fix: serve browse pages from MinIO cache; fix ReapStaleTasks PocketBase filter
All checks were successful
Release / Scraper / Test (push) Successful in 20s
Release / UI / Build (push) Successful in 25s
CI / Scraper / Lint (pull_request) Successful in 10s
Release / v2 / Build ui-v2 (push) Successful in 28s
CI / Scraper / Test (pull_request) Successful in 15s
CI / UI / Build (pull_request) Successful in 25s
Release / Scraper / Docker (push) Successful in 55s
Release / UI / Docker (push) Successful in 43s
CI / Scraper / Docker Push (pull_request) Has been skipped
CI / UI / Docker Push (pull_request) Has been skipped
Release / v2 / Docker / ui-v2 (push) Successful in 36s
Release / v2 / Test backend (push) Successful in 3m51s
Release / v2 / Docker / runner (push) Successful in 36s
Release / v2 / Docker / backend (push) Successful in 1m34s
iOS CI / Build (pull_request) Successful in 5m33s
iOS CI / Test (pull_request) Successful in 11m25s

- Runner fetches 9 browse combos (genre×sort×status) every 6h and stores
  JSON snapshots in MinIO libnovel-browse bucket (browse_refresh.go)
- Backend handleBrowse reads page-1 results from MinIO first; falls back
  to live novelfire.net fetch; returns empty+cached:false on total failure
  instead of 502
- Add BrowseStore interface (bookstore.go), MinIO put/get helpers (minio.go),
  Store methods + compile-time assertion (store.go), BucketBrowse config,
  wiring in cmd/backend and cmd/runner, docker-compose-new bucket init
- Fix ReapStaleTasks: PocketBase datetime fields require heartbeat_at=null
  (not heartbeat_at="") in filter expressions, and nil (not "") in patch
  payload — was causing 400 errors on every reap cycle
This commit is contained in:
Admin
2026-03-15 21:19:28 +05:00
parent 5825b859b7
commit 3918bc8dc3
12 changed files with 302 additions and 16 deletions

View File

@@ -79,6 +79,7 @@ MINIO_ROOT_USER=admin
MINIO_ROOT_PASSWORD=changeme123
MINIO_BUCKET_CHAPTERS=libnovel-chapters
MINIO_BUCKET_AUDIO=libnovel-audio
MINIO_BUCKET_BROWSE=libnovel-browse
# ── PocketBase ────────────────────────────────────────────────────────────────
# Admin credentials (used by scraper + UI server-side)

View File

@@ -84,6 +84,7 @@ func run() error {
AudioStore: store,
PresignStore: store,
ProgressStore: store,
BrowseStore: store,
Producer: store,
TaskReader: store,
Kokoro: kokoroClient,

View File

@@ -97,13 +97,14 @@ func run() error {
OrchestratorWorkers: workers,
}
deps := runner.Dependencies{
Consumer: store,
BookWriter: store,
BookReader: store,
AudioStore: store,
Novel: novel,
Kokoro: kokoroClient,
Log: log,
Consumer: store,
BookWriter: store,
BookReader: store,
AudioStore: store,
BrowseStore: store,
Novel: novel,
Kokoro: kokoroClient,
Log: log,
}
r := runner.New(rCfg, deps)

View File

@@ -204,16 +204,36 @@ func (s *Server) handleBrowse(w http.ResponseWriter, r *http.Request) {
pageNum = 1
}
targetURL := fmt.Sprintf("%s/genre-%s/sort-%s/status-%s/%s?page=%d",
novelFireBase, genre, sortBy, status, novelType, pageNum)
// ── Try MinIO cache first ─────────────────────────────────────────────
// Only page 1 is cached; higher pages fall through to live fetch.
if pageNum == 1 && s.deps.BrowseStore != nil {
if data, ok, err := s.deps.BrowseStore.GetBrowsePage(r.Context(), genre, sortBy, status, novelType, 1); err == nil && ok {
w.Header().Set("Content-Type", "application/json")
w.Header().Set("Cache-Control", "public, max-age=300")
_, _ = w.Write(data)
return
}
}
// ── Fall back to live novelfire.net fetch ──────────────────────────────
ctx, cancel := context.WithTimeout(r.Context(), 45*time.Second)
defer cancel()
targetURL := fmt.Sprintf("%s/genre-%s/sort-%s/status-%s/%s?page=%d",
novelFireBase, genre, sortBy, status, novelType, pageNum)
novels, hasNext, err := s.fetchBrowsePage(ctx, targetURL)
if err != nil {
s.deps.Log.Error("handleBrowse: fetch failed", "url", targetURL, "err", err)
jsonError(w, http.StatusBadGateway, err.Error())
// Live fetch also failed — return empty list with cached=false flag so
// the UI can show a "not ready yet" state instead of a hard error.
s.deps.Log.Error("handleBrowse: fetch failed (no cache)", "url", targetURL, "err", err)
w.Header().Set("Cache-Control", "no-store")
writeJSON(w, 0, map[string]any{
"novels": []any{},
"page": pageNum,
"hasNext": false,
"cached": false,
})
return
}
@@ -222,6 +242,7 @@ func (s *Server) handleBrowse(w http.ResponseWriter, r *http.Request) {
"novels": novels,
"page": pageNum,
"hasNext": hasNext,
"cached": false,
})
}

View File

@@ -46,6 +46,8 @@ type Dependencies struct {
PresignStore bookstore.PresignStore
// ProgressStore reads/writes per-session reading progress.
ProgressStore bookstore.ProgressStore
// BrowseStore reads cached browse page snapshots from MinIO.
BrowseStore bookstore.BrowseStore
// Producer creates scrape/audio tasks in PocketBase.
Producer taskqueue.Producer
// TaskReader reads scrape/audio task records from PocketBase.

View File

@@ -123,3 +123,15 @@ type ProgressStore interface {
// DeleteProgress removes progress for a specific slug.
DeleteProgress(ctx context.Context, sessionID, slug string) error
}
// BrowseStore covers browse page snapshot storage.
// The runner writes snapshots; the backend reads them.
type BrowseStore interface {
// PutBrowsePage stores a raw JSON snapshot for a browse page.
// genre, sort, status, novelType and page identify the page.
PutBrowsePage(ctx context.Context, genre, sort, status, novelType string, page int, data []byte) error
// GetBrowsePage retrieves a raw JSON snapshot. Returns (nil, false, nil)
// when no snapshot exists for the given parameters.
GetBrowsePage(ctx context.Context, genre, sort, status, novelType string, page int) ([]byte, bool, error)
}

View File

@@ -44,6 +44,8 @@ type MinIO struct {
BucketAudio string
// BucketAvatars is the bucket that holds user avatar images.
BucketAvatars string
// BucketBrowse is the bucket that holds cached browse page snapshots (JSON).
BucketBrowse string
}
// Kokoro holds connection settings for the Kokoro-FastAPI TTS service.
@@ -118,6 +120,7 @@ func Load() Config {
BucketChapters: envOr("MINIO_BUCKET_CHAPTERS", "libnovel-chapters"),
BucketAudio: envOr("MINIO_BUCKET_AUDIO", "libnovel-audio"),
BucketAvatars: envOr("MINIO_BUCKET_AVATARS", "libnovel-avatars"),
BucketBrowse: envOr("MINIO_BUCKET_BROWSE", "libnovel-browse"),
},
Kokoro: Kokoro{

View File

@@ -0,0 +1,176 @@
package runner
// browse_refresh.go — independent 6-hour loop that fetches novelfire.net
// browse page snapshots and stores them in MinIO.
//
// Design:
// - Runs on its own ticker (BrowseRefreshInterval, default 6h) inside Run().
// - Fetches page 1 for each combination of the standard genre/sort/status
// filter values and stores the parsed JSON blob in MinIO via BrowseStore.
// - The backend's handleBrowse then serves from MinIO instead of calling
// novelfire.net live, which avoids IP-based rate-limiting on the server.
import (
"context"
"encoding/json"
"fmt"
"io"
"net/http"
"regexp"
"strings"
"time"
)
// browseNovelListing mirrors backend.NovelListing for JSON serialisation.
type browseNovelListing struct {
Slug string `json:"slug"`
Title string `json:"title"`
Cover string `json:"cover"`
URL string `json:"url"`
}
// browseSnapshot is the JSON structure stored in MinIO.
type browseSnapshot struct {
Novels []browseNovelListing `json:"novels"`
Page int `json:"page"`
HasNext bool `json:"hasNext"`
// CachedAt is the UTC time the snapshot was written (ISO 8601).
CachedAt string `json:"cachedAt"`
}
// browseCombos lists the filter combinations to pre-fetch.
// Each entry is (genre, sort, status, novelType).
var browseCombos = []struct{ genre, sort, status, novelType string }{
{"all", "popular", "all", "all-novel"},
{"all", "popular", "ongoing", "all-novel"},
{"all", "popular", "completed", "all-novel"},
{"all", "new", "all", "all-novel"},
{"all", "new", "ongoing", "all-novel"},
{"all", "new", "completed", "all-novel"},
{"all", "top-rated", "all", "all-novel"},
{"all", "top-rated", "ongoing", "all-novel"},
{"all", "top-rated", "completed", "all-novel"},
}
const novelFireBrowseBase = "https://novelfire.net"
// runBrowseRefresh fetches all browse combos from novelfire.net and stores
// the results in MinIO. Errors per-combo are logged but do not abort the
// whole refresh cycle.
func (r *Runner) runBrowseRefresh(ctx context.Context) {
if r.deps.BrowseStore == nil {
r.deps.Log.Warn("runner: browse refresh skipped — BrowseStore not configured")
return
}
log := r.deps.Log.With("op", "browse_refresh")
log.Info("runner: browse refresh starting", "combos", len(browseCombos))
ok, fail := 0, 0
for _, c := range browseCombos {
if ctx.Err() != nil {
break
}
novels, hasNext, err := fetchBrowsePage(ctx, c.genre, c.sort, c.status, c.novelType)
if err != nil {
log.Warn("runner: browse fetch failed",
"genre", c.genre, "sort", c.sort, "status", c.status, "err", err)
fail++
continue
}
snap := browseSnapshot{
Novels: novels,
Page: 1,
HasNext: hasNext,
CachedAt: time.Now().UTC().Format(time.RFC3339),
}
data, _ := json.Marshal(snap)
if err := r.deps.BrowseStore.PutBrowsePage(ctx, c.genre, c.sort, c.status, c.novelType, 1, data); err != nil {
log.Warn("runner: browse put failed",
"genre", c.genre, "sort", c.sort, "status", c.status, "err", err)
fail++
continue
}
ok++
}
log.Info("runner: browse refresh finished", "ok", ok, "failed", fail)
}
// fetchBrowsePage calls novelfire.net and returns a list of novel listings
// plus a hasNext flag. Mirrors the logic in backend/handlers.go.
func fetchBrowsePage(ctx context.Context, genre, sort, status, novelType string) ([]browseNovelListing, bool, error) {
pageURL := fmt.Sprintf("%s/genre-%s/sort-%s/status-%s/%s?page=1",
novelFireBrowseBase, genre, sort, status, novelType)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, pageURL, nil)
if err != nil {
return nil, false, fmt.Errorf("build request: %w", err)
}
req.Header.Set("User-Agent", "Mozilla/5.0 (compatible; libnovel-runner/2)")
req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
req.Header.Set("Accept-Language", "en-US,en;q=0.9")
httpClient := &http.Client{Timeout: 45 * time.Second}
resp, err := httpClient.Do(req)
if err != nil {
return nil, false, fmt.Errorf("fetch %s: %w", pageURL, err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
_, _ = io.Copy(io.Discard, resp.Body)
return nil, false, fmt.Errorf("upstream returned %d for %s", resp.StatusCode, pageURL)
}
return parseBrowseHTML(resp.Body)
}
// parseBrowseHTML parses a novelfire HTML response body. Mirrors parseBrowsePage
// in backend/handlers.go — kept separate to avoid coupling packages.
func parseBrowseHTML(r io.Reader) ([]browseNovelListing, bool, error) {
data, err := io.ReadAll(r)
if err != nil {
return nil, false, err
}
body := string(data)
hasNext := strings.Contains(body, `rel="next"`) ||
strings.Contains(body, `aria-label="Next"`) ||
strings.Contains(body, `class="next"`)
slugRe := regexp.MustCompile(`href="/book/([^/"]+)"`)
titleRe := regexp.MustCompile(`class="novel-title[^"]*"[^>]*>([^<]+)<`)
coverRe := regexp.MustCompile(`data-src="(https?://[^"]+)"`)
slugMatches := slugRe.FindAllStringSubmatch(body, -1)
titleMatches := titleRe.FindAllStringSubmatch(body, -1)
coverMatches := coverRe.FindAllStringSubmatch(body, -1)
var novels []browseNovelListing
seen := make(map[string]bool)
for i, sm := range slugMatches {
slug := sm[1]
if seen[slug] {
continue
}
seen[slug] = true
item := browseNovelListing{
Slug: slug,
URL: novelFireBrowseBase + "/book/" + slug,
}
if i < len(titleMatches) {
item.Title = strings.TrimSpace(titleMatches[i][1])
}
if i < len(coverMatches) {
item.Cover = coverMatches[i][1]
}
if item.Title != "" {
novels = append(novels, item)
}
}
return novels, hasNext, nil
}

View File

@@ -44,6 +44,9 @@ type Config struct {
// StaleTaskThreshold is how old a heartbeat must be (or absent) before the
// task is considered orphaned and reset to pending. Defaults to 2m when 0.
StaleTaskThreshold time.Duration
// BrowseRefreshInterval is how often the runner pre-fetches browse page
// snapshots from novelfire.net and stores them in MinIO. Defaults to 6h.
BrowseRefreshInterval time.Duration
}
// Dependencies are the external services the runner depends on.
@@ -56,6 +59,8 @@ type Dependencies struct {
BookReader bookstore.BookReader
// AudioStore persists generated audio and checks key existence.
AudioStore bookstore.AudioStore
// BrowseStore stores browse page snapshots in MinIO.
BrowseStore bookstore.BrowseStore
// Novel is the scraper implementation.
Novel scraper.NovelScraper
// Kokoro is the TTS client.
@@ -91,6 +96,9 @@ func New(cfg Config, deps Dependencies) *Runner {
if cfg.StaleTaskThreshold <= 0 {
cfg.StaleTaskThreshold = 2 * time.Minute
}
if cfg.BrowseRefreshInterval <= 0 {
cfg.BrowseRefreshInterval = 6 * time.Hour
}
if deps.Log == nil {
deps.Log = slog.Default()
}
@@ -121,6 +129,7 @@ func (r *Runner) Run(ctx context.Context) error {
"poll_interval", r.cfg.PollInterval,
"max_scrape", r.cfg.MaxConcurrentScrape,
"max_audio", r.cfg.MaxConcurrentAudio,
"browse_refresh_interval", r.cfg.BrowseRefreshInterval,
)
scrapeSem := make(chan struct{}, r.cfg.MaxConcurrentScrape)
@@ -134,6 +143,12 @@ func (r *Runner) Run(ctx context.Context) error {
tick := time.NewTicker(r.cfg.PollInterval)
defer tick.Stop()
browseTick := time.NewTicker(r.cfg.BrowseRefreshInterval)
defer browseTick.Stop()
// Run one browse refresh and one poll immediately on startup.
go r.runBrowseRefresh(ctx)
// Run one poll immediately on startup, then on each tick.
for {
r.poll(ctx, scrapeSem, audioSem, &wg)
@@ -154,6 +169,8 @@ func (r *Runner) Run(ctx context.Context) error {
r.deps.Log.Warn("runner: drain timeout exceeded, forcing exit")
}
return nil
case <-browseTick.C:
go r.runBrowseRefresh(ctx)
case <-tick.C:
}
}

View File

@@ -22,6 +22,7 @@ type minioClient struct {
bucketChapters string
bucketAudio string
bucketAvatars string
bucketBrowse string
}
func newMinioClient(cfg config.MinIO) (*minioClient, error) {
@@ -78,12 +79,13 @@ func newMinioClient(cfg config.MinIO) (*minioClient, error) {
bucketChapters: cfg.BucketChapters,
bucketAudio: cfg.BucketAudio,
bucketAvatars: cfg.BucketAvatars,
bucketBrowse: cfg.BucketBrowse,
}, nil
}
// ensureBuckets creates all required buckets if they don't already exist.
func (m *minioClient) ensureBuckets(ctx context.Context) error {
for _, bucket := range []string{m.bucketChapters, m.bucketAudio, m.bucketAvatars} {
for _, bucket := range []string{m.bucketChapters, m.bucketAudio, m.bucketAvatars, m.bucketBrowse} {
exists, err := m.client.BucketExists(ctx, bucket)
if err != nil {
return fmt.Errorf("minio: check bucket %q: %w", bucket, err)
@@ -117,6 +119,12 @@ func AvatarObjectKey(userID, ext string) string {
return fmt.Sprintf("%s/%s.%s", userID, ext, ext)
}
// BrowseObjectKey returns the MinIO object key for a cached browse page snapshot.
// Format: browse/{genre}/{sort}/{status}/{type}/page-{n}.json
func BrowseObjectKey(genre, sort, status, novelType string, page int) string {
return fmt.Sprintf("browse/%s/%s/%s/%s/page-%d.json", genre, sort, status, novelType, page)
}
// chapterNumberFromKey extracts the chapter number from a MinIO object key.
// e.g. "my-book/chapter-000042.md" → 42
func chapterNumberFromKey(key string) int {
@@ -192,3 +200,23 @@ func (m *minioClient) listObjectKeys(ctx context.Context, bucket, prefix string)
}
return keys, nil
}
// ── Browse operations ─────────────────────────────────────────────────────────
// putBrowse stores raw JSON bytes for a browse page snapshot.
func (m *minioClient) putBrowse(ctx context.Context, key string, data []byte) error {
return m.putObject(ctx, m.bucketBrowse, key, "application/json", data)
}
// getBrowse retrieves a browse page snapshot. Returns (nil, false, nil) when
// the object does not exist.
func (m *minioClient) getBrowse(ctx context.Context, key string) ([]byte, bool, error) {
if !m.objectExists(ctx, m.bucketBrowse, key) {
return nil, false, nil
}
data, err := m.getObject(ctx, m.bucketBrowse, key)
if err != nil {
return nil, false, err
}
return data, true, nil
}

View File

@@ -50,6 +50,7 @@ var _ bookstore.RankingStore = (*Store)(nil)
var _ bookstore.AudioStore = (*Store)(nil)
var _ bookstore.PresignStore = (*Store)(nil)
var _ bookstore.ProgressStore = (*Store)(nil)
var _ bookstore.BrowseStore = (*Store)(nil)
var _ taskqueue.Producer = (*Store)(nil)
var _ taskqueue.Consumer = (*Store)(nil)
var _ taskqueue.Reader = (*Store)(nil)
@@ -608,12 +609,13 @@ func (s *Store) HeartbeatTask(ctx context.Context, id string) error {
// re-claimed. Returns the number of tasks reaped.
func (s *Store) ReapStaleTasks(ctx context.Context, staleAfter time.Duration) (int, error) {
threshold := time.Now().UTC().Add(-staleAfter).Format(time.RFC3339)
// Match tasks that are running AND (heartbeat_at is empty OR heartbeat_at < threshold).
filter := fmt.Sprintf(`status="running"&&(heartbeat_at=""||heartbeat_at<"%s")`, threshold)
// Match tasks that are running AND (heartbeat_at is null OR heartbeat_at < threshold).
// PocketBase datetime fields require `=null` not `=""` in filter expressions.
filter := fmt.Sprintf(`status="running"&&(heartbeat_at=null||heartbeat_at<"%s")`, threshold)
resetPayload := map[string]any{
"status": string(domain.TaskStatusPending),
"worker_id": "",
"heartbeat_at": "",
"heartbeat_at": nil,
}
total := 0
@@ -767,3 +769,22 @@ func parseAudioTask(raw json.RawMessage) (domain.AudioTask, error) {
Finished: finished,
}, nil
}
// ── BrowseStore ────────────────────────────────────────────────────────────────
func (s *Store) PutBrowsePage(ctx context.Context, genre, sort, status, novelType string, page int, data []byte) error {
key := BrowseObjectKey(genre, sort, status, novelType, page)
if err := s.mc.putBrowse(ctx, key, data); err != nil {
return fmt.Errorf("PutBrowsePage: %w", err)
}
return nil
}
func (s *Store) GetBrowsePage(ctx context.Context, genre, sort, status, novelType string, page int) ([]byte, bool, error) {
key := BrowseObjectKey(genre, sort, status, novelType, page)
data, ok, err := s.mc.getBrowse(ctx, key)
if err != nil {
return nil, false, fmt.Errorf("GetBrowsePage: %w", err)
}
return data, ok, nil
}

View File

@@ -30,6 +30,7 @@ services:
mc mb --ignore-existing local/libnovel-chapters;
mc mb --ignore-existing local/libnovel-audio;
mc mb --ignore-existing local/libnovel-avatars;
mc mb --ignore-existing local/libnovel-browse;
echo 'buckets ready';
"
environment:
@@ -88,7 +89,7 @@ services:
environment:
BACKEND_HTTP_ADDR: ":8080"
LOG_LEVEL: "${LOG_LEVEL:-info}"
# MinIO
# MinIO
MINIO_ENDPOINT: "minio:9000"
MINIO_ACCESS_KEY: "${MINIO_ROOT_USER:-admin}"
MINIO_SECRET_KEY: "${MINIO_ROOT_PASSWORD:-changeme123}"
@@ -96,6 +97,7 @@ services:
MINIO_BUCKET_CHAPTERS: "${MINIO_BUCKET_CHAPTERS:-libnovel-chapters}"
MINIO_BUCKET_AUDIO: "${MINIO_BUCKET_AUDIO:-libnovel-audio}"
MINIO_BUCKET_AVATARS: "${MINIO_BUCKET_AVATARS:-libnovel-avatars}"
MINIO_BUCKET_BROWSE: "${MINIO_BUCKET_BROWSE:-libnovel-browse}"
MINIO_PUBLIC_ENDPOINT: "${MINIO_PUBLIC_ENDPOINT:-http://localhost:9000}"
MINIO_PUBLIC_USE_SSL: "${MINIO_PUBLIC_USE_SSL:-false}"
# PocketBase
@@ -152,6 +154,7 @@ services:
MINIO_BUCKET_CHAPTERS: "${MINIO_BUCKET_CHAPTERS:-libnovel-chapters}"
MINIO_BUCKET_AUDIO: "${MINIO_BUCKET_AUDIO:-libnovel-audio}"
MINIO_BUCKET_AVATARS: "${MINIO_BUCKET_AVATARS:-libnovel-avatars}"
MINIO_BUCKET_BROWSE: "${MINIO_BUCKET_BROWSE:-libnovel-browse}"
MINIO_PUBLIC_ENDPOINT: "${MINIO_PUBLIC_ENDPOINT:-http://localhost:9000}"
MINIO_PUBLIC_USE_SSL: "${MINIO_PUBLIC_USE_SSL:-false}"
# PocketBase