python判斷unicode字元型別
阿新 • • 發佈:2019-01-29
def is_chinese(uchar): """判斷一個unicode是否是漢字""" if uchar >= u'\u4e00' and uchar<=u'\u9fa5': return True else: return False def is_number(uchar): """判斷一個unicode是否是數字""" if uchar >= u'\u0030' and uchar<=u'\u0039': return True else: return False def is_alphabet(uchar): """判斷一個unicode是否是英文字母""" if (uchar >= u'\u0041' and uchar<=u'\u005a') or (uchar >= u'\u0061' and uchar<=u'\u007a'): return True else: return False def is_other(uchar): """判斷是否非漢字,數字和英文字元""" if not (is_chinese(uchar) or is_number(uchar) or is_alphabet(uchar)): return True else: return False def B2Q(uchar): """半形轉全形""" inside_code=ord(uchar) if inside_code<0x0020 or inside_code>0x7e: #不是半形字元就返回原來的字元 return uchar if inside_code==0x0020: #除了空格其他的全形半形的公式為:半形=全形-0xfee0 inside_code=0x3000 else: inside_code+=0xfee0 return unichr(inside_code) def Q2B(uchar): """全形轉半形""" inside_code=ord(uchar) if inside_code==0x3000: inside_code=0x0020 else: inside_code-=0xfee0 if inside_code<0x0020 or inside_code>0x7e: #轉完之後不是半形字元返回原來的字元 return uchar return unichr(inside_code) def stringQ2B(ustring): """把字串全形轉半形""" return "".join([Q2B(uchar) for uchar in ustring]) def uniform(ustring): """格式化字串,完成全形轉半形,大寫轉小寫的工作""" return stringQ2B(ustring).lower() def string2List(ustring): """將ustring按照中文,字母,數字分開""" retList=[] utmp=[] for uchar in ustring: if is_other(uchar): if len(utmp)==0: continue else: retList.append("".join(utmp)) utmp=[] else: utmp.append(uchar) if len(utmp)!=0: retList.append("".join(utmp)) return retList if __name__=="__main__": #test Q2B and B2Q for i in range(0x0020,0x007F): print Q2B(B2Q(unichr(i))),B2Q(unichr(i)) #test uniform ustring=u'中國 人名a高頻A' ustring=uniform(ustring) ret=string2List(ustring) print ret