golangLAKEHOUSE/cmd/catalogd/main.go

// catalogd is the metadata authority — registers Parquet datasets,
// persists manifests in storaged, rehydrates them on startup, and
// answers GET/list queries. ADR-020 idempotency contract enforced
// by internal/catalogd/registry.go.
package main

import (
	"context"
	"encoding/json"
	"errors"
	"flag"
	"log/slog"
	"net/http"
	"os"
	"time"

	"github.com/go-chi/chi/v5"

	"git.agentview.dev/profit/golangLAKEHOUSE/internal/catalogd"
	"git.agentview.dev/profit/golangLAKEHOUSE/internal/shared"
	"git.agentview.dev/profit/golangLAKEHOUSE/internal/storeclient"
)

func main() {
	configPath := flag.String("config", "lakehouse.toml", "path to TOML config")
	flag.Parse()

	cfg, err := shared.LoadConfig(*configPath)
	if err != nil {
		slog.Error("config", "err", err)
		os.Exit(1)
	}
	if cfg.Catalogd.StoragedURL == "" {
		slog.Error("config", "err", "catalogd.storaged_url is required")
		os.Exit(1)
	}

	store := storeclient.New(cfg.Catalogd.StoragedURL)
	registry := catalogd.NewRegistry(store)

	rehydrateCtx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
	n, err := registry.Rehydrate(rehydrateCtx)
	cancel()
	if err != nil {
		slog.Error("rehydrate", "err", err)
		os.Exit(1)
	}
	slog.Info("rehydrated", "manifests", n)

	h := newHandlers(registry)

	if err := shared.Run("catalogd", cfg.Catalogd.Bind, h.register); err != nil {
		slog.Error("server", "err", err)
		os.Exit(1)
	}
}

type handlers struct {
	reg *catalogd.Registry
}

func newHandlers(r *catalogd.Registry) *handlers { return &handlers{reg: r} }

func (h *handlers) register(r chi.Router) {
	r.Post("/catalog/register", h.handleRegister)
	r.Get("/catalog/manifest/*", h.handleGetManifest)
	r.Get("/catalog/list", h.handleList)
}

// registerRequest mirrors POST body shape.
type registerRequest struct {
	Name              string            `json:"name"`
	SchemaFingerprint string            `json:"schema_fingerprint"`
	Objects           []catalogd.Object `json:"objects"`
	RowCount          *int64            `json:"row_count,omitempty"`
}

// registerResponse adds the existing flag so callers can distinguish
// fresh registration from idempotent re-register.
type registerResponse struct {
	Manifest *catalogd.Manifest `json:"manifest"`
	Existing bool               `json:"existing"`
}

func (h *handlers) handleRegister(w http.ResponseWriter, r *http.Request) {
	defer r.Body.Close()
	r.Body = http.MaxBytesReader(w, r.Body, 4<<20) // 4 MiB cap on register payloads
	var req registerRequest
	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
		http.Error(w, "decode body: "+err.Error(), http.StatusBadRequest)
		return
	}
	m, existing, err := h.reg.Register(r.Context(), req.Name, req.SchemaFingerprint, req.Objects, req.RowCount)
	if errors.Is(err, catalogd.ErrFingerprintConflict) {
		http.Error(w, err.Error(), http.StatusConflict)
		return
	}
	if errors.Is(err, catalogd.ErrEmptyName) || errors.Is(err, catalogd.ErrEmptyFingerprint) {
		// Per scrum S2 (Opus): sentinel-based detection, not substring match.
		http.Error(w, err.Error(), http.StatusBadRequest)
		return
	}
	if err != nil {
		slog.Error("register", "name", req.Name, "err", err)
		http.Error(w, "internal", http.StatusInternalServerError)
		return
	}
	w.Header().Set("Content-Type", "application/json")
	_ = json.NewEncoder(w).Encode(registerResponse{Manifest: m, Existing: existing})
}

func (h *handlers) handleGetManifest(w http.ResponseWriter, r *http.Request) {
	name := chi.URLParam(r, "*")
	m, err := h.reg.Get(name)
	if errors.Is(err, catalogd.ErrManifestNotFound) {
		http.Error(w, "not found", http.StatusNotFound)
		return
	}
	if err != nil {
		slog.Error("get manifest", "name", name, "err", err)
		http.Error(w, "internal", http.StatusInternalServerError)
		return
	}
	w.Header().Set("Content-Type", "application/json")
	_ = json.NewEncoder(w).Encode(m)
}

func (h *handlers) handleList(w http.ResponseWriter, _ *http.Request) {
	items := h.reg.List()
	w.Header().Set("Content-Type", "application/json")
	_ = json.NewEncoder(w).Encode(map[string]any{"manifests": items, "count": len(items)})
}