sunrise

#!/usr/bin/env python
# -*- coding:GBK -*- 
 
"""漢字處理的工具:
判斷unicode是否是漢字，數(shù)字，英文，或者其他字符。
全角符號(hào)轉(zhuǎn)半角符號(hào)。"""
 
def is_chinese(uchar):
        """判斷一個(gè)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(gè)unicode是否是數(shù)字"""
        if uchar >= u'\u0030' and uchar<=u'\u0039':
                return True
        else:
                return False
 
def is_alphabet(uchar):
        """判斷一個(gè)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(shù)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):
        """半角轉(zhuǎn)全角"""
        inside_code=ord(uchar)
        if inside_code<0x0020 or inside_code>0x7e:      #不是半角字符就返回原來的字符
                return uchar
        if inside_code==0x0020: #除了空格其他的全角半角的公式為:半角=全角-0xfee0
                inside_code=0x3000
        else:
                inside_code+=0xfee0
        return unichr(inside_code)
 
def Q2B(uchar):
        """全角轉(zhuǎn)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:      #轉(zhuǎn)完之后不是半角字符返回原來的字符
                return uchar
        return unichr(inside_code)


 
def stringQ2B(ustring):
        """把字符串全角轉(zhuǎn)半角"""
        return "".join([Q2B(uchar) for uchar in ustring])
 
def uniform(ustring):
        """格式化字符串，完成全角轉(zhuǎn)半角，大寫轉(zhuǎn)小寫的工作"""
        return stringQ2B(ustring).lower()
 
def string2List(ustring):
        """將ustring按照中文，字母，數(shù)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