BIDI_EXTRACTION_AI/BiddingKG/dl/assembly/time_attrs.py

# -*- coding: utf-8 -*-
"""Phase 6 migration from interface/getAttributes.py.

本模块承载从 ``BiddingKG.dl.interface.getAttributes`` 原样迁出的时间相关属性
装配函数，作为 Phase 6 装配层（assembly）重组的一部分。原位置与行号：

    - ``turnBidWay``           — 采购方式归一（原 3315-3333 行）
    - ``my_time_format_pattern`` — 时间正则常量（原 3370 行）
    - ``time_sub_pattern``     — 时间分隔符正则常量（原 3371 行）
    - ``my_timeFormat``        — 时间文本格式化为 ``YYYY-MM-DD`` 列表（原 3373-3457 行）
    - ``timeAdd``              — 日期加减天数/分钟（原 3459-3463 行）
    - ``getTimeAttributes``    — 装配时间类属性（原 3465-4210 行）
    - ``getOtherAttributes``   — 装配其它属性（资金来源/服务期等）（原 4413-4529 行）

注：``extract_serviceTime``、``get_days_between``、``turnMoneySource`` 已先一步
下沉到 ``BiddingKG.dl.common.attr_utils``，本模块按依赖方向约束改为从
``common.attr_utils`` 显式导入，避免反向依赖 ``interface.getAttributes``。
"""

from __future__ import absolute_import

import re
import time
from datetime import datetime
from decimal import Decimal

from BiddingKG.dl.common.attr_utils import extract_serviceTime, get_days_between, turnMoneySource
from BiddingKG.dl.ratio.re_ratio import getUnifyNum
from BiddingKG.dl.common.Utils import isValidDate, getDigitsDic

__all__ = ["turnBidWay", "my_timeFormat", "timeAdd", "getTimeAttributes", "getOtherAttributes",
           "my_time_format_pattern", "time_sub_pattern"]


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

my_time_format_pattern = re.compile("((?:(?P<year>20\d{2}|\d{2}|二[零〇0][零〇一二三四五六七八九0]{2})\s*[-/年.]\s*)?(?P<month>\d{1,2}|[一二三四五六七八九十]{1,3})\s*[-/月.]\s*(?P<day>\d{1,2}|[一二三四五六七八九十]{1,3}))(?:.?(?:[0-1][0-9]|2[0-4]|[0-9]):[0-5][0-9](?::[0-5][0-9])?)?")
time_sub_pattern = re.compile("[\[\]【】()（）{}｛｝]+")
from BiddingKG.dl.ratio.re_ratio import getUnifyNum
def my_timeFormat(_time,page_time):
    # if page_time:
    #     current_year = time.strftime("%Y",time.localtime(int(datetime.strptime(page_time, '%Y-%m-%d').timestamp())))
    # else:
    #     current_year = time.strftime("%Y",time.localtime())
    _time = re.sub(time_sub_pattern,"",_time)
    all_match = re.finditer(my_time_format_pattern,_time)
    time_list = []
    idx = 0
    global_year = ""
    for _match in all_match:
        if len(_match.group())>0:
            idx += 1
            legal = True
            year = ""
            month = ""
            day = ""
            for k,v in _match.groupdict().items():
                if k=="year":
                    year = v
                if k=="month":
                    month = v
                if k=="day":
                    day = v
            if year!="":
                if year==None: # 例：5月18日
                    if idx==2 and global_year: # 例：2025年5月14日-5月18日，第二个时间没年份
                        year = global_year
                    else:
                        legal = False
                else:
                    if re.search("^\d+$", year):
                        if len(year) == 2:
                            year = "20" + year
                            # if int(year) - int(current_year) > 5 or int(year) - int(current_year) < -1:
                            #     legal = False
                        # else:
                        #     if int(year) - int(current_year)>10 or int(year) - int(current_year) < -1:
                        #         legal = False
                    else:
                        _year = ""
                        for word in year:
                            if word == '0':
                                _year += word
                            else:
                                _year += str(getDigitsDic(word))
                        year = _year
            else:
                legal = False
            if month!="":
                if re.search("^\d+$", month):
                    if int(month) > 12:
                        legal = False
                else:
                    month = int(getUnifyNum(month))
                    if month >= 1 and month <= 12:
                        month = str(month)
                    else:
                        legal = False
            else:
                legal = False
            if day!="":
                if re.search("^\d+$", day):
                    if int(day) > 31:
                        legal = False
                else:
                    day = int(getUnifyNum(day))
                    if day >= 1 and day <= 31:
                        day = str(day)
                    else:
                        legal = False
            else:
                legal = False
            if legal and not isValidDate(int(year),int(month),int(day)):
                legal = False
            if legal:
                # 数字字符格式化
                year = str(int(year))
                month = str(int(month))
                day = str(int(day))
                time_list.append("%s-%s-%s"%(year,month.rjust(2,"0"),day.rjust(2,"0")))
                # if idx==1 and not global_year:
                if not global_year:
                    global_year = year
    return time_list,global_year

def timeAdd(_time,days,format="%Y-%m-%d",minutes=0):
    a = time.mktime(time.strptime(_time,format))+86400*days+60*minutes

    _time1 = time.strftime(format,time.localtime(a))
    return _time1

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


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

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

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

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

    last_sentence_index = 0
    last_time_type = ""
    last_time_index = {
        'time_bidstart':"time_bidclose",
        'time_publicityStart':"time_publicityEnd",
        'time_getFileStart':"time_getFileEnd",
        'time_registrationStart':"time_registrationEnd",
        'time_earnestMoneyStart':"time_earnestMoneyEnd",
        'time_commencement':"time_completion",
        'time_listingStart':"time_listingEnd",
        'time_contractStart':"time_contractEnd"
    }
    # time_entitys = [[_entity,my_timeFormat(_entity.entity_text,page_time)] for _entity in time_entitys]
    new_time_entitys = []
    year_list = []
    for _entity in time_entitys:
        _time_list,_year = my_timeFormat(_entity.entity_text,page_time)
        _in_attachment = _entity.in_attachment
        if _time_list:
            new_time_entitys.append([_entity,_time_list,_year])
            year_list.append([_year,_in_attachment])
    get_all_time = False if False in [i[1] for i in year_list] else True
    if page_time:
        current_year = time.strftime("%Y",time.localtime(int(datetime.strptime(page_time, '%Y-%m-%d').timestamp())))
        year_list.append([current_year,False])
    else:
        current_year = time.strftime("%Y",time.localtime())
    if get_all_time:
        year_list = [i[0] for i in year_list]
    else:
        year_list = [i[0] for i in year_list if not i[1]]
    year_list = [(y,year_list.count(y)) for y in year_list if y[:2]=='20']
    year_list.sort(key=lambda x:x[1],reverse=True)
    most_year = year_list[0][0] if year_list else ""
    if most_year:
        time_entitys = [item for item in new_time_entitys if int(item[2])-int(most_year)<=10 and int(item[2])-int(most_year)>=-1]
    else:
        time_entitys = new_time_entitys

    # print(time_entitys)
    for entity_idx in range(len(time_entitys)):
        entity = time_entitys[entity_idx][0]
        extract_time = time_entitys[entity_idx][1]
        sentence_text = list_sentence[entity.sentence_index].sentence_text
        previous_entity = time_entitys[entity_idx-1][0] if entity_idx!=0 else None
        previous_extract_time = time_entitys[entity_idx-1][1] if entity_idx!=0 else None
        next_entity = time_entitys[entity_idx+1][0] if entity_idx!=len(time_entitys)-1 else None
        next_extract_time = time_entitys[entity_idx+1][1] if entity_idx!=len(time_entitys)-1 else None
        # 实体有效上下文
        entity_context_begin = previous_entity.wordOffset_end if previous_entity and previous_entity.sentence_index==entity.sentence_index else 0
        entity_context_end = next_entity.wordOffset_begin if next_entity and next_entity.sentence_index==entity.sentence_index else len(sentence_text)

        if entity.sentence_index!=last_sentence_index:
            # sentence_index 不同句子重置last_time_type
            last_time_type = ""
        entity_left = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 2):entity.wordOffset_begin]
        entity_left2 = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 10):entity.wordOffset_begin]
        entity_left3 = sentence_text[max(entity_context_begin, entity.wordOffset_begin - 30):entity.wordOffset_begin]
        entity_right = sentence_text[entity.wordOffset_end:min(entity.wordOffset_end + 3,entity_context_end)]
        entity_right2 = sentence_text[entity.wordOffset_end:entity_context_end]
        entity_right2 = re.sub(r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+",'',entity_right2)[:60] # 去除网址
        # print(entity.entity_text,entity_right2)
        label_prob = entity.values[entity.label]
        entity_text = entity.entity_text
        in_attachment = entity.in_attachment
        if extract_time:
            definite_time_list = []
            t = re.compile("(北京时间)?(?P<day>下午|上午|早上)?(?P<hour>(?:[0-1][0-9]|2[0-4]|[0-9]))[:：时点](?P<half_hour>半)?(?P<minute>(?:[0-5][0-9]|[0-9]))?[:：分]?(?P<second>[0-5][0-9])?秒?")
            _entity_text = re.sub(" (?=[^\d])|(?<=[^\d]) ","",entity_text)
            _entity_text_len = len(_entity_text)
            _entity_text = _entity_text + sentence_text[entity.wordOffset_end:entity.wordOffset_end+20]
            t_in_word_num = len(re.findall(t,_entity_text))
            # t_out_of_word = re.search("^[^\d]{,2}"+t.pattern,re.sub(" (?=[^\d])|(?<=[^\d]) ","",sentence_text[entity.wordOffset_end:]))
            begin_index = 0
            definite_time_idx_list = []
            for _num in range(t_in_word_num):
                if begin_index> _entity_text_len + 8:
                    break
                t_in_word = re.search(t, _entity_text[begin_index:])
                # print(_entity_text[begin_index:])
                if t_in_word:
                    if _num==0 and t_in_word.start() > _entity_text_len + 8:
                        break
                    begin_index += t_in_word.end()
                    # print('t_in_word',entity_text,t_in_word.groupdict())
                    day = t_in_word.groupdict().get('day',"")
                    hour = t_in_word.groupdict().get('hour',"")
                    half_hour = t_in_word.groupdict().get('half_hour',"")
                    minute = t_in_word.groupdict().get('minute',"")
                    second = t_in_word.groupdict().get('second',"")
                    if not minute:
                        second = ""
                    if hour:
                        if day=='下午' and int(hour)<12:
                            hour = str(int(hour)+12)
                        if int(hour)>=24:
                            continue
                    else:
                        hour = "00"
                    if not minute:
                        if half_hour:
                            minute = "30"
                        else:
                            minute = "00"
                    if int(minute)>=60:
                        continue
                    if not second:
                        second = "00"
                    if int(second)>=60:
                        continue
                    definite_time = "%s:%s:%s"%(hour.rjust(2,"0"),minute.rjust(2,"0"),second.rjust(2,"0"))
                    # print(definite_time)
                    definite_time_list.append(definite_time)
                    definite_time_idx_list.append([begin_index-len(t_in_word.group()),begin_index])

            if len(extract_time)==1 and len(definite_time_list)>=2: # 实体只包含一个时间，"2024-12-09 09:00~16:00" 考虑单个时间对应两个详细时间段的识别
                # 前两个详细时间的间隔
                distance = definite_time_idx_list[1][0] - definite_time_idx_list[0][1]
                if distance<=8 and int(definite_time_list[1][:2])>=int(definite_time_list[0][:2]): # 判断详细时间都‘小时’顺序从小到大
                    new_extract_time = []
                    for d_time in definite_time_list[:2]:
                        if d_time == "24:00:00":  # 修正不规范时间表述
                            d_time = "23:59:59"
                        new_extract_time.append(extract_time[0] + " " + d_time)
                    extract_time = new_extract_time
                else:
                    if definite_time_list[0] == "24:00:00":  # 修正不规范时间表述
                        definite_time_list[0] = "23:59:59"
                    if definite_time_list[0] != "00:00:00":
                        extract_time[0] = extract_time[0] + " " + definite_time_list[0]
            else:
                min_len = min(len(extract_time),len(definite_time_list))
                for i in range(min_len):
                    if definite_time_list[i] == "24:00:00": # 修正不规范时间表述
                        definite_time_list[i] = "23:59:59"
                    if definite_time_list[i] != "00:00:00":
                        extract_time[i] = extract_time[i] + " " + definite_time_list[i]

        if extract_time:
            # 时间变更prob优化
            if re.search("原",entity_left2):
                last_index = 0
                for item in re.finditer("原",entity_left2):
                    last_index = item.start() + 1
                label_prob = label_prob - 0.2 * last_index / len(entity_left2)
                # print('prob优化',label_prob,extract_time)
            elif (re.search("改正|更正|修正|修改|更改|变更|延期|调整|变成",entity_left3[-20:]) or re.search("现",entity_left3[-10:])) and not re.search("更正日期",entity_left3[-8:]):
                last_time_label = dict_time2label.get(last_time_type,None)
                if last_time_label and entity.label==0:
                    entity.label = last_time_label
                    label_prob = 1.5
                elif last_time_label and entity.label==last_time_label:# 前后两个相同类型的时间为变更关系
                    label_prob = 2

            # 优化多个并列的时间，如：开标时间和截标时间，截标时间和报名结束时间
            if entity.label in [2,3,9]:
                if entity.label==2 and re.search("截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止|文件.{,2}([递提]交|接收)",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], label_prob-0.1, in_attachment))
                if entity.label==3 and re.search("开标|(评审|比选).{,2}(?:开始)?(时间|日期)|选取.{,2}(时间|日期)",entity_left3):
                    dict_time['time_bidopen'].append((extract_time[0], label_prob-0.1, in_attachment))
                if entity.label==3 and re.search("报名",entity_left3):
                    dict_time['time_registrationEnd'].append((extract_time[0], 0.5, in_attachment))
                if entity.label==3 and re.search("获取",entity_left3[-20:]):
                    dict_time['time_getFileEnd'].append((extract_time[0], 0.45, in_attachment))
                if entity.label==9 and re.search("截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止|文件.{,2}([递提]交|接收)",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], label_prob-0.1, in_attachment))
            if entity.label in [11, 3]:
                if entity.label==11 and re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], 0.5, in_attachment))
                if entity.label==3 and re.search("保证金.{,2}(接受|收取)|(接受|收取).{,2}保证金",entity_left3):
                    dict_time['time_earnestMoneyEnd'].append((extract_time[0], 0.5, in_attachment))
            if entity.label in [6, 7]:
                if re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    dict_time['time_bidclose'].append((extract_time[0], 0.5, in_attachment))
            if entity.label==0:
                if re.search("文件.{,2}([递提]交|接收)|截标|投标.{,2}截止|([递提]交|接收)(?:文件)?.{,2}截止|报价.{,2}截止|响应.{,2}截止",entity_left3):
                    if len(extract_time)>=2:
                        dict_time['time_bidstart'].append((extract_time[0], 0.45, in_attachment))
                        dict_time['time_bidclose'].append((extract_time[1], 0.45, in_attachment))
                    else:
                        dict_time['time_bidclose'].append((extract_time[0], 0.45, in_attachment))
            if entity.label==6:
                # "文件获取时间"和"报名时间"并列
                if re.search("报名",entity_left3):
                    if len(extract_time)==1:
                        dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            # 获取文件/报名/报价 时间补充（上下文表达过长无法通过模型识别）
            # if entity.label == 0:
            #     if re.search("(获取|领取|售卖|出售|购买|下载).{,4}(招标|投标|采购)?(文件|标书)|(文件|标书).{,4}(获取|售卖|出售|发售|购买)", entity_left3):
            #         if len(extract_time)==2:
            #             dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_getFileEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if next_entity and next_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[entity.wordOffset_end:next_entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(next_extract_time)==1:
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_getFileEnd'].append((next_extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_getFileEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|在线|线下|线上|网上).{,2}报名|报名.{,2}(开始)?(时间|日期)", entity_left3):
            #         if len(extract_time)==2:
            #             dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if next_entity and next_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[entity.wordOffset_end:next_entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(next_extract_time)==1:
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_registrationEnd'].append((next_extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_registrationEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #
            #     if re.search("(获取|售卖|出售|购买).{,4}(招标|投标|采购)?(文件|标书)|(文件|标书).{,4}(获取|售卖|出售|发售|购买)", entity_right2):
            #         if len(extract_time)==2:
            #             dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_getFileEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if previous_entity and previous_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[previous_entity.wordOffset_end:entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(previous_extract_time)==1:
            #                     dict_time['time_getFileStart'].append((previous_extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_getFileEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_getFileEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_getFileStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|在线|线下).{,2}报名", entity_right2):
            #         if len(extract_time) == 2:
            #             dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #             dict_time['time_registrationEnd'].append((extract_time[1], 0.51, in_attachment))
            #         else:
            #             if previous_entity and previous_entity.sentence_index==entity.sentence_index:
            #                 mid_text = sentence_text[previous_entity.wordOffset_end:entity.wordOffset_begin]
            #                 if len(mid_text)<=10 and re.search("至|到|[-—]|[～~]",mid_text) and len(previous_extract_time)==1:
            #                     dict_time['time_registrationStart'].append((previous_extract_time[0], 0.51, in_attachment))
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #             if not dict_time['time_registrationEnd']:
            #                 if re.search("前|止|截止", entity_right) or re.search("前",entity_text[-2:]):
            #                     dict_time['time_registrationEnd'].append((extract_time[0], 0.51, in_attachment))
            #                 elif re.search("起|开?始", entity_right) or re.search("起",entity_text[-2:]):
            #                     dict_time['time_registrationStart'].append((extract_time[0], 0.51, in_attachment))
            #     if re.search("(进行|开始).{,4}(报价|投标|竞价)", entity_right2):
            #         if len(extract_time) == 2:
            #             dict_time['time_bidstart'].append((extract_time[0], 0.51, in_attachment))
            #             # dict_time['time_bidclose'].append((extract_time[1], 0.51, in_attachment))

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

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

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

            if re.search("至|到|[日\d][-—]$|[～~]", entity_left):
                if entity.sentence_index == last_sentence_index:
                    time_type = last_time_index.get(last_time_type)
                    if time_type:
                        dict_time[time_type].append((extract_time[0], 0.5 + label_prob / 10,in_attachment))
                        last_time_type = ""
                        last_sentence_index = entity.sentence_index
                        continue
            if entity.label!=0:
                if entity.label==1 and label_prob>0.5:
                    dict_time['time_release'].append((extract_time[0],label_prob,in_attachment))
                    last_time_type = 'time_release'
                elif entity.label==2 and label_prob>0.5:
                    dict_time['time_bidopen'].append((extract_time[0],label_prob,in_attachment))
                    last_time_type = 'time_bidopen'
                elif entity.label==3 and label_prob>0.5:
                    if re.search("(资格)?预审文件[\u4e00-\u9fa5]{,4}截止",entity_left3[-15:]):
                        # 排除"资格预审文件提交截止时间"
                        last_time_type = ''
                        continue
                    if len(extract_time)==1:
                        dict_time['time_bidclose'].append((extract_time[0],label_prob,in_attachment))
                        last_time_type = 'time_bidclose'
                    elif len(extract_time)==2:
                        dict_time['time_bidstart'].append((extract_time[0], 0.6, in_attachment))
                        dict_time['time_bidclose'].append((extract_time[1], label_prob, in_attachment))
                        last_time_type = 'time_bidclose'
                elif entity.label==12 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_bidclose'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_bidclose'
                        else:
                            dict_time['time_bidstart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_bidstart'
                    else:
                        dict_time['time_bidstart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_bidclose'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==4 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_publicityEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_publicityEnd'
                        else:
                            dict_time['time_publicityStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_publicityStart'
                    else:
                        dict_time['time_publicityStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_publicityEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==5 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_publicityEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_publicityEnd'
                    else:
                        dict_time['time_publicityStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_publicityEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==6 and label_prob>0.5:
                    if len(extract_time)==1:
                        if (re.search("前|截?止",entity_right) and re.search("前|截?止(?!时间|日期)",entity_right2[:len(entity_right)+3])) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_getFileEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_getFileEnd'
                        else:
                            dict_time['time_getFileStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_getFileStart'
                    else:
                        dict_time['time_getFileStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_getFileEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==7 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_getFileEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_getFileEnd'
                    else:
                        dict_time['time_getFileStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_getFileEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==8 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_registrationEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_registrationEnd'
                        else:
                            dict_time['time_registrationStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_registrationStart'
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==9 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_registrationEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_registrationEnd'
                    else:
                        dict_time['time_registrationStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_registrationEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==10 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_earnestMoneyEnd'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_earnestMoneyEnd'
                        else:
                            dict_time['time_earnestMoneyStart'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_earnestMoneyStart'
                    else:
                        dict_time['time_earnestMoneyStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_earnestMoneyEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==11 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_earnestMoneyEnd'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_earnestMoneyEnd'
                    else:
                        dict_time['time_earnestMoneyStart'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_earnestMoneyEnd'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==13 and label_prob>0.5:
                    if len(extract_time)==1:
                        if re.search("前|止|截止",entity_right) or re.search("至|止|到",entity_left) or re.search("前",entity_text[-2:]):
                            dict_time['time_completion'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_completion'
                        else:
                            dict_time['time_commencement'].append((extract_time[0], label_prob,in_attachment))
                            last_time_type = 'time_commencement'
                    else:
                        dict_time['time_commencement'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_completion'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                elif entity.label==14 and label_prob>0.5:
                    if len(extract_time)==1:
                        dict_time['time_completion'].append((extract_time[0], label_prob,in_attachment))
                        last_time_type = 'time_completion'
                    else:
                        dict_time['time_commencement'].append((extract_time[0],label_prob,in_attachment))
                        dict_time['time_completion'].append((extract_time[1],label_prob,in_attachment))
                        last_time_type = ''
                else:
                    last_time_type = ""
            else:
                last_time_type = ""
        else:
            last_time_type = ""
        last_sentence_index = entity.sentence_index

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

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


        return dict_time

    # dict_time = add_time_by_parseDocument(dict_time,parse_document)

    # print(dict_time)
    result_dict = dict((key,"") for key in dict_time.keys())
    for time_type,value in dict_time.items():
        list_time = dict_time[time_type]
        if list_time:
            for in_attachment in [False,True]:
                _list_time = [_time for _time in list_time if _time[2]==in_attachment]
                if time_type in ['time_getFileEnd','time_registrationEnd','time_bidclose','time_bidopen']:
                    # 过滤与page_time差距过大的时间(需加上公告类别判断[52,101,114])
                    # print(time_type,_list_time,timeAdd(page_time,-7))
                    tmp_list_time = []
                    # for add_day in [ 1, 0, -7, -15, -31]:
                    for add_day in [ 1, 0, -7, -15, -31, -60, -90]:
                        tmp_list_time = [_time for _time in list_time if _time[0][:10] >= timeAdd(page_time,add_day) and _time[0][:10] < timeAdd(page_time,180)]
                        if tmp_list_time:
                            break
                    _list_time = tmp_list_time
                else:
                    if time_type not in ['time_contractEnd','time_completion']:
                        _list_time = [_time for _time in list_time if _time[0][:10] >= timeAdd(page_time, -180) and _time[0][:10] < timeAdd(page_time,180)]
                    else:
                        _list_time = [_time for _time in list_time if _time[0][:10] >= timeAdd(page_time, -180)]

                if _list_time:
                    _list_time.sort(key=lambda x:(x[1],len(x[0])),reverse=True) # sort_key: label_prob,时间文本长度(优先有具体时分秒的)
                    if in_attachment==True and len(result_dict[time_type])>0:
                        break
                    result_dict[time_type] = _list_time[0][0]
    # print('time result_dict',result_dict)
    # result_dict 纠错
    if not result_dict['time_bidclose']:
        if result_dict['time_bidstart']: # 无截标时间，投标开始和开标时间一样
            if result_dict['time_bidstart'][:10] in result_dict['time_bidopen']:
                result_dict['time_bidstart'] = ""
                result_dict['time_bidclose'] = result_dict['time_bidopen']
        if not result_dict['time_bidclose']:
            if result_dict['time_getFileEnd']:  # 无截标时间，获取文件截止时间和开标时间一样
                if result_dict['time_getFileEnd'][:10] in result_dict['time_bidopen']:
                    result_dict['time_bidclose'] = result_dict['time_bidopen']
    else:
        if result_dict['time_bidopen']: # 截标时间 和 开标时间 时分秒互补
            if len(result_dict['time_bidclose'])<len(result_dict['time_bidopen']) and result_dict['time_bidclose'] in result_dict['time_bidopen']:
                result_dict['time_bidclose'] = result_dict['time_bidopen']
            elif len(result_dict['time_bidclose'])>len(result_dict['time_bidopen']) and result_dict['time_bidopen'] in result_dict['time_bidclose']:
                result_dict['time_bidopen'] = result_dict['time_bidclose']
    # 截标时间与开标时间差距过大时,互补修复
    if result_dict['time_bidopen'][:10]>=page_time:
        if result_dict['time_bidclose'][:10] < timeAdd(result_dict['time_bidopen'][:10], -7) and len(dict_time['time_bidclose'])>0:
            result_dict['time_bidclose'] = result_dict['time_bidopen'][:10]
    if result_dict['time_bidclose'][:10]>=page_time:
        if result_dict['time_bidopen'][:10] < timeAdd(result_dict['time_bidclose'][:10], -7) and len(dict_time['time_bidopen'])>0:
            result_dict['time_bidopen'] = result_dict['time_bidclose'][:10]
    # 开始结束对应时间纠错
    for begin_time_type,end_time_type in last_time_index.items():
        if result_dict[end_time_type] and result_dict[end_time_type][:10] < result_dict[begin_time_type][:10]:
            # print('error time',end_time_type,result_dict[end_time_type])
            result_dict[end_time_type] = ""

    return result_dict

def getOtherAttributes(list_entity,page_time,prem,channel_dic):
    dict_other = {"moneysource":"",
                  "person_review":[],
                  "serviceTime":"",
                  "product":[],
                  "total_tendereeMoney":0,
                  "total_tendereeMoneyUnit":''}
    list_serviceTime = []
    last_moneysource_prob = 0
    for entity in list_entity:
        if entity.entity_type == 'bidway':
            dict_other["bidway"] = turnBidWay(entity.entity_text)
        elif entity.entity_type=='moneysource':
            if dict_other["moneysource"] and entity.in_attachment:
                continue
            if not dict_other["moneysource"]:
                dict_other["moneysource"] = entity.entity_text
                last_moneysource_prob = entity.prob
            elif entity.prob>last_moneysource_prob:
                dict_other["moneysource"] = entity.entity_text
                last_moneysource_prob = entity.prob
        elif entity.entity_type=='serviceTime':
            # print(entity.entity_text)
            # if list_serviceTime and entity.in_attachment:
            #     continue
            if re.search("[^之]日|天|年|月|周|星期", entity.entity_text) or re.search("\d{4}[-./]\d{1,2}", entity.entity_text):
                list_serviceTime.append(entity)
        elif entity.entity_type=="person" and entity.label ==4 and entity.entity_text not in dict_other["person_review"]: # 20240624评审专家去重
            dict_other["person_review"].append(entity.entity_text)
        elif entity.entity_type=='product' and entity.entity_text not in dict_other["product"]: #顺序去重保留
            dict_other["product"].append(entity.entity_text)
        elif entity.entity_type=='money' and entity.notes=='总投资' and float(entity.entity_text)>5000000 and float(dict_other["total_tendereeMoney"])<float(entity.entity_text): # 20250702 限制总投资为500万的以上
            dict_other["total_tendereeMoney"] = str(Decimal(entity.entity_text))
            dict_other["total_tendereeMoneyUnit"] = entity.money_unit

    time_contractEnd = prem[0].get("time_contractEnd","")[:10]
    time_contractStart = prem[0].get("time_contractStart","")[:10]
    serviceTime_dict = {"service_start":"", "service_end":"", "service_days": 0}
    if time_contractEnd:
        serviceTime_dict['service_end'] = time_contractEnd
        if time_contractStart:
            if get_days_between(time_contractStart,time_contractEnd)>0:
                serviceTime_dict['service_start'] = time_contractStart
    # print([i.entity_text for i in list_serviceTime])
    if list_serviceTime and not serviceTime_dict['service_end']:
        list_serviceTime_inAtt = [serviceTime for serviceTime in list_serviceTime if serviceTime.in_attachment==1]
        list_serviceTime = [serviceTime for serviceTime in list_serviceTime if serviceTime.in_attachment==0]
        error_serviceTime = []
        for list_time in [list_serviceTime,list_serviceTime_inAtt]:
            if not serviceTime_dict['service_end'] and not serviceTime_dict['service_days']:
                list_time.sort(key=lambda x: (x.prob,-x.sentence_index,-x.begin_index), reverse=True)
                for _serviceTime in list_time:
                    # 优先取具体时间(20XX年x月x日-20XX年x月x日)
                    if re.search("20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?[^。\d半一二三四五六七八九十壹两叁贰肆伍陆柒捌玖拾;；]{,4}20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?",_serviceTime.entity_text):
                        _extract_time,_ = my_timeFormat(_serviceTime.entity_text,page_time)
                        if _extract_time and len(_extract_time)==2:
                            # 排除开始和结束时间一样的错误模板，例：“履约期限：2023年02月15日至2023年02月15日”
                            if _extract_time[0]!=_extract_time[1]:
                                # dict_other["serviceTime"] = _serviceTime.entity_text
                                # extract_time = extract_serviceTime(_serviceTime.entity_text)
                                # if extract_time['service_end']:
                                serviceTime_dict['service_start'] = _extract_time[0]
                                serviceTime_dict['service_end'] = _extract_time[1]
                                break
                            else:
                                error_serviceTime.append(_serviceTime.entity_text)
                if not serviceTime_dict['service_end']:
                    for _serviceTime in list_time:
                        # 优先取具体时间(20XX年x月-20XX年x月)
                        if re.search("20\d{2}[年/.\-]\d{1,2}月?[^。\d半一二三四五六七八九十壹两叁贰肆伍陆柒捌玖拾;；]{,3}20\d{2}[年/.\-]\d{1,2}月?", _serviceTime.entity_text):
                            # dict_other["serviceTime"] = _serviceTime.entity_text
                            extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                            if extract_time['service_end']:
                                serviceTime_dict = extract_time
                                break
                if not serviceTime_dict['service_end']:
                    for _serviceTime in list_time:
                        # 优先取具体时间(20XX年x月x日)
                        if re.search("20\d{2}[年/.\-]\d{1,2}[月/.\-]\d{1,2}日?",_serviceTime.entity_text):
                            if _serviceTime.entity_text not in error_serviceTime:
                                # dict_other["serviceTime"] = _serviceTime.entity_text
                                extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                                if extract_time['service_end']:
                                    serviceTime_dict = extract_time
                                    break
                if not serviceTime_dict['service_end'] and not serviceTime_dict['service_days']:
                    for _serviceTime in list_time:
                        if _serviceTime.entity_text not in error_serviceTime:
                            # dict_other["serviceTime"] = _serviceTime.entity_text
                            extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                            # service_days > 3
                            if extract_time['service_end'] or extract_time['service_days']>3:
                                serviceTime_dict = extract_time
                                break
                # 若上一步仍无结果，取消service_days > 3 的条件
                if not serviceTime_dict['service_end'] and not serviceTime_dict['service_days']:
                    for _serviceTime in list_time:
                        if _serviceTime.entity_text not in error_serviceTime:
                            # dict_other["serviceTime"] = _serviceTime.entity_text
                            extract_time = extract_serviceTime(_serviceTime.entity_text,page_time)
                            if extract_time['service_end'] or extract_time['service_days']:
                                serviceTime_dict = extract_time
                                break

    if serviceTime_dict['service_start'] and serviceTime_dict['service_end']:
        service_days = get_days_between(serviceTime_dict['service_start'],serviceTime_dict['service_end'])
        serviceTime_dict['service_days'] = service_days
    dict_other["serviceTime"] = serviceTime_dict
    if not time_contractEnd and channel_dic['docchannel']['docchannel']=='合同公告': # 用serviceTime补充合同开始结束时间,公告类型为合同公告
        if serviceTime_dict['service_start'] and serviceTime_dict['service_end']:
            prem[0]["time_contractStart"] = serviceTime_dict['service_start']
            prem[0]["time_contractEnd"] = serviceTime_dict['service_end']

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