BIDI_EXTRACTION_AI/BiddingKG/dl/assembly/role_money.py

"""Phase 6 migration from interface/getAttributes.py.

This module hosts the role/money/KM-matching functions migrated verbatim from
``BiddingKG.dl.interface.getAttributes`` as part of the Phase 6 assembly
re-organization. It contains the legal role-combination search, expectation
scoring, role-list extraction, KM-based attribute dispatch, and the large
``findAttributeAfterEntity`` routine that links money / service-time / ratio /
contacts attributes to role entities, plus the package-role-money entry points
``initPackageAttr`` and ``getPackageRoleMoney``.

The relation-extraction model is lazily loaded on first use to avoid
triggering a model load at import time.
"""

from __future__ import absolute_import

import re
import copy
import math
import uuid
from decimal import Decimal

from scipy.optimize import linear_sum_assignment
import numpy as np

from BiddingKG.dl.common.Utils import getUnifyMoney
from BiddingKG.dl.common.attr_utils import extract_serviceTime
from BiddingKG.dl.interface.Entitys import PREM, Role, Entity, Match
from BiddingKG.dl.assembly.package_scope import (
    getPackage,
    getPackagesFromArticle,
    dict_role_id,
    role2id_dict,
)

_relationExtraction_model = None


def _get_relationExtraction_model():
    global _relationExtraction_model
    if _relationExtraction_model is None:
        from BiddingKG.dl.interface.modelFactory import Model_relation_extraction
        _relationExtraction_model = Model_relation_extraction()
    return _relationExtraction_model


__all__ = [
    "get_legal_comba",
    "get_dict_entity_prob",
    "getSumExpectation",
    "getRoleList",
    "dispatch",
    "findAttributeAfterEntity",
    "initPackageAttr",
    "getPackageRoleMoney",
]


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


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
    main_contain_winner = False # 2024/10/11 判断正文是否包含中标人
    for entity in list_entity:
        if entity.entity_type in ['org','company'] and entity.label==2 and entity.values[entity.label]>0.7 and entity.in_attachment==False:
            main_contain_winner = True
            break

    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 main_contain_winner and entity.in_attachment and entity.label in [2,3,4]: # 2024/10/11 正文包含中标人，不再提取附件中标人 避免 例：504046747 附件角色OCR错字变两个标段
                    continue
                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':  # 20240809 由于包号对应不上注销
            #     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 dispatch(match_list):
    main_roles = list(set([match.main_role for match in match_list]))
    # print('main_roles',[i.entity_text for i in main_roles])
    attributes = list(set([match.attribute for match in match_list]))
    # try:
    #     print('attributes',[i.entity_text for i in attributes])
    # except:
    #     pass

    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]


def findAttributeAfterEntity(PackDict,roleSet,PackageList,PackageSet,list_sentence,list_entity,list_outline,winter_scope,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
                    if money.notes == '单价':
                        packDict[packageName]["roleList"][i].unit_price = money.entity_text
                    else:
                        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)
                    if money.notes == '单价':
                        packDict[packageName]["roleList"][i].unit_price = money.entity_text
                    else:
                        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('连接中的金额：{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 and not packDict[packageName]["roleList"][i].serviceTime:
                # packDict[packageName]["roleList"][i].serviceTime = serviceTime.entity_text
                packDict[packageName]["roleList"][i].serviceTime = extract_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
                            elif after_entity.values[after_entity.label] <= 0.6:
                                value *= 20
                        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 or _attribute.values[_attribute.label] <= 0.6:  # 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()
    rule_winter_phone = set()
    tenderee_entity_set = set()
    agency_entity_set = 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)
    for _entity in [entity for entity in list_entity if entity.entity_type in ['company','org']]:
        if _entity.label==0:
            tenderee_entity_set.add(_entity.entity_text)
        elif _entity.label==1:
            agency_entity_set.add(_entity.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|业主|委托)(?: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)(?:单位)?[^。代理]{0,5}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,7}?)"
        "(?:(?:(?:遴选|寻源|采购|招标|竞价|议价|比选|(?:[^受被]|^)委托|询比?价|比价|评选|谈判|邀标|邀请|洽谈|约谈|选取|抽取|抽选|项目|需求?|甲方?|转让|招租|议标|合同主体|挂牌|出租|出让|出售|标卖|处置|发包|最终|建设|业主|竞卖|申购|公选)"
        "(?:人|方|商|单位|组织|用户|业主|主体|部门|公司|企业))(?:单位)?[^。代理]{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|业主)(?: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)(?:单位)?[^。代理]{0,3}(?:地址)[^。]{0,3}(?:电话|联系方式|联系人|联系电话)[:：]?[^。]{0,20}?)"
        "(?:(?:(?:遴选|寻源|采购|招标|竞价|议价|比选|(?:[^受被]|^)委托|询比?价|比价|评选|谈判|邀标|邀请|洽谈|约谈|选取|抽取|抽选|项目|需求?|甲方?|转让|招租|议标|合同主体|挂牌|出租|出让|出售|标卖|处置|发包|最终|建设|业主|竞卖|申购|公选)"
        "(?:人|方|商|单位|组织|用户|业主|主体|部门|公司|企业))(?:单位)?[^。代理]{0,3}(?:地址)[^。]{0,3}(?:电话|联系方式|联系人|联系电话|联系人和联系方式)[:：]?[^。]{0,20}?)"
        # 电话号码
        + phone_pattern)
    re_agent_phone = re.compile(
        "(?:(?:(?:代理|[受被]委托)(?:人|方|商|机构|公司|单位|组织|企业)|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|联系人和联系方式)[:：]?[^。]{0,7}?)"
        # 电话号码
        + phone_pattern)
    re_agent_phone2 = re.compile(
        "(?:(?:(?:代理|[受被]委托)(?:人|方|商|机构|公司|单位|组织|企业)|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|联系人和联系方式)[:：]?[^。]{0,20}?)"
        # 电话号码
        + phone_pattern)
    re_win_tenderer_phone = re.compile(
        "(?:(?:(?:乙|竞得|受让|买受|签约|供货|供应?|合作|承做|承包|承建|承销|承保|承接|承制|承担|承修|承租(?:（包）)?|入围|入选|竞买|中标|中选|中价|中签|成交|候选)"
        "(?:候选|投标)?(?:人|单位|(?:中介)?(?:服务)?机构|供应商|客户|方|公司|企业|厂商|商|社会资本方?)|选定单位|中[标选]银行|成交对象)[^。审核]{0,5}(?:负责人|联系人|项目)?(?:经理|电话|联系方式|联系人|负责人|联系电话|联系人和联系方式)[:：]?[^。]{0,7}?)"
        + phone_pattern)
    re_win_tenderer_phone2 = re.compile(
        "(?:(?:(?:乙|竞得|受让|买受|签约|供货|供应?|合作|承做|承包|承建|承销|承保|承接|承制|承担|承修|承租(?:（包）)?|入围|入选|竞买|中标|中选|中价|中签|成交|候选)"
        "(?:候选|投标)?(?:人|单位|(?:中介)?(?:服务)?机构|供应商|客户|方|公司|企业|厂商|商|社会资本方?)|选定单位|中[标选]银行|成交对象)[^。]{0,3}(?:地址)[^。审核]{0,3}(?:负责人|联系人|项目)?(?:经理|电话|联系方式|联系人|负责人|联系电话|联系人和联系方式)[:：]?[^。]{0,20}?)"
        + phone_pattern)
    not_win_tenderer_contact = re.compile("纪检|监察|质疑|投诉|监督|受理|请.{0,4}(联系|与)"
                                          "|(遴选|寻源|采购|招标|竞价|议价|比选|委托|询比?价|比价|评选|谈判|邀标|邀请|洽谈|约谈|选取|抽取|抽选|项目|需求?|甲方?|转让|招租|议标|合同主体|挂牌|出租|出让|出售|标卖|处置|发包|最终|建设|业主|竞卖|申购|公选|发布|代理|拍卖|转出){1,2}"
                                          "(人|方|商|单位|组织|用户|业主|主体|部门|公司|企业|工厂|银行|机构){0,2}"
                                          "[\u4e00-\u9fa5]{0,4}(联系|咨询|电话)(人|电话|方式)?")

    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)
    # 中标人联系方式规则筛选
    _winter_phone = re.findall(re_win_tenderer_phone, content)
    if _winter_phone:
        for _phone in _winter_phone:
            _phone = _phone.split("/")
            for one_phone in _phone:
                rule_winter_phone.add(one_phone)
    _winter_phone2 = re.findall(re_win_tenderer_phone2, content)
    if _winter_phone2:
        for _phone in _winter_phone2:
            _phone = _phone.split("/")
            for one_phone in _phone:
                rule_winter_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|证书|资格证|资质|价格|金额|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-30):entity.wordOffset_begin]
        entity_left1 = re.sub("，（）\(\)","",entity_left)
        entity_left1 = entity_left1[-5:]
        entity_left2 = [i for i in entity_left.split("，") if i]
        if entity_left2:
            entity_left2 = entity_left2[-1]
        else:
            entity_left2 = ""
        if re.search("地址|地点|银行[：:]",entity_left1) or re.search("地址|地点|银行[：:]",entity_left2):
            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)
    text_data,pre_data = _get_relationExtraction_model().encode([ent for ent in pre_entity+phone_entitys if ent.in_attachment==False], list_sentence)
    # print(pre_data)
    maxlen = 512
    relation_list = []
    if 0<len(text_data)<=maxlen:
        relation_list = _get_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 _get_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(_get_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(_get_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])
    # relation_list = [] # 放弃原来的模型连接，结果不好控制
    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":
                        # print(predicate, _subject.entity_text, _object.entity_text)
                        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("纪检|监察|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]):
                        if _subject.label in [2,3,4] and re.search(not_win_tenderer_contact,list_sentence[_object.sentence_index].sentence_text[max(0,_object.wordOffset_begin-15):_object.wordOffset_begin]):
                            # print('not_win_tenderer_contact1')
                            continue
                        # 角色为招标/代理人，排除"纪检|监察"相关的联系人
                        if (_subject.label in [0,1] or _subject.entity_text in tenderee_entity_set|agency_entity_set) and re.search("纪检|监察|投诉|监督|乙方|中标",list_sentence[_object.sentence_index].sentence_text[max(0,_object.wordOffset_begin - 10):_object.wordOffset_begin]):
                        # if _subject.label in [0,1] and re.search("纪检|监察|乙方|中标",list_sentence[_object.sentence_index].sentence_text[_subject.end_index:_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  # 经过住址的数量
            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 < 60:
                            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 = [ent for ent in pre_entity+ phone_entitys if ent.entity_type not in ['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 < 30:
                            # 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
                elif after_entity.entity_type == "person":
                    person_nums += 1
                elif after_entity.entity_type in ["company","org"]:
                    break
            # 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 < 30:
                        # 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]
    # print([(mat.main_role.entity_text,mat.attribute.entity_text) for mat in t_match_list])
    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:
                                    # 角色为中标候选人，联系人无号码且上文没有联系关键词时排除
                                    if re.search("联系人|联系方式|电话|负责人|经理|法人|法定代表人",list_sentence[per.sentence_index].sentence_text[max(0, per.wordOffset_begin - 10):per.wordOffset_begin]):
                                        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))

    # 使用中标信息大纲提取联系人
    winter_scope_group = []
    if winter_scope:
        winter_scope_begin = winter_scope[0]
        winter_scope_end = winter_scope[1]
        # print(list_sentence[winter_scope_begin[0]].sentence_text[winter_scope_begin[1]:winter_scope_end[1]])
        winter_temporary_list = []
        for entity in list_entity:
            if entity.entity_type in ['org', 'company', 'person']:
                winter_temporary_list.append(entity)
        winter_temporary_list = sorted(winter_temporary_list, key=lambda x: (x.sentence_index, x.begin_index))
        winter_temporary_list2 = []
        for _entity in winter_temporary_list:
            if _entity.sentence_index>=winter_scope_begin[0] and _entity.sentence_index<=winter_scope_end[0]:
                if (_entity.sentence_index==winter_scope_begin[0] and _entity.wordOffset_begin>=winter_scope_begin[1]) or \
                        _entity.sentence_index>winter_scope_begin[0]:
                    if (_entity.sentence_index == winter_scope_end[0] and _entity.wordOffset_end<=winter_scope_end[1]) or \
                            _entity.sentence_index<winter_scope_end[0]:
                        winter_temporary_list2.append(_entity)
        # print('winter_scope_entity',[i.entity_text for i in winter_temporary_list2])
        winter_scope_group = winter_temporary_list2

        match_list_winter = []
        for index in range(len(winter_scope_group)):
            entity = winter_scope_group[index]
            if entity.entity_type in ['company','org']:
                match_nums = 0
                for after_index in range(index + 1, min(len(winter_scope_group), index + 4)):
                    after_entity = winter_scope_group[after_index]
                    if match_nums > 2:
                        break
                    if after_entity.entity_type == '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 >= 30:
                            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(not_win_tenderer_contact, list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 15):after_entity.wordOffset_begin]):
                            break
                        # 角色为中标候选人，联系人无号码且上文没有联系关键词时排除
                        if entity.label in [2, 3, 4] and not after_entity.person_phone and not re.search(
                                "联系人|联系方式|电话|负责人|经理|法人|法定代表人", list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 10):after_entity.wordOffset_begin]):
                            continue
                        # 角色为招标/代理人，排除"纪检|监察"相关的联系人
                        if (entity.label in [0,1] or entity.entity_text in tenderee_entity_set|agency_entity_set) and re.search("纪检|监察|投诉|监督|乙方|中标", 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 distance < 80:
                            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_list_winter.append(Match(entity, after_entity, value))
                            match_nums += 1
                # 前向查找匹配
                if index != 0:
                    previous_entity = winter_scope_group[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
                        # 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(not_win_tenderer_contact, list_sentence[previous_entity.sentence_index].sentence_text[
                                                                                             max(0,previous_entity.wordOffset_begin - 15):previous_entity.wordOffset_begin]):
                            break
                        # 角色为中标候选人，联系人无号码且上文没有联系关键词时排除
                        if entity.label in [2, 3, 4] and not previous_entity.person_phone and not re.search(
                                "联系人|联系方式|电话|负责人|经理|法人|法定代表人",list_sentence[previous_entity.sentence_index].sentence_text[
                                max(0, previous_entity.wordOffset_begin - 10):previous_entity.wordOffset_begin]):
                            continue
                        # 角色为招标/代理人，排除"纪检|监察"相关的联系人
                        if (entity.label in [0,1] or entity.entity_text in tenderee_entity_set|agency_entity_set) and re.search("纪检|监察|投诉|监督|乙方|中标", list_sentence[previous_entity.sentence_index].sentence_text[
                                                                               max(0,previous_entity.wordOffset_begin - 10):previous_entity.wordOffset_begin]):
                            break
                        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_list_winter.append(Match(entity, previous_entity, value))
        # test
        # match_list_winter = company_contact_link([winter_scope_group])
        # km算法分配求解
        result_winter = dispatch(match_list_winter)
        for match in result_winter:
            _company = match[0]
            _person = match[1]
            _person = _person.entity_text
            # 更新中标人联系方式
            if _company.label==2:
                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 == "win_tenderer":
                            if PackDict[k]["roleList"][i].entity_text == _company.entity_text:
                                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))
                if phone_:
                    for p in phone_:
                        rule_winter_phone.add(p)
                    # print('rule_winter_phone',rule_winter_phone)

    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>=30:
                                    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("纪检|监察|质疑|投诉|监督|受理|项目(单位|业主)?联系|(采购|招标)人?联系|请.{0,4}联系", list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 10):after_entity.wordOffset_begin]):
                                if entity.label in [2, 3, 4] and re.search(not_win_tenderer_contact, list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 15):after_entity.wordOffset_begin]):
                                    # print('not_win_tenderer_contact2')
                                    break
                                # 角色为中标候选人，联系人无号码且上文没有联系关键词时排除
                                # print('test',after_entity.entity_text,after_entity.person_phone,list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 10):after_entity.wordOffset_begin])
                                if entity.label in [2, 3, 4] and not after_entity.person_phone and not re.search("联系人|联系方式|电话|负责人|经理|法人|法定代表人",list_sentence[after_entity.sentence_index].sentence_text[max(0,after_entity.wordOffset_begin - 10):after_entity.wordOffset_begin]):
                                    continue
                                # 角色为招标/代理人，排除"纪检|监察"相关的联系人
                                if (entity.label in [0,1] or entity.entity_text in tenderee_entity_set|agency_entity_set) and re.search("纪检|监察|投诉|监督|乙方|中标",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("纪检|监察|质疑|投诉|监督|受理|项目(单位|业主)?联系|(采购|招标)人?联系|请.{0,4}联系",mid_sentence[-10:]):
                                            if entity.label in [2, 3, 4] and re.search(not_win_tenderer_contact,mid_sentence[-15:]):
                                                # print('not_win_tenderer_contact3')
                                                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("纪检|监察|质疑|投诉|监督|受理|项目(单位|业主)?联系|(采购|招标)人?联系|请.{0,4}联系", mid_sentence[-10:]):
                                        elif entity.label in [2, 3, 4] and re.search(not_win_tenderer_contact, mid_sentence[-15:]):
                                            # print('not_win_tenderer_contact4')
                                            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
                                    # 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(not_win_tenderer_contact,list_sentence[previous_entity.sentence_index].sentence_text[
                                                                               max(0,previous_entity.wordOffset_begin - 15):previous_entity.wordOffset_begin]):
                                        # print('not_win_tenderer_contact2')
                                        break
                                    # 角色为中标候选人，联系人无号码且上文没有联系关键词时排除
                                    if entity.label in [2, 3,4] and not previous_entity.person_phone and not re.search("联系人|联系方式|电话|负责人|经理|法人|法定代表人",
                                            list_sentence[previous_entity.sentence_index].sentence_text[max(0,previous_entity.wordOffset_begin - 10):previous_entity.wordOffset_begin]):
                                        continue
                                    # 角色为招标/代理人，排除"纪检|监察"相关的联系人
                                    if (entity.label in [0,1] or entity.entity_text in tenderee_entity_set|agency_entity_set) and re.search("纪检|监察|投诉|监督|乙方|中标", list_sentence[previous_entity.sentence_index].sentence_text[
                                                                                           max(0,previous_entity.wordOffset_begin - 10):previous_entity.wordOffset_begin]):
                                        break
                                    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)
    result2.sort(key=lambda x: (x[0].sentence_index, x[0].begin_index))
    # print(result2)
    for match in result2:
        entity = match[0]
        # print(entity.entity_text)
        # print(entity.label)
        # print(match[1])
        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 PackDict[k]["roleList"][i].linklist and entity.in_attachment:
                                    # 中标联系人已有值时，跳过附件提取的
                                    # print('win test', person_, phone_)
                                    continue
                                if not phone_:
                                    PackDict[k]["roleList"][i].linklist.append((person_, ""))
                                for p in phone_:
                                    # print('win test',person_, p)
                                    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 = []
    tenderee_agency_contact = []
    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]])
                tenderee_agency_contact.extend([person_phone[0]+'-'+person_phone[1] for person_phone in PackDict[k]["roleList"][i].linklist])
            # 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 or tenderee_agency_contact:
                    remove_list = []
                    for item in PackDict[k]["roleList"][i].linklist:
                        if item[1] and item[1] in tenderee_agency_phone:
                            if item[1] not in rule_winter_phone:
                                # print('remove win phone',item)
                                remove_list.append(item)
                        elif item[0]+'-'+item[1] in tenderee_agency_contact:
                            if item[1] not in rule_winter_phone:
                                # print('remove win phone', item)
                                remove_list.append(item)
                    for _item in remove_list:
                        PackDict[k]["roleList"][i].linklist.remove(_item)
                elif not tenderee_agency_phone:
                    # 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:
                        # 排除非正则规则识别的联系方式
                        if _item[1] not in rule_winter_phone:
                            remove_list.append(_item)
                    # print('remove_list',remove_list)
                    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" and entity.notes != '单价':
                    if entity.in_attachment == False: # 20251009 修复 659780102 正文中标人与附件错误金额链接， 某服务采购代理业务成交金额或者暂定价为150万元，
                        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' or float(entity.entity_text)<100000000):
                    '''
                    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
                            if entity.notes == '单价':
                                PackDict["Project"]["unit_tendereeMoney"] = str(Decimal(entity.entity_text))
                            else:
                                PackDict["Project"]["tendereeMoney"] = str(Decimal(entity.entity_text))
                            PackDict["Project"]["tendereeMoneyUnit"] = entity.money_unit
                            max_prob = entity.values[entity.label]
                    else:
                        if entity.notes == '单价':
                            PackDict[packageName]["unit_tendereeMoney"] = str(Decimal(entity.entity_text))
                        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

    '''标段链接包名包号'''
    pk_name_l = []
    pk_code_l = []
    count_dic = {
        'package': set(),
        'name': set(),
        'code': set()
    }

    def get_sort_dist(l, max_sent_dist=2):
        '''
        计算标段与其他要素距离，并按距离排序返回字典
        :param l: [(entity.entity_type, entity.entity_text, entity.sentence_index, entity.wordOffset_begin, entity.wordOffset_end)]
        :param max_sent_dist: 最大句子距离
        :return:
        '''
        l.sort(key=lambda x: [x[2],x[3],x[4]]) # 20241204 多个字段排序 修复 561998414 第一标段西铭矿清水泵采购 标段和包名开始位置一样的情况
        link_dic = {}
        i = 1
        while i < len(l):
            ty1, ent1, s1, b1, e1, in_att1 = l[i - 1]
            ty2, ent2, s2, b2, e2, in_att2 = l[i]
            if ty1 != ty2 and in_att1 == in_att2 and s2 - s1 <= max_sent_dist:
                if ty1 == 'package':
                    if ent1 not in link_dic:
                        link_dic[ent1] = []
                    if s1 == s2:
                        dist = abs(b2 - e1) if b2 > e1 else 0
                    else:
                        dist = len(list_sentence[s1].sentence_text) - e1
                        for id in range(s1+1, s2):
                            dist += len(list_sentence[id].sentence_text)
                        dist += b2
                    if in_att1:
                        dist += 100 # 附件的距离加100
                    link_dic[ent1].append((s2 - s1, dist, ent2))
                elif ty2 == 'package':
                    if ent2 not in link_dic:
                        link_dic[ent2] = []
                    if s1 == s2:
                        dist = abs(b2 - e1) if b2 > e1 else 0
                    else:
                        dist = len(list_sentence[s1].sentence_text) - e1
                        for id in range(s1+1, s2):
                            dist += len(list_sentence[id].sentence_text)
                        dist += b2
                    if in_att1:
                        dist += 100  # 附件的距离加100
                    if s1!=s2 or e1!=e2:
                        dist += 30 # 包号在实体后面距离再加30
                    link_dic[ent2].append((s2 - s1, dist, ent1))
            i += 1
        return link_dic

    for entity in list_entity:
        if entity.entity_type == 'package':
            pk_name_l.append((entity.entity_type, entity.entity_text, entity.sentence_index, entity.wordOffset_begin, entity.wordOffset_end, entity.in_attachment))
            pk_code_l.append((entity.entity_type, entity.entity_text, entity.sentence_index, entity.wordOffset_begin, entity.wordOffset_end, entity.in_attachment))
            count_dic['package'].add(entity.entity_text)
        elif entity.entity_type == 'name':
            pk_name_l.append((entity.entity_type, entity.entity_text, entity.sentence_index, entity.wordOffset_begin, entity.wordOffset_end, entity.in_attachment))
            count_dic['name'].add(entity.entity_text)
        elif entity.entity_type == 'code':
            pk_code_l.append((entity.entity_type, entity.entity_text, entity.sentence_index, entity.wordOffset_begin, entity.wordOffset_end, entity.in_attachment))
            count_dic['code'].add(entity.entity_text)
    if len(count_dic['package']) > 0:
        if len(count_dic['name'])>0:
            link_dic = get_sort_dist(pk_name_l)
            for k, v in link_dic.items():
                v.sort(key=lambda x: [x[0], x[1]])
                if v[0][0] < 2 and v[0][1] < 200: # 标段号与包名句子数小于2，字距离小于200的才添加
                    PackDict[k]["name"] = v[0][2]
        if len(count_dic['code'])>0:
            link_dic = get_sort_dist(pk_code_l)
            for k, v in link_dic.items():
                v.sort(key=lambda x: [x[0], x[1]])
                if v[0][0] < 2 and v[0][1] < 200:
                    PackDict[k]["code"] = v[0][2]

    #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 float(PackDict[pack].get("unit_tendereeMoney", 0)) > 10000 and PackDict[pack]["tendereeMoney"]==0: # 单价补充招标金额
            PackDict[pack]["tendereeMoney"] = PackDict[pack].get("unit_tendereeMoney", 0)
        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():
            if float(v[0].unit_price) < float(list(v[1])[0]): # 20241128 金额大于单价时才作链接金额
                v[0].money = list(v[1])[0]
    # 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','win_tenderer']]
        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) and \
                                    not re.search("代理|乙方|竞得|受让|买受|签约|供货|供应|承做|承包|承建|承销|承保|承接|承制|承担|承修|承租(?:（包）)?|入围|入选|竞买|中标|中选|中价|中签|成交|候选",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 ",".join(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 ",".join(exist_phone):
                                        tenderee_agency_role[0].linklist.append(("", sentence_phone[0]))
                                        get_contacts = True
                                        break
                    # if not get_contacts: # 会召回错误数据，不启用规则
                    #     # 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 ",".join(exist_phone):
                    #                         tenderee_agency_role[0].linklist.append((_entity.entity_text, _p))
                    #                         get_contacts = True
                    #                 break
                    # if not get_contacts: # 会召回错误数据，不启用规则
                    #     # 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 ",".join(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) and \
                                        not re.search("代理|乙方|竞得|受让|买受|签约|供货|供应|承做|承包|承建|承销|承保|承接|承制|承担|承修|承租(?:（包）)?|入围|入选|竞买|中标|中选|中价|中签|成交|候选",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 ",".join(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() + 50]
                                match_text = match_text.split("。")[0]
                                sentence_phone = phone.findall(match_text)
                                if sentence_phone:
                                    if sentence_phone[0] not in ",".join(exist_phone):
                                        tenderee_agency_role[0].linklist.append(("", sentence_phone[0]))
                                        get_tenderee_contacts = True
                                        break
                            if get_tenderee_contacts:
                                break

    # 如果同一个电话连到了不同的单位就直接去掉(2024-09-03 新增)
    get_phone_dict = dict()
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            for item in PackDict[k]["roleList"][i].linklist:
                if item[1]:
                    if item[1] not in get_phone_dict:
                        get_phone_dict[item[1]] = set()
                    get_phone_dict[item[1]].add(PackDict[k]["roleList"][i].entity_text)
    # print(get_phone_dict)
    remove_phone = []
    for phone,role_list in get_phone_dict.items():
        if len(role_list)>1:
            remove_phone.append(phone)
    for k in PackDict.keys():
        for i in range(len(PackDict[k]["roleList"])):
            remove_list = []
            for item in PackDict[k]["roleList"][i].linklist:
                if item[1] and item[1] in remove_phone:
                    remove_list.append(item)
            for _item in remove_list:
                PackDict[k]["roleList"][i].linklist.remove(_item)

    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,winter_scope):
    '''
    @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, winter_scope)
    return PackDict