BIDI_ML_INFO_EXTRACTION/BiddingKG/deepdive/test/testOne2.py

#coding:utf8

import re

import time
import psycopg2

conn = psycopg2.connect(dbname="BiddingKM_test_10000",user="postgres",password="postgres",host="192.168.2.101")
    
cursor = conn.cursor()


def getDigitsDic(unit):
    DigitsDic = {"零":0, "壹":1, "贰":2, "叁":3, "肆":4, "伍":5, "陆":6, "柒":7, "捌":8, "玖":9,
                 "〇":0, "一":1, "二":2, "三":3, "四":4, "五":5, "六":6, "七":7, "八":8, "九":9}
    return DigitsDic.get(unit)

def getMultipleFactor(unit):
    MultipleFactor = {"兆":float(1000000000000),"亿":100000000,"万":10000,"仟":1000,"千":1000,"佰":100,"百":100,"拾":10,"十":10,"元":1,"角":0.1,"分":0.01}
    return MultipleFactor.get(unit)

def getUnifyMoney(money):
    #print(money)
    
    money = re.sub("[，,]","",money)
    result = 0
    chnDigits = ["零", "壹", "贰", "叁", "肆", "伍", "陆", "柒", "捌", "玖"]
    chnFactorUnits = ["兆", "亿", "万", "仟", "佰", "拾","元","角","分"]
    lcChnDigits = ["〇", "一", "二", "三", "四", "五", "六", "七", "八", "九"]
    lcChnFactorUnits = ["兆", "亿", "万", "千", "百", "十","元","角","分"]
    
    DigitsDic = {"零":0, "壹":1, "贰":2, "叁":3, "肆":4, "伍":5, "陆":6, "柒":7, "捌":8, "玖":9,
                 "〇":0, "一":1, "二":2, "三":3, "四":4, "五":5, "六":6, "七":7, "八":8, "九":9}
    
    MultipleFactor = {"兆":float(1000000000000),"亿":100000000,"万":10000,"仟":1000,"千":1000,"佰":100,"百":100,"拾":10,"十":10,"元":1,"角":0.1,"分":0.01}
    
    LowMoneypattern = re.compile("^(\d+,?)+(\.\d+)?$")
    BigMoneypattern = re.compile("^[%s]$"%("".join(chnDigits)))
    if re.search(LowMoneypattern,money) is not None:
        return float(money)
    elif re.search(BigMoneypattern,money) is not None:
        return DigitsDic.get(money)
    
    for factorUnit in chnFactorUnits:
        if re.search(re.compile(".*%s.*"%(factorUnit)),money) is not None:
            subMoneys = re.split(re.compile("%s(?!.*%s.*)"%(factorUnit,factorUnit)),money)
            if re.search(re.compile("^(\d+(,)?)+(\.\d+)?$"),subMoneys[0]) is not None:
                result += float(subMoneys[0])*MultipleFactor.get(factorUnit)
            elif len(subMoneys[0])==1:
                if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[0]) is not None:
                    result += DigitsDic.get(subMoneys[0])*MultipleFactor.get(factorUnit)
            else:
                result += float(getUnifyMoney(subMoneys[0]))*MultipleFactor.get(factorUnit)
            
            if len(subMoneys)>1:
                if re.search(re.compile("^(\d+(,)?)+(\.\d+)?[百千万亿]?\s?(元)?$"),subMoneys[1]) is not None:
                    result += float(subMoneys[1])
                elif len(subMoneys[1])==1:
                    if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[1]) is not None:
                        result += DigitsDic.get(subMoneys[1])
                else:
                    result += float(getUnifyMoney(subMoneys[1]))
            break
    return result
    
    
''''''
doc_id = "6cf0f360-9c7f-11e8-9b67-44a8424942f7"
sql = " select tokens,sentence_index from sentences where doc_id='"+doc_id+"' order by sentence_index asc "
cursor.execute(sql)
rows = cursor.fetchall()
for row in rows:
    #text = "，中标金额：人民币（万元）：5,700，万，陆拾柒万玖仟陆佰伍拾元陆角柒分（￥679,650.00）"
    print(row[1])
    tokens = row[0]
    list_tokenbegin = []
    begin = 0
    for i in range(0,len(tokens)):
        list_tokenbegin.append(begin)
        begin += len(str(tokens[i]))
    list_tokenbegin.append(begin+1)
    
    #money_patten = re.compile("((?:#sp#)(?:\d+,?)+(?:.\d{2,4})+(?:#sp#)|(?:(?:#sp#)[零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{1,})+(?:#sp#))*")
    money_patten = re.compile("(([1-9],?(?:\d+,?)+(?:.\d{2,4})?[百千万亿]?[元整]+)|([零壹贰叁肆伍陆柒捌玖拾佰仟萬億十百千万亿元角分]{3,})|(?:[（\(]?([万]?)元[）\)]?[:：]?|[￥¥]+，?)([1-9],?(?:\d+,?)+(?:.\d{2,4})?(?:，?)[百千万亿]?))*")
    
    all_match = re.findall(money_patten,"".join(tokens))
    index = 0
    for i in range(len(all_match)):
        if len(all_match[i][0])>0:
            unit = ""
            if len(all_match[i][1])>0:
                entity_text = all_match[i][1]
            elif len(all_match[i][2])>0:
                entity_text = all_match[i][2]
            else:
                entity_text = all_match[i][4]
                unit = all_match[i][3]
            index += len(all_match[i][0])-len(entity_text)
            #entity_text = getUnifyMoney(all_match[i])
            for j in range(len(list_tokenbegin)):
                if list_tokenbegin[j]==index:
                    begin_index = j
                    break
                elif list_tokenbegin[j]>index:
                    begin_index = j-1
                    break
            index += len(str(entity_text))
            for j in range(len(list_tokenbegin)):
                if list_tokenbegin[j]>=index:
                    end_index = j-1
                    break
            print("".join(tokens))
            print(entity_text)
            print(unit)
            if len(unit)>0:
                entity_text = getUnifyMoney(entity_text)*getMultipleFactor(unit)
            else:
                entity_text = getUnifyMoney(entity_text)
            print(entity_text,begin_index,end_index,index)
        else:
            index += 1