#!/usr/bin/env bash
# lib/apl/conformance.sh — run APL test suites, emit scoreboard.json + scoreboard.md.

set -uo pipefail
cd "$(git rev-parse --show-toplevel)"

SX_SERVER="${SX_SERVER:-/root/rose-ash/hosts/ocaml/_build/default/bin/sx_server.exe}"
if [ ! -x "$SX_SERVER" ]; then
  SX_SERVER="hosts/ocaml/_build/default/bin/sx_server.exe"
fi
if [ ! -x "$SX_SERVER" ]; then
  echo "ERROR: sx_server.exe not found." >&2
  exit 1
fi

SUITES=(structural operators dfn tradfn valence programs system idioms eval-ops pipeline)

OUT_JSON="lib/apl/scoreboard.json"
OUT_MD="lib/apl/scoreboard.md"

run_suite() {
  local suite=$1
  local file="lib/apl/tests/${suite}.sx"
  local TMP
  TMP=$(mktemp)
  cat > "$TMP" << EPOCHS
(epoch 1)
(load "spec/stdlib.sx")
(load "lib/r7rs.sx")
(load "lib/apl/runtime.sx")
(load "lib/apl/tokenizer.sx")
(load "lib/apl/parser.sx")
(load "lib/apl/transpile.sx")
(epoch 2)
(eval "(define apl-test-pass 0)")
(eval "(define apl-test-fail 0)")
(eval "(define apl-test (fn (name got expected) (if (= got expected) (set! apl-test-pass (+ apl-test-pass 1)) (set! apl-test-fail (+ apl-test-fail 1)))))")
(epoch 3)
(load "${file}")
(epoch 4)
(eval "(list apl-test-pass apl-test-fail)")
EPOCHS

  local OUTPUT
  OUTPUT=$(timeout 300 "$SX_SERVER" < "$TMP" 2>/dev/null)
  rm -f "$TMP"

  local LINE
  LINE=$(echo "$OUTPUT" | awk '/^\(ok-len 4 / {getline; print; exit}')
  if [ -z "$LINE" ]; then
    LINE=$(echo "$OUTPUT" | grep -E '^\(ok 4 \([0-9]+ [0-9]+\)\)' | tail -1 \
            | sed -E 's/^\(ok 4 //; s/\)$//')
  fi

  local P F
  P=$(echo "$LINE" | sed -E 's/^\(([0-9]+) ([0-9]+)\).*/\1/')
  F=$(echo "$LINE" | sed -E 's/^\(([0-9]+) ([0-9]+)\).*/\2/')
  P=${P:-0}
  F=${F:-0}
  echo "${P} ${F}"
}

declare -A SUITE_PASS
declare -A SUITE_FAIL
TOTAL_PASS=0
TOTAL_FAIL=0

echo "Running APL conformance suite..." >&2
for s in "${SUITES[@]}"; do
  read -r p f < <(run_suite "$s")
  SUITE_PASS[$s]=$p
  SUITE_FAIL[$s]=$f
  TOTAL_PASS=$((TOTAL_PASS + p))
  TOTAL_FAIL=$((TOTAL_FAIL + f))
  printf "  %-12s %d/%d\n" "$s" "$p" "$((p+f))" >&2
done

# scoreboard.json
{
  printf '{\n'
  printf '  "suites": {\n'
  first=1
  for s in "${SUITES[@]}"; do
    if [ $first -eq 0 ]; then printf ',\n'; fi
    printf '    "%s": {"pass": %d, "fail": %d}' "$s" "${SUITE_PASS[$s]}" "${SUITE_FAIL[$s]}"
    first=0
  done
  printf '\n  },\n'
  printf '  "total_pass": %d,\n' "$TOTAL_PASS"
  printf '  "total_fail": %d,\n' "$TOTAL_FAIL"
  printf '  "total": %d\n' "$((TOTAL_PASS + TOTAL_FAIL))"
  printf '}\n'
} > "$OUT_JSON"

# scoreboard.md
{
  printf '# APL Conformance Scoreboard\n\n'
  printf '_Generated by `lib/apl/conformance.sh`_\n\n'
  printf '| Suite | Pass | Fail | Total |\n'
  printf '|-------|-----:|-----:|------:|\n'
  for s in "${SUITES[@]}"; do
    p=${SUITE_PASS[$s]}
    f=${SUITE_FAIL[$s]}
    printf '| %s | %d | %d | %d |\n' "$s" "$p" "$f" "$((p+f))"
  done
  printf '| **Total** | **%d** | **%d** | **%d** |\n' "$TOTAL_PASS" "$TOTAL_FAIL" "$((TOTAL_PASS + TOTAL_FAIL))"
  printf '\n'
  printf '## Notes\n\n'
  printf '%s\n' '- Suites use the standard `apl-test name got expected` framework loaded against `lib/apl/runtime.sx` + `lib/apl/transpile.sx`.'
  printf '%s\n' '- `lib/apl/tests/parse.sx` and `lib/apl/tests/scalar.sx` use their own self-contained frameworks and are excluded from this scoreboard.'
} > "$OUT_MD"

echo "Wrote $OUT_JSON and $OUT_MD" >&2
echo "Total: $TOTAL_PASS pass, $TOTAL_FAIL fail" >&2

[ "$TOTAL_FAIL" -eq 0 ]