常用方法

[NSCharacterSet alphanumericCharacterSet];          //所有数字和字母(大小写)
[NSCharacterSet decimalDigitCharacterSet];          //0-9的数字
[NSCharacterSet letterCharacterSet];                //所有字母
[NSCharacterSet lowercaseLetterCharacterSet];       //小写字母
[NSCharacterSet uppercaseLetterCharacterSet];       //大写字母
[NSCharacterSet punctuationCharacterSet];           //标点符号
[NSCharacterSet whitespaceAndNewlineCharacterSet];  //空格和换行符
[NSCharacterSet whitespaceCharacterSet];            //空格

挤压空格

NSString *string = @"   Lorem      ipsum dolar     sit  amet.";
string = [string stringByTrimmingCharactersInSet:[NSCharacterSet whitespaceCharacterSet]];

NSArray *components = [string componentsSeparatedByCharactersInSet:[NSCharacterSet whitespaceCharacterSet]];
components = [components filteredArrayUsingPredicate:[NSPredicate predicateWithFormat:@"self <> ''"]];

string = [components componentsJoinedByString:@" "];
//string = "Lorem ipsum dolar sit amet."

不要用 NSCharacterSet 来分词。 用 CFStringTokenizer 来替代它。