BIDI_ML_INFO_EXTRACTION/BiddingKG/maxcompute/documentDumplicate.py

#coding:UTF8
from odps.udf import annotate
from odps.udf import BaseUDTF
from odps.udf import BaseUDAF

@annotate('string,string -> string,bigint,bigint,string,string,string,string,string,string,string,string,string,string,string,string,string,string,bigint')
class f_decode_extract(BaseUDTF):

    def __init__(self):
        import logging
        import json
        import time,re
        global json,logging,time,re
        self.time_pattern = "\d{4}\-\d{2}\-\d{2}.*"
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self, extractjson,otherjson):
        if extractjson is not None:
            _extract = json.loads(extractjson)
        else:
            _extract = {}
        if otherjson is not None:
            _other = json.loads(otherjson)
        else:
            _other = {}
        project_code = ""
        project_name = ""
        tenderee = ""
        agency = ""
        win_tenderer = ""
        bidding_budget = ""
        win_bid_price = ""
        page_time_stamp = 0
        docchannel = 0
        extract_count = 0
        page_time = _other.get("pageTime",time.strftime('%Y-%m-%d',time.localtime()))
        doctitle = _other.get("doctitle","")
        doctitle_refine = re.sub(r'工程|服务|询价|比价|谈判|竞争性|磋商|结果|中标|招标|采购|的|公示|公开|成交|公告|评标|候选人|交易|通知|废标|流标|终止|中止|一笔|预告|单一来源|询价|竞价', '',  doctitle)
        area = _other.get("area","")
        province = _other.get("province","")
        city = _other.get("city","")
        district = _other.get("district","")
        web_source_no = _other.get("webSourceNo","")
        docchannel = _other.get("docchannel",0)
        if re.search(self.time_pattern,page_time) is not None:
            timeArray = time.strptime(page_time[:11], "%Y-%m-%d")
            page_time_stamp = int(time.mktime(timeArray))
        list_code = _extract.get("code",[])
        if len(list_code)>0:
            project_code = list_code[0]
        project_name = _extract.get("name","")
        dict_pack = _extract.get("prem",{})
        logging.info(dict_pack)
        for _key in dict_pack.keys():
            if dict_pack[_key]["tendereeMoney"]!='' and float(dict_pack[_key]["tendereeMoney"])>0:
                extract_count += 1
                if bidding_budget=="":
                    bidding_budget = str(dict_pack[_key]["tendereeMoney"])
            for _role in dict_pack[_key]["roleList"]:
                extract_count += 1
                if _role[2]!='' and float(_role[2])>0:
                    extract_count += 1
                if _role[0]=="tenderee":
                    tenderee = _role[1]
                if _role[0]=="win_tenderer":
                    if  win_tenderer=="":
                        win_tenderer = _role[1]
                    if _role[2]!='' and float(_role[2])>0:
                        if win_bid_price=="":
                            win_bid_price = str(_role[2])
                if _role[0]=="agency":
                    agency = _role[1]


        if project_code!="":
            extract_count += 1
        if project_name!="":
            extract_count += 1
        logging.info(page_time+doctitle+doctitle_refine+area+province+city+
                     district+web_source_no+project_code+project_name+tenderee+agency+win_tenderer+bidding_budget+win_bid_price)
        self.forward(page_time,page_time_stamp,docchannel,doctitle,doctitle_refine,area,province,city,
                     district,web_source_no,project_code,project_name,tenderee,agency,win_tenderer,bidding_budget,win_bid_price,extract_count)

@annotate('string,string,string,string,string -> string,string,string,bigint')
class f_decode_sub_docs_json(BaseUDTF):

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self, project_code,project_name,tenderee,agency,sub_docs_json):
        columns = {"win_tenderer":"","bidding_budget":"","win_bid_price":""}
        extract_count = 0
        if project_code!="":
            extract_count += 1
        if project_name!="":
            extract_count += 1
        if tenderee!="":
            extract_count += 1
        if agency!="":
            extract_count += 1
        if sub_docs_json is not None:
            for sub_docs in json.loads(sub_docs_json):
                for _key_sub_docs in sub_docs.keys():
                    extract_count += 1
                    if _key_sub_docs in columns:
                        if columns[_key_sub_docs]=="" and str(sub_docs[_key_sub_docs]) not in ["","0"]:
                            if _key_sub_docs in ["bidding_budget","win_bid_price"]:
                                if float(sub_docs[_key_sub_docs])>0:
                                    columns[_key_sub_docs] = str(sub_docs[_key_sub_docs])
                            else:
                                columns[_key_sub_docs] = str(sub_docs[_key_sub_docs])
        self.forward(columns["win_tenderer"],columns["bidding_budget"],columns["win_bid_price"],extract_count)

@annotate("string->bigint")
class totimestamp(object):

    def __init__(self):
        import time
        global time
        import logging
        import json
        import re
        global json,logging,re
        self.time_pattern = "\d{4}\-\d{2}\-\d{2}.*"
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def evaluate(self, str_time):
        try:
            logging.info(str_time)
            if str_time is not None and re.search(self.time_pattern,str_time) is not None:
                timeArray = time.strptime(str_time[:10], "%Y-%m-%d")
                timeStamp = int(time.mktime(timeArray))
                return timeStamp
            else:
                return 0
        except Exception as e:
            return 0

@annotate("string->string")
class refind_name(object):

    def __init__(self):
        import logging
        import re
        global logging,re
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def evaluate(self, title):
        if title is not None:
            return re.sub(r'工程|服务|询价|比价|谈判|竞争性|磋商|结果|中标|招标|采购|的|公示|公开|成交|公告|评标|候选人|交易|通知|废标|流标|终止|中止|一笔|预告|单一来源|询价|竞价', '',  title)
        return ""


@annotate('bigint,bigint,bigint,string,bigint,string->string')
class f_set_docid(BaseUDAF):
    '''
    项目编号、中标单位、len(项目编号)>7、中标单位<> ""
    '''

    def __init__(self):
        import json
        global json

    def new_buffer(self):
        return [[]]

    def iterate(self, buffer,docid, page_time_stamp,extract_count,defind_column,defind_count,tenderee):
        buffer[0].append({"docid":docid,"page_time_stamp":page_time_stamp,"extract_count":extract_count,
                          "defind_column":defind_column,"defind_count":defind_count,"tenderee":tenderee})

    def merge(self, buffer, pbuffer):
        buffer[0].extend(pbuffer[0])

    def terminate(self, buffer):
        list_docs = buffer[0]
        list_docs.sort(key=lambda x:x["page_time_stamp"])
        list_group = []
        _begin = 0
        defind_count = 0
        if len(list_docs)>0:
            defind_count = list_docs[0]["defind_count"]
        for i in range(len(list_docs)-1):
            if abs(list_docs[i]["page_time_stamp"]-list_docs[i+1]["page_time_stamp"])<=86400*2:
                continue
            else:
                _group = []
                _set_column = set()
                _set_tenderee = set()
                for j in range(_begin,i+1):
                    _set_tenderee.add(list_docs[j]["tenderee"])
                    _set_column.add(list_docs[j]["defind_column"])
                    _group.append({"docid":list_docs[j]["docid"],"extract_count":list_docs[j]["extract_count"]})

                if len(_group)>=3 and len(_set_tenderee)>1:
                    pass
                else:
                    if len(_group)>1:
                        if defind_count==2:
                            if len(_set_column)>=2:
                                list_group.append(_group)
                        elif defind_count==1:
                            if len(_set_column)==1:
                                list_group.append(_group)
                        elif defind_count==0:
                            list_group.append(_group)

                _begin = i+1
        if len(list_docs)>1:
            _set_column = set()
            _set_tenderee = set()
            _group = []
            for j in range(_begin,len(list_docs)):
                if list_docs[j]["tenderee"] is not None and list_docs[j]["tenderee"]!="":
                    _set_tenderee.add(list_docs[j]["tenderee"])
                _set_column.add(list_docs[j]["defind_column"])
                _group.append({"docid":list_docs[j]["docid"],"extract_count":list_docs[j]["extract_count"]})
            if len(_group)>=3 and len(_set_tenderee)>1:
                pass
            else:
                if len(_group)>1:
                    if defind_count==2:
                        if len(_set_column)>=2:
                            list_group.append(_group)
                    elif defind_count==1:
                        if len(_set_column)==1:
                            list_group.append(_group)
                    elif defind_count==0:
                        list_group.append(_group)

        return json.dumps(list_group)


@annotate('bigint->string')
class f_stamp_squence(BaseUDAF):
    '''
    项目编号、中标单位、len(项目编号)>7、中标单位<> ""
    '''

    def __init__(self):
        import json
        global json
        import logging
        global logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def new_buffer(self):
        return [set()]

    def iterate(self, buffer,page_time_stamp):
        buffer[0].add(page_time_stamp)

    def merge(self, buffer, pbuffer):
        buffer[0] |= pbuffer[0]

    def terminate(self, buffer):
        if 0 in buffer[0]:
            buffer[0].remove(0)
        list_stamp = list(buffer[0])
        list_stamp.sort(key=lambda x:x)
        list_stamp_final = []
        _begin = 0
        _time_decase = 86400*2
        logging.info(str(list_stamp))
        for _index in range(len(list_stamp)-1):
            if list_stamp[_index+1]-list_stamp[_index]<_time_decase:
                continue
            else:
                list_stamp_final.append([list_stamp[_begin]-_time_decase,list_stamp[_index]+_time_decase])
                _begin = _index+1
        if len(list_stamp)>0:
            list_stamp_final.append([list_stamp[_begin]-_time_decase,list_stamp[-1]+_time_decase])

        return json.dumps(list_stamp_final)

@annotate("bigint,string->bigint")
class in_stamp(object):

    def __init__(self):
        import logging
        import re
        import json
        global logging,re,json
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def evaluate(self, page_time_stamp,json_stamp):
        list_stamp = json.loads(json_stamp)
        int_flag = 0
        for item in list_stamp:
            if page_time_stamp <item[0]:
                break
            if page_time_stamp>item[0] and page_time_stamp<item[1]:
                int_flag = 1
                break
        return int_flag

@annotate('string -> bigint,bigint,bigint,bigint')
class f_split_group_single(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self, json_set_docid):
        list_group = json.loads(json_set_docid)
        for item in list_group:
            for index_i in range(len(item)):
                for index_j in range(len(item)):
                    if index_i!=index_j and item[index_i]["docid"]!=item[index_j]["docid"]:
                        self.forward(item[index_i]["docid"],item[index_j]["docid"],item[index_i]["extract_count"],item[index_j]["extract_count"])


@annotate('bigint,string->string')
class group_document(BaseUDAF):
    '''
    项目编号、中标单位、len(项目编号)>7、中标单位<> ""
    '''

    def __init__(self):
        import json
        global json

    def new_buffer(self):
        return [[]]

    def iterate(self, buffer,id,json_set_docid):
        buffer[0].append({"id":id,"json_set_docid":json.loads(json_set_docid)})

    def merge(self, buffer, pbuffer):
        buffer[0].extend(pbuffer[0])

    def terminate(self, buffer):
        return json.dumps(buffer[0])

@annotate('bigint,string,bigint,string -> bigint,bigint,string')
class decare_document(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,group_id1, json_list_doc1,group_id2,json_list_doc2):
        #y=x，少掉近一半的数据
        if group_id1>=group_id2:
            list_doc1 = json.loads(json_list_doc1)
            list_doc2 = json.loads(json_list_doc2)
            for _doc1 in list_doc1:
                for _doc2 in list_doc2:
                    #同一个重复group不做判断
                    if _doc1["id"]!=_doc2["id"]:
                        #判断两个group是否有重复
                        _set1 = set()
                        for _item1 in _doc1["json_set_docid"]:
                            _set1.add(_item1["docid"])
                        _set2 = set()
                        for _item2 in _doc2["json_set_docid"]:
                            _set2.add(_item2["docid"])
                        if len(_set1&_set2)>0:
                            new_json_set_docid = _doc1["json_set_docid"]
                            for _item2 in _doc2["json_set_docid"]:
                                if _item2["docid"] not in _set1:
                                    new_json_set_docid.append(_item2)
                            self.forward(_doc1["id"],_doc2["id"],json.dumps(new_json_set_docid))

@annotate('bigint,bigint,bigint,bigint->string')
class choose_document(BaseUDAF):
    '''
    项目编号、中标单位、len(项目编号)>7、中标单位<> ""
    '''

    def __init__(self):
        import json
        global json

    def new_buffer(self):
        return [[]]

    def iterate(self, buffer,docid1,extract_count1,docid2,extract_count2):
        buffer[0].append([docid1,extract_count1,docid2,extract_count2])

    def merge(self, buffer, pbuffer):
        buffer[0].extend(pbuffer[0])

    def terminate(self, buffer):
        list_pair = buffer[0]
        list_pair.sort(key=lambda x:x[3],reverse=True)
        _max_count = list_pair[0][3]
        save_flag = 0
        list_dumplicate = []
        _set = set()
        for item in buffer[0]:
            _set.add(str(item[2]))
        #不包含这条公告
        # _set.add(list_pair[0][0])
        if list_pair[0][1]>_max_count:
            save_flag = 1
            # _set.remove(list_pair[0][0])
            list_dumplicate = list(_set)
        else:
            if list_pair[0][1]<_max_count:
                save_flag = 0
            else:
                less_docid = list_pair[0][0]
                for item in list_pair:
                    if item[3]>=_max_count and item[2]<less_docid:
                        less_docid = item[2]
                if less_docid==list_pair[0][0]:
                    save_flag = 1
                else:
                    save_flag = 0
            list_dumplicate = list(_set)
        return json.dumps({"save_flag":save_flag,"dumplicates":list_dumplicate})


@annotate('string -> bigint,string')
class f_get_choose_document(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,json_choose):
        if json_choose is None:
            self.forward(1,None)
        else:
            _choose = json.loads(json_choose)
            self.forward(_choose["save_flag"],",".join(_choose["dumplicates"]))

@annotate('bigint,bigint,bigint,bigint->string')
class group_document_bestFirst(BaseUDAF):
    '''
    将组里面最优的放在前面
    '''

    def __init__(self):
        import json
        global json

    def new_buffer(self):
        return [[]]

    def iterate(self, buffer,docid1,extract_count1,docid2,extract_count2):
        buffer[0].append([docid1,extract_count1,docid2,extract_count2])

    def merge(self, buffer, pbuffer):
        buffer[0].extend(pbuffer[0])

    def terminate(self, buffer):
        list_pair = buffer[0]
        list_pair.sort(key=lambda x:x[3],reverse=True)
        _max_count = list_pair[0][3]
        save_flag = 0
        list_dumplicate = []
        _set = set()
        for item in buffer[0]:
            _set.add(item[2])
        _set.add(list_pair[0][0])
        best_docid = None
        if list_pair[0][1]>_max_count:
            best_docid = list_pair[0][0]
        else:
            best_docid = list_pair[0][2]
            for item in list_pair:
                if item[3]>=_max_count and item[2]<best_docid:
                    best_docid = item[2]
        _set.remove(best_docid)
        list_dumplicate = list(_set)
        list_dumplicate.sort(key=lambda x:x)
        list_dumplicate.insert(0,best_docid)
        list_dumplicate_str = []
        for item in list_dumplicate:
            list_dumplicate_str.append(str(item))
        return ",".join(list_dumplicate_str)

@annotate('string -> bigint,string')
class f_get_best_dumplicates(BaseUDTF):
    '''
    得到每个分组中最优的那一条及其重复记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,list_dumplicate_str):
        if list_dumplicate_str is None:
            pass
        else:
            list_dumplicate = list_dumplicate_str.split(",")
            if len(list_dumplicate)>0:
                self.forward(int(list_dumplicate[0]),",".join(list_dumplicate[1:]))
            else:
                pass

@annotate('bigint,bigint->string')
class bridge2group(BaseUDAF):
    '''
    项目编号、中标单位、len(项目编号)>7、中标单位<> ""
    '''

    def __init__(self):
        import json
        global json

    def new_buffer(self):
        return [set()]

    def iterate(self, buffer,docid1,docid2):
        buffer[0].add(docid1)
        buffer[0].add(docid2)

    def merge(self, buffer, pbuffer):
        buffer[0] |= pbuffer[0]

    def terminate(self, buffer):
        list_pair = list(buffer[0])
        list_pair.sort(key=lambda x:x,reverse=True)
        return json.dumps(list_pair)

@annotate('string -> bigint,bigint')
class group2bridge(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,json_list_docid):
        list_docid = json.loads(json_list_docid)
        for _docid in list_docid:
            self.forward(list_docid[-1],_docid)

@annotate('bigint,bigint,string -> bigint')
class f_get_dump_docid(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,docid,save_flag,dumplicates):
        if save_flag==0:
            self.forward(docid)
            if dumplicates is not None:
                list_docid = dumplicates.split(",")
                if len(list_docid)>0:
                    for _docid in list_docid[1:]:
                        self.forward(int(_docid))
        else:
            if dumplicates is not None:
                list_docid = dumplicates.split(",")
                if len(list_docid)>0:
                    for _docid in list_docid:
                        self.forward(int(_docid))

@annotate('string -> bigint,bigint')
class f_get_docid(BaseUDTF):
    '''
    将多个组拆解成多条记录
    '''

    def __init__(self):
        import logging
        import json
        global json,logging
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def process(self,json_set_docid):
        team_id = 0
        if json_set_docid is not None:
            list_docses = json.loads(json_set_docid)
            for list_docs in list_docses:
                team_id += 1
                for item in list_docs:
                    self.forward(team_id,item["docid"])

@annotate("string->bigint")
class get_count_dump(object):

    def __init__(self):
        import logging
        import re
        global logging,re
        logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')

    def evaluate(self, title):
        _count = 0
        if title is not None:
            _count = len(title.split(","))
        return _count