Skip to content

Implement ES2025 RegExp pattern modifiers #1520

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

Closed
andreasrosdal wants to merge 3 commits into from
+211 −36
Closed

Implement ES2025 RegExp pattern modifiers #1520

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6a9f835
Implement ES2025 RegExp pattern modifiers
claude May 31, 2026
2e8c7c2
Fix lre-test by appending RegExp modifier opcodes at the end
claude May 31, 2026
0e51b1a
Fix CI for RegExp modifiers: regenerate repl.c, record known errors
claude May 31, 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
18 changes: 9 additions & 9 deletions gen/repl.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
const uint32_t qjsc_repl_size = 24338;

const uint8_t qjsc_repl[24338] = {
0x1a, 0x8e, 0x10, 0xe1, 0xf4, 0xb5, 0x04, 0x01,
0x1a, 0x8e, 0x2b, 0x32, 0xdd, 0xb5, 0x04, 0x01,
0x0e, 0x72, 0x65, 0x70, 0x6c, 0x2e, 0x6a, 0x73,
0x01, 0x0e, 0x71, 0x6a, 0x73, 0x3a, 0x73, 0x74,
0x64, 0x01, 0x0c, 0x71, 0x6a, 0x73, 0x3a, 0x6f,
Expand Down Expand Up @@ -1323,13 +1323,13 @@ const uint8_t qjsc_repl[24338] = {
0x79, 0x5d, 0x2b, 0x24, 0x07, 0x96, 0x01, 0x00,
0x00, 0x01, 0x00, 0x43, 0x00, 0x00, 0x00, 0x09,
0x06, 0x00, 0x00, 0x00, 0x05, 0x08, 0xf5, 0xff,
0xff, 0xff, 0x0c, 0x00, 0x06, 0x1d, 0x20, 0x00,
0xff, 0xff, 0x0c, 0x00, 0x21, 0x1d, 0x20, 0x00,
0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xff, 0xff,
0xff, 0x7f, 0x01, 0x00, 0x00, 0x00, 0x16, 0x07,
0x00, 0x64, 0x00, 0x64, 0x00, 0x67, 0x00, 0x67,
0x00, 0x69, 0x00, 0x69, 0x00, 0x6d, 0x00, 0x6d,
0x00, 0x73, 0x00, 0x73, 0x00, 0x75, 0x00, 0x76,
0x00, 0x79, 0x00, 0x79, 0x00, 0x0b, 0x07, 0x0d,
0x00, 0x79, 0x00, 0x79, 0x00, 0x0b, 0x22, 0x0d,
0x00, 0x0b, 0xd8, 0xba, 0xa6, 0xf0, 0x03, 0xe3,
0x28, 0xd7, 0xd8, 0xbb, 0x9d, 0x46, 0xcf, 0xd8,
0xbb, 0xad, 0xf0, 0x17, 0xcb, 0x04, 0xc3, 0x01,
Expand Down Expand Up @@ -1722,7 +1722,7 @@ const uint8_t qjsc_repl[24338] = {
0x24, 0x5d, 0x2a, 0x07, 0xaa, 0x01, 0x00, 0x00,
0x01, 0x00, 0x4d, 0x00, 0x00, 0x00, 0x09, 0x06,
0x00, 0x00, 0x00, 0x05, 0x08, 0xf5, 0xff, 0xff,
0xff, 0x0c, 0x00, 0x06, 0x16, 0x04, 0x00, 0x24,
0xff, 0x0c, 0x00, 0x21, 0x16, 0x04, 0x00, 0x24,
0x00, 0x24, 0x00, 0x41, 0x00, 0x5a, 0x00, 0x5f,
0x00, 0x5f, 0x00, 0x61, 0x00, 0x7a, 0x00, 0x1d,
0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
Expand Down Expand Up @@ -1952,7 +1952,7 @@ const uint8_t qjsc_repl[24338] = {
0x7c, 0x5c, 0x5c, 0x2e, 0x29, 0x2a, 0x22, 0x07,
0x98, 0x01, 0x00, 0x00, 0x02, 0x01, 0x44, 0x00,
0x00, 0x00, 0x09, 0x06, 0x00, 0x00, 0x00, 0x05,
0x08, 0xf5, 0xff, 0xff, 0xff, 0x0c, 0x00, 0x06,
0x08, 0xf5, 0xff, 0xff, 0xff, 0x0c, 0x00, 0x21,
0x01, 0x22, 0x0e, 0x01, 0x01, 0x0a, 0x27, 0x00,
0x00, 0x00, 0x1a, 0x0c, 0x01, 0x0a, 0x14, 0x00,
0x00, 0x00, 0x16, 0x03, 0x00, 0x00, 0x00, 0x21,
Expand All @@ -1965,7 +1965,7 @@ const uint8_t qjsc_repl[24338] = {
0x07, 0x98, 0x01, 0x00, 0x00, 0x02, 0x01, 0x44,
0x00, 0x00, 0x00, 0x09, 0x06, 0x00, 0x00, 0x00,
0x05, 0x08, 0xf5, 0xff, 0xff, 0xff, 0x0c, 0x00,
0x06, 0x01, 0x27, 0x0e, 0x01, 0x01, 0x0a, 0x27,
0x21, 0x01, 0x27, 0x0e, 0x01, 0x01, 0x0a, 0x27,
0x00, 0x00, 0x00, 0x1a, 0x0c, 0x01, 0x0a, 0x14,
0x00, 0x00, 0x00, 0x16, 0x03, 0x00, 0x00, 0x00,
0x26, 0x00, 0x28, 0x00, 0x5b, 0x00, 0x5d, 0x00,
Expand All @@ -1976,7 +1976,7 @@ const uint8_t qjsc_repl[24338] = {
0x5d, 0x2b, 0x5c, 0x3e, 0x07, 0x74, 0x00, 0x00,
0x01, 0x00, 0x32, 0x00, 0x00, 0x00, 0x09, 0x06,
0x00, 0x00, 0x00, 0x05, 0x08, 0xf5, 0xff, 0xff,
0xff, 0x0c, 0x00, 0x06, 0x01, 0x3c, 0x1d, 0x0c,
0xff, 0x0c, 0x00, 0x21, 0x01, 0x3c, 0x1d, 0x0c,
0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xff,
0xff, 0xff, 0x7f, 0x01, 0x00, 0x00, 0x00, 0x16,
0x02, 0x00, 0x00, 0x00, 0x3d, 0x00, 0x3f, 0x00,
Expand All @@ -1985,7 +1985,7 @@ const uint8_t qjsc_repl[24338] = {
0x5d, 0x5d, 0x2b, 0x5c, 0x5d, 0x07, 0x74, 0x00,
0x00, 0x01, 0x00, 0x32, 0x00, 0x00, 0x00, 0x09,
0x06, 0x00, 0x00, 0x00, 0x05, 0x08, 0xf5, 0xff,
0xff, 0xff, 0x0c, 0x00, 0x06, 0x01, 0x5b, 0x1d,
0xff, 0xff, 0x0c, 0x00, 0x21, 0x01, 0x5b, 0x1d,
0x0c, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00,
0xff, 0xff, 0xff, 0x7f, 0x01, 0x00, 0x00, 0x00,
0x16, 0x02, 0x00, 0x00, 0x00, 0x5c, 0x00, 0x5e,
Expand All @@ -2002,7 +2002,7 @@ const uint8_t qjsc_repl[24338] = {
0x2d, 0x39, 0x5d, 0x2a, 0x07, 0x9e, 0x03, 0x00,
0x00, 0x01, 0x00, 0xc7, 0x00, 0x00, 0x00, 0x09,
0x06, 0x00, 0x00, 0x00, 0x05, 0x08, 0xf5, 0xff,
0xff, 0xff, 0x0c, 0x00, 0x06, 0x1d, 0x10, 0x00,
0xff, 0xff, 0x0c, 0x00, 0x21, 0x1d, 0x10, 0x00,
0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0xff, 0xff,
0xff, 0x7f, 0x01, 0x00, 0x00, 0x00, 0x16, 0x03,
0x00, 0x30, 0x00, 0x39, 0x00, 0x5f, 0x00, 0x5f,
Expand Down
17 changes: 15 additions & 2 deletions libregexp-opcode.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,8 @@ DEF(char16, 3)
DEF(char32, 5)
DEF(dot, 1)
DEF(any, 1) /* same as dot but match any character including line terminator */
DEF(line_start, 1)
DEF(line_end, 1)
DEF(line_start, 1) /* multiline ^: match at string start or after a line terminator */
DEF(line_end, 1) /* multiline $: match at string end or before a line terminator */
DEF(goto, 5)
DEF(split_goto_first, 5)
DEF(split_next_first, 5)
Expand All @@ -55,4 +55,17 @@ DEF(check_advance, 1) /* pop one stack element and check that it is different fr
DEF(prev, 1) /* go to the previous char */
DEF(simple_greedy_quant, 17)

/* Opcodes added for ES2025 RegExp pattern modifiers. Appended at the end so the
numeric values of the opcodes above stay stable (e.g. hardcoded bytecode in
lre-test.c and the bytecode validator depend on them). */
DEF(char8_ci, 2) /* case-insensitive: canonicalize the input before comparing */
DEF(char16_ci, 3)
DEF(char32_ci, 5)
DEF(bol, 1) /* absolute ^: match only at the start of the string */
DEF(eol, 1) /* absolute $: match only at the end of the string */
DEF(back_reference_ci, 2) /* case-insensitive back reference */
DEF(backward_back_reference_ci, 2) /* must come after back_reference_ci */
DEF(range_ci, 3) /* case-insensitive range, variable length */
DEF(range32_ci, 3) /* case-insensitive range32, variable length */

#endif /* DEF */
Loading
Loading