Skip to content

Fix UTF-16 surrogate validation #291

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
efegokdemir wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix UTF-16 surrogate validation #291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions bifromq-util/src/main/java/org/apache/bifromq/util/UTF8Util.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,9 @@ public static boolean isWellFormed(String str, boolean sanityCheck) {
if (cl == '\u0000') {
return false;
}
if (Character.isLowSurrogate(cl)) {
return false;
}
if (sanityCheck && isUnacceptableChar(cl)) {
return false;
}
Expand All @@ -47,15 +50,19 @@ public static boolean isWellFormed(String str, boolean sanityCheck) {
if (cr == '\u0000') {
return false;
}
if (Character.isSurrogatePair(cl, cr)) {
if (Character.isHighSurrogate(cl)) {
if (!Character.isLowSurrogate(cr)) {
return false;
}
} else if (Character.isLowSurrogate(cr)) {
return false;
}
if (sanityCheck && isUnacceptableChar(cr)) {
return false;
}
cl = cr;
}
return true;
return !Character.isHighSurrogate(cl);
}

public static boolean isValidUTF8Payload(ByteBuffer payload) {
Expand Down
5 changes: 4 additions & 1 deletion bifromq-util/src/test/java/org/apache/bifromq/util/UTF8UtilTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,10 @@ public void emptyClientId() {
@Test
public void mustNotChars() {
assertFalse(UTF8Util.isWellFormed("hello\u0000world", false)); // null character U+0000
assertFalse(UTF8Util.isWellFormed("hello\uD83D\uDE0Aworld", false)); // surrogate pairs
assertTrue(UTF8Util.isWellFormed("hello\uD83D\uDE0Aworld", false)); // valid surrogate pair
assertFalse(UTF8Util.isWellFormed("hello\uD83Dworld", false)); // unpaired high surrogate
assertFalse(UTF8Util.isWellFormed("hello\uDE0Aworld", false)); // unpaired low surrogate
assertFalse(UTF8Util.isWellFormed("hello\uD83D", false)); // trailing high surrogate
}

@Test
Expand Down