iOS開發中，比較蛋疼的一個問題，NSData轉UTF-8格式的NSString，有時候會返回nil。

究其原因，無非就是：UTF-8的字符中混進了其他編碼格式的字符，這樣NSData轉NSString的時候，就是返回nil

而現在網上的方法基本就這幾個：

http://blog.csdn.net/cuibo1123/article/details/40938225
http://blog.csdn.net/xocom/article/details/50905578
http://www.cnblogs.com/xiao-love-meng/p/5757564.html

這幾個方法都不完美，都不能完全解決我遇到的問題。

我的解決方法：

查了UTF-8的wiki，utf-8的編碼格式如下，理論上可以到6個字節，但之用到了4個字節。

utf-8的編碼規則

其中，有一些特殊字節是不會出現在utf-8中的：

utf-8中不會出現的字節

其中，還指出了判斷utf-8的方法：

UTF-8字符串可以由一個簡單的算法可靠地識別出來。就是，一個字符串在任何其它編碼中表現為合法的UTF-8的可能性很低，并隨字符串長度增長而減小。舉例說，字符值C0,C1,F5至FF從來沒有出現。為了更好的可靠性，可以使用正則表達式來統計非法過長和替代值（可以查看W3 FAQ: Multilingual Forms上的驗證UTF-8字符串的正則表達式）。

$field =~
  m/\A(
     [\x09\x0A\x0D\x20-\x7E]            # ASCII
   | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
   |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
   | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
   |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
   |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
   | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
   |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
  )*\z/x;

因此，我們只要把上面的代碼，轉換成OC語言就行了：
這里我直接寫了一個Category：

//
// Created by WDY on 2016/11/24.
// Copyright (c) 2016 andforce. All rights reserved.
//

#import "NSData+UTF8.h"

@implementation NSData (UTF8)

- (NSString *)utf8String {
    NSString *string = [[NSString alloc] initWithData:self encoding:NSUTF8StringEncoding];
    if (string == nil) {
        string = [[NSString alloc] initWithData:[self UTF8Data] encoding:NSUTF8StringEncoding];
    }
    return string;
}

//              https://zh.wikipedia.org/wiki/UTF-8
//              https://www.w3.org/International/questions/qa-forms-utf-8
//
//            $field =~
//                    m/\A(
//            [\x09\x0A\x0D\x20-\x7E]            # ASCII
//            | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
//            |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
//            | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
//            |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
//            |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
//            | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
//            |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
//            )*\z/x;

- (NSData *)UTF8Data {
    //保存結果
    NSMutableData *resData = [[NSMutableData alloc] initWithCapacity:self.length];

    NSData *replacement = [@"?" dataUsingEncoding:NSUTF8StringEncoding];

    uint64_t index = 0;
    const uint8_t *bytes = self.bytes;

    long dataLength = (long) self.length;

    while (index < dataLength) {
        uint8_t len = 0;
        uint8_t firstChar = bytes[index];

            // 1個字節
        if ((firstChar & 0x80) == 0 && (firstChar == 0x09 || firstChar == 0x0A || firstChar == 0x0D || (0x20 <= firstChar && firstChar <= 0x7E))) {
            len = 1;
        }
            // 2字節
        else if ((firstChar & 0xE0) == 0xC0 && (0xC2 <= firstChar && firstChar <= 0xDF)) {
            if (index + 1 < dataLength) {
                uint8_t secondChar = bytes[index + 1];
                if (0x80 <= secondChar && secondChar <= 0xBF) {
                    len = 2;
                }
            }
        }
            // 3字節
        else if ((firstChar & 0xF0) == 0xE0) {
            if (index + 2 < dataLength) {
                uint8_t secondChar = bytes[index + 1];
                uint8_t thirdChar = bytes[index + 2];
                
                if (firstChar == 0xE0 && (0xA0 <= secondChar && secondChar <= 0xBF) && (0x80 <= thirdChar && thirdChar <= 0xBF)) {
                    len = 3;
                } else if (((0xE1 <= firstChar && firstChar <= 0xEC) || firstChar == 0xEE || firstChar == 0xEF) && (0x80 <= secondChar && secondChar <= 0xBF) && (0x80 <= thirdChar && thirdChar <= 0xBF)) {
                    len = 3;
                } else if (firstChar == 0xED && (0x80 <= secondChar && secondChar <= 0x9F) && (0x80 <= thirdChar && thirdChar <= 0xBF)) {
                    len = 3;
                }
            }
        }
            // 4字節
        else if ((firstChar & 0xF8) == 0xF0) {
            if (index + 3 < dataLength) {
                uint8_t secondChar = bytes[index + 1];
                uint8_t thirdChar = bytes[index + 2];
                uint8_t fourthChar = bytes[index + 3];
                
                if (firstChar == 0xF0) {
                    if ((0x90 <= secondChar & secondChar <= 0xBF) && (0x80 <= thirdChar && thirdChar <= 0xBF) && (0x80 <= fourthChar && fourthChar <= 0xBF)) {
                        len = 4;
                    }
                } else if ((0xF1 <= firstChar && firstChar <= 0xF3)) {
                    if ((0x80 <= secondChar && secondChar <= 0xBF) && (0x80 <= thirdChar && thirdChar <= 0xBF) && (0x80 <= fourthChar && fourthChar <= 0xBF)) {
                        len = 4;
                    }
                } else if (firstChar == 0xF3) {
                    if ((0x80 <= secondChar && secondChar <= 0x8F) && (0x80 <= thirdChar && thirdChar <= 0xBF) && (0x80 <= fourthChar && fourthChar <= 0xBF)) {
                        len = 4;
                    }
                }
            }
        }
            // 5個字節
        else if ((firstChar & 0xFC) == 0xF8) {
            len = 0;
        }
            // 6個字節
        else if ((firstChar & 0xFE) == 0xFC) {
            len = 0;
        }

        if (len == 0) {
            index++;
            [resData appendData:replacement];
        } else {
            [resData appendBytes:bytes + index length:len];
            index += len;
        }
    }

    return resData;
}
@end