Created
October 26, 2019 07:11
-
-
Save AugustNagro/4fa5bd7287870433fb24a1fd645836bd to your computer and use it in GitHub Desktop.
Pattern match a UTF-8 ByteBuffer in Java
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
| import java.nio.ByteBuffer; | |
| import java.nio.charset.StandardCharsets; | |
| public class Utf8CharSeq implements CharSequence { | |
| private final ByteBuffer b; | |
| public Utf8CharSeq(ByteBuffer b) { | |
| this.b = b; | |
| } | |
| @Override | |
| public int length() { | |
| return b.remaining(); | |
| } | |
| @Override | |
| public char charAt(int index) { | |
| return (char) (0xFF & b.get(index)); | |
| } | |
| @Override | |
| public CharSequence subSequence(int start, int end) { | |
| ByteBuffer bb = b.duplicate(); | |
| bb.position(bb.position() + start); | |
| bb.limit(bb.position() + end - start); | |
| return new Utf8CharSeq(bb); | |
| } | |
| /** | |
| * Do not call. Only implemented so | |
| * Matcher.group(..) returns in correct UTF-16 | |
| * encoding for matching subsequence. | |
| */ | |
| @Override | |
| public String toString() { | |
| return StandardCharsets.UTF_8.decode(b).toString(); | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment