Learn to use JavaScript to implement UTF-8 encoding and decoding

首先简单介绍一下UTF-8。UTF-8以字节为单位对Unicode进行编码。 UTF-8的特点是对不同范围的字符使用不同长度的编码。 对于0x00-0x7F之间的字符，UTF-8编码与ASCII编码完全相同。UTF-8编码的最大长度是6个字节。 6字节模板有31个x，即可以容纳31位二进制数字。Unicode的最大码位0x7FFFFFFF也只有31位。

function utf8Encode(inputStr) { var outputStr = ""; for(var i = 0; i < inputStr.length; i++) { var temp = inputStr.charCodeAt(i); //0xxxxxxx if(temp < 128) { outputStr += String.fromCharCode(temp); } //110xxxxx 10xxxxxx else if(temp < 2048) { outputStr += String.fromCharCode((temp >> 6) | 192); outputStr += String.fromCharCode((temp & 63) | 128); } //1110xxxx 10xxxxxx 10xxxxxx else if(temp < 65536) { outputStr += String.fromCharCode((temp >> 12) | 224); outputStr += String.fromCharCode(((temp >> 6) & 63) | 128); outputStr += String.fromCharCode((temp & 63) | 128); } //11110xxx 10xxxxxx 10xxxxxx 10xxxxxx else { outputStr += String.fromCharCode((temp >> 18) | 240); outputStr += String.fromCharCode(((temp >> 12) & 63) | 128); outputStr += String.fromCharCode(((temp >> 6) & 63) | 128); outputStr += String.fromCharCode((temp & 63) | 128); } } return outputStr; }

function utf8Decode(inputStr) { var outputStr = ""; var code1, code2, code3, code4; for(var i = 0; i < inputStr.length; i++) { code1 = inputStr.charCodeAt(i); if(code1 < 128) { outputStr += String.fromCharCode(code1); } else if(code1 < 224) { code2 = inputStr.charCodeAt(++i); outputStr += String.fromCharCode(((code1 & 31) << 6) | (code2 & 63)); } else if(code1 < 240) { code2 = inputStr.charCodeAt(++i); code3 = inputStr.charCodeAt(++i); outputStr += String.fromCharCode(((code1 & 15) << 12) | ((code2 & 63) << 6) | (code3 & 63)); } else { code2 = inputStr.charCodeAt(++i); code3 = inputStr.charCodeAt(++i); code4 = inputStr.charCodeAt(++i); outputStr += String.fromCharCode(((code1 & 7) << 18) | ((code2 & 63) << 12) |((code3 & 63) << 6) | (code2 & 63)); } } return outputStr; }