Skip to content

Add checks for surrogate pairing for UTF-8 generation #1500

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

Merged
merged 2 commits into from
Nov 4, 2025
+32 −12
Merged

Add checks for surrogate pairing for UTF-8 generation #1500

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
01fcea5
Add checks for surrogate pairing for UTF-8 generation
cowtowncoder Nov 4, 2025
0bf0d2e
Add release notes
cowtowncoder Nov 4, 2025
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
2 changes: 2 additions & 0 deletions release-notes/VERSION-2.x
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,8 @@ a pure JSON library.
#1470: Add method `copyCurrentStructureExact()` to `JsonGenerator`
(contributed by Lars H)
#1477: Add `JsonGenerator.has(StreamWriteCapability)` convenience method
#1500: Add checks for surrogate pairing for UTF-8 generation
(fix by @cowtowncoder, w/ Claude code)

2.20.1 (30-Oct-2025)

Expand Down
42 changes: 30 additions & 12 deletions src/main/java/com/fasterxml/jackson/core/json/UTF8JsonGenerator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1528,9 +1528,12 @@ private final void _writeStringSegment2(final char[] cbuf, int offset, final int
final boolean combineSurrogates = Feature.COMBINE_UNICODE_SURROGATES_IN_UTF8.enabledIn(_features);
if (combineSurrogates && offset < end) {
char highSurrogate = (char) ch;
char lowSurrogate = cbuf[offset++];
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
char lowSurrogate = cbuf[offset];
if (_isEndOfSurrogatePair(lowSurrogate)) {
offset++;
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
}
}
}
outputPtr = _outputMultiByteChar(ch, outputPtr);
Expand Down Expand Up @@ -1576,9 +1579,12 @@ private final void _writeStringSegment2(final String text, int offset, final int
final boolean combineSurrogates = Feature.COMBINE_UNICODE_SURROGATES_IN_UTF8.enabledIn(_features);
if (combineSurrogates && offset < end) {
char highSurrogate = (char) ch;
char lowSurrogate = text.charAt(offset++);
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
char lowSurrogate = text.charAt(offset);
if (_isEndOfSurrogatePair(lowSurrogate)) {
offset++;
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
}
}
}
outputPtr = _outputMultiByteChar(ch, outputPtr);
Expand Down Expand Up @@ -1752,9 +1758,12 @@ private final void _writeCustomStringSegment2(final char[] cbuf, int offset, fin
final boolean combineSurrogates = Feature.COMBINE_UNICODE_SURROGATES_IN_UTF8.enabledIn(_features);
if (combineSurrogates && offset < end) {
char highSurrogate = (char) ch;
char lowSurrogate = cbuf[offset++];
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
char lowSurrogate = cbuf[offset];
if (_isEndOfSurrogatePair(lowSurrogate)) {
offset++;
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
}
}
}
outputPtr = _outputMultiByteChar(ch, outputPtr);
Expand Down Expand Up @@ -1819,9 +1828,12 @@ private final void _writeCustomStringSegment2(final String text, int offset, fin
final boolean combineSurrogates = Feature.COMBINE_UNICODE_SURROGATES_IN_UTF8.enabledIn(_features);
if (combineSurrogates && offset < end) {
char highSurrogate = (char) ch;
char lowSurrogate = text.charAt(offset++);
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
char lowSurrogate = text.charAt(offset);
if (_isEndOfSurrogatePair(lowSurrogate)) {
offset++;
outputPtr = _outputSurrogatePair(highSurrogate, lowSurrogate, outputPtr);
continue;
}
}
}
outputPtr = _outputMultiByteChar(ch, outputPtr);
Expand Down Expand Up @@ -2291,5 +2303,11 @@ private static boolean _isStartOfSurrogatePair(final int ch) {
// In 0xD800 - 0xDBFF range?
return (ch & 0xFC00) == 0xD800;
}

// @since 2.21
private static boolean _isEndOfSurrogatePair(final int ch) {
// In 0xDC00 - 0xDFFF range?
return (ch & 0xFC00) == 0xDC00;
}
}