Skip to content

Port lre fixes 1 #1425

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
saghul wants to merge 4 commits into
base: master
Choose a base branch
from
+26 −15
Open

Port lre fixes 1 #1425

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f17ffc2
Fix RegExp.prototype[Symbol.split] to not coerce captures to strings
saghul Mar 14, 2026
e226db0
Fix Regexp.prototype[Symbol.match] to use CreateDataPropertyOrThrow
saghul Mar 14, 2026
9555bfa
Adjust lastIndex to leading surrogate in unicode RegExp
saghul Mar 14, 2026
1de61dc
Make \x{N} a syntax error in escape sequences
saghul Mar 14, 2026
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
34 changes: 25 additions & 9 deletions libregexp.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -477,9 +477,21 @@ int lre_parse_escape(const uint8_t **pp, int allow_utf16)
c = '\v';
break;
case 'x':
{
int h0, h1;

h0 = from_hex(*p++);
if (h0 < 0)
return -1;
h1 = from_hex(*p++);
if (h1 < 0)
return -1;
c = (h0 << 4) | h1;
}
break;
case 'u':
{
int h, n, i;
int h, i;
uint32_t c1;

if (*p == '{' && allow_utf16) {
Expand All @@ -497,14 +509,8 @@ int lre_parse_escape(const uint8_t **pp, int allow_utf16)
}
p++;
} else {
if (c == 'x') {
n = 2;
} else {
n = 4;
}

c = 0;
for(i = 0; i < n; i++) {
for(i = 0; i < 4; i++) {
h = from_hex(*p++);
if (h < 0) {
return -1;
Expand Down Expand Up @@ -2501,6 +2507,7 @@ int lre_exec(uint8_t **capture,
REExecContext s_s, *s = &s_s;
int re_flags, i, alloca_size, ret;
StackInt *stack_buf;
const uint8_t *cptr;

re_flags = lre_get_flags(bc_buf);
s->multi_line = (re_flags & LRE_FLAG_MULTILINE) != 0;
Expand All @@ -2527,8 +2534,17 @@ int lre_exec(uint8_t **capture,
capture[i] = NULL;
alloca_size = s->stack_size_max * sizeof(stack_buf[0]);
stack_buf = alloca(alloca_size);

cptr = cbuf + (cindex << cbuf_type);
if (0 < cindex && cindex < clen && s->cbuf_type == 2) {
const uint16_t *p = (const uint16_t *)cptr;
if (is_lo_surrogate(*p) && is_hi_surrogate(p[-1])) {
cptr = (const uint8_t *)(p - 1);
}
Comment on lines +2540 to +2543
Copy link
Copy Markdown
Contributor

@bnoordhuis bnoordhuis Mar 28, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unsafe/unsound when the pointer is unaligned. Something like this is sound (assuming it's not readying before the start of the buffer, of course):

Suggested change
const uint16_t *p = (const uint16_t *)cptr;
if (is_lo_surrogate(*p) && is_hi_surrogate(p[-1])) {
cptr = (const uint8_t *)(p - 1);
}
uint16_t c[2];
memcpy(c, &cptr[-2], sizeof(c));
if (is_lo_surrogate(c[1]) && is_hi_surrogate(c[0])) {
cptr -= 2;
}

The high/low surrogate checks look inverted though.

}

ret = lre_exec_backtrack(s, capture, stack_buf, 0, bc_buf + RE_HEADER_LEN,
cbuf + (cindex << cbuf_type), false);
cptr, false);
lre_realloc(s->opaque, s->state_stack, 0);
return ret;
}
Expand Down
7 changes: 1 addition & 6 deletions quickjs.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47979,7 +47979,7 @@ static JSValue js_regexp_Symbol_match(JSContext *ctx, JSValueConst this_val,
if (JS_IsException(matchStr))
goto exception;
isEmpty = JS_IsEmptyString(matchStr);
if (JS_SetPropertyInt64(ctx, A, n++, matchStr) < 0)
if (JS_DefinePropertyValueInt64(ctx, A, n++, matchStr, JS_PROP_C_W_E | JS_PROP_THROW) < 0)
goto exception;
if (isEmpty) {
int64_t thisIndex, nextIndex;
Expand Down Expand Up @@ -48588,11 +48588,6 @@ static JSValue js_regexp_Symbol_split(JSContext *ctx, JSValueConst this_val,
sub = JS_GetPropertyInt64(ctx, z, i);
if (JS_IsException(sub))
goto exception;
if (!JS_IsUndefined(sub)) {
sub = JS_ToStringFree(ctx, sub);
if (JS_IsException(sub))
goto exception;
}
if (JS_DefinePropertyValueInt64(ctx, A, lengthA++, sub, JS_PROP_C_W_E | JS_PROP_THROW) < 0)
goto exception;
if (lengthA == lim)
Expand Down
Loading