import pandas, re
# ⌃R을(를) 눌러 실행하거나 내 코드로 바꿉니다.
# 클래스, 파일, 도구 창, 액션 및 설정을 어디서나 검색하려면 ⇧ 두 번을(를) 누릅니다.


def load_excel(filename):
    df = pandas.read_excel(filename, engine="openpyxl")
    df = df[['po_idx_통합', 'po_idx_공구', 'po_idx_할인', 'po_idx_심쿵', 'po_title_통합', 'po_keyword_통합']]
    df.to_feather("./data.feather")
    return df

def getblacketedDics(terms, list):
    terms = re.sub(r"\s","",terms).lower()
    s = re.findall(r"\[(.*?)\]", terms)
    for i in range(len(s)):
        list.append(s[i])
    return s

def getblacketedTerm(terms, diclist):
    terms = re.sub(r"\s","",terms).lower()
    s = re.findall(r"\[(.*?)\]", terms)
    res = ''
    for i in range(len(s)):
        if s[i] in diclist:
            res = res + str(s[i])
            res = res + ","
    res = re.sub(r"\,$","",res)
    return res

def getblandTerm(terms, diclist):
    terms = re.sub(r"\s","",terms).lower()
    s = re.findall(r"\[(.*?)\]", terms)
    res = ''
    for i in range(len(s)):
        if s[i] not in diclist:
            res = res + str(s[i])
            res = res + ","
    res = re.sub(r"\,$","",res)
    return res

def load_branddic():
    dicfilename = "./branddic_20230420.xlsx"
    df = pandas.read_excel(dicfilename, engine="openpyxl")
    return df[0].values.tolist()

def load_brandblackdic():
    dicfilename = "./branddic_blacklist_20230420.xlsx"
    df = pandas.read_excel(dicfilename, engine="openpyxl")
    return df[0].values.tolist()

if __name__ == '__main__':
    datadf = pandas.read_feather("./data.feather")
    #diclist = load_branddic()
    diclist = load_brandblackdic()

    #datadf['branddic'] = datadf.apply(lambda x:getblacketedTerm(x['po_title_통합'], diclist), axis=1)
    datadf['branddic'] = datadf.apply(lambda x: getblandTerm(x['po_title_통합'], diclist), axis=1)
    datadf.to_excel("./_tmpTest.xlsx")
    #print(datadf.info())
    #print(dic)



# https://www.jetbrains.com/help/pycharm/에서 PyCharm 도움말 참조
    #df = load_excel("./20230420_통합상품_키워드.xlsx")
    #상품명 다른 케이스 리뷰
    #sdf = df[(df['po_title_통합'] != df['po_title_공구']) & (df['po_title_공구'].notnull())]
    #sdf = sdf[['po_idx_통합','po_title_통합','po_title_공구']]
    #print(sdf)
    #sdf.to_excel("./tmpTest.xlsx")
    #통합명만 써도 됨...
    #
    #print(df.info())

    #Build 기본 사전 데이터 밑 데이터
    #df = pandas.read_feather("./data.feather")
    #diclist = []
    #df['blacked'] = df.apply(lambda x: getblacketedDics(x['po_title_통합'], diclist), axis=1)
    #df.to_excel("./tmpTest.xlsx")
    #diclist = list(set(diclist))
    #dicdf = pandas.DataFrame(diclist)
    #dicdf.to_excel("./dic.xlsx")
    #print(dicdf)
    #엑셀로 받아 사전을 빌드하여 branddic이름으로 저장.