Below this small tool contained has judged unicode whether was the Chinese character, numeral, English, or other characters. The double-byte mark transfers the half-angle mark. Work and so on unicode string of character normalization. Also some can process the multi-sound character the Chinese character to transfer the Pinyin the procedure, but also in reorganization.

#! /usr/bin/env python # - * - coding:GBK - *- """ Chinese character processing tool: Judges unicode whether is the Chinese character, numeral, English, or other characters. The double-byte mark transfers the half-angle mark.""" __author__= " internetsweeper <zhengbin0713@gmail.com> “ __date__= " 2007-08-04 " def is_chinese(uchar: """ judges unicode whether is Chinese character """ if uchar >= u'u4e00' and uchar< =u'u9fa5': return True else: return False def is_number(uchar: """ judges unicode whether is digital """ if uchar >= u'u0030' and uchar< =u'u0039': return True else: return False def is_alphabet(uchar: """ judges unicode whether is English letter """ 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: """ judges whether non-Chinese character, digital and English character """ if not (is_chinese(uchar or is_number(uchar or is_alphabet(uchar: return True else: return False def B2Q(uchar: The """ half-angle transfers double-byte """ inside_code=ord(uchar if inside_code< 0x0020 or inside_code> 0x7e: # Is not the half-angle character on the returns original character return uchar if inside_code==0x0020: # Except the blank space other double-byte half-angle formula is: Half-angle = double-byte - 0xfee0 inside_code=0x3000 else: inside_code+=0xfee0 return unichr(inside_code def Q2B(uchar: The """ double-byte transfers half-angle """ inside_code=ord(uchar if inside_code==0x3000: inside_code=0x0020 else: inside_code-=0xfee0 if inside_code< 0x0020 or inside_code> 0x7e: After # transfers is not the half-angle character returns original character return uchar return unichr(inside_code def stringQ2B(ustring: """ transfers the string of character double-byte half-angle """ return "" .join ([Q2B(uchar for uchar in ustring] def uniform(ustring: The """ formatting string of character, completes the double-byte to transfer the half-angle, the capital letter transfers the small letter work """ return stringQ2B(ustring.lower( def string2List(ustring: """ defers to ustring Chinese, the letter, the numeral separates """ 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'zhongguo personal name a high frequency A' ustring=uniform(ustring ret=string2List(ustring print ret