public
Last active

Re-written and modularized UTF-8 and Base64 Javascript Encoding and Decoding Libraries / Modules for AMD, CommonJS, Nodejs and Browsers. Cross-browser compatible.

  • Download Gist
base64-utf8.module.js
JavaScript
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
// UTF8 Module
//
// Cleaner and modularized utf-8 encoding and decoding library for javascript.
//
// copyright: MIT
// author: Nijiko Yonskai, @nijikokun, nijikokun@gmail.com
(function (name, definition, context, dependencies) {
if (typeof context['module'] !== 'undefined' && context['module']['exports']) { if (dependencies && context['require']) { for (var i = 0; i < dependencies.length; i++) context[dependencies[i]] = context['require'](dependencies[i]); } context['module']['exports'] = definition.apply(context); }
else if (typeof context['define'] !== 'undefined' && context['define'] === 'function' && context['define']['amd']) { define(name, (dependencies || []), definition); }
else { context[name] = definition.apply(context); }
})('utf8', function () {
return {
encode: function (string) {
if (typeof string !== 'string') return string;
else string = string.replace(/\r\n/g, "\n");
var output = "", i = 0, charCode;
 
for (i; i < string.length; i++) {
charCode = string.charCodeAt(i);
 
if (charCode < 128)
output += String.fromCharCode(charCode);
else if ((charCode > 127) && (charCode < 2048))
output += String.fromCharCode((charCode >> 6) | 192),
output += String.fromCharCode((charCode & 63) | 128);
else
output += String.fromCharCode((charCode >> 12) | 224),
output += String.fromCharCode(((charCode >> 6) & 63) | 128),
output += String.fromCharCode((charCode & 63) | 128);
}
 
return output;
},
 
decode: function (string) {
if (typeof string !== 'string') return string;
var output = "", i = 0, charCode = 0;
 
while (i < string.length) {
charCode = string.charCodeAt(i);
 
if (charCode < 128)
output += String.fromCharCode(charCode),
i++;
else if ((charCode > 191) && (charCode < 224))
output += String.fromCharCode(((charCode & 31) << 6) | (string.charCodeAt(i + 1) & 63)),
i += 2;
else
output += String.fromCharCode(((charCode & 15) << 12) | ((string.charCodeAt(i + 1) & 63) << 6) | (string.charCodeAt(i + 2) & 63)),
i += 3;
}
 
return output;
}
};
}, this);
 
// Base64 Module
//
// Cleaner, modularized and properly scoped base64 encoding and decoding module for strings.
//
// copyright: MIT
// author: Nijiko Yonskai, @nijikokun, nijikokun@gmail.com
(function (name, definition, context, dependencies) {
if (typeof context['module'] !== 'undefined' && context['module']['exports']) { if (dependencies && context['require']) { for (var i = 0; i < dependencies.length; i++) context[dependencies[i]] = context['require'](dependencies[i]); } context['module']['exports'] = definition.apply(context); }
else if (typeof context['define'] !== 'undefined' && context['define'] === 'function' && context['define']['amd']) { define(name, (dependencies || []), definition); }
else { context[name] = definition(); }
})('base64', function (utf8) {
var $this = this;
var $utf8 = utf8 || this.utf8;
var map = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
 
return {
encode: function (input) {
if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
if (typeof input !== 'string') return input;
else input = $utf8.encode(input);
if (typeof $this.btoa !== 'undefined') return $this.btoa(input);
var output = "", a, b, c, d, e, f, g, i = 0;
 
while (i < input.length) {
a = input.charCodeAt(i++);
b = input.charCodeAt(i++);
c = input.charCodeAt(i++);
d = a >> 2;
e = ((a & 3) << 4) | (b >> 4);
f = ((b & 15) << 2) | (c >> 6);
g = c & 63;
 
if (isNaN(b)) f = g = 64;
else if (isNaN(c)) g = 64;
 
output += map.charAt(d) + map.charAt(e) + map.charAt(f) + map.charAt(g);
}
 
return output;
},
 
decode: function (input) {
if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
if (typeof input !== 'string') return input;
else input.replace(/[^A-Za-z0-9\+\/\=]/g, "");
if (typeof $this.atob !== 'undefined') return $this.atob(input);
var output = "", a, b, c, d, e, f, g, i = 0;
 
while (i < input.length) {
d = map.indexOf(input.charAt(i++));
e = map.indexOf(input.charAt(i++));
f = map.indexOf(input.charAt(i++));
g = map.indexOf(input.charAt(i++));
 
a = (d << 2) | (e >> 4);
b = ((e & 15) << 4) | (f >> 2);
c = ((f & 3) << 6) | g;
 
output += String.fromCharCode(a);
if (f != 64) output += String.fromCharCode(b);
if (g != 64) output += String.fromCharCode(c);
}
 
return $utf8.decode(output);
}
}
}, this, [ "utf8" ]);
base64.module.js
JavaScript
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
// Base64 Module
//
// Cleaner, modularized and properly scoped base64 encoding and decoding module for strings.
//
// copyright: MIT
// author: Nijiko Yonskai, @nijikokun, nijikokun@gmail.com
(function (name, definition, context, dependencies) {
if (typeof context['module'] !== 'undefined' && context['module']['exports']) { if (dependencies && context['require']) { for (var i = 0; i < dependencies.length; i++) context[dependencies[i]] = context['require'](dependencies[i]); } context['module']['exports'] = definition.apply(context); }
else if (typeof context['define'] !== 'undefined' && context['define'] === 'function' && context['define']['amd']) { define(name, (dependencies || []), definition); }
else { context[name] = definition(); }
})('base64', function (utf8) {
var $this = this;
var $utf8 = utf8 || this.utf8;
var map = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
 
return {
encode: function (input) {
if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
if (typeof input !== 'string') return input;
else input = $utf8.encode(input);
if (typeof $this.btoa !== 'undefined') return $this.btoa(input);
var output = "", a, b, c, d, e, f, g, i = 0;
 
while (i < input.length) {
a = input.charCodeAt(i++);
b = input.charCodeAt(i++);
c = input.charCodeAt(i++);
d = a >> 2;
e = ((a & 3) << 4) | (b >> 4);
f = ((b & 15) << 2) | (c >> 6);
g = c & 63;
 
if (isNaN(b)) f = g = 64;
else if (isNaN(c)) g = 64;
 
output += map.charAt(d) + map.charAt(e) + map.charAt(f) + map.charAt(g);
}
 
return output;
},
 
decode: function (input) {
if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
if (typeof input !== 'string') return input;
else input.replace(/[^A-Za-z0-9\+\/\=]/g, "");
if (typeof $this.atob !== 'undefined') return $this.atob(input);
var output = "", a, b, c, d, e, f, g, i = 0;
 
while (i < input.length) {
d = map.indexOf(input.charAt(i++));
e = map.indexOf(input.charAt(i++));
f = map.indexOf(input.charAt(i++));
g = map.indexOf(input.charAt(i++));
 
a = (d << 2) | (e >> 4);
b = ((e & 15) << 4) | (f >> 2);
c = ((f & 3) << 6) | g;
 
output += String.fromCharCode(a);
if (f != 64) output += String.fromCharCode(b);
if (g != 64) output += String.fromCharCode(c);
}
 
return $utf8.decode(output);
}
}
}, this, [ "utf8" ]);
utf8.module.js
JavaScript
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
// UTF8 Module
//
// Cleaner and modularized utf-8 encoding and decoding library for javascript.
//
// copyright: MIT
// author: Nijiko Yonskai, @nijikokun, nijikokun@gmail.com
(function (name, definition, context, dependencies) {
if (typeof context['module'] !== 'undefined' && context['module']['exports']) { if (dependencies && context['require']) { for (var i = 0; i < dependencies.length; i++) context[dependencies[i]] = context['require'](dependencies[i]); } context['module']['exports'] = definition.apply(context); }
else if (typeof context['define'] !== 'undefined' && context['define'] === 'function' && context['define']['amd']) { define(name, (dependencies || []), definition); }
else { context[name] = definition.apply(context); }
})('utf8', function () {
return {
encode: function (string) {
if (typeof string !== 'string') return string;
else string = string.replace(/\r\n/g, "\n");
var output = "", i = 0, charCode;
 
for (i; i < string.length; i++) {
charCode = string.charCodeAt(i);
 
if (charCode < 128)
output += String.fromCharCode(charCode);
else if ((charCode > 127) && (charCode < 2048))
output += String.fromCharCode((charCode >> 6) | 192),
output += String.fromCharCode((charCode & 63) | 128);
else
output += String.fromCharCode((charCode >> 12) | 224),
output += String.fromCharCode(((charCode >> 6) & 63) | 128),
output += String.fromCharCode((charCode & 63) | 128);
}
 
return output;
},
 
decode: function (string) {
if (typeof string !== 'string') return string;
var output = "", i = 0, charCode = 0;
 
while (i < string.length) {
charCode = string.charCodeAt(i);
 
if (charCode < 128)
output += String.fromCharCode(charCode),
i++;
else if ((charCode > 191) && (charCode < 224))
output += String.fromCharCode(((charCode & 31) << 6) | (string.charCodeAt(i + 1) & 63)),
i += 2;
else
output += String.fromCharCode(((charCode & 15) << 12) | ((string.charCodeAt(i + 1) & 63) << 6) | (string.charCodeAt(i + 2) & 63)),
i += 3;
}
 
return output;
}
};
}, this);

There is an error in the "decode" function of "base64". You must use the "window.atob" function and not the "window.btoa" function.

Thanks! I've updated it to use atob @tadaa9

Thanks for that code. In some Browsers (i.e. my Chrome28 and FF22) the native btoa function has problems with multi byte characters (throws InvalidCharacterError).

So, wouldn't it be better to utf8 de/encode those strings, too? Something like:

encode: function (input) {
      if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
      if (typeof input !== 'string') return input;
      else input = $utf8.encode(input);
      if (typeof $this.btoa !== 'undefined') return $this.btoa(input); // moved
      var output = "", a, b, c, d, e, f, g, i = 0;
      // ...

and

decode: function (input) {
      if (typeof $utf8 === 'undefined') throw { error: "MissingMethod", message: "UTF8 Module is missing." };
      if (typeof input !== 'string') return input;
      else input.replace(/[^A-Za-z0-9\+\/\=]/g, "");
      if (typeof $this.atob !== 'undefined') return $utf8.decode($this.atob(input)); // moved and decoded
      // ...

With these changes i get no problems with lines like:

base64.decode(base64.encode('Hello World 秦始皇帝'))

@delbertooo Actually this makes more sense. Updating to reflect changes

I'm having a lot of trouble getting this library to work because I can find no documentation or examples of how to integrate this library and I'm unsure if it's the content I'm attempting to decode or the way I'm attempting to use it. Could we get a link to a couple examples demonstrating it's use and any details concerning Content Delivery Network (CDN) access?

@modusinternet simply copy the raw data from the first file on this gist (it includes both base64 and utf8)

then you simply base64.decode(base64.encode('Hello World 秦始皇帝'))

Please sign in to comment on this gist.

Something went wrong with that request. Please try again.