python是个什么东西---python---python的字符处理
# -*- coding:UTF-8 -*-"""字符处理的工具:
判断unicode是否是中文,日文,数字,英文,或者其他字符。
全角符号转半角符号。"""
def is_number(self, 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_other(self, uchar):
"""判断是否非汉字，数字和英文字符"""
if not (self.is_unicode(uchar) or self.is_number(uchar) or self.is_alphabet(uchar)):
return True
else:
return False
def is_alphabet(self, 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_unicode(self, uchar):
"""判断一个unicode是否是汉字"""
# \u4e00-\u9fa5 (中文)
# \u0800-\u4e00 (日文)
if uchar >= u'\u4e00' and uchar <= u'\u9fa5':
return True
elif uchar >= u'\u0800' and uchar <= u'\u4e00':
return True
else:
return False
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_code0x7e: #转完之后不是半角字符返回原来的字符
return uchar
return unichr(inside_code)
def stringQ2B(ustring):
"""把字符串全角转半角"""
return "".join()
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__":
# #test Q2B and B2Q
# for i in range(0x0020,0x007F):
# print Q2B(B2Q(unichr(i))),B2Q(unichr(i))
#test uniform
ustring = u'中国 人名ａ高频Ａ'
ustring = uniform(ustring)
ret = string2List(ustring)
print ret
页:
[1]