golangLAKEHOUSE/scripts/d6_smoke.sh

#!/usr/bin/env bash
# D6 smoke — proves the Day 6 acceptance gate end-to-end.
#
# Validates the gateway as a reverse proxy: every assertion goes
# through :3110 (gateway), NOT directly to the backing services.
#   - /v1/health → gateway's own /health (no proxy)
#   - /v1/ingest?name=X with multipart CSV → ingestd → storaged + catalogd
#   - /v1/sql with SELECT count(*) → queryd
#   - /v1/catalog/list → catalogd
#   - /v1/storage/list → storaged
#   - /v1/<unknown> → 404 (not the gateway's job to mediate; chi rejects)
#
# Requires storaged + catalogd + ingestd + queryd + gateway up.
#
# Usage: ./scripts/d6_smoke.sh

set -euo pipefail
cd "$(dirname "$0")/.."

export PATH="$PATH:/usr/local/go/bin"

echo "[d6-smoke] building all 5 binaries..."
go build -o bin/ ./cmd/storaged ./cmd/catalogd ./cmd/ingestd ./cmd/queryd ./cmd/gateway

# Cleanup any prior processes.
pkill -f "bin/storaged" 2>/dev/null || true
pkill -f "bin/catalogd" 2>/dev/null || true
pkill -f "bin/ingestd"  2>/dev/null || true
pkill -f "bin/queryd"   2>/dev/null || true
pkill -f "bin/gateway"  2>/dev/null || true
sleep 0.3

PIDS=()
TMP="$(mktemp -d)"
cleanup() {
  echo "[d6-smoke] cleanup"
  for p in "${PIDS[@]}"; do
    [ -n "$p" ] && kill "$p" 2>/dev/null || true
  done
  rm -rf "$TMP"
}
trap cleanup EXIT INT TERM

poll_health() {
  local port="$1" deadline=$(($(date +%s) + 5))
  while [ "$(date +%s)" -lt "$deadline" ]; do
    if curl -sS --max-time 1 "http://127.0.0.1:$port/health" >/dev/null 2>&1; then return 0; fi
    sleep 0.05
  done
  return 1
}

echo "[d6-smoke] launching storaged → catalogd → ingestd..."
./bin/storaged > /tmp/storaged.log 2>&1 &
PIDS+=($!)
poll_health 3211 || { echo "storaged failed"; tail -10 /tmp/storaged.log; exit 1; }

# Clean any prior smoke artifacts.
NAME="d6_workers"
for k in $(curl -sS "http://127.0.0.1:3211/storage/list?prefix=_catalog/manifests/" | jq -r '.objects[]?.Key // empty' 2>/dev/null); do
  curl -sS -o /dev/null -X DELETE "http://127.0.0.1:3211/storage/delete/$k" || true
done
for k in $(curl -sS "http://127.0.0.1:3211/storage/list?prefix=datasets/$NAME/" | jq -r '.objects[]?.Key // empty' 2>/dev/null); do
  curl -sS -o /dev/null -X DELETE "http://127.0.0.1:3211/storage/delete/$k" || true
done

./bin/catalogd > /tmp/catalogd.log 2>&1 &
PIDS+=($!)
poll_health 3212 || { echo "catalogd failed"; tail -10 /tmp/catalogd.log; exit 1; }

./bin/ingestd > /tmp/ingestd.log 2>&1 &
PIDS+=($!)
poll_health 3213 || { echo "ingestd failed"; tail -10 /tmp/ingestd.log; exit 1; }

# Build the CSV BEFORE launching queryd so its initial Refresh sees
# the dataset (the same trick D5 uses).
cat > "$TMP/workers.csv" <<'EOF'
id,name,salary,active,weight
1,Alice,50000,true,165.5
2,Bob,60000,false,180.0
3,Carol,55000,true,135.2
EOF

echo "[d6-smoke] launching gateway:"
./bin/gateway > /tmp/gateway.log 2>&1 &
PIDS+=($!)
poll_health 3110 || { echo "gateway failed"; tail -10 /tmp/gateway.log; exit 1; }

FAILED=0

echo "[d6-smoke] /v1/ingest?name=$NAME (gateway → ingestd):"
INGEST="$(curl -sS -X POST -F "file=@$TMP/workers.csv" "http://127.0.0.1:3110/v1/ingest?name=$NAME")"
RC="$(echo "$INGEST" | jq -r '.row_count')"
PARQUET_KEY="$(echo "$INGEST" | jq -r '.parquet_key')"
if [ "$RC" = "3" ] && [ "${PARQUET_KEY#datasets/$NAME/}" != "$PARQUET_KEY" ]; then
  echo "  ✓ ingest row_count=3, content-addressed key"
else
  echo "  ✗ ingest → $INGEST"; FAILED=1
fi

# Now launch queryd (after the dataset is registered).
./bin/queryd > /tmp/queryd.log 2>&1 &
PIDS+=($!)
poll_health 3214 || { echo "queryd failed"; tail -20 /tmp/queryd.log; exit 1; }

echo "[d6-smoke] /v1/catalog/list (gateway → catalogd):"
CATALOG="$(curl -sS http://127.0.0.1:3110/v1/catalog/list)"
COUNT="$(echo "$CATALOG" | jq -r '.count')"
if [ "$COUNT" = "1" ]; then
  echo "  ✓ catalog count=1"
else
  echo "  ✗ catalog → $CATALOG"; FAILED=1
fi

echo "[d6-smoke] /v1/storage/list?prefix=datasets/$NAME/ (gateway → storaged):"
STORAGE="$(curl -sS "http://127.0.0.1:3110/v1/storage/list?prefix=datasets/$NAME/")"
OBJ_COUNT="$(echo "$STORAGE" | jq -r '.objects | length')"
if [ "$OBJ_COUNT" -ge "1" ]; then
  echo "  ✓ storage list returned $OBJ_COUNT object(s) under datasets/$NAME/"
else
  echo "  ✗ storage list → $STORAGE"; FAILED=1
fi

echo "[d6-smoke] /v1/sql SELECT count(*) (gateway → queryd):"
SQL_RESP="$(curl -sS -X POST http://127.0.0.1:3110/v1/sql \
  -H 'Content-Type: application/json' \
  -d "{\"sql\":\"SELECT count(*) FROM \\\"$NAME\\\"\"}")"
N="$(echo "$SQL_RESP" | jq -r '.rows[0][0]')"
if [ "$N" = "3" ]; then
  echo "  ✓ count(*)=3"
else
  echo "  ✗ sql → $SQL_RESP"
  echo "  queryd log:"; tail -15 /tmp/queryd.log
  FAILED=1
fi

echo "[d6-smoke] /v1/sql with row data (full round-trip):"
ROWS_RESP="$(curl -sS -X POST http://127.0.0.1:3110/v1/sql \
  -H 'Content-Type: application/json' \
  -d "{\"sql\":\"SELECT id, name FROM \\\"$NAME\\\" ORDER BY id LIMIT 1\"}")"
ROW0_NAME="$(echo "$ROWS_RESP" | jq -r '.rows[0][1]')"
if [ "$ROW0_NAME" = "Alice" ]; then
  echo "  ✓ rows[0].name=Alice (full ingest → storage → catalog → query through gateway)"
else
  echo "  ✗ rows → $ROWS_RESP"; FAILED=1
fi

echo "[d6-smoke] /v1/unknown → 404:"
HTTP="$(curl -sS -o /dev/null -w '%{http_code}' http://127.0.0.1:3110/v1/unknown)"
if [ "$HTTP" = "404" ]; then
  echo "  ✓ unknown route → 404"
else
  echo "  ✗ unknown route → $HTTP"; FAILED=1
fi

# Cleanup smoke artifacts.
for k in $(curl -sS "http://127.0.0.1:3211/storage/list?prefix=datasets/$NAME/" | jq -r '.objects[]?.Key // empty' 2>/dev/null); do
  curl -sS -o /dev/null -X DELETE "http://127.0.0.1:3211/storage/delete/$k" || true
done
curl -sS -o /dev/null -X DELETE "http://127.0.0.1:3211/storage/delete/_catalog/manifests/$NAME.parquet" || true

if [ "$FAILED" -eq 0 ]; then
  echo "[d6-smoke] D6 acceptance gate: PASSED"
  exit 0
else
  echo "[d6-smoke] D6 acceptance gate: FAILED"
  exit 1
fi