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 +1,54 @@
-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**.
 
 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
 ===
 
@@ -20,15 +64,29 @@ 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
@@ -64,14 +122,22 @@ alert(sMyOutput);
 License
 =======
 
-Mozilla has licensed this code in the Public Domain, which means that I am at liberty to re-license my copy
+* `index.js` and `unibabel.hex.js` are dual-licensed as Apache 2.0 and MIT.
-under the Apache 2, which is something that, general speaking, your legal department will feel more comfortable with.
+* `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
 ------
 

bower.json

@@ -1,10 +1,9 @@
 {
   "name": "unibabel",
   "main": "index.js",
-  "version": "2.0.0",
+  "homepage": "https://git.coolaj86.com/coolaj86/unibabel.js",
-  "homepage": "https://github.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');
+}
+
+}());

index.js

@@ -1,4 +1,4 @@
-(function () {
+(function (exports) {
 'use strict';
 
 function utf8ToBinaryString(str) {
@@ -6,7 +6,7 @@ function utf8ToBinaryString(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('0x' + p1);
+    return String.fromCharCode(parseInt(p1, 16));
   });
 
   return binstr;
@@ -25,7 +25,7 @@ function utf8ToBase64(str) {
 
 function binaryStringToUtf8(binstr) {
   var escstr = binstr.replace(/(.)/g, function (m, p) {
-    var code = p.charCodeAt(p).toString(16).toUpperCase();
+    var code = p.charCodeAt(0).toString(16).toUpperCase();
     if (code.length < 2) {
       code = '0' + code;
     }
@@ -36,9 +36,7 @@ function binaryStringToUtf8(binstr) {
 }
 
 function bufferToUtf8(buf) {
-  var binstr = Array.prototype.map.call(buf, function (ch) {
+  var binstr = bufferToBinaryString(buf);
-    return '0x' + String.fromCharCode(ch);
-  }).join('');
 
   return binaryStringToUtf8(binstr);
 }
@@ -65,7 +63,7 @@ function bufferToBase64(arr) {
 function binaryStringToBuffer(binstr) {
   var buf;
 
-  if ('undefined' === typeof Uint8Array) {
+  if ('undefined' !== typeof Uint8Array) {
     buf = new Uint8Array(binstr.length);
   } else {
     buf = [];
@@ -84,7 +82,7 @@ function base64ToBuffer(base64) {
   return buf;
 }
 
-window.Unibabel = {
+exports.Unibabel = {
   utf8ToBinaryString: utf8ToBinaryString
 , utf8ToBuffer: utf8ToBuffer
 , utf8ToBase64: utf8ToBase64
@@ -103,4 +101,4 @@ window.Unibabel = {
 , base64ToArr: base64ToBuffer
 };
 
-}());
+}('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-dom.js

@@ -1 +0,0 @@
-index.js

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));