Created
September 18, 2017 06:55
-
-
Save otakustay/bc56fb0a144987b1a7829c26f707a8e0 to your computer and use it in GitHub Desktop.
isUTF8.java
This file contains hidden or 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
| public class App { | |
| static boolean isUTF8(int[] buf) { | |
| int i = 0; | |
| int len = buf.length; | |
| while(i < len) { | |
| // UTF8-1 = %x00-7F | |
| if (buf[i] <= 0x7F) { | |
| i++; | |
| continue; | |
| } | |
| // UTF8-2 = %xC2-DF UTF8-tail | |
| if (buf[i] >= 0xC2 && buf[i] <= 0xDF) { | |
| // if(buf[i + 1] >= 0x80 && buf[i + 1] <= 0xBF) { | |
| if (buf[i + 1] >> 6 == 2) { | |
| i += 2; | |
| continue; | |
| } else { | |
| return false; | |
| } | |
| } | |
| // UTF8-3 = %xE0 %xA0-BF UTF8-tail | |
| // UTF8-3 = %xED %x80-9F UTF8-tail | |
| if ( | |
| ( | |
| (buf[i] == 0xE0 && buf[i + 1] >= 0xA0 && buf[i + 1] <= 0xBF) || | |
| (buf[i] == 0xED && buf[i + 1] >= 0x80 && buf[i + 1] <= 0x9F) | |
| ) && buf[i + 2] >> 6 == 2 | |
| ) { | |
| i += 3; | |
| continue; | |
| } | |
| // UTF8-3 = %xE1-EC 2( UTF8-tail ) | |
| // UTF8-3 = %xEE-EF 2( UTF8-tail ) | |
| if ( | |
| ( | |
| (buf[i] >= 0xE1 && buf[i] <= 0xEC) || | |
| (buf[i] >= 0xEE && buf[i] <= 0xEF) | |
| ) && | |
| buf[i + 1] >> 6 == 2 && | |
| buf[i + 2] >> 6 == 2 | |
| ) { | |
| i += 3; | |
| continue; | |
| } | |
| // UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) | |
| // %xF1-F3 3( UTF8-tail ) | |
| // %xF4 %x80-8F 2( UTF8-tail ) | |
| if ( | |
| ( | |
| (buf[i] == 0xF0 && buf[i + 1] >= 0x90 && buf[i + 1] <= 0xBF) || | |
| (buf[i] >= 0xF1 && buf[i] <= 0xF3 && buf[i + 1] >> 6 == 2) || | |
| (buf[i] == 0xF4 && buf[i + 1] >= 0x80 && buf[i + 1] <= 0x8F) | |
| ) && | |
| buf[i + 2] >> 6 == 2 && | |
| buf[i + 3] >> 6 == 2 | |
| ) { | |
| i += 4; | |
| continue; | |
| } | |
| return false; | |
| } | |
| return true; | |
| } | |
| public static void main(String args[]) { | |
| int[] bytes = {0x20, 0xce, 0xd2, 0xca, 0xc7, 0xcb, 0xad, 0x0a}; | |
| boolean result = App.isUTF8(bytes); | |
| System.out.println(result); | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment