ocaml: phase 5.1 wildcard_match.ml baseline (* / ? matcher, 6/18 match)

Recursive wildcard matcher:

  let rec is_match s i p j =
    if j = String.length p then i = String.length s
    else if p.[j] = '*' then
         is_match s i p (j + 1)             (* * matches empty   *)
      || (i < String.length s && is_match s (i + 1) p j)  (* * eats char *)
    else
      i < String.length s
      && (p.[j] = '?' || p.[j] = s.[i])
      && is_match s (i + 1) p (j + 1)

Patterns vs texts:
  a*b      | aaab abc abxyz xy xyz axby   -> 1 match
  ?b*c     | aaab abc abxyz xy xyz axby   -> 1 match
  *x*y*    | aaab abc abxyz xy xyz axby   -> 4 matches
                                  total   = 6

Tests deeply nested short-circuit && / ||, char equality on
pattern bytes, doubly-nested List.iter cross product.

173 baseline programs total.

lib/ocaml/baseline/expected.json

@@ -157,6 +157,7 @@
   "tic_tac_toe.ml": 1,
   "topo_dfs.ml": 24135,
   "topo_sort.ml": 6,
+  "wildcard_match.ml": 6,
   "word_freq.ml": 8,
   "xor_cipher.ml": 601,
   "zerosafe.ml": 28,

lib/ocaml/baseline/wildcard_match.ml

@@ -0,0 +1,24 @@
+let rec is_match s i p j =
+  if j = String.length p then i = String.length s
+  else if p.[j] = '*' then
+    is_match s i p (j + 1)
+    || (i < String.length s && is_match s (i + 1) p j)
+  else
+    i < String.length s
+    && (p.[j] = '?' || p.[j] = s.[i])
+    && is_match s (i + 1) p (j + 1)
+
+let count_match patterns texts =
+  let count = ref 0 in
+  List.iter (fun p ->
+    List.iter (fun t ->
+      if is_match t 0 p 0 then count := !count + 1
+    ) texts
+  ) patterns;
+  !count
+
+;;
+
+let patterns = ["a*b"; "?b*c"; "*x*y*"] in
+let texts = ["aaab"; "abc"; "abxyz"; "xy"; "xyz"; "axby"] in
+count_match patterns texts

plans/ocaml-on-sx.md

@@ -407,6 +407,17 @@ _Newest first._
   binary search tree (`type 'a tree = Leaf | Node of 'a * 'a tree *
   'a tree`) with insert + in-order traversal. Tests parametric ADT,
   recursive match, List.append, List.fold_left.
+- 2026-05-11 Phase 5.1 — wildcard_match.ml baseline (recursive `*`
+  /`?` wildcard matcher; over 3×6 = 18 (pattern, text) combos,
+  6 match). Cases:
+    a*b   — 1 match (aaab)
+    ?b*c  — 1 match (abc)
+    *x*y* — 4 matches (abxyz, xy, xyz, axby)
+  is_match uses `||` for the `*` alternation (consume zero or one
+  more char and recurse) and `&&` for the literal/`?` case.
+  Tests deeply nested short-circuit, char equality in pattern
+  predicate, doubly-nested `List.iter` to enumerate the cross
+  product. 173 baseline programs total.
 - 2026-05-11 Phase 5.1 — powerset_target.ml baseline (count subsets
   of {1..10} summing to 15 = 20). Generates the full 2^10 = 1024
   powerset by recursive doubling: `gen (h :: rest) = gen rest @