全角转半角

def sbc_to_dbc(ustring):
    ss = []
    
    for s in ustring:
        rstring = ""
        
        for uchar in s:
            inside_code = ord(uchar)
            
            if inside_code == 12288:  # 全角空格直接转换
                inside_code = 32
            elif (inside_code >= 65281 and inside_code <= 65374):  # 全角字符（除空格）根据关系转化
                inside_code -= 65248
                
            rstring += chr(inside_code)
            
        ss.append(rstring)
    return ''.join(ss)

替换内容，此处实际应用中可以根据规则定义在配置文件，或者数据库表中。type为1，表示文本替换，type为2表示正则替换，注意的是，这个替换规则是有处理顺序的

replaces =[
    {"src":"毫克","type":1,"dest":"mg"},
    {"src":"克","type":1,"dest":"g"},
    {"src":"毫升","type":1,"dest":"ml"},
    {"src":"升","type":1,"dest":"l"},
    {"src":"公斤","type":1,"dest":"kg"},
    {"src":"。","type":1,"dest":" "},
    {"src":",","type":1,"dest":" "},
    {"src":"x","type":1,"dest":"*"},
    {"src":"×","type":1,"dest":"*"},
    {"src":" +","type":2,"dest":" "}
]
def text_replace(txt):
    for item in replaces:
        replace_type = item["type"]
        src = item["src"]
        dest = item["dest"]
        
        if replace_type == 1:
            txt = txt.replace(src,dest)
        elif replace_type == 2:
            txt = re.sub(src,dest,txt)
    
    return txt

标准化方法，移除两边空格和换行符，并转换成小写

def normalize(txt):
    return text_replace(sbc_to_dbc(txt.strip().lower()))