-
-
Save mikesherov/1008218 to your computer and use it in GitHub Desktop.
140byt.es -- convert string to array of UTF-8 bytes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // http://en.wikipedia.org/wiki/UTF-8 | |
| function stringToByteArray(a,b,c,d,e,f,g,h,j){ | |
| for( | |
| b = [ | |
| e = | |
| f = | |
| d = 0 | |
| ] // initialise variables | |
| ; | |
| c = a.charCodeAt(d++) // get the character code from the string | |
| ; | |
| ){ | |
| g = 128; // 128 is the base for a lot of numbers below | |
| c < g // under 128 is UTF-8 (ASCII range), 1 byte | |
| ? | |
| b[e] = c // add to byte array | |
| : | |
| c < g*4 // under 2048 2bytes | |
| ? | |
| f = 1 // 1 bytes left to process | |
| : | |
| c < 65536 // under 65536 is 3bytes | |
| ? | |
| f = 2 // 2 left to process | |
| : | |
| c < 2<<20 && f = 3; // 3bytes left to process | |
| for( // process the remaining bytes indicated by `f` | |
| j = e++, // move onto the next slot in the byte array | |
| h = f | |
| ; | |
| f-- > 0 // -1 and check if greater than 0 still | |
| ; | |
| ) | |
| g += (2<<(5-f)), | |
| b[e++] = 128 + (c >> f*6 & 63), // shift f * 6 bits, mask 1byte and add 128 | |
| b[j] = g + (c >> 6*h) //set the first byte | |
| } | |
| return b // return the byte array | |
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| function(a,b,c,d,e,f,g,h,j){for(b=[e=f=d=0];c=a.charCodeAt(d++);){g=128;c<g?b[e]=c:c<g*4?f=1:c<65536?f=2:c<2<<20&&f=3;for(j=e++,h=f;f-->0;)g+=(2<<(5-f)),b[e++]=128+(c>>f*6&63),b[j]=g+(c>>6*h)}return b} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE | |
| Version 2, December 2004 | |
| Copyright (C) 2011 YOUR_NAME_HERE <YOUR_URL_HERE> | |
| Everyone is permitted to copy and distribute verbatim or modified | |
| copies of this license document, and changing it is allowed as long | |
| as the name is changed. | |
| DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE | |
| TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION | |
| 0. You just DO WHAT THE FUCK YOU WANT TO. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "name": "stringToByteArray", | |
| "description": "Convert a string of characters to an array of UTF-8 bytes", | |
| "keywords": [ | |
| "cryptography", | |
| "utf8", | |
| ] | |
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| function stringToByteArray(str) { | |
| var bytes = [], code, i; | |
| for(i = 0; i < str.length; i++) { | |
| code = str.charCodeAt(i); | |
| if (code < 128) { | |
| bytes.push(code); | |
| } else if (code < 2048) { | |
| bytes.push(192+(code>>6), 128+(code&63)); | |
| } else if (code < 65536) { | |
| bytes.push(224+(code>>12), 128+((code>>6)&63), 128+(code&63)); | |
| } else if (code < 2097152) { | |
| bytes.push(240+(code>>18), 128+((code>>12)&63), 128+((code>>6)&63), 128+(code&63)); | |
| } | |
| } | |
| return bytes; | |
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <!DOCTYPE html> | |
| <title>stringToByteArray</title> | |
| <div><b id="ret"></b> Before golfing value</div> | |
| <div><b id="ret2"></b> After golfing value</div> | |
| <script> | |
| // write a small example that shows off the API for your example | |
| // and tests it in one fell swoop. | |
| function stringToByteArrayOld(str) { | |
| var bytes = [], code, i; | |
| for(i = 0; i < str.length; i++) { | |
| code = str.charCodeAt(i); | |
| if (code < 128) { | |
| bytes.push(code); | |
| } else if (code < 2048) { | |
| bytes.push(192+(code>>6), 128+(code&63)); | |
| } else if (code < 65536) { | |
| bytes.push(224+(code>>12), 128+((code>>6)&63), 128+(code&63)); | |
| } else if (code < 2097152) { | |
| bytes.push(240+(code>>18), 128+((code>>12)&63), 128+((code>>6)&63), 128+(code&63)); | |
| } | |
| } | |
| return bytes; | |
| } | |
| var stringToByteArray = function(a,b,c,d,e,f,g,h,j){for(b=[e=f=d=0];c=a.charCodeAt(d++);){g=128;c<g?b[e]=c:c<g*4?f=1:c<65536?f=2:c<2<<20&&f=3;for(j=e++,h=f;f-->0;)g+=(2<<(5-f)),b[e++]=128+(c>>f*6&63),b[j]=g+(c>>6*h)}return b}; | |
| document.getElementById( "ret" ).innerHTML = stringToByteArrayOld("hello☺䭢it works👍"); | |
| document.getElementById( "ret2" ).innerHTML = stringToByteArray("hello☺䭢it works👍"); | |
| </script> |
That's weird. The demo I modified from yours to compare function calls before and after. Seems to work every time I run it....
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
FYI demo doesn't seem to work. before and after seem to differ