用Javascript解码UTF-8

我在一个传递UTF-8编码的string的XHTML网页中有Javascript。 它需要继续通过UTF-8版本，并解码它。 如何解码显示的UTF-8string？

<script type="text/javascript"> // <![CDATA[ function updateUser(usernameSent){ var usernameReceived = usernameSent; // Current value: Größe var usernameDecoded = usernameReceived; // Decode to: Größe var html2id = ''; html2id += 'Encoded: ' + usernameReceived + '<br />Decoded: ' + usernameDecoded; document.getElementById('userId').innerHTML = html2id; } // ]]> </script> 

Answer 1

为了回答最初的问题：这里是你如何在javascript中解码utf-8：

http://ecmanaut.blogspot.ca/2006/07/encoding-decoding-utf8-in-javascript.html

特别，

 function encode_utf8(s) { return unescape(encodeURIComponent(s)); } function decode_utf8(s) { return decodeURIComponent(escape(s)); } 

我只是在我的代码中使用它，它完美的作品。

Answer 2

这应该工作：

 // http://www.onicos.com/staff/iz/amuse/javascript/expert/utf.txt /* utf.js - UTF-8 <=> UTF-16 convertion * * Copyright (C) 1999 Masanao Izumo <[e-mail]> * Version: 1.0 * LastModified: Dec 25 1999 * This library is free. You can redistribute it and/or modify it. */ function Utf8ArrayToStr(array) { var out, i, len, c; var char2, char3; out = ""; len = array.length; i = 0; while(i < len) { c = array[i++]; switch(c >> 4) { case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7: // 0xxxxxxx out += String.fromCharCode(c); break; case 12: case 13: // 110x xxxx 10xx xxxx char2 = array[i++]; out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F)); break; case 14: // 1110 xxxx 10xx xxxx 10xx xxxx char2 = array[i++]; char3 = array[i++]; out += String.fromCharCode(((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0)); break; } } return out; } 

查看JSFiddle演示 。

也看到相关的问题： 这里和这里

Answer 3

@阿尔伯特的解决scheme是我认为最接近的解决scheme，但它最多只能parsing3个字节的UTF-8字符

 function utf8ArrayToStr(array) { var out, i, len, c; var char2, char3; out = ""; len = array.length; i = 0; // XXX: Invalid bytes are ignored while(i < len) { c = array[i++]; if (c >> 7 == 0) { // 0xxx xxxx out += String.fromCharCode(c); continue; } // Invalid starting byte if (c >> 6 == 0x02) { continue; } // #### MULTIBYTE #### // How many bytes left for thus character? var extraLength = null; if (c >> 5 == 0x06) { extraLength = 1; } else if (c >> 4 == 0x0e) { extraLength = 2; } else if (c >> 3 == 0x1e) { extraLength = 3; } else if (c >> 2 == 0x3e) { extraLength = 4; } else if (c >> 1 == 0x7e) { extraLength = 5; } else { continue; } // Do we have enough bytes in our data? if (i+extraLength > len) { var leftovers = array.slice(i-1); // If there is an invalid byte in the leftovers we might want to // continue from there. for (; i < len; i++) if (array[i] >> 6 != 0x02) break; if (i != len) continue; // All leftover bytes are valid. return {result: out, leftovers: leftovers}; } // Remove the UTF-8 prefix from the char (res) var mask = (1 << (8 - extraLength - 1)) - 1, res = c & mask, nextChar, count; for (count = 0; count < extraLength; count++) { nextChar = array[i++]; // Is the char valid multibyte part? if (nextChar >> 6 != 0x02) {break;}; res = (res << 6) | (nextChar & 0x3f); } if (count != extraLength) { i--; continue; } if (res <= 0xffff) { out += String.fromCharCode(res); continue; } res -= 0x10000; var high = ((res >> 10) & 0x3ff) + 0xd800, low = (res & 0x3ff) + 0xdc00; out += String.fromCharCode(high, low); } return {result: out, leftovers: []}; } 

这将返回{result: "parsed string", leftovers: [list of invalid bytes at the end]}以防您正在parsing块中的string。

编辑：解决@unhammer发现的问题。

Answer 4

也许使用textDecoder就足够了。

不支持所有的浏览器。 但是，如果您使用人行横道或任何其他使用情况下，您知道使用哪个浏览器可能就足够了。

 var decoder = new TextDecoder('utf-8'), decodedMessage; decodedMessage = decoder.decode(message.data); 

Answer 5

这是一个解决scheme，处理所有的Unicode代码点，包括上（4字节）值，并支持所有现代浏览器（IE和其他> 5.5）。 它使用decodeURIComponent（），但不使用弃用的escape / unescape函数：

 function utf8_to_str(a) { for(var i=0, s=''; i<a.length; i++) { var h = a[i].toString(16) if(h.length < 2) h = '0' + h s += '%' + h } return decodeURIComponent(s) } 

经过testing并在GitHub上提供

从string创buildUTF-8：

 function utf8_from_str(s) { for(var i=0, enc = encodeURIComponent(s), a = []; i < enc.length;) { if(enc[i] === '%') { a.push(parseInt(enc.substr(i+1, 2), 16)) i += 3 } else { a.push(enc.charCodeAt(i++)) } } return a } 

经过testing并在GitHub上提供

Answer 6

更新@艾伯特的回答为表情符号添加条件。

 function Utf8ArrayToStr(array) { var out, i, len, c; var char2, char3, char4; out = ""; len = array.length; i = 0; while(i < len) { c = array[i++]; switch(c >> 4) { case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7: // 0xxxxxxx out += String.fromCharCode(c); break; case 12: case 13: // 110x xxxx 10xx xxxx char2 = array[i++]; out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F)); break; case 14: // 1110 xxxx 10xx xxxx 10xx xxxx char2 = array[i++]; char3 = array[i++]; out += String.fromCharCode(((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0)); break; case 15: // 1111 0xxx 10xx xxxx 10xx xxxx 10xx xxxx char2 = array[i++]; char3 = array[i++]; char4 = array[i++]; out += String.fromCodePoint(((c & 0x07) << 18) | ((char2 & 0x3F) << 12) | ((char3 & 0x3F) << 6) | (char4 & 0x3F)); break; } return out; } 

Answer 7

我寻找一个简单的解决scheme，这对我很好：

 //input data view = new Uint8Array(data); //output string serialString = ua2text(view); //convert UTF8 to string function ua2text(ua) { s = ""; for (var i = 0; i < ua.length; i++) { s += String.fromCharCode(ua[i]); } return s; } 

我唯一的问题是有时我会一次得到一个angular色。 这可能是由我的源代码arrays缓冲区的devise。 我使用https://github.com/xseignard/cordovarduino来读取Android设备上的串行数据。;