feat(api): Redis read cache for product details and search
CI / Go (api) (pull_request) Successful in 54s
CI / Python (ingestion) (pull_request) Successful in 19s
CI / Migrations (postgres) (pull_request) Successful in 27s

Stage-0 caching from docs/scalability.md. The Go API now caches hot
product-detail and search-result reads in Redis with a fail-open,
epoch-versioned scheme; Python ingestion bumps the epoch after a write
run to invalidate the cache globally in O(1).

- api/internal/cache: fail-open Cache (GetJSON/SetJSON) namespaced by an
  epoch counter (og:cache:epoch); disabled when Redis is unconfigured.
- store: ProductByID/ProductByGTIN (24h TTL) and SearchProducts (1h TTL)
  read-through the cache via WithCache.
- ingestion: bump_cache_epoch() called after update_off/seed_off/
  import_bypos/dedup commits when rows changed; best-effort, never fails
  a run. Adds redis dependency.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
rosemariejebbjtxbfp
2026-06-24 06:52:51 +00:00
parent 20b9eb0fc9
commit a75318b811
11 changed files with 403 additions and 4 deletions
+77 -3
View File
@@ -4,21 +4,35 @@ package store
import (
"context"
"crypto/sha1"
"encoding/hex"
"encoding/json"
"errors"
"strconv"
"strings"
"time"
"github.com/jackc/pgx/v5"
"github.com/jackc/pgx/v5/pgxpool"
"github.com/baicai2026-baicai/goods/api/internal/cache"
)
// Cache TTLs for the public read cache. Product details are far less volatile
// than search result sets, so they live longer; both are also invalidated
// wholesale whenever ingestion bumps the cache epoch.
const (
productCacheTTL = 24 * time.Hour
searchCacheTTL = time.Hour
)
// ErrNotFound is returned when a requested row does not exist.
var ErrNotFound = errors.New("not found")
// Store wraps a PostgreSQL connection pool.
// Store wraps a PostgreSQL connection pool and an optional read cache.
type Store struct {
pool *pgxpool.Pool
pool *pgxpool.Pool
cache *cache.Cache
}
// New constructs a Store from an existing pgx pool.
@@ -26,6 +40,30 @@ func New(pool *pgxpool.Pool) *Store {
return &Store{pool: pool}
}
// WithCache attaches a Redis-backed read cache. A nil or disabled cache leaves
// the Store reading straight from PostgreSQL.
func (s *Store) WithCache(c *cache.Cache) *Store {
s.cache = c
return s
}
// cacheGet reads a cached JSON value into dest, reporting a hit. It is a no-op
// miss when no cache is attached.
func (s *Store) cacheGet(ctx context.Context, suffix string, dest any) bool {
if s.cache == nil {
return false
}
return s.cache.GetJSON(ctx, suffix, dest)
}
// cacheSet stores a JSON value when a cache is attached.
func (s *Store) cacheSet(ctx context.Context, suffix string, val any, ttl time.Duration) {
if s.cache == nil {
return
}
s.cache.SetJSON(ctx, suffix, val, ttl)
}
// Ping verifies database connectivity.
func (s *Store) Ping(ctx context.Context) error {
return s.pool.Ping(ctx)
@@ -222,6 +260,10 @@ func stringifyAttr(v any) string {
// ProductByGTIN looks up an active product by any of its barcodes.
func (s *Store) ProductByGTIN(ctx context.Context, gtin string) (*Product, error) {
const suffix = "prod:gtin:"
if cached := new(Product); s.cacheGet(ctx, suffix+gtin, cached) {
return cached, nil
}
row := s.pool.QueryRow(ctx, productSelect+`
WHERE p.status = 'active'
AND (p.gtin = $1 OR EXISTS (
@@ -238,11 +280,16 @@ func (s *Store) ProductByGTIN(ctx context.Context, gtin string) (*Product, error
if p.Specs, err = s.buildSpecs(ctx, p.ArchiveKind, attrs); err != nil {
return nil, err
}
s.cacheSet(ctx, suffix+gtin, p, productCacheTTL)
return p, nil
}
// ProductByID looks up a product by its UUID.
func (s *Store) ProductByID(ctx context.Context, id string) (*Product, error) {
const suffix = "prod:id:"
if cached := new(Product); s.cacheGet(ctx, suffix+id, cached) {
return cached, nil
}
row := s.pool.QueryRow(ctx, productSelect+" WHERE p.id = $1", id)
p, attrs, err := scanProduct(row)
if err != nil {
@@ -254,6 +301,7 @@ func (s *Store) ProductByID(ctx context.Context, id string) (*Product, error) {
if p.Specs, err = s.buildSpecs(ctx, p.ArchiveKind, attrs); err != nil {
return nil, err
}
s.cacheSet(ctx, suffix+id, p, productCacheTTL)
return p, nil
}
@@ -268,6 +316,11 @@ const fuzzyThreshold = "0.42"
// similarity blended with quality_score so the best, most-complete records
// surface first. Without a query, results are ordered by quality_score.
func (s *Store) SearchProducts(ctx context.Context, f SearchFilters, limit, offset int) ([]ProductSummary, int, error) {
suffix := searchCacheSuffix(f, limit, offset)
if entry := new(searchCacheEntry); s.cacheGet(ctx, suffix, entry) {
return entry.Items, entry.Total, nil
}
args := []any{}
where := "WHERE p.status = 'active'"
@@ -334,7 +387,28 @@ LEFT JOIN category c ON c.id = p.category_id `
}
out = append(out, ps)
}
return out, total, rows.Err()
if err := rows.Err(); err != nil {
return nil, 0, err
}
s.cacheSet(ctx, suffix, searchCacheEntry{Items: out, Total: total}, searchCacheTTL)
return out, total, nil
}
// searchCacheEntry is the cached payload for a SearchProducts call.
type searchCacheEntry struct {
Items []ProductSummary `json:"items"`
Total int `json:"total"`
}
// searchCacheSuffix derives a stable cache key from the full filter set and
// paging window so distinct queries never collide.
func searchCacheSuffix(f SearchFilters, limit, offset int) string {
raw := strings.Join([]string{
f.Query, f.Category, f.Brand, f.Country,
strconv.Itoa(limit), strconv.Itoa(offset),
}, "\x1f")
sum := sha1.Sum([]byte(raw))
return "search:" + hex.EncodeToString(sum[:])
}
// Nutriments returns just the nutrition payload for a product.