#!/usr/bin/env bash
# conformance/run.sh — the clawhdf5 conformance sweep, end to end.
#
#   fetch the pinned corpora (cached) -> build the probe -> probe every file
#   with clawhdf5 and with h5py (and h5dump for the CVE corpus), each under a
#   timeout and a memory limit -> compare -> write CONFORMANCE.md -> check the
#   result against conformance/baseline.json.
#
# Usage: conformance/run.sh [--no-fetch] [--no-report] [--update-baseline]
#
# Environment:
#   CLAWHDF5_PYTHON    python with h5py, numpy, hdf5plugin (default: repo .venv, then python3)
#   CONFORMANCE_CACHE  corpus / build / results cache (default: conformance/.cache)
#   CONFORMANCE_OUT    results directory (default: $CONFORMANCE_CACHE/results)
#   CONFORMANCE_REPORT report path (default: CONFORMANCE.md at the repo root)
#   JOBS               parallel files (default: nproc)
#   CONFORMANCE_PROBE  use this prebuilt probe binary instead of building one
#   TMO / MEM_KB       per-process timeout in seconds (20) / address-space limit in KiB (4 GiB)
#
# Exit status: 0 = gate passed; 1 = a panic/hang/crash/oom in clawhdf5, or the
# ok count fell below the baseline, or a baseline-ok file regressed; 2 = setup error.
set -euo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
ROOT="$(cd "$HERE/.." && pwd)"
FETCH=1 REPORT=1 UPDATE=0
for a in "$@"; do
  case "$a" in
    --no-fetch) FETCH=0 ;;
    --no-report) REPORT=0 ;;
    --update-baseline) UPDATE=1 ;;
    -h|--help) sed -n '2,23p' "$0"; exit 0 ;;
    *) echo "unknown argument: $a" >&2; exit 2 ;;
  esac
done

export PATH="$HOME/.cargo/bin:$PATH"
CACHE="${CONFORMANCE_CACHE:-$HERE/.cache}"
mkdir -p "$CACHE"; CACHE="$(cd "$CACHE" && pwd)"
OUT="${CONFORMANCE_OUT:-$CACHE/results}"
REPORT_PATH="${CONFORMANCE_REPORT:-$ROOT/CONFORMANCE.md}"
JOBS="${JOBS:-$(nproc 2>/dev/null || echo 4)}"
if [ -n "${CLAWHDF5_PYTHON:-}" ]; then PY="$CLAWHDF5_PYTHON"
elif [ -x "$ROOT/.venv/bin/python" ]; then PY="$ROOT/.venv/bin/python"
else PY="$(command -v python3)"; fi
export PY TMO="${TMO:-20}" MEM_KB="${MEM_KB:-4194304}"
command -v h5dump >/dev/null || { echo "error: h5dump not found (install hdf5-tools)" >&2; exit 2; }
"$PY" -c 'import h5py, numpy, hdf5plugin' || { echo "error: $PY lacks h5py/numpy/hdf5plugin" >&2; exit 2; }

t0=$(date +%s)
[ "$FETCH" = 1 ] && bash "$HERE/fetch-corpus.sh" "$CACHE"
C="$CACHE/corpus"
[ -d "$C" ] || { echo "error: no corpus in $C (run without --no-fetch)" >&2; exit 2; }

if [ -n "${CONFORMANCE_PROBE:-}" ]; then
  export PROBE="$CONFORMANCE_PROBE"   # a prebuilt probe, e.g. an older one for a before/after
else
  echo "== building the probe"
  CARGO_TARGET_DIR="${CARGO_TARGET_DIR:-$CACHE/target}" \
    cargo build -q --release --manifest-path "$HERE/probe/Cargo.toml"
  export PROBE="${CARGO_TARGET_DIR:-$CACHE/target}/release/conformance-probe"
fi
t1=$(date +%s)

rm -rf "$OUT"; mkdir -p "$OUT"
"$PY" "$HERE/list_files.py" "$C" > "$OUT/files.txt"
echo "== probing $(wc -l <"$OUT/files.txt") files, $JOBS at a time (timeout ${TMO}s, limit $((MEM_KB / 1024)) MiB)"
export C OUT HERE
# The shell's "Segmentation fault (core dumped)" notices go to probe.log; the
# signals themselves are recorded in each side's .rc.
xargs -a "$OUT/files.txt" -d '\n' -P "$JOBS" -I{} bash -c '
  f="$1"; d="$OUT/runs/${f//\//__}"
  case "$f" in cve_hdf5/*) export WITH_H5DUMP=1 ;; esac
  "$HERE/run_one.sh" "$C/$f" "$d"' _ {} 2>"$OUT/probe.log"
echo "== comparing"
"$PY" "$HERE/compare.py" "$OUT" >/dev/null
t2=$(date +%s)
cat > "$OUT/meta.json" <<EOF
{"build_seconds": $((t1 - t0)), "probe_seconds": $((t2 - t1)), "jobs": $JOBS, "timeout_s": $TMO, "mem_kb": $MEM_KB}
EOF
export CONFORMANCE_CMD="${CONFORMANCE_CMD:-conformance/run.sh${*:+ $*}}"
if [ "$REPORT" = 1 ]; then
  "$PY" "$HERE/report.py" "$OUT" "$REPORT_PATH" "$C"
  echo "== wrote $REPORT_PATH"
fi
if [ "$UPDATE" = 1 ]; then
  "$PY" "$HERE/check.py" "$OUT" "$HERE/baseline.json" --update
fi
"$PY" "$HERE/check.py" "$OUT" "$HERE/baseline.json"