From 3759aad7a640f39afddaf682d47f9b5539f361dc Mon Sep 17 00:00:00 2001
From: giles <giles.bradshaw@rose-ash.com>
Date: Sat, 9 May 2026 19:47:21 +0000
Subject: [PATCH] ocaml: phase 5.1 anagram_groups.ml baseline (group by
 canonical anagram, 3 groups)

canonical builds a sorted-by-frequency string representation:

  let canonical s =
    let chars = Array.make 26 0 in
    for i = 0 to String.length s - 1 do
      let k = Char.code s.[i] - Char.code 'a' in
      if k >= 0 && k < 26 then chars.(k) <- chars.(k) + 1
    done;
    expand into a-z order via a Buffer

For 'eat', 'tea', 'ate' -> all canonicalise to 'aet'. For 'tan',
'nat' -> 'ant'. For 'bat' -> 'abt'.

group_anagrams folds the input, accumulating per-key string lists;
final answer is Hashtbl.length (number of distinct groups):

  ['eat'; 'tea'; 'tan'; 'ate'; 'nat'; 'bat']  -> 3 groups

99 baseline programs total.
---
 lib/ocaml/baseline/anagram_groups.ml | 29 ++++++++++++++++++++++++++++
 lib/ocaml/baseline/expected.json     |  1 +
 plans/ocaml-on-sx.md                 |  8 ++++++++
 3 files changed, 38 insertions(+)
 create mode 100644 lib/ocaml/baseline/anagram_groups.ml

diff --git a/lib/ocaml/baseline/anagram_groups.ml b/lib/ocaml/baseline/anagram_groups.ml
new file mode 100644
index 00000000..eab32fe5
--- /dev/null
+++ b/lib/ocaml/baseline/anagram_groups.ml
@@ -0,0 +1,29 @@
+let canonical s =
+  let chars = Array.make 26 0 in
+  for i = 0 to String.length s - 1 do
+    let k = Char.code s.[i] - Char.code 'a' in
+    if k >= 0 && k < 26 then chars.(k) <- chars.(k) + 1
+  done;
+  let buf = Buffer.create 26 in
+  for i = 0 to 25 do
+    for _ = 1 to chars.(i) do
+      Buffer.add_string buf (String.make 1 (Char.chr (i + Char.code 'a')))
+    done
+  done;
+  Buffer.contents buf
+
+let group_anagrams xs =
+  let h = Hashtbl.create 8 in
+  List.iter (fun s ->
+    let k = canonical s in
+    let cur = match Hashtbl.find_opt h k with
+              | Some xs -> xs
+              | None -> []
+    in
+    Hashtbl.replace h k (s :: cur)
+  ) xs;
+  Hashtbl.length h
+
+;;
+
+group_anagrams ["eat"; "tea"; "tan"; "ate"; "nat"; "bat"]
diff --git a/lib/ocaml/baseline/expected.json b/lib/ocaml/baseline/expected.json
index 7a5bb436..bc8170b1 100644
--- a/lib/ocaml/baseline/expected.json
+++ b/lib/ocaml/baseline/expected.json
@@ -2,6 +2,7 @@
   "ackermann.ml": 125,
   "adler32.ml": 300286872,
   "anagram_check.ml": 2,
+  "anagram_groups.ml": 3,
   "anagrams.ml": 3,
   "atm.ml": 120,
   "bag.ml": 3,
diff --git a/plans/ocaml-on-sx.md b/plans/ocaml-on-sx.md
index e73aeb8b..3c78bdef 100644
--- a/plans/ocaml-on-sx.md
+++ b/plans/ocaml-on-sx.md
@@ -407,6 +407,14 @@ _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.
+- 2026-05-09 Phase 5.1 — anagram_groups.ml baseline (group strings
+  by canonical anagram form, ["eat";"tea";"tan";"ate";"nat";"bat"]
+  has 3 groups). canonical builds a sorted-by-frequency string
+  representation: count letters, then expand into a-z order. Used
+  as Hashtbl key. group_anagrams folds the input list, accumulating
+  per-key string lists; final answer is Hashtbl.length (number of
+  distinct groups). Tests count-then-expand canonical pattern +
+  Hashtbl as multimap. 99 baseline programs total.
 - 2026-05-09 Phase 5.1 — monotonic.ml baseline (monotonicity check,
   4/5 inputs monotonic). Tracks two bool refs (inc, dec). Each pair
   of consecutive elements: if `h < prev` clear `inc`, if `h > prev`