Skip to content
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

Implement extended named capture group identifiers #90

Merged
merged 1 commit into from
Nov 19, 2023
Merged

Implement extended named capture group identifiers #90

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
23 changes: 14 additions & 9 deletions libregexp.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1071,11 +1071,10 @@ static int re_is_simple_quantifier(const uint8_t *bc_buf, int bc_buf_len)
}

/* '*pp' is the first char after '<' */
static int re_parse_group_name(char *buf, int buf_size,
const uint8_t **pp, BOOL is_utf16)
static int re_parse_group_name(char *buf, int buf_size, const uint8_t **pp)
{
const uint8_t *p;
uint32_t c;
const uint8_t *p, *p1;
uint32_t c, d;
char *q;

p = *pp;
Expand All @@ -1086,11 +1085,18 @@ static int re_parse_group_name(char *buf, int buf_size,
p++;
if (*p != 'u')
return -1;
c = lre_parse_escape(&p, is_utf16 * 2);
c = lre_parse_escape(&p, 2); // accept surrogate pairs
} else if (c == '>') {
break;
} else if (c >= 128) {
c = unicode_from_utf8(p, UTF8_CHAR_LEN_MAX, &p);
if (c >= 0xD800 && c <= 0xDBFF) {
d = unicode_from_utf8(p, UTF8_CHAR_LEN_MAX, &p1);
if (d >= 0xDC00 && d <= 0xDFFF) {
c = 0x10000 + 0x400 * (c - 0xD800) + (d - 0xDC00);
p = p1;
}
}
} else {
p++;
}
Expand Down Expand Up @@ -1140,8 +1146,7 @@ static int re_parse_captures(REParseState *s, int *phas_named_captures,
/* potential named capture */
if (capture_name) {
p += 3;
if (re_parse_group_name(name, sizeof(name), &p,
s->is_utf16) == 0) {
if (re_parse_group_name(name, sizeof(name), &p) == 0) {
if (!strcmp(name, capture_name))
return capture_index;
}
Expand Down Expand Up @@ -1314,7 +1319,7 @@ static int re_parse_term(REParseState *s, BOOL is_backward_dir)
} else if (p[2] == '<') {
p += 3;
if (re_parse_group_name(s->u.tmp_buf, sizeof(s->u.tmp_buf),
&p, s->is_utf16)) {
&p)) {
return re_parse_error(s, "invalid group name");
}
if (find_group_name(s, s->u.tmp_buf) > 0) {
Expand Down Expand Up @@ -1378,7 +1383,7 @@ static int re_parse_term(REParseState *s, BOOL is_backward_dir)
}
p1 += 3;
if (re_parse_group_name(s->u.tmp_buf, sizeof(s->u.tmp_buf),
&p1, s->is_utf16)) {
&p1)) {
if (s->is_utf16 || re_has_named_captures(s))
return re_parse_error(s, "invalid group name");
else
Expand Down
2 changes: 0 additions & 2 deletions test262_errors.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,8 +37,6 @@ test262/test/built-ins/Function/internals/Construct/derived-this-uninitialized-r
test262/test/built-ins/Function/internals/Construct/derived-this-uninitialized-realm.js:20: strict mode: Test262Error: Expected a ReferenceError but got a different error constructor with the same name
test262/test/built-ins/RegExp/lookahead-quantifier-match-groups.js:27: Test262Error: Expected [a, abc] and [a, undefined] to have the same contents. ? quantifier
test262/test/built-ins/RegExp/lookahead-quantifier-match-groups.js:27: strict mode: Test262Error: Expected [a, abc] and [a, undefined] to have the same contents. ? quantifier
test262/test/built-ins/RegExp/named-groups/non-unicode-property-names-valid.js:46: SyntaxError: invalid group name
test262/test/built-ins/RegExp/named-groups/non-unicode-property-names-valid.js:46: strict mode: SyntaxError: invalid group name
test262/test/built-ins/RegExp/prototype/Symbol.match/flags-tostring-error.js:22: Test262Error: Expected a CustomError but got a Test262Error
test262/test/built-ins/RegExp/prototype/Symbol.match/flags-tostring-error.js:22: strict mode: Test262Error: Expected a CustomError but got a Test262Error
test262/test/built-ins/RegExp/prototype/Symbol.match/get-flags-err.js:23: Test262Error: Expected a CustomError but got a Test262Error
Expand Down