Skip to content

bound recovery scan to input end in xs_textdecoder_decode #1637

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
rootvector2 wants to merge 1 commit into
base: public
Choose a base branch
from
+29 −6
Open

bound recovery scan to input end in xs_textdecoder_decode #1637

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
26 changes: 20 additions & 6 deletions modules/data/text/decoder/textdecoder.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,10 +187,17 @@ void xs_textdecoder_decode(xsMachine *the)
else if (first > 0xF4) // no valid next byte
clen = 0;

const uint8_t *s = &utf8[1];
while (clen-- > 0) {
uint8_t c = c_read8(src);
if ((lower <= c) && (c <= upper))
src++;
uint8_t c = *s++;
if ((lower <= c) && (c <= upper)) {
if (bufferLength) {
bufferLength--;
buffer++;
}
else
src++;
}
else
break;
}
Expand Down Expand Up @@ -321,10 +328,17 @@ void xs_textdecoder_decode(xsMachine *the)
else if (first > 0xF4) // no valid next byte
clen = 0;

const uint8_t *s = &utf8[1];
while (clen-- > 0) {
uint8_t c = c_read8(src);
if ((lower <= c) && (c <= upper))
src++;
uint8_t c = *s++;
if ((lower <= c) && (c <= upper)) {
if (bufferLength) {
bufferLength--;
buffer++;
}
else
src++;
}
else
break;
}
Expand Down
9 changes: 9 additions & 0 deletions tests/modules/data/text/decoder/decodestream.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,3 +46,12 @@ assert.sameValue("\uFFFD", decoder.decode());

assert.sameValue("", decoder.decode(Uint8Array.of(0xF0, 0x9F, 0x92), {stream: true}));
assert.sameValue("\uFFFD", decoder.decode());

// illegal sequence spanning a buffered partial lead and a short final chunk:
// the recovery scan must consume from the buffered bytes before src and stop at the
// end of the input. The chunk is a view whose backing store holds continuation bytes
// (0x90) past its length, so the bytes seen are F0 80 90 90: the 0x80 is below the
// 0x90 lower bound for an F0 lead, so it and the two trailing 0x90 each decode to U+FFFD.
assert.sameValue("", decoder.decode(Uint8Array.of(0xF0, 0x80), {stream: true}));
assert.sameValue("\uFFFD\uFFFD\uFFFD\uFFFD", decoder.decode(new Uint8Array(8).fill(0x90).subarray(0, 2), {stream: true}));
assert.sameValue("", decoder.decode());