避免unicode字符被截断的方法

Posted 2021-01-08 oyhj

NSString *str = @"????????";
NSRange range = NSMakeRange(2, str.length - 2);
NSString *subStr = [str substringWithRange:range];

这里的str.length = 8，因为字符串是unicode格式，一个字符是4个字节组合表示的。

- (NSString *)utf8ToUnicode:(NSString *)string{
    
    NSUInteger length = [string length];
    NSMutableString *str = [NSMutableString stringWithCapacity:0];
    for (int i = 0;i < length; i++){
        NSMutableString *s = [NSMutableString stringWithCapacity:0];
        unichar _char = [string characterAtIndex:i];
        // 判断是否为英文和数字
        if (_char <= ‘9‘ && _char >=‘0‘){
            [s appendFormat:@"%@",[string substringWithRange:NSMakeRange(i,1)]];
        }else if(_char >=‘a‘ && _char <= ‘z‘){
            [s appendFormat:@"%@",[string substringWithRange:NSMakeRange(i,1)]];
        }else if(_char >=‘A‘ && _char <= ‘Z‘)
        {
            [s appendFormat:@"%@",[string substringWithRange:NSMakeRange(i,1)]];
        }else{
            // 中文和字符
            [s appendFormat:@"\u%x",[string characterAtIndex:i]];
            // 不足位数补0 否则解码不成功
            if (s.length == 4) {
                [s insertString:@"00" atIndex:2];
            } else if (s.length == 5) {
                [s insertString:@"0" atIndex:2];
            }
        }
        [str appendFormat:@"%@", s];
    }
    return str;
}

NSString *strB = [self utf8ToUnicode:str];

将中文转成unicode形式，strB = @"ud83dudc74ud83cudffbud83dudc6eud83cudffd";

那[email protected]"ud83cudffbud83dudc6eud83cudffd";但是因为被截断后，打印出来变成了??????，而如果range.location从1开始，出现都是unicode形式的字符串，因为被截断后没有对应的组合字符串可以显示。可以利用循环打印下结果

for (int i = 0; i < str.length; i++) {
        NSRange range = NSMakeRange(i, str.length - i);
        NSString *temp = [str substringWithRange:range];
        NSLog(@"temp = %@", temp);
}

/*
     temp = ????????
     temp = udc74ud83cudffbud83dudc6eud83cudffd
     temp = ??????
     temp = udffbud83dudc6eud83cudffd
     temp = ????
     temp = udc6eud83cudffd
     temp = ??
     temp = udffd
*/

结果可能不是我们想要的，我们如果想要截断后的字符为显示字符的子集，也就是????或????或者????????。那么可以使用

rangeOfComposedCharacterSequencesForRange:调整range，防止有效的unicode字符被截断成无效字符(无显示意义)。请看下面

for (int i = 0; i < str.length; i++) {
        NSRange range = NSMakeRange(i, str.length - i);
        range = [str rangeOfComposedCharacterSequencesForRange:range];
        NSString *temp = [str substringWithRange:range];
        NSLog(@"temp = %@", temp);
}

/*
     temp = ????????
     temp = ????????
     temp = ????????
     temp = ????????
     temp = ????
     temp = ????
     temp = ????
     temp = ????
*/