update links

Fixes binaryStringToUtf8 and compiler type mismatch warning in utf8ToBinaryString

LICENSE

@@ -1,3 +1,32 @@
+At your option you may choose either of the following licenses:
+
+  * The MIT License (MIT)
+  * The Apache License 2.0 (Apache-2.0)
+
+
+The MIT License (MIT)
+
+Copyright (c) 2015 AJ ONeal
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+
                                  Apache License
                            Version 2.0, January 2004
                         http://www.apache.org/licenses/
@@ -186,7 +215,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright {yyyy} {name of copyright owner}
+   Copyright 2015 AJ ONeal
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.
@@ -199,4 +228,3 @@
    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and
    limitations under the License.
-

README.md

@@ -1,10 +1,98 @@
-utf8-typed
-==========
+Unibabel
+========
 
-Base64, TypedArrays, and UTF-8 / Unicode conversions in Browser (and Node) JavaScript
+Minimalistic **Base64**, **TypedArrays**, and **UTF-8** / **Unicode** conversions in Browser (and Node) JavaScript. Optional add-on support for **hex** and **base32**.
 
-This is based wholly on the work by good folks at the MDN.
-See <https://developer.mozilla.org/en-US/docs/Web/API/WindowBase64/Base64_encoding_and_decoding>
+See <https://coolaj86.com/articles/base64-unicode-utf-8-javascript-and-you/>
+
+See also
+
+  * [TextEncoder](https://developer.mozilla.org/en-US/docs/Web/API/TextEncoder/encode) / [TextDecoder](https://developer.mozilla.org/en-US/docs/Web/API/TextDecoder/decode)
+  * [DateView](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/DataView)
+  * [text-encoding](https://github.com/inexorabletash/text-encoding)
+  * [TextEncoderLite (based on Buffer)](https://github.com/coolaj86/TextEncoderLite/tree/litest)
+  * [TextEncoderLite (based on text-encoding)](https://github.com/coolaj86/TextEncoderLite/tree/lite)
+  * [Beatgammit's base64-js](https://github.com/beatgammit/base64-js)
+
+Are you in the right place?
+------------------------
+
+Dear Node.js Users:
+
+You SHOULD NOT use this module. You already have [`Buffer`](https://nodejs.org/api/buffer.html) and [`thirty-two`](https://github.com/chrisumbel/thirty-two):
+
+```javascript
+var buf = new Buffer('I ½ ♥ 💩', 'utf8');
+buf.toString('hex');
+buf.toString('base64');
+buf.toString('ascii');
+buf.toString('utf8');
+buf.toString('binary'); // deprecated, do not use
+```
+
+Install
+-------
+
+You just include the `index.js` in a lovely script tag.
+
+```bash
+bower install --save unibabel
+```
+
+```html
+<script src="/bower_components/unibabel/index.js"></script>
+```
+
+Dear WebPack / Broccoli, Gulp / Grunt Users:
+
+I don't know how your build systems work these days,
+but Unibabel is exported as `Unibabel`
+and you can access it as `window.Unibabel`.
+
+API
+===
+
+```javascript
+// TypedArray <--> UTF8
+var uint8Array = Unibabel.strToUtf8Arr(str);
+var str = Unibabel.utf8ArrToStr(uint8Array);
+
+// TypedArray <--> Base64
+var base64 = Unibabel.arrToBase64(uint8Array)
+var uint8Array = Unibabel.base64ToArr(base64)
+```
+
+**Normal APIs**
+
+`index.js`
+
+* utf8ToBuffer(utf8str) => array
+* bufferToUtf8(array) => string
+* utf8ToBase64(utf8str) => base64
+* base64ToUtf8(base64) => string
+* bufferToBase64(array) => base64
+* base64ToBuffer(base64) => array
+
+**Hex APIs**
+
+`unibabel.hex.js`
+
+* hexToBuffer(hexstr) => array
+* bufferToHex(array) => hexstr
+
+**Base32 APIs**
+
+`unibabel.base32.js`
+
+* base32ToBuffer(b32str) => array
+* bufferToBase32(array) => b32str
+
+**Helper APIs**
+
+* utf8ToBinaryString(utf8str) => binstr
+* binaryStringToUtf8(binstr) => utf8str
+* bufferToBinaryString(buffer) => binstr
+* binaryStringToBuffer(binstr) => array
 
 Examples
 ========
@@ -12,25 +100,21 @@ Examples
 ```javascript
 // Base64
 
-var myArray = base64DecToArr("QmFzZSA2NCDigJQgTW96aWxsYSBEZXZlbG9wZXIgTmV0d29yaw=="); // "Base 64 \u2014 Mozilla Developer Network"
-
-var myBuffer = base64DecToArr("QmFzZSA2NCDigJQgTW96aWxsYSBEZXZlbG9wZXIgTmV0d29yaw==").buffer; // "Base 64 \u2014 Mozilla Developer Network"
+var myArray = Unibabel.base64ToArr("QmFzZSA2NCDigJQgTW96aWxsYSBEZXZlbG9wZXIgTmV0d29yaw=="); // "Base 64 \u2014 Mozilla Developer Network"
+var myBuffer = Unibabel.base64ToArr("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);
+var aMyUTF8Input = Unibabel.strToUtf8Arr(sMyInput);
+var sMyBase64 = Unibabel.arrToBase64(aMyUTF8Input);
 
 alert(sMyBase64);
 
-var aMyUTF8Output = base64DecToArr(sMyBase64);
-
-var sMyOutput = UTF8ArrToStr(aMyUTF8Output);
+var aMyUTF8Output = Unibabel.base64ToArr(sMyBase64);
+var sMyOutput = Unibabel.utf8ArrToStr(aMyUTF8Output);
 
 alert(sMyOutput);
 ```
@@ -38,7 +122,38 @@ 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.
+* `index.js` and `unibabel.hex.js` are dual-licensed as Apache 2.0 and MIT.
+* `unibabel.base32.js` is a modified version of [thirty-two](https://github.com/chrisumbel/thirty-two) and is therefore licensed MIT.
+
+Some parts of the code were taken from MDN, which Mozilla has licensed in the Public Domain,
+which means that I am at liberty to re-license my copy under the Apache 2 and MIT licenses.
 
 See <https://developer.mozilla.org/en-US/docs/MDN/About#Copyrights_and_licenses>
+
+ChangeLog
+====
+
+v2.1.0
+------
+
+Added `unibabel.base32.js`
+
+v2.0.0
+------
+
+The new implementation is binary compatible with node.js, TextEncoder,
+and other more-common UTF-8 encodings.
+
+It is also based on DOM APIs which result in much less code and are still
+backwards compatible all the way back to IE6 (not on purpose, just that
+it happens to work).
+
+See <https://coolaj86.com/articles/base64-unicode-utf-8-javascript-and-you/>
+
+v1.0.0
+------
+
+This version was based on the work by good folks at the MDN, however,
+the UTF-8 conversion was not byte-compatible with other UTF-8 conversions
+(such as node.js and TextEncoder), so don't use it.
+See <https://developer.mozilla.org/en-US/docs/Web/API/WindowBase64/Base64_encoding_and_decoding>

bower.json

@@ -1,10 +1,9 @@
 {
   "name": "unibabel",
   "main": "index.js",
-  "version": "1.0.0-rc1",
-  "homepage": "https://github.com/coolaj86/unibabel-js",
+  "homepage": "https://git.coolaj86.com/coolaj86/unibabel.js",
   "authors": [
-    "AJ ONeal <awesome@coolaj86.com>"
+    "AJ ONeal <coolaj86@gmail.com>"
   ],
   "description": "Convert between UTF8, TypedArrays, and Base64",
   "moduleType": [
@@ -12,15 +11,21 @@
     "node"
   ],
   "keywords": [
+    "ascii",
+    "binary",
     "utf8",
     "utf-8",
     "ArrayBuffer",
     "TypedArrays",
+    "TypedArray",
     "Uint",
+    "Uint8Array",
     "Base64",
-    "b64"
+    "b64",
+    "Base32",
+    "b32"
   ],
-  "license": "Apache2",
+  "license": "Apache-2.0",
   "ignore": [
     "**/.*",
     "node_modules",

examples/index.html

@@ -0,0 +1,12 @@
+<html>
+<head>
+  <meta charset="UTF-8">
+</head>
+<body>
+  This is for testing. Look in the console.
+  <script src="../index.js"></script>
+  <script src="../unibabel.hex.js"></script>
+  <script src="../unibabel.base32.js"></script>
+  <script src="./test.js"></script>
+</body>
+</html>

examples/node-buffer.js

@@ -0,0 +1,30 @@
+var str = "I ½ ♥ 𩶘";
+var buf = new Buffer(str);
+var base64 = buf.toString('base64');
+var hex = buf.toString('hex');
+var bytes = Array.prototype.map.call(buf, function (byte) {
+  return byte;
+});
+
+console.log('');
+console.log('UTF-8');
+console.log(str);
+console.log(base64);
+console.log(hex);
+console.log('[ ' + bytes.join(', ') + ' ]');
+console.log('');
+
+// Array.prototype.map.call(crypto.randomBytes(8), function (b) { return b; });
+var bytes = [ 255, 226, 26, 243, 134, 206, 147, 107 ];
+buf = new Buffer(bytes);
+str = buf.toString('binary');
+base64 = buf.toString('base64');
+hex = buf.toString('hex');
+
+console.log('');
+console.log('binary');
+console.log(str);
+console.log(base64);
+console.log(hex);
+console.log(bytes);
+console.log('');

examples/node-thirty-two.js

@@ -0,0 +1,8 @@
+var base32 = require('thirty-two');
+var str = "I ½ ♥ 𩶘";
+var buf = new Buffer(str, 'utf8');
+console.log('charLen', 7);
+console.log('byteLen', buf.byteLength, JSON.stringify(buf.toString('utf8')));
+var b32 = base32.encode(buf); // to base32
+console.log('encoded', b32.toString('utf8'));
+console.log('decoded', base32.decode(b32).toString('utf8'));

examples/test.js

@@ -0,0 +1,95 @@
+(function () {
+'use strict';
+
+var Unibabel = window.Unibabel;
+
+//UTF-8
+var pass = true;
+var references = {
+  string: "I ½ ♥ 𩶘"
+, array: [ 73, 32, 194, 189, 32, 226, 153, 165, 32, 240, 169, 182, 152 ]
+, hex: "4920c2bd20e299a520f0a9b698"
+, base64: "SSDCvSDimaUg8Km2mA=="
+, base32: 'JEQMFPJA4KM2KIHQVG3JQ==='
+};
+references.buffer = new Uint8Array(references.array);
+var binrefs = {
+  // Note that the binary string "ÿâó<86>Î<93>k" can't be serialized to text
+  array: [ 255, 226, 26, 243, 134, 206, 147, 107 ]
+, hex: "ffe21af386ce936b"
+, base64: "/+Ia84bOk2s="
+};
+binrefs.buffer = new Uint8Array(binrefs.array);
+
+var str = references.string;
+var buf = Unibabel.utf8ToBuffer(references.string);
+var base64 = Unibabel.bufferToBase64(references.buffer);
+var hex = Unibabel.bufferToHex(references.buffer);
+var b32 = Unibabel.bufferToBase32(references.buffer);
+
+function buffersAreEqual(buf1, buf2) {
+  if (buf1.length !== buf2.length) {
+    return false;
+  }
+  return Array.prototype.every.call(buf1, function (byte, i) {
+    if (byte === buf2[i]) {
+      return true;
+    }
+  });
+}
+
+// TODO compare buffer
+if (!buffersAreEqual(buf, references.array)) {
+  pass = false;
+  console.warn('[FAIL] utf8 -> buffer', buf);
+}
+if (base64 !== references.base64) {
+  pass = false;
+  console.warn('[FAIL] utf8 -> base64', base64);
+}
+if (hex !== references.hex) {
+  pass = false;
+  console.warn('[FAIL] utf8 -> hex', hex);
+}
+
+
+// binary
+var bytes = binrefs.array;
+buf = new Uint8Array(bytes);
+str = Unibabel.bufferToBinaryString(buf);
+base64 = Unibabel.bufferToBase64(buf);
+hex = Unibabel.bufferToHex(buf);
+
+// This can't be properly tested because binary strings can't be parsed
+// if (str !== "ÿâó†Î“k") {
+//   pass = false;
+//   console.log('[FAIL] binary -> str', str);
+// }
+if (binrefs.base64 !== base64) {
+  pass = false;
+  console.warn('[FAIL] binary -> base64', base64);
+}
+if (binrefs.hex !== hex) {
+  pass = false;
+  console.warn('[FAIL] binary -> hex', hex);
+}
+
+//
+// Base32
+//
+b32 = Unibabel.bufferToBase32(references.buffer);
+if (references.base32 !== b32) {
+  pass = false;
+  console.warn('[FAIL] binary -> base32', references.base32, '!==', b32);
+}
+buf = Unibabel.base32ToBuffer(references.base32);
+if (!buffersAreEqual(buf, references.buffer)) {
+  pass = false;
+  console.warn('[FAIL] base32 -> binary', references.buffer, '!==', buf);
+}
+
+if (pass) {
+  console.info('[PASS] :-D');
+}
+
+}());

examples/utf8-mdn.js

@@ -0,0 +1,198 @@
+(function (exports) {
+"use strict";
+var Unibabel = {};
+
+/*\
+|*|
+|*|  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, delim) {
+
+  var nMod3 = 2, sB64Enc = "";
+
+  for (var nLen = aBytes.length, nUint24 = 0, nIdx = 0; nIdx < nLen; nIdx++) {
+    nMod3 = nIdx % 3;
+    if (delim) {
+      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;
+
+}
+
+// helpers, not generally useful
+Unibabel.uint6ToB64 = uint6ToB64;
+Unibabel.b64ToUint6 = b64ToUint6;
+
+/* Base64 <--> TypedArray <--> UTF-8 */
+
+// TypedArray <--> UTF-8
+Unibabel.strToUtf8Arr = strToUTF8Arr;
+Unibabel.utf8ArrToStr = UTF8ArrToStr;
+// TypedArray <--> Base64
+Unibabel.arrToBase64 = base64EncArr;
+Unibabel.base64ToArr = base64DecToArr;
+
+if ('undefined' !== typeof module) {
+  module.exports = exports = Unibabel;
+}
+
+exports.Unibabel = Unibabel;
+}('undefined' !== typeof window ? window : exports));

index.js

@@ -1,194 +1,104 @@
 (function (exports) {
-"use strict";
-var Unibabel = {};
+'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 utf8ToBinaryString(str) {
+  var escstr = encodeURIComponent(str);
+  // replaces any uri escape sequence, such as %0A,
+  // with binary escape, such as 0x0A
+  var binstr = escstr.replace(/%([0-9A-F]{2})/g, function(match, p1) {
+    return String.fromCharCode(parseInt(p1, 16));
+  });
 
+  return binstr;
 }
 
-function base64DecToArr (sBase64, nBlocksSize) {
+function utf8ToBuffer(str) {
+  var binstr = utf8ToBinaryString(str);
+  var buf = binaryStringToBuffer(binstr);
+  return buf;
+}
 
-  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;
+function utf8ToBase64(str) {
+  var binstr = utf8ToBinaryString(str);
+  return btoa(binstr);
+}
 
+function binaryStringToUtf8(binstr) {
+  var escstr = binstr.replace(/(.)/g, function (m, p) {
+    var code = p.charCodeAt(0).toString(16).toUpperCase();
+    if (code.length < 2) {
+      code = '0' + code;
     }
+    return '%' + code;
+  });
+
+  return decodeURIComponent(escstr);
+}
+
+function bufferToUtf8(buf) {
+  var binstr = bufferToBinaryString(buf);
+
+  return binaryStringToUtf8(binstr);
+}
+
+function base64ToUtf8(b64) {
+  var binstr = atob(b64);
+
+  return binaryStringToUtf8(binstr);
+}
+
+function bufferToBinaryString(buf) {
+  var binstr = Array.prototype.map.call(buf, function (ch) {
+    return String.fromCharCode(ch);
+  }).join('');
+
+  return binstr;
+}
+
+function bufferToBase64(arr) {
+  var binstr = bufferToBinaryString(arr);
+  return btoa(binstr);
+}
+
+function binaryStringToBuffer(binstr) {
+  var buf;
+
+  if ('undefined' !== typeof Uint8Array) {
+    buf = new Uint8Array(binstr.length);
+  } else {
+    buf = [];
   }
 
-  return taBytes;
+  Array.prototype.forEach.call(binstr, function (ch, i) {
+    buf[i] = ch.charCodeAt(0);
+  });
+
+  return buf;
 }
 
-/* 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 base64ToBuffer(base64) {
+  var binstr = atob(base64);
+  var buf = binaryStringToBuffer(binstr);
+  return buf;
 }
 
-function base64EncArr (aBytes) {
+exports.Unibabel = {
+  utf8ToBinaryString: utf8ToBinaryString
+, utf8ToBuffer: utf8ToBuffer
+, utf8ToBase64: utf8ToBase64
+, binaryStringToUtf8: binaryStringToUtf8
+, bufferToUtf8: bufferToUtf8
+, base64ToUtf8: base64ToUtf8
+, bufferToBinaryString: bufferToBinaryString
+, bufferToBase64: bufferToBase64
+, binaryStringToBuffer: binaryStringToBuffer
+, base64ToBuffer: base64ToBuffer
 
-  var nMod3 = 2, sB64Enc = "";
+// compat
+, strToUtf8Arr: utf8ToBuffer
+, utf8ArrToStr: bufferToUtf8
+, arrToBase64: bufferToBase64
+, base64ToArr: base64ToBuffer
+};
 
-  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;
-
-}
-
-// helpers, not generally useful
-Unibabel.uint6ToB64 = uint6ToB64;
-Unibabel.b64ToUint6 = b64ToUint6;
-
-/* Base64 <--> TypedArray <--> UTF-8 */
-
-// TypedArray <--> UTF-8
-Unibabel.strToUtf8Arr = strToUTF8Arr;
-Unibabel.Utf8ArrToStr = UTF8ArrToStr;
-// TypedArray <--> Base64
-Unibabel.base64ToArr = base64EncArr;
-Unibabel.arrToBase64 = base64DecToArr;
-
-if ('undefined' !== typeof module) {
-  module.exports = exports = Unibabel;
-}
-
-exports.Unibabel = Unibabel;
-}('undefined' !== typeof window ? window : exports));
+}('undefined' !== typeof exports && exports || 'undefined' !== typeof window && window || global));

node.js

@@ -0,0 +1,19 @@
+'use strict';
+
+console.warn("Please don't use Unibabel in node.js. If you think you really think you have a valid use case please report it at https://git.coolaj86.com/coolaj86/unibabel.js/issues/new");
+throw new Error("[unibabel] you're doing it wrong");
+
+/*
+var data = 'I ½ ♥ 💩';
+var encoding = 'utf8';
+var buf = new Buffer(data, encoding);
+buf.toString('hex');
+buf.toString('base64');
+buf.toString('ascii');
+buf.toString('utf8');
+buf.toString('binary'); // deprecated, do not use
+
+var Base32 = require('thirty-two');
+var b32 = Base32.encode(buf);
+Base32.decode(buf);
+*/

package.json

@@ -0,0 +1,37 @@
+{
+  "name": "unibabel",
+  "version": "2.1.8",
+  "description": "Base64, TypedArrays, and UTF-8 / Unicode conversions in Browser (and Node) JavaScript",
+  "main": "node.js",
+  "browser": {
+    "./node.js": "./index.js"
+  },
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://git.coolaj86.com/coolaj86/unibabel.js.git"
+  },
+  "keywords": [
+    "ascii",
+    "binary",
+    "utf8",
+    "utf-8",
+    "ArrayBuffer",
+    "TypedArrays",
+    "TypedArray",
+    "Uint",
+    "Uint8Array",
+    "Base64",
+    "b64",
+    "Base32",
+    "b32"
+  ],
+  "author": "AJ ONeal <coolaj86@gmail.com> (https://coolaj86.com/)",
+  "license": "(MIT OR Apache-2.0)",
+  "bugs": {
+    "url": "https://git.coolaj86.com/coolaj86/unibabel.js/issues"
+  },
+  "homepage": "https://git.coolaj86.com/coolaj86/unibabel.js#readme"
+}

unibabel.base32.js

@@ -0,0 +1,142 @@
+/*
+Copyright (c) 2011, Chris Umbel
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+*/
+(function (exports) {
+'use strict';
+
+var charTable = "ABCDEFGHIJKLMNOPQRSTUVWXYZ234567";
+var byteTable = [
+    0xff, 0xff, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+    0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06,
+    0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e,
+    0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16,
+    0x17, 0x18, 0x19, 0xff, 0xff, 0xff, 0xff, 0xff,
+    0xff, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06,
+    0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e,
+    0x0f, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16,
+    0x17, 0x18, 0x19, 0xff, 0xff, 0xff, 0xff, 0xff
+];
+
+function quintetCount(buff) {
+    var quintets = Math.floor(buff.length / 5);
+    return buff.length % 5 === 0 ? quintets: quintets + 1;
+}
+
+exports.bufferToBase32 = function(plain) {
+    // plain MUST come in either as Array or Uint8Array
+    if('undefined' !== typeof Uint8Array) {
+        if (!(plain instanceof Uint8Array)){
+            plain = new Uint8Array(plain);
+        }
+    }
+    var i = 0;
+    var j = 0;
+    var shiftIndex = 0;
+    var digit = 0;
+    var encoded = new Array(quintetCount(plain) * 8);
+
+    /* byte by byte isn't as pretty as quintet by quintet but tests a bit
+        faster. will have to revisit. */
+    while(i < plain.length) {
+        var current = plain[i];
+
+        if(shiftIndex > 3) {
+            digit = current & (0xff >> shiftIndex);
+            shiftIndex = (shiftIndex + 5) % 8;
+            digit = (digit << shiftIndex) | ((i + 1 < plain.length) ?
+                plain[i + 1] : 0) >> (8 - shiftIndex);
+            i++;
+        } else {
+            digit = (current >> (8 - (shiftIndex + 5))) & 0x1f;
+            shiftIndex = (shiftIndex + 5) % 8;
+            if(shiftIndex === 0) { i++; }
+        }
+
+        encoded[j] = charTable[digit];
+        j++;
+    }
+
+    for(i = j; i < encoded.length; i++) {
+        encoded[i] = '=';
+    }
+
+    return encoded.join('');
+};
+
+exports.base32ToBuffer = function(encoded) {
+    var shiftIndex = 0;
+    var plainDigit = 0;
+    var plainChar;
+    var plainPos = 0;
+    var len = Math.ceil(encoded.length * 5 / 8);
+    var decoded;
+    encoded = encoded.split('').map(function (ch) {
+      return ch.charCodeAt(0);
+    });
+    if('undefined' !== typeof Uint8Array) {
+        encoded = new Uint8Array(encoded);
+        decoded = new Uint8Array(len);
+    } else {
+        decoded = new Array(len);
+    }
+
+    /* byte by byte isn't as pretty as octet by octet but tests a bit
+        faster. will have to revisit. */
+    for(var i = 0; i < encoded.length; i++) {
+        if(encoded[i] === 0x3d){ //'='
+            break;
+        }
+
+        var encodedByte = encoded[i] - 0x30;
+
+        if(encodedByte < byteTable.length) {
+            plainDigit = byteTable[encodedByte];
+
+            if(shiftIndex <= 3) {
+                shiftIndex = (shiftIndex + 5) % 8;
+
+                if(shiftIndex === 0) {
+                    plainChar |= plainDigit;
+                    decoded[plainPos] = plainChar;
+                    plainPos++;
+                    plainChar = 0;
+                } else {
+                    plainChar |= 0xff & (plainDigit << (8 - shiftIndex));
+                }
+            } else {
+                shiftIndex = (shiftIndex + 5) % 8;
+                plainChar |= 0xff & (plainDigit >>> shiftIndex);
+                decoded[plainPos] = plainChar;
+                plainPos++;
+
+                plainChar = 0xff & (plainDigit << (8 - shiftIndex));
+            }
+        } else {
+            throw new Error('Invalid input - it is not base32 encoded string');
+        }
+    }
+
+    if (decoded.slice) { // Array or TypedArray
+      return decoded.slice(0, plainPos);
+    } else { // Mobile Safari TypedArray
+      return new Uint8Array(Array.prototype.slice.call(decoded, 0, plainPos));
+    }
+};
+
+}(window.Unibabel || window));

unibabel.hex.js

@@ -0,0 +1,46 @@
+(function () {
+'use strict';
+
+function bufferToHex(arr) {
+  var i;
+  var len;
+  var hex = '';
+  var c;
+
+  for (i = 0, len = arr.length; i < len; i += 1) {
+    c = arr[i].toString(16);
+    if (c.length < 2) {
+      c = '0' + c;
+    }
+    hex += c;
+  }
+
+  return hex;
+}
+
+function hexToBuffer(hex) {
+  // TODO use Uint8Array or ArrayBuffer or DataView
+  var i;
+  var byteLen = hex.length / 2;
+  var arr;
+  var j = 0;
+
+  if (byteLen !== parseInt(byteLen, 10)) {
+    throw new Error("Invalid hex length '" + hex.length + "'");
+  }
+
+  arr = new Uint8Array(byteLen);
+
+  for (i = 0; i < byteLen; i += 1) {
+    arr[i] = parseInt(hex[j] + hex[j + 1], 16);
+    j += 2;
+  }
+
+  return arr;
+}
+
+// Hex Convenience Functions
+window.Unibabel.hexToBuffer = hexToBuffer;
+window.Unibabel.bufferToHex = bufferToHex;
+
+}());