鸿蒙HarmonyOS中GB2312转解码

字符串转GB2312字节数组

说明：字节在ArkTs上认为是number，字节数组ArkTs中可以用Uint8Array处理。

如果想实现字符串转字节数组， Java 中可以通过

byte[] nameD = name.getBytes("GB2312");

但是OpenHarmony上，通过ArkTs要想将字符串转为GB2312字节数组，好像没有现成的方法实现。

所以，就手搓一份代码吧：参考UTF-8和GB2312的转码， # js javascript UTF-8 GB2312编码转换

编写ArkTs代码如下：

下面这两个数组的定义，请参考上面的链接，掘金的代码块，超出了字符限制，无法完全展示，只要将上面链接里的数组数据，复制到对应省略的位置即可。 _GB2312_1_87 = [];//GB2312字库结束 _UCS2_Big_1_87 = [];//GB2312字库结束

GB2312转码实现类

ini 复制代码

class GB2312{

  _GB2312_1_87 = [```];//GB2312字库结束

  _UCS2_Big_1_87 = [```];//GB2312字库结束

  //大小头互换（高8位和低8位互换）
  ConvetEndian(uincodeLE) {
    //高8位和低8位互换
    var tmp1 = 0, tmp2 = 0, tmp3 = 0;
    tmp1 = (uincodeLE & 0x00FF);
    tmp2 = uincodeLE >> 8;
    tmp3 = tmp2 | (tmp1 << 8);
    return tmp3;
  }

  GB2312_TO_Unicode(gcode) {
    for (var i = 0; i < 7614; i++) {
      if (gcode == this._GB2312_1_87[i]) {
        return this._UCS2_Big_1_87[i];
      }
    }
    return -1;
  }

  Unicode_TO_GB2312(ucode) {
    for (var i = 0; i < 7614; i++) {
      if (ucode == this._UCS2_Big_1_87[i]) {
        return this._GB2312_1_87[i];
      }
    }
    return -1;
  }

  //将不定长的数据转换成UNICODE,最长6个字节。返回转换结果，失败返回-1

  utf8ToUnicode(indata) {
    /*UTF-8编码方式
     * 0000 0000 - 0000 007F | 00 0XXXXXXX
     * 0000 0080 - 0000 07FF | C0 110XXXXX 10XXXXXX
     * 0000 0800 - 0000 FFFF | E0 1110XXXX 10XXXXXX 10XXXXXX
     * 0001 0000 - 001F FFFF | F0 11110XXX 10XXXXXX 10XXXXXX 10XXXXXX
     * 0020 0000 - 03FF FFFF | F8 111110XX 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX
     * 0400 0000 - 7FFF FFFF | FC 1111110X 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX
     */
    var hbs = indata[0];
    var dcode = 0;
    var dcnt = 0;

    //先看第一个字节，有多少个字节的有效数据，同时取得第一个字节的有效数据
    if (hbs > 0xFE) //超标，不能转换
    {
      return -1;
    }
    else if (hbs >= 0xFC) // 6
    {
      dcnt = 6;
      dcode |= (hbs & 0x01);
    }
    else if (hbs >= 0xF8) // 5
    {
      dcnt = 5;
      dcode |= (hbs & 0x03);
    }
    else if (hbs >= 0xF0) // 4
    {
      dcnt = 4;
      dcode |= (hbs & 0x07);
    }
    else if (hbs >= 0xE0) // 3
    {
      dcnt = 3;
      dcode |= (hbs & 0x0F);
    }
    else if (hbs >= 0xC0) // 2
    {
      dcnt = 2;
      dcode |= (hbs & 0x1F);
    }
    else {
      dcnt = 1;
    }
    if (dcnt == 1) {
      return indata[0];
    }
    for (var i = 1; i < dcnt; i++) {
      dcode <<= 6;                 //低位留出6个bit给新数据
      dcode |= (indata[i] & 0x3F); //取得新数据的低位6个bit
    }
    return dcode;
  }

  //将最大16位的unicode编码转换成utf8
  Unicode_TO_UTF8(code) {
    /*UTF-8编码方式
     * 0000 0000 - 0000 007F | 0XXXXXXX
     * 0000 0080 - 0000 07FF | 110XXXXX 10XXXXXX
     * 0000 0800 - 0000 FFFF | 1110XXXX 10XXXXXX 10XXXXXX
     * 0001 0000 - 001F FFFF | 11110XXX 10XXXXXX 10XXXXXX 10XXXXXX
     * 0020 0000 - 03FF FFFF | 111110XX 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX
     * 0400 0000 - 7FFF FFFF | 1111110X 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX 10XXXXXX
     */
    var out = [0];
    var bCnt = -1;
    if (code > 0x7FFFFFFF) //太大放不下了
    {
      bCnt = -1;
      return -1;
    }
    else if (code > 0x03FFFFFF) // 6个字节,0400 0000 - 7FFF FFFF
    {
      bCnt = 6;
    }
    else if (code > 0x001FFFFF) // 5个字节
    {
      bCnt = 5;
    }
    else if (code > 0x0000FFFF) // 4个字节
    {
      bCnt = 4;
    }
    else if (code > 0x000007FF) // 3个字节
    {
      bCnt = 3;
    }
    else if (code > 0x0000007F) // 2个字节
    {
      bCnt = 2;
    }
    else // 1个字节
    {
      bCnt = 1;
    }
    if (bCnt == 1) {
      out[0] = code;
      return bCnt;
    }
    var hbs = 0x80; //首字节高位
    var utf8Code = 0;
    //    qDebug("codeIn:%x",code);
    for (var i = 0; i < (bCnt - 1); i++) {
      out[bCnt - i - 1] = 0x80 | (code & 0x3f); //取最后6Bits
      code >>= 6;                               //丢掉6Bits
      hbs >>= 1;
      hbs |= 0x80; //首字节高位多一个"1"

    }
    out[0] = hbs | code; //首字节
    for (var i = 0; i < bCnt; i++) {
      utf8Code <<= 8;
      utf8Code |= out[i];
    }
    return utf8Code;
  }

  // 字符串转成GB2312的Hex字符串
  // let gb2312HexString = GB2312.TextCodec("GB2312","long",fixedMsg.Message);
  TextCodec(codeType, format, inputStr) {
    // var InputStrCode = '';
    // var OutputStr = '\n';
    var OutputStr = '';
    var inputCode = 0;
    var targetCode = 0;
    var inputChar = new String;
    for (var i = 0; i < inputStr.length; i++) {
      inputCode = inputStr.charCodeAt(i);
      inputChar = inputStr.charAt(i);
      targetCode = inputCode;
      // OutputStr += "//targetCode:" + targetCode.toString(16).toUpperCase() + "\n";
      if (inputCode > 0x80) {//acscii 0~127
        var unicode = inputCode;//Mixly 默认编码 UCS-2 Big Endian
        // OutputStr += "//unicode:" + unicode.toString(16).toUpperCase() + "\n";
        switch (codeType) {
          case "GB2312":
            targetCode = this.Unicode_TO_GB2312(unicode);
            break;
          case "UTF-8":
            targetCode = this.Unicode_TO_UTF8(unicode);
            break;
          case "UCS-2 Big Endian":
            targetCode = unicode;
            break;
          case "UCS-2 Little Endian":
            targetCode = this.ConvetEndian(unicode);
            break;
          default:
            break;
        }
      }
      switch (format) {
        case 'short':
          if (targetCode & 0xff0000)//3bytes
          {
            for (var k = 2; k >= 0; k--) {
              var _byte = (targetCode >> (8 * k)) & 0xff;
              OutputStr += '0x' + _byte.toString(16).toUpperCase() + ',';
            }
          }
          else if (targetCode & 0xff00)//2bytes
          {
            for (var k = 1; k >= 0; k--) {
              var _byte = (targetCode >> (8 * k)) & 0xff;
              OutputStr += '0x' + _byte.toString(16).toUpperCase() + ',';
            }
          }
          else //1byte
          {
            var _byte = targetCode;
            OutputStr += '0x' + _byte.toString(16).toUpperCase() + ',';
          }
          OutputStr += "//" + inputChar + " " + codeType + "\n";
          break;
        case 'long':
          // OutputStr += '0x' + targetCode.toString(16).toUpperCase() + ',' + "//" + inputChar + " " + codeType + "\n";
          OutputStr += targetCode.toString(16).toUpperCase();
          break;
        default:
          OutputStr += '0x' + targetCode.toString(16).toUpperCase() + ',' + "//" + inputChar + " " + codeType + "\n";
          break;
      }
    }
    return OutputStr;
  };
}

export default new GB2312()

使用下面的调用方法，就可以得到Hex16进制的字符串。然后再使用字符串转字节数组的方式，得到ArkTs中的字节数组Uint8Array

调用方法

ini 复制代码

let gb2312HexString = GB2312.TextCodec("GB2312","long",fixedMsg.Message);
let GB2312Bytes:Uint8Array = BCDDecode.hexStr2Bytes(gb2312HexString);

Hex转Uint8array

ini 复制代码

hexStr2Bytes(src: string): Uint8Array {
  src = src.replace(/\s+/g, ""); // 移除所有空白字符
  const l = src.length / 2;
  const ret = new Uint8Array(l);
  for (let i = 0; i < l; i++) {
    const m = i * 2 + 1;
    const n = m + 1;
    const sss = "0x" + src.substring(i * 2, m) + src.substring(m, n);
    ret[i] = parseInt(sss, 16); // parseInt 可以直接解析十六进制字符串
  }
  return ret;
}

GB2312字节数组转字符串

下面代码直接调用

php 复制代码

/**
 * 将 Uint8Array 转换为 GB2312 编码的字符串
 * @param data Uint8Array 数据
 * @returns GB2312 编码的字符串
 */
gb2312BytesToString(buffer: Uint8Array):string {
  let textDecoder = util.TextDecoder.create("gb2312");
  return textDecoder.decodeWithStream(buffer)
}