coop/rose-ash
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Step 13: String/regex primitives — PCRE-compatible, cross-host

Browse Source 
New primitives in sx_primitives.ml:
  char-at, char-code, parse-number — string inspection + conversion
  regex-match, regex-match?, regex-find-all — PCRE pattern matching
  regex-replace, regex-replace-first — PCRE substitution
  regex-split — split by PCRE pattern

Uses Re.Pcre (OCaml re library) so regex patterns use the same syntax
as JS RegExp — patterns in .sx files work identically on browser and
server. Replaces the old test-only regex-find-all stub.

Also: split now handles multi-char separators via Re.

176 new tests (10 suites). 2912/2912 total, zero failures.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
giles
2026-04-05 20:38:40 +00:00
parent 516f9c7186
commit 5d88b363e4
4 changed files with 247 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
hosts/ocaml/bin/run_tests.ml
View File

@@ -470,52 +470,7 @@ let make_test_env () =
let stack = try Hashtbl.find _scope_stacks name with Not_found -> [] in
(match stack with _ :: rest -> Hashtbl.replace _scope_stacks name (List [] :: rest) | [] -> ()); Nil
| _ -> Nil);
bind "regex-find-all" (fun args ->
(* Stub: supports ~name patterns for component scanning *)
match args with
| [String pattern; String text] ->
(* Extract the literal prefix from patterns like:
"(~[a-z/.-]+" → prefix "~", has_group=true
"\(~([a-zA-Z_]..." → prefix "(~", has_group=true *)
let prefix, has_group =
if String.length pattern >= 4 && pattern.[0] = '\\' && pattern.[1] = '(' then
(* Pattern like \(~(...) — literal "(" + "~" prefix, group after *)
let s = String.sub pattern 2 (String.length pattern - 2) in
let lit_end = try String.index s '(' with Not_found -> try String.index s '[' with Not_found -> String.length s in
let lit = String.sub s 0 lit_end in
("(" ^ lit, true)
else if String.length pattern > 2 && pattern.[0] = '(' then
let s = String.sub pattern 1 (String.length pattern - 1) in
let p = try String.sub s 0 (String.index s '[')
with Not_found -> try String.sub s 0 (String.index s '(')
with Not_found -> s in
((if String.length p > 0 then p else "~"), true)
else (pattern, false)
in
let results = ref [] in
let len = String.length text in
let plen = String.length prefix in
let i = ref 0 in
while !i <= len - plen do
if String.sub text !i plen = prefix then begin
(* Find end of identifier *)
let j = ref (!i + plen) in
while !j < len && let c = text.[!j] in
(c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9')
|| c = '-' || c = '/' || c = '_' || c = '.' do
incr j
done;
let full_match = String.sub text !i (!j - !i) in
(* If pattern has capture group, strip the literal prefix to simulate group 1 *)
let result = if has_group then
String.sub full_match plen (String.length full_match - plen)
else full_match in
results := String result :: !results;
i := !j
end else incr i
done;
List (List.rev !results)
| _ -> List []);
(* regex-find-all now provided by sx_primitives.ml *)
bind "callable?" (fun args ->
match args with
| [NativeFn _] | [Lambda _] | [Component _] | [Island _] -> Bool true