From 047ea62d430cafdf010b64f84be47ca77968607c Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Mon, 11 May 2026 02:25:04 +0000
Subject: [PATCH] ocaml: phase 5.1 regex_simple.ml baseline (./* matcher, 7/28
 match)

Recursive regex matcher with Leetcode-style semantics:
  .   matches any single character
  <c>* matches zero or more of <c>

  let rec is_match s i p j =
    if j = String.length p then i = String.length s
    else
      let first = i < String.length s
                  && (p.[j] = '.' || p.[j] = s.[i])
      in
      if j + 1 < String.length p && p.[j+1] = '*' then
           is_match s i p (j + 2)                   (* skip * group *)
        || (first && is_match s (i + 1) p j)        (* consume one  *)
      else
        first && is_match s (i + 1) p (j + 1)

Patterns vs texts:
  .a.b    | aabb axb "" abcd abc aaabbbc x   -> 1 match
  a.*b    | aabb axb "" abcd abc aaabbbc x   -> 2 matches
  x*      | aabb axb "" abcd abc aaabbbc x   -> 2 matches
  a*b*c   | aabb axb "" abcd abc aaabbbc x   -> 2 matches
                                             total = 7

Complements wildcard_match.ml which uses LIKE-style * / ?.

182 baseline programs total.
---
 lib/ocaml/baseline/expected.json   |  1 +
 lib/ocaml/baseline/regex_simple.ml | 27 +++++++++++++++++++++++++++
 plans/ocaml-on-sx.md               | 12 ++++++++++++
 3 files changed, 40 insertions(+)
 create mode 100644 lib/ocaml/baseline/regex_simple.ml

diff --git a/lib/ocaml/baseline/expected.json b/lib/ocaml/baseline/expected.json
index 35371c95..29e29d25 100644
--- a/lib/ocaml/baseline/expected.json
+++ b/lib/ocaml/baseline/expected.json
@@ -149,6 +149,7 @@
   "radix_sort.ml": 802002,
   "roman.ml": 44,
   "rolling_hash.ml": 6,
+  "regex_simple.ml": 7,
   "reverse_int.ml": 54329,
   "rpn.ml": 9,
   "run_decode.ml": 21,
diff --git a/lib/ocaml/baseline/regex_simple.ml b/lib/ocaml/baseline/regex_simple.ml
new file mode 100644
index 00000000..bcc692d6
--- /dev/null
+++ b/lib/ocaml/baseline/regex_simple.ml
@@ -0,0 +1,27 @@
+let rec is_match s i p j =
+  if j = String.length p then i = String.length s
+  else
+    let first =
+      i < String.length s
+      && (p.[j] = '.' || p.[j] = s.[i])
+    in
+    if j + 1 < String.length p && p.[j + 1] = '*' then
+      is_match s i p (j + 2)
+      || (first && is_match s (i + 1) p j)
+    else
+      first && is_match s (i + 1) p (j + 1)
+
+let count_match pats 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
+  ) pats;
+  !count
+
+;;
+
+let pats = [".a.b"; "a.*b"; "x*"; "a*b*c"] in
+let texts = ["aabb"; "axb"; ""; "abcd"; "abc"; "aaabbbc"; "x"] in
+count_match pats texts
diff --git a/plans/ocaml-on-sx.md b/plans/ocaml-on-sx.md
index 6cc60e48..41d81acd 100644
--- a/plans/ocaml-on-sx.md
+++ b/plans/ocaml-on-sx.md
@@ -407,6 +407,18 @@ _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 — regex_simple.ml baseline (recursive `.`/`*`
+  regex matcher; over 4×7 = 28 (pattern, text) combos, 7 match).
+  Cases per pattern:
+    .a.b   — 1 match (aabb)
+    a.*b   — 2 matches (aabb, axb)
+    x*     — 2 matches ("" and "x")
+    a*b*c  — 2 matches (abc, aaabbbc)
+  Two-position lookahead for `p.[j+1] = '*'` to decide between
+  zero-match and consume-one-char-and-retry. Complements
+  wildcard_match.ml (LIKE-style `*` / `?` semantics); this one
+  has Leetcode-style `.` (any char) and `<c>*` (zero+ of c).
+  182 baseline programs total.
 - 2026-05-11 Phase 5.1 — palindrome_part.ml baseline (minimum
   palindrome-partition cuts in "aabba" = 1). Two-phase DP:
     1) `is_pal.(i).(j)` table via length-major iteration.