您好,登錄后才能下訂單哦!
js的string變量存儲(chǔ)字符串使用的是unicode編碼,要保存時(shí)必須選擇其他編碼后進(jìn)行傳輸,比如轉(zhuǎn)成utf-8,utf-32等。存儲(chǔ)到數(shù)據(jù)庫(kù)中為utf-8編碼,讀取出來如何轉(zhuǎn)換成正確的字符串就成了問題?,F(xiàn)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(zhuǎn)。
/** * 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(duì)emoji的字節(jié)字符,占兩個(gè)unicode字符。使用String.fromCharCode也可以實(shí)現(xiàn),需要進(jìn)行兩次fromCharCode,沒有fromPointCode方便。下面展示了utf-8的4字節(jié)轉(zhuǎn)換為unicode(utf-16)的過程。
//高char10位[一個(gè)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(gè)0即可,低位char已經(jīng)占據(jù)10位 unicode = unicode - parseInt('1000000',2) //加上utf-16高char的標(biāo)識(shí)符 unicode = 0xD800 + unicode; console.log(unicode); unicodeStr += String.fromCharCode(unicode); //低char10位[一個(gè)unicode字符](4+6) unicode = ((utf8Bytes[pos+2] & 0x0F) << 6) | (utf8Bytes[pos+3] & 0x3F); //加上utf-16低char的標(biāo)識(shí)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(shí)現(xiàn)unicode碼字符串與utf8字節(jié)數(shù)據(jù)互轉(zhuǎn)詳解整合,希望對(duì)大家有所幫助,如果大家有任何疑問請(qǐng)給我留言,小編會(huì)及時(shí)回復(fù)大家的。在此也非常感謝大家對(duì)億速云網(wǎng)站的支持!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。