diff --git a/README.md b/README.md index 3745ad3..ef475f1 100644 --- a/README.md +++ b/README.md @@ -4,10 +4,41 @@ utf8-typed Base64, TypedArrays, and UTF-8 / Unicode conversions in Browser (and Node) JavaScript This is based wholly on the work by good folks at the MDN. +See -See https://developer.mozilla.org/en-US/docs/Web/API/WindowBase64/Base64_encoding_and_decoding +Examples +======== + +```javascript +// Base64 + +var myArray = base64DecToArr("QmFzZSA2NCDigJQgTW96aWxsYSBEZXZlbG9wZXIgTmV0d29yaw=="); // "Base 64 \u2014 Mozilla Developer Network" + +var myBuffer = base64DecToArr("QmFzZSA2NCDigJQgTW96aWxsYSBEZXZlbG9wZXIgTmV0d29yaw==").buffer; // "Base 64 \u2014 Mozilla Developer Network" + +console.log(myBuffer.byteLength); + +// Crazy Unicode + +var sMyInput = "I'm a ☢ ☃ that plays 𝄢 guitar and spea̧͈͖ks Ar̽̾̈́͒͑ ̶̧̨̱̹̭̯ͧ̾ͬC̷̙̲̝͖ͭ̏ͥͮ͟Oͮ͏̮̪̝͍M̲̖͊̒ͪͩͬ̚̚͜!"; + +var aMyUTF8Input = strToUTF8Arr(sMyInput); + +var sMyBase64 = base64EncArr(aMyUTF8Input); + +alert(sMyBase64); + +var aMyUTF8Output = base64DecToArr(sMyBase64); + +var sMyOutput = UTF8ArrToStr(aMyUTF8Output); + +alert(sMyOutput); +``` License ======= -Mozilla has licensed this code in the Public Domain, which means that I am at liberty to re-license my copy under the Apache 2, which is something that, general speaking, your legal department will feel more comfortable with. +Mozilla has licensed this code in the Public Domain, which means that I am at liberty to re-license my copy +under the Apache 2, which is something that, general speaking, your legal department will feel more comfortable with. + +See diff --git a/index.js b/index.js new file mode 100644 index 0000000..f331e1d --- /dev/null +++ b/index.js @@ -0,0 +1,172 @@ +"use strict"; + +/*\ +|*| +|*| Base64 / binary data / UTF-8 strings utilities +|*| +|*| https://developer.mozilla.org/en-US/docs/Web/JavaScript/Base64_encoding_and_decoding +|*| +\*/ + +/* Array of bytes to base64 string decoding */ + +function b64ToUint6 (nChr) { + + return nChr > 64 && nChr < 91 ? + nChr - 65 + : nChr > 96 && nChr < 123 ? + nChr - 71 + : nChr > 47 && nChr < 58 ? + nChr + 4 + : nChr === 43 ? + 62 + : nChr === 47 ? + 63 + : + 0; + +} + +function base64DecToArr (sBase64, nBlocksSize) { + + var + sB64Enc = sBase64.replace(/[^A-Za-z0-9\+\/]/g, ""), nInLen = sB64Enc.length, + nOutLen = nBlocksSize ? Math.ceil((nInLen * 3 + 1 >> 2) / nBlocksSize) * nBlocksSize : nInLen * 3 + 1 >> 2, taBytes = new Uint8Array(nOutLen); + + for (var nMod3, nMod4, nUint24 = 0, nOutIdx = 0, nInIdx = 0; nInIdx < nInLen; nInIdx++) { + nMod4 = nInIdx & 3; + nUint24 |= b64ToUint6(sB64Enc.charCodeAt(nInIdx)) << 6 * (3 - nMod4); + if (nMod4 === 3 || nInLen - nInIdx === 1) { + for (nMod3 = 0; nMod3 < 3 && nOutIdx < nOutLen; nMod3++, nOutIdx++) { + taBytes[nOutIdx] = nUint24 >>> (16 >>> nMod3 & 24) & 255; + } + nUint24 = 0; + + } + } + + return taBytes; +} + +/* Base64 string to array encoding */ + +function uint6ToB64 (nUint6) { + + return nUint6 < 26 ? + nUint6 + 65 + : nUint6 < 52 ? + nUint6 + 71 + : nUint6 < 62 ? + nUint6 - 4 + : nUint6 === 62 ? + 43 + : nUint6 === 63 ? + 47 + : + 65; + +} + +function base64EncArr (aBytes) { + + var nMod3 = 2, sB64Enc = ""; + + for (var nLen = aBytes.length, nUint24 = 0, nIdx = 0; nIdx < nLen; nIdx++) { + nMod3 = nIdx % 3; + if (nIdx > 0 && (nIdx * 4 / 3) % 76 === 0) { sB64Enc += "\r\n"; } + nUint24 |= aBytes[nIdx] << (16 >>> nMod3 & 24); + if (nMod3 === 2 || aBytes.length - nIdx === 1) { + sB64Enc += String.fromCharCode(uint6ToB64(nUint24 >>> 18 & 63), uint6ToB64(nUint24 >>> 12 & 63), uint6ToB64(nUint24 >>> 6 & 63), uint6ToB64(nUint24 & 63)); + nUint24 = 0; + } + } + + return sB64Enc.substr(0, sB64Enc.length - 2 + nMod3) + (nMod3 === 2 ? '' : nMod3 === 1 ? '=' : '=='); + +} + +/* UTF-8 array to DOMString and vice versa */ + +function UTF8ArrToStr (aBytes) { + + var sView = ""; + + for (var nPart, nLen = aBytes.length, nIdx = 0; nIdx < nLen; nIdx++) { + nPart = aBytes[nIdx]; + sView += String.fromCharCode( + nPart > 251 && nPart < 254 && nIdx + 5 < nLen ? /* six bytes */ + /* (nPart - 252 << 30) may be not so safe in ECMAScript! So...: */ + (nPart - 252) * 1073741824 + (aBytes[++nIdx] - 128 << 24) + (aBytes[++nIdx] - 128 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128 + : nPart > 247 && nPart < 252 && nIdx + 4 < nLen ? /* five bytes */ + (nPart - 248 << 24) + (aBytes[++nIdx] - 128 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128 + : nPart > 239 && nPart < 248 && nIdx + 3 < nLen ? /* four bytes */ + (nPart - 240 << 18) + (aBytes[++nIdx] - 128 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128 + : nPart > 223 && nPart < 240 && nIdx + 2 < nLen ? /* three bytes */ + (nPart - 224 << 12) + (aBytes[++nIdx] - 128 << 6) + aBytes[++nIdx] - 128 + : nPart > 191 && nPart < 224 && nIdx + 1 < nLen ? /* two bytes */ + (nPart - 192 << 6) + aBytes[++nIdx] - 128 + : /* nPart < 127 ? */ /* one byte */ + nPart + ); + } + + return sView; + +} + +function strToUTF8Arr (sDOMStr) { + + var aBytes, nChr, nStrLen = sDOMStr.length, nArrLen = 0; + + /* mapping... */ + + for (var nMapIdx = 0; nMapIdx < nStrLen; nMapIdx++) { + nChr = sDOMStr.charCodeAt(nMapIdx); + nArrLen += nChr < 0x80 ? 1 : nChr < 0x800 ? 2 : nChr < 0x10000 ? 3 : nChr < 0x200000 ? 4 : nChr < 0x4000000 ? 5 : 6; + } + + aBytes = new Uint8Array(nArrLen); + + /* transcription... */ + + for (var nIdx = 0, nChrIdx = 0; nIdx < nArrLen; nChrIdx++) { + nChr = sDOMStr.charCodeAt(nChrIdx); + if (nChr < 128) { + /* one byte */ + aBytes[nIdx++] = nChr; + } else if (nChr < 0x800) { + /* two bytes */ + aBytes[nIdx++] = 192 + (nChr >>> 6); + aBytes[nIdx++] = 128 + (nChr & 63); + } else if (nChr < 0x10000) { + /* three bytes */ + aBytes[nIdx++] = 224 + (nChr >>> 12); + aBytes[nIdx++] = 128 + (nChr >>> 6 & 63); + aBytes[nIdx++] = 128 + (nChr & 63); + } else if (nChr < 0x200000) { + /* four bytes */ + aBytes[nIdx++] = 240 + (nChr >>> 18); + aBytes[nIdx++] = 128 + (nChr >>> 12 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 6 & 63); + aBytes[nIdx++] = 128 + (nChr & 63); + } else if (nChr < 0x4000000) { + /* five bytes */ + aBytes[nIdx++] = 248 + (nChr >>> 24); + aBytes[nIdx++] = 128 + (nChr >>> 18 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 12 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 6 & 63); + aBytes[nIdx++] = 128 + (nChr & 63); + } else /* if (nChr <= 0x7fffffff) */ { + /* six bytes */ + aBytes[nIdx++] = 252 + (nChr >>> 30); + aBytes[nIdx++] = 128 + (nChr >>> 24 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 18 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 12 & 63); + aBytes[nIdx++] = 128 + (nChr >>> 6 & 63); + aBytes[nIdx++] = 128 + (nChr & 63); + } + } + + return aBytes; + +}