BIDI_ML_INFO_EXTRACTION/BiddingKG/deepdive/udf/commonutil.py

#coding:utf8

import re
from decimal import *
import logging
logging.basicConfig(level = logging.INFO,format = '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def log(msg):
    logger.info(msg)


def find_index(list,text):
    for item in list:
        index = text.find(item)
        if index>=0:
            return index
    return -1

def get_index_in_tokens(index,tokes):
    length = 0
    i = 0
    for item in tokes:
        if length>=index:
            return i
        length += len(item)
        i += 1
    return -1

def combine(list1,list2):
    result = []
    for item1 in list1:
        for item2 in list2:
            result.append(str(item1)+str(item2))
    return result

def getUnifyMoney(money):
    #print(money)
    
    money = re.sub("[，,]","",money)
    result = Decimal(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":Decimal(1000000000000),"亿":Decimal(100000000),"万":Decimal(10000),"仟":Decimal(1000),"千":Decimal(1000),"佰":Decimal(100),"百":Decimal(100),"拾":Decimal(10),"十":Decimal(10),"元":Decimal(1),"角":round(Decimal(0.1),1),"分":round(Decimal(0.01),2)}
    
    LowMoneypattern = re.compile("^(\d+,?)+(\.\d+)?$")
    BigMoneypattern = re.compile("^[%s]$"%("".join(chnDigits)))
    if re.search(LowMoneypattern,money) is not None:
        return Decimal(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+)?$"),subMoneys[0]) is not None:
                result += Decimal(subMoneys[0])*(MultipleFactor.get(factorUnit))
            elif len(subMoneys[0])==1:
                if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[0]) is not None:
                    result += Decimal(DigitsDic.get(subMoneys[0]))*(MultipleFactor.get(factorUnit))
            else:
                result += Decimal(getUnifyMoney(subMoneys[0]))*(MultipleFactor.get(factorUnit))
            
            if len(subMoneys)>1:
                if re.search(re.compile("^(\d+(,)?)+(\.\d+)?[百千万亿]?\s?(元)?$"),subMoneys[1]) is not None:
                    result += Decimal(subMoneys[1])
                elif len(subMoneys[1])==1:
                    if re.search(re.compile("^[%s]$"%("".join(chnDigits))),subMoneys[1]) is not None:
                        result += Decimal(DigitsDic.get(subMoneys[1]))
                else:
                    result += Decimal(getUnifyMoney(subMoneys[1]))
            break
    return result

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":Decimal(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 getUnifyMoney2(money1):
    chnDigits = ["零", "壹", "贰", "叁", "肆", "伍", "陆", "柒", "捌", "玖"]
    chnFactorUnits = ["兆", "亿", "万", "仟", "佰", "拾","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]$"%("".join(chnDigits)))
    if re.search(LowMoneypattern,money1) is not None:
        result = money1
    else:
        money = re.sub(re.compile("[^%s]"%("".join(chnDigits)+"".join(chnFactorUnits))),'',money1)
        result = 0
        index = 0
        last_Factor_index = -1
        last_factor = -1
        while(index<len(money)):
            if re.search("^[%s]$"%("".join(chnFactorUnits)),money[index]) is not None:
                factor_index = chnFactorUnits.index(money[index])
                if factor_index<last_Factor_index:
                    factor = money[index]
                    temp_result = 0
                    for i in range(last_factor+1,index):
                        if re.search("^[%s]$"%("".join(chnDigits)),money[i]) is not None:
                            if i<index-1:
                                if re.search("^[%s]$"%("".join(chnFactorUnits)),money[i+1]) is not None:
                                    temp_result += DigitsDic.get(money[i])
                            else:
                                temp_result += DigitsDic.get(money[i])
                    result += temp_result*MultipleFactor.get(money[index])
                    last_factor = index
                    last_Factor_index = -1
                else:
                    last_Factor_index = factor_index
            index += 1
        temp_result = 0
        for i in range(last_factor+1,index):
            if re.search("^[%s]$"%("".join(chnDigits)),money[i]) is not None:
                if i<index-1:
                    if re.search("^[%s]$"%("".join(chnFactorUnits)),money[i+1]) is not None:
                        temp_result *= MultipleFactor.get(money[i+1])
                else:
                    temp_result += MultipleFactor.get(money[i])
        result += temp_result
    return str(result)