Skip to content

mruby-regexp: Fix String#gsub block handling for zero-width matches #6893

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
matz merged 3 commits into from
Jun 15, 2026
+34 −12
Merged

mruby-regexp: Fix String#gsub block handling for zero-width matches #6893

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
c784755
mruby-regexp: Fix String#gsub to handle zero-width matches correctly
nattzn Jun 15, 2026
9e211c5
mruby-regexp: Fix String#gsub block offsets for UTF-8 strings
nattzn Jun 15, 2026
6d99e8d
mruby-regexp: Avoid multiline ^ match after final newline
nattzn Jun 15, 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
28 changes: 18 additions & 10 deletions mrbgems/mruby-regexp/mrblib/string_regexp.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,21 +35,29 @@ def gsub(pattern, replacement = nil, &block)
end
# block case: keep in Ruby to avoid VM callback from C
parts = []
rest = self
while rest.length > 0
md = pattern.match(rest)
pos = 0
len = self.bytesize
while pos <= len
md = pattern.match(self, pos)
break unless md
parts << md.pre_match
match_start = md.begin(0)
match_end = md.end(0)
parts << self.byteslice(pos, match_start - pos)
parts << block.call(md[0]).to_s
matched_len = md[0].length
if matched_len == 0
parts << rest[0] if rest.length > 0
rest = rest[1..-1] || ""
if match_start == match_end
rest = self.byteslice(match_end..-1)
if rest && rest.bytesize > 0
char = rest[0]
parts << char
pos = match_end + char.bytesize
else
pos = match_end + 1
end
else
rest = md.post_match
pos = match_end
end
end
parts << rest
parts << self.byteslice(pos..-1)
parts.join
end

Expand Down
4 changes: 2 additions & 2 deletions mrbgems/mruby-regexp/src/re_exec.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -145,7 +145,7 @@ add_thread(pike_state *s, re_threadlist *list,
continue;

case RE_BOL:
if (sp == s->str || ((s->pat->flags & RE_FLAG_MULTILINE) && sp > s->str && sp[-1] == '\n')) {
if (sp == s->str || ((s->pat->flags & RE_FLAG_MULTILINE) && sp > s->str && sp < s->str_end && sp[-1] == '\n')) {
pc++; continue;
}
return;
Expand Down Expand Up @@ -452,7 +452,7 @@ bt_match(const mrb_regexp_pattern *pat, const char *str, const char *str_end,
}

case RE_BOL:
if (sp != str && !(pat->flags & RE_FLAG_MULTILINE && sp > str && sp[-1] == '\n')) return FALSE;
if (sp != str && !(pat->flags & RE_FLAG_MULTILINE && sp > str && sp < str_end && sp[-1] == '\n')) return FALSE;
pc++;
break;

Expand Down
14 changes: 14 additions & 0 deletions mrbgems/mruby-regexp/test/regexp.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -349,6 +349,20 @@
assert_equal "HELLO WORLD", "hello world".gsub(/\w+/) { |m| m.upcase }
end

assert("String#gsub with block and zero-width match") do
assert_equal "!abc", "abc".gsub(/^/) { "!" }
assert_equal "a!bc", "abc".gsub(/(?=b)/) { "!" }
assert_equal "!a!b!c!", "abc".gsub(//) { "!" }
assert_equal "!\n", "\n".gsub(/^/m) { "!" }
assert_equal "!a\n", "a\n".gsub(/^/m) { "!" }
assert_equal "!a\n!b", "a\nb".gsub(/^/m) { "!" }
if __ENCODING__ == "UTF-8"
assert_equal "！いろは", "いろは".gsub(/^/) { "！" }
assert_equal "い！ろは", "いろは".gsub(/(?=ろ)/) { "！" }
assert_equal "！い！ろ！は！", "いろは".gsub(//) { "！" }
end
end

assert("String#gsub date reformat") do
result = "2026-03-21".gsub(/(\d+)-(\d+)-(\d+)/) { "#{$~[3]}/#{$~[2]}/#{$~[1]}" }
assert_equal "21/03/2026", result
Expand Down
Loading