit == 0:
                    unit_1 = CN_UNIT[d]
                    # 这里的处理主要是考虑到类似于二十三亿五千万这种数
                    if result == 0:
                        result = CN_UNIT[d]
                    else:
                        result *= CN_UNIT[d]
                    unit = CN_UNIT[d]
                    result_1 = result
                elif unit > CN_UNIT[d]:
                    result -= DigitsDic[text[i - 1]]
                    result += DigitsDic[text[i - 1]] * CN_UNIT[d]
                    unit = CN_UNIT[d]
                elif unit <= CN_UNIT[d]:
                    if (CN_UNIT[d] < unit_1) and (len(result_list) == control):
                        result_list.append(result_1)
                        result = (result - result_1) * CN_UNIT[d]
                        control += 1
                    else:
                        result *= CN_UNIT[d]
                    unit = CN_UNIT[d]
                    if len(result_list) == control:
                        unit_1 = unit
                        result_1 = result
            else:
                return ""

        return sum(result_list) + result

    serviceTime_dict = {"service_start": "", "service_end": "", "service_days": ""}
    re_num = re.findall(r'[〇一二三四五六七八九零壹贰叁肆伍陆柒捌玖貮两十拾百佰千仟]+',service_time)
    for _num in re_num:
        if not re.search("[十拾百佰千仟]",_num):
            num = ""
            for word in _num:
                num += str(DigitsDic.get(word,word))
            service_time = service_time.replace(_num,num,1)
        else:
            num = str(get_num(_num))
            service_time = service_time.replace(_num,num,1)

    end_time = ""
    service_days = 0
    re_page_time = re.search("20\d{2}-\d{2}-\d{2}", page_time)
    page_time = re_page_time.group() if re_page_time else "2000-01-01" # page_time为空时默认值为2000-01-01
    if re.search(pattern1,service_time):
        # end_time = re.findall(pattern1,service_time)[-1]
        time_list = []
        for _time in re.findall(pattern1,service_time):
            _time = re.sub("日","",_time)
            _time = re.sub("[年月\./]","-",_time)
            _year,_month,_day = _time.split("-")
            _month = int(_month)
            _day = int(_day)
            _year = int(_year)
            if _year>2050 or _year<=2000 or _month>12 or _month<=0 or _day<=0 or _day>31:
                service_days = 0
            else:
                if isValidDate(_year,_month,_day):
                    _time = str(_year)+'-'+str(_month)+'-'+str(_day)
                    _time = _time.split("-")[0] + '-' + _time.split("-")[1].rjust(2,"0") + '-' + _time.split("-")[2].rjust(2,"0")
                    time_list.append(_time)
        if len(time_list)>=2:
            if get_days_between(page_time,time_list[1])>1 and get_days_between(time_list[0],time_list[1])>0:
                serviceTime_dict['service_end'] = time_list[1]
                serviceTime_dict['service_start'] = time_list[0]
        else:
            if get_days_between(page_time, time_list[0]) > 1:
                serviceTime_dict['service_end'] = time_list[0]
            # service_days = (time.mktime(time.strptime(end_time,"%Y-%m-%d"))-page_timestamp)/(24*60*60)
    elif re.search(pattern3,service_time):
        time_list = []
        # end_time = re.findall(pattern3,service_time)[-1]
        for _time in re.findall(pattern3,service_time):
            _time = re.sub("月","",_time)
            _time = re.sub("[年\./]","-",_time)
            _year,_month = _time.split("-")
            _day = 0
            _month = int(_month)
            _year = int(_year)
            if _year>2050 or _year<=2000 or _month>12 or _month<=0:
                service_days = 0
            else:
                _day = get_month_days(_year,_month)
                if isValidDate(_year, _month, _day):
                    _time = str(_year)+'-'+str(_month)+'-'+str(_day)
                    _time = _time.split("-")[0] + '-' + _time.split("-")[1].rjust(2,"0") + '-' + _time.split("-")[2].rjust(2,"0")
                    time_list.append(_time)
        if len(time_list) >= 2:
            if get_days_between(page_time, time_list[1]) > 1 and get_days_between(time_list[0], time_list[1]) > 0:
                serviceTime_dict['service_end'] = time_list[1]
                serviceTime_dict['service_start'] = time_list[0]
        else:
            if get_days_between(page_time, time_list[0]) > 1:
                serviceTime_dict['service_end'] = time_list[0]
                # service_days = (time.mktime(time.strptime(end_time,"%Y-%m-%d"))-page_timestamp)/(24*60*60)
    elif re.search(pattern2,service_time) or re.search(pattern4,service_time):
        for pattern in [pattern2,pattern4]:
            unit = 1
            match = re.findall(pattern,service_time)
            if len(set(match))==1:
                match_text = match[0]
                if "月" in match_text:
                    unit = 30
                elif "年" in match_text:
                    unit = 365
                elif "周" in match_text or "星期" in match_text:
                    unit = 7
                match_num = float(re.search("\d+",match_text).group())
                # 数字能被365整除，单位更正为天
                if int(match_num)%365==0:
                    unit = 1
                if unit==365:
                    if match_num>10:#单位为'年'时，排除数字过大的
                        match_num = 0
                elif unit==30:
                    if match_num>60:#单位为'月'时，排除数字过大的
                        match_num = 0
                elif unit==1:
                    if match_num>4000:#单位为'日'时，排除数字过大的
                        match_num = 0
                service_days = match_num * unit
                if int(service_days) % 360==0:
                    service_days = service_days / 360 * 365
                service_days = int(service_days)
                if service_days <= 1 and service_days > 4000:
                    service_days = 0

                if service_days>0:
                    service_days = str(service_days) + "天"
                    serviceTime_dict['service_days'] = service_days
                    break
    elif "半年" in service_time:
        service_days = 180
        service_days = str(service_days) + "天"
        serviceTime_dict['service_days'] = service_days

    return serviceTime_dict

def getOtherAttributes(list_entity,page_time,prem):
    dict_other = {"moneysource":"",
                  "person_review":[],
                  "serviceTime":"",
                  "product":[],
                  "total_tendereeMoney":0,
                  "total_tendereeMoneyUnit":''}
    list_serviceTime = []
    last_moneysource_prob = 0
    for entity in list_entity:
        if entity.entity_type == 'bidway':
            dict_other["bidway"] = turnBidWay(entity.entity_text)
        elif entity.entity_type=='moneysource':
            if dict_other["moneysource"] and entity.in_attachment:
                continue
            if not dict_other["moneysource"]:
                dict_other["moneysource"] = entity.entity_text
                last_moneysource_prob = entity.prob
            elif entity.prob>last_moneysource_prob:
                dict_other["moneysource"] = entity.entity_text
                last_moneysource_prob = entity.prob
        elif entity.entity_type=='serviceTime':
            # print(entity.entity_text)
            # if list_serviceTime and entity.in_attachment:
            #     continue
            if re.search("[^之]日|天|年|月|周|星期", entity.entity_text) or re.search("\d{4}[-./]\d{1,2}", entity.entity_text):
                list_serviceTime.append(entity)
        elif entity.entity_type=="person" and entity.label ==4 and entity.entity_text not in dict_other["person_review"]: # 20240624评审专家去重
            dict_other["person_review"].append(entity.entity_text)
        elif entity.entity_type=='product' and entity.entity_text not in dict_other["product"]: #顺序去重保留
            dict_other["product"].append(entity.entity_text)
        elif entity.entity_type=='money' and entity.notes=='总投资' and float(dict_other["total_tendereeMoney"])<float(entity.entity_text):
            dict_other["total_tendereeMoney"] = str(Decimal(entity.entity_text))
            dict_other["total_tendereeMoneyUnit"] = entity.money_unit

    time_contractEnd = prem[0].get("time_contractEnd","")[:10]
    time_contractStart = prem[0].get("time_contractStart","")[:10]
    serviceTime_dict = {"service_start":"", "service_end":"", "service_days": ""}
    if time_contractEnd:
        serviceTime_dict['service_end'] = time_contractEnd
        if time_contractStart:
            if get_days_between(time_contractStart,time_contractEnd)>0:
                serviceTime_dict['service_start'] = time_contractStart
    # print([i.entity_text for i in list_serviceTime])
    if list_serviceTime and not serviceTime_dict['service_end']:
        list_serviceTime_inAtt = [serviceTime for serviceTime in list_serviceTime if serviceTime.in_attachment==1]
        list_serviceTime = [serviceTime for serviceTime in list_serviceTime if serviceTime.in_attachment==0]
        # if not list_serviceTime:
        #     list_serviceTime = list_serviceTime_inAtt
        error_serviceTime = []
        for list_time in [list_serviceTime,list_serviceTime_inAtt]:
            # if not dict_other["serviceTime"]:
            if not serviceTime_dict['service_end']:
                list_time.sort(key=lambda x: (x.prob,-x.sentence_index,-x.begin_index), reverse=True)
                for _serviceTime in list_time:
                    # 优先取具体时间(20XX年x月x日-20XX年x月x日)
                    if re.search("20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?[^。\d半一二三四五六七八九十壹两叁贰肆伍陆柒捌玖拾;；]{,4}20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?",_serviceTime.entity_text):
                        _extract_time = my_timeFormat(_serviceTime.entity_text,page_time)
                        if _extract_time and len(_extract_time)==2:
                            # 排除开始和结束时间一样的错误模板，例：“履约期限：2023年02月15日至2023年02月15日”
                            if _extract_time[0]!=_extract_time[1]:
                                # dict_other["serviceTime"] = _serviceTime.entity_text
                                # extract_time = extract_serviceTime(_serviceTime.entity_text)
                                # if extract_time['service_end']:
                                serviceTime_dict['service_start'] = _extract_time[0]
                                serviceTime_dict['service_end'] = _extract_time[1]
                                break
                            else:
                                error_serviceTime.append(_serviceTime.entity_text)
                # if not dict_other["serviceTime"]:
                if not serviceTime_dict['service_end']:
                    for _serviceTime in list_time:
                        # 优先取具体时间(20XX年x月-20XX年x月)
                        if re.search("20\d{2}[年/.\-]\d{1,2}月?[^。\d半一二三四五六七八九十壹两叁贰肆伍陆柒捌玖拾;；]{,3}20\d{2}[年/.\-]\d{1,2}月?", _serviceTime.entity_text):
                            # dict_other["serviceTime"] = _serviceTime.entity_text
                            extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                            if extract_time['service_end']:
                                serviceTime_dict = extract_time
                                break
                # if not dict_other["serviceTime"]:
                if not serviceTime_dict['service_end']:
                    for _serviceTime in list_time:
                        # 优先取具体时间(20XX年x月x日)
                        if re.search("20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?",_serviceTime.entity_text):
                            if _serviceTime.entity_text not in error_serviceTime:
                                # dict_other["serviceTime"] = _serviceTime.entity_text
                                extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                                if extract_time['service_end']:
                                    serviceTime_dict = extract_time
                                    break
                # if not dict_other["serviceTime"]:
                if not serviceTime_dict['service_end'] and not serviceTime_dict['service_days']:
                    for _serviceTime in list_time:
                        if _serviceTime.entity_text not in error_serviceTime:
                            # dict_other["serviceTime"] = _serviceTime.entity_text
                            extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                            if extract_time['service_end'] or extract_time['service_days']:
                                serviceTime_dict = extract_time
                                break
    if serviceTime_dict['service_start'] and serviceTime_dict['service_end']:
        service_days = get_days_between(serviceTime_dict['service_start'],serviceTime_dict['service_end'])
        serviceTime_dict['service_days'] = str(service_days) + "天"
    dict_other["serviceTime"] = serviceTime_dict
    if not time_contractEnd and prem[0]['docchannel']['docchannel']=='合同公告': # 用serviceTime补充合同开始结束时间,公告类型为合同公告
        if serviceTime_dict['service_start'] and serviceTime_dict['service_end']:
            prem[0]["time_contractStart"] = serviceTime_dict['service_start']
            prem[0]["time_contractEnd"] = serviceTime_dict['service_end']

    if dict_other['moneysource']:
        dict_other['moneysource'] = turnMoneySource(dict_other['moneysource'])
    # dict_other["product"] = list(set(dict_other["product"])) # 已在添加时 顺序去重保留
    return dict_other

def getMoneyRange(RoleList):
    pass

def getPREMs(list_sentences,list_entitys,list_articles,list_outlines,page_time):
    '''
    @param:
        list_sentence:所有文章的句子list
        list_entity:所有文章的实体list
    @return:list of dict which include文章的包-角色-实体名称-金额-联系人-联系电话  
    '''
    result = []
    for list_sentence,list_entity,list_article,list_outline in zip(list_sentences,list_entitys,list_articles,list_outlines):
        RoleList = getPackageRoleMoney(list_sentence,list_entity,list_outline)
        result.append(dict({"prem": RoleList, "docid": list_article.doc_id},
                           **getTimeAttributes(list_entity, list_sentence,page_time),
                           **{"fingerprint": list_article.fingerprint,
                              "match_enterprise": list_article.match_enterprise,
                              "match_enterprise_type": list_article.match_enterprise_type,
                              "process_time": getCurrent_date(),
                              "attachmentTypes": list_article.attachmentTypes, "bidway": list_article.bidway}))
        # result.append(dict({"prem":RoleList,"docid":list_article.doc_id},**getOtherAttributes(list_entity),**getTimeAttributes(list_entity,list_sentence),
        #                    **{"fingerprint":list_article.fingerprint,"match_enterprise":list_article.match_enterprise,
        #                       "match_enterprise_type":list_article.match_enterprise_type,"process_time":getCurrent_date(),
        #                       "attachmentTypes":list_article.attachmentTypes, "bidway": list_article.bidway}))
    return result

def correct_rolemoney(prem, total_product_money, list_articles): # 2022/9/26修改为 中标金额小于表格单价数量合计总金额十分之一时替换
    '''
    最后根据表格提取的单价数量合计对比更新中标金额，或中标金额为0全文只有一个总价或合计时，作为中标金额
    :param prem: 列表
    :param total_product_money: 表格统计金额
    :param list_articles: 文章对象
    :return:
    '''
    if '##attachment##' in list_articles[0].content:
        content, attachment = list_articles[0].content.split('##attachment##')
        if len(content) < 200:
            content += attachment
    else:
        content = list_articles[0].content
    if len(re.findall('win_tenderer|second_tenderer|third_tenderer', str(prem[0]['prem'])))==1 and re.search('(中标|成交|合同|投标)）?(总?金额|[报总]?价)：', content) == None: # 只有一个中标角色且没有明确中标金额表达的
        if total_product_money>0 and total_product_money<5000000000:
            for value in prem[0]['prem'].values():
                ree_money = float(value['tendereeMoney'])
                for l in value['roleList']:
                    try:
                        # if l[0] == 'win_tenderer' and float(l[2])<total_product_money:
                        #     l[2] = total_product_money
                        #     log('修改中标金额为所有产品总金额')
                        # if l["role_name"] == 'win_tenderer' and float(l["role_money"]['money']) == 0 and float(l["role_money"]['money'])<total_product_money/10:
                        if l["role_name"] == 'win_tenderer' and (float(l["role_money"]['money']) == 0 or float(l["role_money"]['money'])<ree_money/2): # 改为小于一半招标金额或为0时替换为合计金额
                            l["role_money"]['money'] = total_product_money
                            # print('修改中标金额为所有产品总金额')
                    except Exception as e:
                        print('表格产品价格修正中标价格报错：%s'%e)
        elif (len(re.findall('合计', content)) == 1 or len(re.findall('总价', content)) == 1):
            ser = re.search('(?P<header>合计(（万?元）)?：)(?P<money>[\d,.]+(万?元)?)', content) if len(re.findall('合计', content)) == 1 else re.search('(?P<header>总价(（万?元）)?：)(?P<money>[\d,.]+(万?元)?)', content)
            if ser:
                money_text = ser.group('money')
                header = ser.group('header')
                money, money_unit = money_process(money_text, header)
                if 100<money<8000000:
                    for value in prem[0]['prem'].values():
                        for l in value['roleList']:
                            try: # 如果原中标金额为0 或 金额小于合计金额0.1倍且正文没中标金额关键词 替换为 合计金额
                                if l["role_name"] == 'win_tenderer' and (float(l["role_money"]['money'])==0 or (float(l["role_money"]['money']) < money / 10 and re.search('(中标|成交|合同)(总?金额|[单报总]?价)', content) == None)):
                                    l["role_money"]['money'] = str(money)
                                    l["role_money"]['money_unit'] = money_unit
                                    # print('修改中标金额为总价或合计金额')
                            except Exception as e:
                                print('修正中标价格报错：%s' % e)

def limit_maximum_amount(dic, list_entity):
    '''
    通过关键词、行业、公告类别等设置最高最低角色金额
    :param dic: 最终返回所有字段结果字典
    :param list_entity: 实体列表
    :return:
    '''
    indu_amount = {
        '计算机设备': 200000000,
        '办公设备': 100000000,
        '家具用具': 500000000,
        '办公消耗用品及类似物品': 100000000,
        '日杂用品': 100000000,
        '餐饮业': 1000000000,
        '物业管理': 1000000000,
        '工程技术与设计服务': 1000000000,
        '工程评价服务': 100000000,
        '其他工程服务': 100000000,
        '工程监理服务': 100000000,
        '工程造价服务': 100000000,
        '会计、审计及税务服务': 100000000,
        '其他专业咨询与调查': 100000000
    }
    title = dic.get('doctitle_refine', '')
    name = dic.get('name', '')
    product = '，'.join(dic.get('product', []))
    text = "%s；%s；%s"%(title, name, product)
    doctype = dic.get('docchannel', {}).get('doctype', '') # 公告类型
    industry = dic['industry'].get('class_name', '')
    category = dic['industry'].get('class', '') # 行业门类
    moneys = [float(it.entity_text) for it in list_entity if it.entity_type=='money' and re.search('^\d+(\.\d+)?', it.entity_text) and 5000<float(it.entity_text)<5000000]
    maximum_amount = 10000000000
    minximum_amount = 100
    if re.search('监理|造价咨询|设计|勘察|招标代理中介服务|工程审计', text) and re.search('施工|总承包|ppp|PPP', text.replace('施工监理', '监理'))==None:
        # print('监理设计等限额')
        maximum_amount = 1000000000
        minximum_amount = 200
    elif re.search('施工|总承包|ppp|PPP|公路|道路|桥梁|铁路|土地使用权|地块|棚改|征地拆迁|棚户区改造|土地征收|建设用地|社会保险', text) or category in ['金融业', '建筑业'] or doctype == '土地矿产':
        # print('施工、铁路等限额')
        if industry in ['科研、医疗、教育用房', '住宅、商业用房', '场馆、站港用房','工业、生产用房','专业施工']:
            maximum_amount = 20000000000
            minximum_amount = 200
        elif industry in ['修缮工程', '电气安装', '管道和设备安装', '建筑装饰和装修业', '建筑物拆除和场地准备活动']:
            maximum_amount = 10000000000
            minximum_amount = 100
        else:
            maximum_amount = 50000000000
            minximum_amount = 500
    elif re.search('(办公|体育)(用品|设备|器材)|耗材|打印机|复印机|打印纸|粉盒|墨粉|复印纸|网上超市|电子卖场|家电|配电箱采购|配件|备件', text):
        # print('商品采购限额')
        maximum_amount = 80000000
        minximum_amount = 10
    elif re.search('修理|维修|(安保|保安|安全|保洁|物业|后勤|管理|代理|中介|印刷)服务', text):
        # print('维修限额')
        maximum_amount = 50000000
    elif re.search('(速递|快递|邮政|邮寄)(物流)?服务', text):
        # print('快递限额')
        maximum_amount = 80000000
        minximum_amount = 10
    elif industry in indu_amount:
        maximum_amount = indu_amount[industry]
    # print('maximum_amount：', maximum_amount)
    for value in dic['prem'].values():
        for l in value['roleList']:
            if l["role_name"] in ['win_tenderer', 'second_tenderer', 'third_tenderer']:
                date = float(re.search('(\d+)天', l.get('serviceTime', '')).group(1)) if re.search('(\d+)天', l.get('serviceTime', '')) else 0
                if 0 < date < 180 and float(l["role_money"]['money']) > 10000000000: # 工期小于180天且金额大于百亿的，错误
                    l["role_money"]['money'] = str(Decimal(l["role_money"]['money']) / 10000)
                    # print('工期纠正百亿以上金额 ')
                elif float(l["role_money"]['money']) > maximum_amount:
                    flag = 1
                    for money in moneys:
                        if float(l["role_money"]['money'])/money == 10000 and l['role_money']['money_unit'] == '万元':
                            l["role_money"]['money'] = str(Decimal(l["role_money"]['money']) / 10000)
                            # print('万倍关系纠正连接金额')
                            flag = 0
                            break
                    if flag and l["role_money"]['money_unit'] == '万元' or re.search('^\d{11,}(\.0)?$', str(l["role_money"]['money'])):
                        l["role_money"]['money'] = str(Decimal(l["role_money"]['money']) / 10000)
                        # print('行业限额纠正连接金额')
                    elif industry in ['餐饮业', '物业管理'] and maximum_amount == indu_amount[industry]:
                        l["role_money"]['money'] = str(Decimal(l["role_money"]['money']) / 10000)
                    # elif flag and l["role_money"]['money_unit'] == '元':
                    #     l["role_money"]['money'] = 0
                elif 0<float(l["role_money"]['money']) < minximum_amount:
                    if l["role_money"]['money_unit'] == '元' and re.search('^\d{1,2}\.\d{4,6}$', str(l["role_money"]['money'])):
                        # print('单位元小金额且格式类似万元的乘以万倍')
                        l["role_money"]['money'] = str(Decimal(l["role_money"]['money']) * 10000)
                    else:
                        # print('中标金额小于限额：%d元 去除' % minximum_amount)
                        l["role_money"]['money'] = 0

            if float(value['tendereeMoney']) > maximum_amount:
                flag = 1
                for money in moneys:
                    if float(value['tendereeMoney'])/money == 10000 and l['role_money']['money_unit'] == '万元':
                        value['tendereeMoney'] = str(Decimal(value['tendereeMoney'])/10000)
                        # print('万倍关系纠正连接金额')
                        flag = 0
                        break
                if (flag and value['tendereeMoneyUnit'] == '万元' or re.search('^\d{11,}(\.0)?$', str(value['tendereeMoney']))) and float(value['tendereeMoney']) > maximum_amount*100:  #2024/5/23 改为单位万元且超过限额100倍才除一万，避免不合理纠正 比如 174255856 项目（系统）一亿变一万
                    value['tendereeMoney'] = str(Decimal(value['tendereeMoney']) / 10000)
                    # print('行业限额纠正连接金额')
                elif industry in ['餐饮业', '物业管理'] and maximum_amount == indu_amount[industry]:
                    value['tendereeMoney'] = str(Decimal(value['tendereeMoney']) / 10000)
                # elif flag and value['tendereeMoneyUnit'] == '元':
                #     value['tendereeMoney'] = 0
            elif 0<float(value['tendereeMoney']) < minximum_amount:
                if value['tendereeMoneyUnit'] == '元' and re.search('^\d{1,2}\.\d{4,6}$', str(value['tendereeMoney'])):
                    # print('单位元小金额且格式类似万元的乘以万倍')
                    value['tendereeMoney'] = str(Decimal(value['tendereeMoney']) * 10000)
                else:
                    # print('招标金额小于限额：%d元 去除' % minximum_amount)
                    value['tendereeMoney'] = 0


def limit_maximum_amount_backup(prem, industry):
    indu = industry['industry'].get('class_name', '')
    indu_amount = {
        '计算机设备': 200000000,
        '办公设备': 100000000,
        '家具用具': 500000000,
        '办公消耗用品及类似物品': 100000000,
        '日杂用品': 100000000,
        '餐饮业': 1000000000,
        '物业管理': 1000000000,
        '工程技术与设计服务': 1000000000,
        '工程评价服务': 100000000,
        '其他工程服务': 100000000,
        '工程监理服务': 100000000,
        '工程造价服务': 100000000,
        '会计、审计及税务服务': 100000000,
    }
    if indu in indu_amount:
        maximum_amount = indu_amount[indu]
        try:
            for value in prem[0]['prem'].values():
                for l in value['roleList']:
                    if l["role_name"] == 'win_tenderer' and float(l["role_money"]['money']) > maximum_amount:
                        if indu in ['餐饮业', '物业管理']:
                            l["role_money"]['money'] = str(float(l["role_money"]['money'])/10000)
                        elif l["role_money"]['money_unit'] == '万元':
                            l["role_money"]['money'] = str(float(l["role_money"]['money'])/10000)
                if float(value['tendereeMoney']) > maximum_amount:
                    if indu in ['餐饮业', '物业管理']:
                        value['tendereeMoney'] = float(value['tendereeMoney'])/10000
                    elif value['tendereeMoneyUnit'] == '万元':
                        value['tendereeMoney'] = float(value['tendereeMoney']) / 10000
        except Exception as e:
            print('行业分类限制最高金额抛出异常：%s' % e)

def get_win_joint(prem, list_entitys, list_sentences, list_articles):
    '''
    获取联合体信息， 添加到prem
    :param prem:
    :param list_entitys:
    :param list_sentences:
    :param list_articles:
    :return:
    '''
    try:
        if 'win_tenderer' in str(prem) and re.search('联合(体|投标人)：|联合体(成员|单位)[12345一二三四五]?：|(联合体)?成员单位[12345一二三四五]?：|特殊普通合伙：|（联合(体|投标人)）|（联合体(成员|单位)方?[12345一二三四五]?）|（(联合体)?成员单位[12345一二三四五]?）|（特殊普通合伙|成员?）|[，；]成：|（成[），]', list_articles[0].content):
            sentences = sorted(list_sentences[0], key=lambda x:x.sentence_index)
            for project in prem[0].values():
                if not isinstance(project, dict):
                    continue
                for v in project.values():
                    for d in v['roleList']:
                        if d.get('role_name', '') == 'win_tenderer':
                            winner = d.get('role_text')
                            join_l = [winner]
                            for list_entity in list_entitys:
                                for i in range(len(list_entity)-1):
                                    _entity = list_entity[i]
                                    b = _entity.wordOffset_begin
                                    e = _entity.wordOffset_end
                                    if _entity.entity_type in ['org', 'company'] and _entity.label==2\
                                            and _entity.entity_text==winner:
                                        s = sentences[_entity.sentence_index].sentence_text
                                        for j in range(i+1, len(list_entity)):
                                            behind_entity = list_entity[j]
                                            b2 = behind_entity.wordOffset_begin
                                            e2 = behind_entity.wordOffset_end
                                            if _entity.sentence_index == behind_entity.sentence_index and behind_entity.entity_type in ['org', 'company'] \
                                                    and b2-e<10 and re.search('联合(体|投标人)：|联合体(成员|单位)[12345一二三四五]?：|(联合体)?成员单位[12345一二三四五]?：|特殊普通合伙：|[，；]成：|（成）$', s[b2-e:b2]) or \
                                                re.search('（联合(体|投标人)）|（联合体(成员|单位)方?[12345一二三四五]?）|（(联合体)?成员单位[12345一二三四五]?）|（特殊普通合伙|成员?）|^（成[），]$', s[e2:e2+10]) and behind_entity.label in [2, 5]:
                                                join_l.append(behind_entity.entity_text)
                                                b = b2
                                                e = e2
                                            else:
                                                break
                                        if len(join_l)>1:
                                            d['win_tenderer_joint'] = '，'.join(set(join_l))



                                            # behind_entity = list_entity[i + 1]
                                    # if _entity.sentence_index== behind_entity.sentence_index and _entity.entity_type in ['org', 'company'] and _entity.label==2\
                                    #         and _entity.entity_text==winner and behind_entity.entity_type in ['org', 'company'] and behind_entity.label==5:
                                    #     s = sentences[_entity.sentence_index].sentence_text
                                    #     b = _entity.wordOffset_begin
                                    #     e = _entity.wordOffset_end
                                    #     b2 = behind_entity.wordOffset_begin
                                    #     e2 = behind_entity.wordOffset_end
                                        # if re.search('（联合体）', s[e2:e2+6]) and b2-e<3:
                                        #     print('联合体：', s[max(0, b-10):e2+10])
                                        #     d['win_tenderer_joint'] = '%s，%s'%(_entity.entity_text, behind_entity.entity_text)
                                        #     break
                                        # elif re.search('（联合体((牵头|主办)(人|方|单位)|主体)|牵头(人|方|单位)）|(联合体)?成员：|特殊普通合伙：', s[e:b2]) and b2-e<10:
                                        #     d['win_tenderer_joint'] = '%s，%s' % (_entity.entity_text, behind_entity.entity_text)
                                        #     print('联合体：', s[max(0, b - 10):e2 + 10])
                                        #     break
    except Exception as e:
        print('获取联合体抛出异常', e)

def get_multi_winner_and_money(channel_dic, prem, list_entitys,list_sentences):
    '''
    获取多中标人及正文、附件所有金额，多中标人multi_winner写入prem，返回金额列表
    :param channel_dic:
    :param prem:
    :param list_entitys:
    :param list_sentences:
    :return:
    '''
    moneys = []
    moneys_attachment = []
    if channel_dic['docchannel']['docchannel'] in ['中标信息','候选人公示','合同公告'] and 'win_tenderer' in str(prem):
        sentences = sorted(list_sentences[0], key=lambda x: x.sentence_index)
        finalists = [] # 入围供应商
        i = 0
        while i < len(list_entitys[0])-1:
            ent = list_entitys[0][i]
            b_idx_fr = ent.wordOffset_begin
            e_idx_fr = ent.wordOffset_end
            multi_winner_l = []
            i += 1
            if ent.entity_type in ['money']:
                money = float(ent.entity_text)
                if ent.in_attachment:
                    moneys_attachment.append(money)
                else:
                    moneys.append(money)
            if ent.entity_type in ['org', 'company'] and ent.label == 2 and ent.values[ent.label]>0.8:
                if ent.entity_text not in multi_winner_l:
                    multi_winner_l.append(ent.entity_text)
                sentence_text = sentences[ent.sentence_index].sentence_text
                pre_text = sentence_text[max(0, b_idx_fr-10):b_idx_fr]
                if re.search('入围', pre_text) and re.search('未入围', pre_text)==None and ent.entity_text not in finalists:
                    finalists.append(ent.entity_text)
                for j in range(i, len(list_entitys[0])):
                    ent_bh = list_entitys[0][j]
                    b_idx_bh = ent_bh.wordOffset_begin
                    e_idx_bh = ent_bh.wordOffset_end
                    if ent_bh.entity_type in ['org', 'company'] and ent_bh.label == 5 and ent_bh.sentence_index == ent.sentence_index and b_idx_bh-e_idx_fr==1:
                        sentence_text = sentences[ent_bh.sentence_index].sentence_text
                        if sentence_text[e_idx_fr:b_idx_bh] in ['；','、','&','，'] and (len(sentence_text)==e_idx_bh or sentence_text[e_idx_bh] in ['；','、','&', '，', '。']): # 修复多中标人刚好在文末index超出报错，例子 407126558
                            if ent_bh.entity_text not in multi_winner_l:
                                multi_winner_l.append(ent_bh.entity_text)
                            e_idx_fr = e_idx_bh
                            i = j + 1
                        else:
                            break
                    elif ent_bh.entity_type in ['org', 'company'] and ent_bh.label == 5 and ent_bh.sentence_index == ent.sentence_index and b_idx_bh==e_idx_fr:
                        if ent_bh.entity_text not in multi_winner_l:
                            multi_winner_l.append(ent_bh.entity_text)
                        e_idx_fr = e_idx_bh
                        i = j + 1
                    else:
                        break
            if len(multi_winner_l)>=2:
                for project in prem[0].values():
                    if not isinstance(project, dict):
                        continue
                    for v in project.values():
                        for d in v['roleList']:
                            if d.get('role_name', '') == 'win_tenderer' and d.get('role_text', '') == multi_winner_l[0]:
                                # d['multi_winner'] = ','.join(set(multi_winner_l))
                                d['multi_winner'] = ','.join(multi_winner_l)
                                break
        if len(finalists)>=2:
            for project in prem[0].values():
                if not isinstance(project, dict):
                    continue
                for v in project.values():
                    for d in v['roleList']:
                        if d.get('role_name', '') == 'win_tenderer':
                            winner = d.get('role_text')
                            if winner in finalists:
                                d['multi_winner'] = ','.join(finalists)
    else:
        for i in range(len(list_entitys[0])):
            ent = list_entitys[0][i]
            if ent.entity_type in ['money']:
                money = float(ent.entity_text)
                if ent.in_attachment:
                    moneys_attachment.append(money)
                else:
                    moneys.append(money)
    return {'moneys': list(set(moneys)), 'moneys_attachment': list(set(moneys_attachment))}

def update_prem(old_prem, new_prem, in_attachment=False):
    '''
    根据新旧对比，更新数据
    :param old_prem:
    :param new_prem: 表格提取的要素
    :return:
    '''
    if len(new_prem) >= 1 :
        '''如果表格提取的包大于2，原来的包比表格提取的包多则删除原来多余的包，以表格的为准'''
        if len(new_prem) >= 2 and len(new_prem)<len(old_prem) <= len(new_prem)*2:
            del_k = []
            for k in old_prem:
                if k not in new_prem and k != 'Project':
                    del_k.append(k)
            for k in del_k:
                old_prem.pop(k)

        if len(old_prem) > len(new_prem) and in_attachment==False: # 如果表格有提取，非表格包数比表格提取多，去掉非表格在附件里提取的包
            del_k = []
            for k in old_prem:
                if 'in_attachment' in old_prem[k] and old_prem[k]['in_attachment'] and k not in new_prem and k != 'Project':
                    del_k.append(k)
            for k in del_k:
                old_prem.pop(k)

        # if len(new_prem) > len(old_prem) and [k for k in new_prem if '自增' not in k] == []:  # 如果表格提取包号都为自增编号且包数大于非表格提取，不进行更新 例 244355092  281854766
        #     return None

        if len(old_prem) == 2 and len(new_prem) == 1 and ('Project' in new_prem or set(new_prem)&set(old_prem)==set()): # 如果表格提取包为Project,非表格提取两个包且一个包为Project，把表格提取合并到非Project包
            k = list(old_prem.keys()-set(['Project']))[0]
            k_new = list(new_prem.keys())[0]
            new_prem[k] = new_prem.pop(k_new)

        if len(new_prem) == len(old_prem) == 1 and 'Project' not in new_prem and 'Project' in old_prem: # 如果表格提取到包号，非表格没提取到，合并到Project
            k = list(new_prem.keys())[0]
            new_prem['Project'] = new_prem[k]

        multi_tendereeMoney = [] # 多包招标金额
        for k, v in new_prem.items():
            if k == 'Project':
                if 'Project' in old_prem:
                    tmp_l = [] # 保存新旧同时包含的角色
                    if v.get('code', "") != "":
                        old_prem['Project']['code'] = v.get('code', "")
                    if v.get('name', "") != "":
                        old_prem['Project']['name'] = v.get('name', "")
                    for d in old_prem['Project']['roleList']:
                        for d2 in v['roleList']:
                            if d['role_name'] == d2['role_name']: # 同时包含的角色用表格的替换
                                tmp_l.append(d2)
                                if d2['role_text'] != "":
                                    d['role_text'] = d2['role_text']
                                if float(d2['role_money']['money']) != 0:  # 如果表格提取的金额不为0才替换
                                    d['role_money']['money'] = d2['role_money']['money']
                                    d['role_money']['money_unit'] = d2['role_money']['money_unit']
                    for d2 in v['roleList']:
                        if d2 not in tmp_l: # 把新预测有，旧没有的角色添加上去
                            old_prem['Project']['roleList'].append(d2)
                    if float(new_prem['Project']['tendereeMoney'])!=0:
                        old_prem['Project']['tendereeMoney'] = new_prem['Project']['tendereeMoney'] # 20240508 修复 464187225 表格提取纠正招标金额错误
                else:
                    old_prem[k] = v
            else:
                if v['tendereeMoney'] != 0:
                    multi_tendereeMoney.append(v['tendereeMoney'])
                if k.startswith('自增'): # 表格提取的没找到包号 按行数添加包号，前面加自增，例 自增1
                    k = k[2:]
                if k not in old_prem:  # 新有旧没有的包直接添加
                    old_prem[k] = v
                else:
                    tmp_l = []  # 保存新旧同时包含的角色
                    if v.get('code', "") != "":
                        old_prem[k]['code'] = v.get('code', "")
                    if v.get('name', "") != "":
                        old_prem[k]['name'] = v.get('name', "")
                    for d in old_prem[k]['roleList']:
                        for d2 in v['roleList']:
                            if d['role_name'] == d2['role_name']:
                                tmp_l.append(d2)
                                if d2['role_text'] != "":
                                    d['role_text'] = d2['role_text']
                                if float(d2['role_money']['money']) != 0: # 如果表格提取的金额不为0才替换
                                    d['role_money']['money'] = d2['role_money']['money']
                                    d['role_money']['money_unit'] = d2['role_money']['money_unit']
                    for d2 in v['roleList']:
                        if d2 not in tmp_l: # 把新预测有，旧没有的角色添加上去
                            old_prem[k]['roleList'].append(d2)
                    if v['tendereeMoney'] != 0:
                        old_prem[k]['tendereeMoney'] = v['tendereeMoney']  # 2024/05/24 使用表格招标金额
        if multi_tendereeMoney and 'Project' in old_prem and float(old_prem['Project']['tendereeMoney'])!=0: # 表格提取到多标段招标金额，去掉Project包招标金额
            old_prem['Project']['tendereeMoney'] = 0

    # return old_prem

def  confirm_prem(prem, channel_dic):
    '''
    规则检查纠正prem，如果Project包中标人在其他包中标人，去掉project包中标角色；如果有其他包中标人，去掉roleList为空的包；
    :param prem: prem 字段字典
    :return:
    '''
    if len(prem) > 1:  # 表格提取到中标人的，去掉project包中标人
        pro_winner = set()
        other_winner = set()
        empty_roleList = []
        for k in prem:
            prem[k]['uuid'] = str(uuid.uuid4()) # 20240627 每个包都添加uuid
            if prem[k]['roleList'] == []:
                empty_roleList.append(k)
            for d in prem[k]['roleList']:
                if d['role_name'] in ['win_tenderer', 'pre_win_tenderer', 'second_tenderer','third_tenderer']:
                    if k == 'Project':
                        pro_winner.add(d['role_text'])
                    else:
                        other_winner.add(d['role_text'])
        if pro_winner & other_winner != set():
            prem['Project']['roleList'] = [d for d in prem['Project']['roleList'] if
                                               d['role_name'] not in ['win_tenderer', 'second_tenderer',
                                                                      'third_tenderer']]
        if other_winner and channel_dic['docchannel']['docchannel'] in ['中标信息', '候选人公示', '合同公告']:
            for k in empty_roleList:
                prem.pop(k)
    elif "Project" in prem:
        prem['Project']['uuid'] = str(uuid.uuid4())


def fix_single_source(prem, channel_dic, original_docchannel):
    if prem.get('bidway', '') == '单一来源' and channel_dic['docchannel']['docchannel'] == '招标公告' and original_docchannel==52:
        for l in prem['prem'].values():
            for d in l['roleList']:
                if d['role_name'] == "win_tenderer":
                    d['role_name'] = 'pre_win_tenderer'

if __name__=="__main__":
    '''
    conn = getConnection()
    cursor = conn.cursor()
    #sql = " select distinct A.doc_id from entity_mention A,test_predict_role B where A.entity_id=B.entity_id limit 200"
    sql = " select B.doc_id,B.prem from articles_processed A, articles_validation B where A.id=B.doc_id "
    
    result = []
    
    cursor.execute(sql)
    rows = cursor.fetchall()
    count = 0
    for row in rows:
        
        count += 1
        # print(count)
        doc_id = row[0]
        
        roleList = getPackageRoleMoney(doc_id)
        result.append([doc_id,str(roleList),row[1]])
        ''''''
    with codecs.open("getAttribute.html","w",encoding="utf8") as f:
        f.write('<html><head>\
        <meta http-equiv="Content-Type"\
        content="text/html; charset=UTF-8">\
        </head>\
        <body bgcolor="#FFFFFF">\
        <table border="1">\
        <tr>\
        <td>doc_id</td>\
        <td>角色</td>\
        </tr>')
        for item in result:
            f.write("<tr>"+"<td>"+item[0]+"</td>"+"<td>"+item[1]+"</td>"+"<td>"+item[2]+"</td>"+"</tr>")
        f.write("</table></body>")
    '''