python 字符处理代码 1.0

最新推荐文章于 2022-07-05 23:04:51 发布

原创最新推荐文章于 2022-07-05 23:04:51 发布 · 506 阅读

0 ·

CC 4.0 BY-SA版权

python 专栏收录该内容

3 篇文章

订阅专栏

本文介绍了一种使用 Python 进行字符串处理的方法，包括如何转换全角字符为半角字符、检查字符串编码类型、过滤特殊字符等。此外，还详细讲解了如何处理 Unicode 字符和字符串，例如判断字符类型、提取特定字符集、验证字符串格式等。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#! /usr/bin/env python
# -*- coding: gbk -*-
import os
import string

class CBunchStrTools:
@staticmethod
def Atoa(num):
str0 = '%d' %num
return str0
@staticmethod
def strQ2B(ustring):
"""把字符串全角转半角"""
rstring = ""
for uchar in ustring:
inside_code=ord(uchar)
if inside_code==0x3000:
inside_code=0x0020
else:
inside_code-=0xfee0
if inside_code<0x0020 or inside_code>0x7e: #转完之后不是半角字符返回原来的字符
rstring += uchar
rstring += unichr(inside_code)
return rstring
@staticmethod
def CheckCodeType(str):
code_type = 0
strlen = len(str)
i = 0
while True:
if i >= strlen :
return code_type
# 1(129-254) 2(64-254)
#print ord(str[i])
if (ord(str[i]) == 10) or (ord(str[i]) == 14) or (ord(str[i]) == 32) or (ord(str[i]) >= ord('A') and ord(str[i]) <= ord('Z')) or (ord(str[i]) >= ord('a') and ord(str[i]) <= ord('z')) or (ord(str[i]) >= ord('0') and ord(str[i]) <= ord('9')):
code_type = code_type | 0x01
i = i + 1
continue

elif (i + 1) < strlen:
if ord(str[i]) >= 129 and ord(str[i]) <= 254 and ord(str[i + 1]) >= 64 and ord(str[i + 1]) <= 254:
code_type = code_type | 0x2;
i = i + 2
continue
else:
return code_type

else:
print str[i]
return 0
#false mean not find ,true mean find it
@staticmethod
def FilterSpeChar(str):
tmpStr = "`!@$%^&*()=[]{}\\|:;\"\',/<>?"
for tmpChar in tmpStr:
if str.find(tmpChar) < 0:
continue
else:
return False
return True

#false mean not find ,true mean find it
@staticmethod
def FilterSpeHz(str):
tmpStr = "~~！@#￥%……&*（）【】｛｝：；“‘《》，。？、"

for tmpChar in tmpStr:
if str.find(tmpChar) < 0:
continue
else:
return True
return False

class CUnicodeChar:
@staticmethod
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

@staticmethod
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

@staticmethod
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

@staticmethod
def is_other(uchar):
"""判断是否非汉字，数字和英文字符"""
if not (CUnicodeChar.is_chinese(uchar) or CUnicodeChar.is_number(uchar) or CUnicodeChar.is_alphabet(uchar)):
return True
else:
return False

@staticmethod
def B2Q(uchar):
"""半角转全角"""
inside_code=ord(uchar)
if inside_code<0x0020 or inside_code>0x7e: #不是半角字符就返回原来的字符
return uchar
if inside_code==0x0020: #除了空格其他的全角半角的公式为:半角=全角-0xfee0
inside_code=0x3000
else:
inside_code+=0xfee0
return unichr(inside_code)

@staticmethod
def Q2B(uchar):
"""全角转半角"""
inside_code=ord(uchar)
if inside_code==0x3000:
inside_code=0x0020
else:
inside_code-=0xfee0

class CUnicodeStr:
def test(self):
pass
#处理unicode字符
@staticmethod
def DealSpace(ustr):
str0 = ustr.strip()
str1 = ustr.replace(" ", " ")
str1 = " ".join(str1.split())
return str1

@staticmethod
def IsDigitStr(str):
d1 = str.split(".")
if str.isdigit():
return True
elif len(d1) == 2:
if d1[0].isdigit() and d1[1].isdigit():
return True

return False

@staticmethod
def IsAlphabetlt3Str(str):
for ch in str:
if CUnicodeChar.is_alphabet(ch) or CUnicodeChar.is_number(ch):
continue
else:
return False
if len(str) < 3:
return True
else:
return False

@staticmethod
def IsFirstIsTip(str):
if str.replace(" ", "") == "":
return False
str = str.strip()
if str[0] == ".":
return True
return False

@staticmethod
def IsLastIsTip(str):
if str.replace(" ", "") == "":
return False
str = str.strip()
if str[len(str) - 1] == ".":
return True
return False

@staticmethod
def IsDigitThenChar(str):
if len(str) < 2:
return False
flag = 0
digitstr = ""
for ch in str:
#判断存在小数点和数字符号
if CUnicodeChar.is_number(ch) or ch == ".":
digitstr = digitstr + ch
if flag == 2:
return False
elif flag == 1 or flag == 0:
flag = 1
continue
else:
return False

#判断是数字
if CUnicodeStr.IsDigitStr(digitstr):
pass
else:
return False

if CUnicodeChar.is_alphabet(ch):
if flag == 0:
return False
else:
flag = 2
continue
if flag == 2:
return True
else:
return False
@staticmethod
def IsNumAndChar(str):
str = str.strip()
if len(str) <1:
return False
for ch in str:
if CUnicodeChar.is_number(ch) or CUnicodeChar.is_alphabet(ch) or ch == "." or ch == " ":
continue
else:
return False
return True

return False
@staticmethod
def IsCharThenDigit(str):
if len(str) < 2:
return False
flag = 0
for ch in str:
if CUnicodeChar.is_alphabet(ch):
if flag == 2:
return False
elif flag == 1 or flag == 0:
flag = 1
continue
else:
return False

if CUnicodeChar.is_number(ch) or ch == ".":
if flag == 0:
return False
else:
flag = 2
continue
if flag == 2:
return True
else:
return False

@staticmethod
def GetAlphabetFromStr(str):
tmpstr = ""
for ch in str:
if CUnicodeChar.is_alphabet(ch):
tmpstr = tmpstr + ch

return tmpstr

@staticmethod
def GetHzFromStr(str):
tmpstr = ""
for ch in str:
if CUnicodeChar.is_chinese(ch):
tmpstr = tmpstr + ch

return tmpstr

@staticmethod
def IsDigitThenHz(str):
if len(str) < 2:
return False
flag = 0
digitstr = ""
for ch in str:
if CUnicodeChar.is_number(ch) or ch == ".":
digitstr = digitstr + ch
if flag == 2:
return False
elif flag == 1 or flag == 0:
flag = 1
continue
else:
return False

#判断是数字
if CUnicodeStr.IsDigitStr(digitstr):
pass
else:
return False

if CUnicodeChar.is_chinese(ch):
if flag == 0:
return False
else:
flag = 2
continue
if flag == 2:
return True
else:
return False

@staticmethod
def IsKeyWordStr(str):
#为空格去掉
if str.replace(" ", "") == "":
return False

str = str.strip()
#全数字去掉
if CUnicodeStr.IsDigitStr(str):
return False

#第一个字符是"."
if CUnicodeStr.IsFirstIsTip(str):
return False

#最后一个是"."去掉
if CUnicodeStr.IsLastIsTip(str):
return False

#全字母小于三个
if CUnicodeStr.IsAlphabetlt3Str(str):
return False
for ch in str:
#if CUnicodeChar.is_chinese(ch) or CUnicodeChar.is_number(ch) or CUnicodeChar.is_alphabet(ch) or ch == '.' or ch.isspace():
if CUnicodeChar.is_chinese(ch) or CUnicodeChar.is_number(ch) or CUnicodeChar.is_alphabet(ch) or ch == '.' or ch.isspace() or ch == '-' or ch == '#' or ch == '~':
continue
else:
#g_Log.debug("IsKeyWordStr is false as result of : " + ch)
return False
#g_Log.debug("IsKeyWordStr is true")
return True

@staticmethod
def stringQ2B(ustring):
"""把字符串全角转半角"""
return "".join([CUnicodeChar.Q2B(uchar) for uchar in ustring])

@staticmethod
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 CUnicodeStr.stringQ2B(ustring).lower()
@staticmethod
def string2List(ustring):
"""将ustring按照中文，字母，数字分开"""
retList=[]
utmp=[]
for uchar in ustring:
if CUnicodeChar.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