91超碰碰碰碰久久久久久综合_超碰av人澡人澡人澡人澡人掠_国产黄大片在线观看画质优化_txt小说免费全本

溫馨提示×

溫馨提示×

您好,登錄后才能下訂單哦!

密碼登錄×
登錄注冊×
其他方式登錄
點擊 登錄注冊 即表示同意《億速云用戶服務條款》

js實現unicode碼字符串與utf8字節數據互轉詳解

發布時間:2020-09-19 03:29:48 來源:腳本之家 閱讀:470 作者:追極 欄目:web開發

js的string變量存儲字符串使用的是unicode編碼,要保存時必須選擇其他編碼后進行傳輸,比如轉成utf-8,utf-32等。存儲到數據庫中為utf-8編碼,讀取出來如何轉換成正確的字符串就成了問題。現在給出解決方案,可以正確支持中文、emoji表情、英文混合的字符串編碼互轉。

/**
 * Created by hdwang on 2019/1/28.
 */
var convertUtf8 = (function() {

  /**
   * unicode string to utf-8
   * @param text 字符串
   * @returns {*} utf-8編碼
   */
  function toBytes(text) {
    var result = [], i = 0;
    text = encodeURI(text);
    while (i < text.length) {
      var c = text.charCodeAt(i++);

      // if it is a % sign, encode the following 2 bytes as a hex value
      if (c === 37) {
        result.push(parseInt(text.substr(i, 2), 16))
        i += 2;

        // otherwise, just the actual byte
      } else {
        result.push(c)
      }
    }

    return coerceArray(result);
  }


  /**
   * utf8 byte to unicode string
   * @param utf8Bytes
   * @returns {string}
   */
  function utf8ByteToUnicodeStr(utf8Bytes){
    var unicodeStr ="";
    for (var pos = 0; pos < utf8Bytes.length;){
      var flag= utf8Bytes[pos];
      var unicode = 0 ;
      if ((flag >>>7) === 0 ) {
        unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
        pos += 1;

      } else if ((flag &0xFC) === 0xFC ){
        unicode = (utf8Bytes[pos] & 0x3) << 30;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 24;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 18;
        unicode |= (utf8Bytes[pos+3] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+4] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+5] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 6;

      }else if ((flag &0xF8) === 0xF8 ){
        unicode = (utf8Bytes[pos] & 0x7) << 24;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 18;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+3] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+4] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 5;

      } else if ((flag &0xF0) === 0xF0 ){
        unicode = (utf8Bytes[pos] & 0xF) << 18;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 12;
        unicode |= (utf8Bytes[pos+2] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+3] & 0x3F);
        unicodeStr+= String.fromCodePoint(unicode) ;
        pos += 4;

      } else if ((flag &0xE0) === 0xE0 ){
        unicode = (utf8Bytes[pos] & 0x1F) << 12;;
        unicode |= (utf8Bytes[pos+1] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+2] & 0x3F);
        unicodeStr+= String.fromCharCode(unicode) ;
        pos += 3;

      } else if ((flag &0xC0) === 0xC0 ){ //110
        unicode = (utf8Bytes[pos] & 0x3F) << 6;
        unicode |= (utf8Bytes[pos+1] & 0x3F);
        unicodeStr+= String.fromCharCode(unicode) ;
        pos += 2;

      } else{
        unicodeStr+= String.fromCharCode(utf8Bytes[pos]);
        pos += 1;
      }
    }
    return unicodeStr;
  }



  function checkInt(value) {
    return (parseInt(value) === value);
  }

  function checkInts(arrayish) {
    if (!checkInt(arrayish.length)) { return false; }

    for (var i = 0; i < arrayish.length; i++) {
      if (!checkInt(arrayish[i]) || arrayish[i] < 0 || arrayish[i] > 255) {
        return false;
      }
    }

    return true;
  }

  function coerceArray(arg, copy) {

    // ArrayBuffer view
    if (arg.buffer && arg.name === 'Uint8Array') {

      if (copy) {
        if (arg.slice) {
          arg = arg.slice();
        } else {
          arg = Array.prototype.slice.call(arg);
        }
      }

      return arg;
    }

    // It's an array; check it is a valid representation of a byte
    if (Array.isArray(arg)) {
      if (!checkInts(arg)) {
        throw new Error('Array contains invalid value: ' + arg);
      }

      return new Uint8Array(arg);
    }

    // Something else, but behaves like an array (maybe a Buffer? Arguments?)
    if (checkInt(arg.length) && checkInts(arg)) {
      return new Uint8Array(arg);
    }

    throw new Error('unsupported array-like object');
  }

  return {
    toBytes: toBytes,
    fromBytes: utf8ByteToUnicodeStr
  }
})()

針對emoji的字節字符,占兩個unicode字符。使用String.fromCharCode也可以實現,需要進行兩次fromCharCode,沒有fromPointCode方便。下面展示了utf-8的4字節轉換為unicode(utf-16)的過程。

//高char10位[一個unicode字符] (2+6+2=10)
unicode =  ((utf8Bytes[pos] & 0x3)) << 8 |((utf8Bytes[pos+1] & 0x3f) << 2) |((utf8Bytes[pos+2] >> 4) & 0x03);

//減去‭1F600‬中的1,這里減去6個0即可,低位char已經占據10位
unicode = unicode - parseInt('1000000',2)

//加上utf-16高char的標識符
unicode = 0xD800 + unicode;
console.log(unicode);
unicodeStr += String.fromCharCode(unicode);

//低char10位[一個unicode字符](4+6)
unicode = ((utf8Bytes[pos+2] & 0x0F) << 6) | (utf8Bytes[pos+3] & 0x3F);
//加上utf-16低char的標識符
unicode = 0xDC00 + unicode;
console.log(unicode);
unicodeStr+= String.fromCharCode(unicode);
pos += 4;

以上所述是小編給大家介紹的js實現unicode碼字符串與utf8字節數據互轉詳解整合,希望對大家有所幫助,如果大家有任何疑問請給我留言,小編會及時回復大家的。在此也非常感謝大家對億速云網站的支持!

向AI問一下細節

免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。

AI

昌宁县| 宿松县| 巩义市| 南昌市| 璧山县| 巴马| 玛沁县| 柞水县| 利津县| 武山县| 旺苍县| 龙胜| 临汾市| 中江县| 左权县| 云和县| 始兴县| 双柏县| 龙陵县| 策勒县| 镇江市| 桐城市| 济宁市| 平南县| 永城市| 无棣县| 万安县| 屯留县| 琼中| 乌什县| 高青县| 营口市| 裕民县| 麻城市| 寿阳县| 宁远县| 葫芦岛市| 绥江县| 武安市| 绍兴市| 南召县|