From 8fab20c8bcf5b568ab5aac1801915d4a7ac3d2c7 Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Fri, 8 May 2026 19:57:09 +0000
Subject: [PATCH] ocaml: phase 5.1 anagrams.ml baseline (18/18 pass)

Group anagrams by canonical (sorted-chars) key using Hashtbl +
List.sort. Demonstrates char-by-char traversal via String.get + for-loop +
ref accumulator + Hashtbl as a multi-valued counter.
---
 lib/ocaml/baseline/anagrams.ml   | 26 ++++++++++++++++++++++++++
 lib/ocaml/baseline/expected.json |  1 +
 plans/ocaml-on-sx.md             |  3 +++
 3 files changed, 30 insertions(+)
 create mode 100644 lib/ocaml/baseline/anagrams.ml

diff --git a/lib/ocaml/baseline/anagrams.ml b/lib/ocaml/baseline/anagrams.ml
new file mode 100644
index 00000000..a1f4666a
--- /dev/null
+++ b/lib/ocaml/baseline/anagrams.ml
@@ -0,0 +1,26 @@
+(* Baseline: count anagram groups using Hashtbl + sort *)
+
+(* Sort the chars in a string to get its anagram-equivalence key *)
+let canonical s =
+  let n = String.length s in
+  let chars = ref [] in
+  for i = 0 to n - 1 do
+    chars := (String.get s i) :: !chars
+  done ;
+  let sorted = List.sort compare !chars in
+  String.concat "" sorted
+;;
+
+let count_groups words =
+  let counts = Hashtbl.create 16 in
+  List.iter
+    (fun w ->
+      let k = canonical w in
+      match Hashtbl.find_opt counts k with
+      | None -> Hashtbl.add counts k 1
+      | Some n -> Hashtbl.replace counts k (n + 1))
+    words ;
+  Hashtbl.length counts
+;;
+
+count_groups ["eat"; "tea"; "tan"; "ate"; "nat"; "bat"]
diff --git a/lib/ocaml/baseline/expected.json b/lib/ocaml/baseline/expected.json
index 27ecf27b..c22a2ed9 100644
--- a/lib/ocaml/baseline/expected.json
+++ b/lib/ocaml/baseline/expected.json
@@ -1,4 +1,5 @@
 {
+  "anagrams.ml": 3,
   "btree.ml": 39,
   "calc.ml": 13,
   "closures.ml": 315,
diff --git a/plans/ocaml-on-sx.md b/plans/ocaml-on-sx.md
index 879a0226..b1fa4cb7 100644
--- a/plans/ocaml-on-sx.md
+++ b/plans/ocaml-on-sx.md
@@ -407,6 +407,9 @@ _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.
+- 2026-05-08 Phase 5.1 — anagrams.ml baseline (18/18 pass). Counts
+  anagram-equivalence groups via Hashtbl + List.sort + String.get +
+  for-loop. `["eat";"tea";"tan";"ate";"nat";"bat"]` → 3 groups.
 - 2026-05-08 Phase 5.1 — lambda_calc.ml baseline (17/17 pass). Untyped
   lambda calculus interpreter using two ADTs (`type term = Var | Abs |
   App | Num`, `type value = VNum | VClos`), an env as `(string * value)