http://wiki.python.cn/moin/MicroProj/2007-08-07
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96
|
"""汉字处理的工具: 判断unicode是否是汉字,数字,英文,或者其他字符。 全角符号转半角符号。"""
__author__="internetsweeper <zhengbin0713@gmail.com>" __date__="2007-08-04"
def is_chinese(uchar): """判断一个unicode是否是汉字""" if uchar >= u'\u4e00' and uchar<=u'\u9fa5': return True else: return False
def is_number(uchar): """判断一个unicode是否是数字""" if uchar >= u'\u0030' and uchar<=u'\u0039': return True else: return False
def is_alphabet(uchar): """判断一个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): """判断是否非汉字,数字和英文字符""" if not (is_chinese(uchar) or is_number(uchar) or is_alphabet(uchar)): return True else: return False
def B2Q(uchar): """半角转全角""" inside_code=ord(uchar) if inside_code<0x0020 or inside_code>0x7e: return uchar if inside_code==0x0020: inside_code=0x3000 else: inside_code+=0xfee0 return unichr(inside_code)
def Q2B(uchar): """全角转半角""" inside_code=ord(uchar) if inside_code==0x3000: inside_code=0x0020 else: inside_code-=0xfee0 if inside_code<0x0020 or inside_code>0x7e: return uchar return unichr(inside_code)
def stringQ2B(ustring): """把字符串全角转半角""" return "".join([Q2B(uchar) for uchar in ustring])
def uniform(ustring): """格式化字符串,完成全角转半角,大写转小写的工作""" return stringQ2B(ustring).lower()
def string2List(ustring): """将ustring按照中文,字母,数字分开""" 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__": for i in range(0x0020,0x007F): print Q2B(B2Q(unichr(i))),B2Q(unichr(i))
ustring=u'中国 人名a高频A' ustring=uniform(ustring) ret=string2List(ustring) print ret
|