Compare commits

...

2 Commits

Author SHA1 Message Date
Admin
b363c151a5 fix(ui): fix catalogue filters in Svelte 5; improve build badge visibility
Some checks failed
Release / Test backend (push) Successful in 40s
Release / Check ui (push) Successful in 49s
Release / Docker / caddy (push) Failing after 1m0s
CI / Test backend (pull_request) Successful in 40s
CI / Docker / caddy (pull_request) Failing after 21s
CI / Check ui (pull_request) Successful in 48s
Release / Docker / ui (push) Successful in 2m49s
Release / Docker / runner (push) Successful in 3m10s
Release / Docker / backend (push) Successful in 3m47s
Release / Gitea Release (push) Has been skipped
CI / Docker / ui (pull_request) Successful in 1m31s
CI / Docker / backend (pull_request) Successful in 3m13s
CI / Docker / runner (pull_request) Successful in 3m59s
- Catalogue filter selects: replace value= initializer with bind:value +
  onchange goto() so filters navigate immediately on change (no Apply button)
- Add selected= on each <option> for correct DOM initialisation in Svelte 5
- Build badge: give distinct bg-zinc-800 pill, visible zinc-300/400/500 text
  instead of zinc-700/zinc-800 which blended into the footer background
2026-03-28 19:01:58 +05:00
Admin
aef9e04419 fix(runner): harden catalogue scrape against 429s; disable sourcemap upload
Some checks failed
Release / Test backend (push) Successful in 29s
Release / Check ui (push) Successful in 43s
CI / Test backend (pull_request) Successful in 28s
Release / Docker / caddy (push) Successful in 1m8s
CI / Docker / caddy (pull_request) Failing after 39s
CI / Check ui (pull_request) Successful in 55s
Release / Docker / runner (push) Successful in 2m22s
Release / Docker / ui (push) Successful in 2m20s
CI / Docker / backend (pull_request) Successful in 2m32s
CI / Docker / ui (pull_request) Successful in 1m28s
CI / Docker / runner (pull_request) Successful in 2m25s
Release / Docker / backend (push) Successful in 2m33s
Release / Gitea Release (push) Failing after 2s
- scraper.go: ScrapeCatalogue now uses retryGet (9 attempts, 10s base) +
  500–1500ms inter-page jitter instead of bare GetContent. ScrapeMetadata
  also switched to retryGet so a single 429 on a book page is retried rather
  than aborting the whole refresh.
- catalogue_refresh.go: per-book delay is now configurable
  (RUNNER_CATALOGUE_REQUEST_DELAY, default 2s) + up to 50% random jitter
  applied before every metadata fetch. Only metadata is scraped here —
  chapters are fetched on-demand, not during catalogue refresh. Progress
  logged every 50 books instead of 100.
- config.go / runner.go / main.go: add CatalogueRequestDelay field wired
  from RUNNER_CATALOGUE_REQUEST_DELAY env var.
- release.yaml: comment out upload-sourcemaps job and remove it from the
  release needs; GlitchTip auth token needs refreshing after DB wipe.
2026-03-28 16:28:36 +05:00
8 changed files with 144 additions and 95 deletions

View File

@@ -136,52 +136,51 @@ jobs:
cache-to: type=inline
# ── ui: source map upload ─────────────────────────────────────────────────────
# Builds the UI with source maps and uploads them to GlitchTip so that error
# stack traces resolve to original .svelte/.ts file names and line numbers.
# Runs in parallel with docker-ui (both need check-ui to pass first).
upload-sourcemaps:
name: Upload source maps
runs-on: ubuntu-latest
needs: [check-ui]
defaults:
run:
working-directory: ui
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: "22"
cache: npm
cache-dependency-path: ui/package-lock.json
- name: Install dependencies
run: npm ci
- name: Build with source maps
run: npm run build
- name: Download glitchtip-cli
run: |
curl -L "https://gitlab.com/glitchtip/glitchtip-cli/-/jobs/artifacts/v0.1.0/raw/artifacts/glitchtip-cli-linux-x86_64?job=build-linux-x86_64" \
-o /usr/local/bin/glitchtip-cli
chmod +x /usr/local/bin/glitchtip-cli
- name: Inject debug IDs into build artifacts
run: glitchtip-cli sourcemaps inject ./build
env:
SENTRY_URL: https://errors.libnovel.cc/
SENTRY_AUTH_TOKEN: ${{ secrets.GLITCHTIP_AUTH_TOKEN }}
SENTRY_ORG: libnovel
SENTRY_PROJECT: libnovel-ui
- name: Upload source maps to GlitchTip
run: glitchtip-cli sourcemaps upload ./build --release ${{ gitea.ref_name }}
env:
SENTRY_URL: https://errors.libnovel.cc/
SENTRY_AUTH_TOKEN: ${{ secrets.GLITCHTIP_AUTH_TOKEN }}
SENTRY_ORG: libnovel
SENTRY_PROJECT: libnovel-ui
# Commented out: GlitchTip project/auth token needs to be recreated after
# the GlitchTip DB wipe. Re-enable once GLITCHTIP_AUTH_TOKEN is updated.
# upload-sourcemaps:
# name: Upload source maps
# runs-on: ubuntu-latest
# needs: [check-ui]
# defaults:
# run:
# working-directory: ui
# steps:
# - uses: actions/checkout@v4
#
# - uses: actions/setup-node@v4
# with:
# node-version: "22"
# cache: npm
# cache-dependency-path: ui/package-lock.json
#
# - name: Install dependencies
# run: npm ci
#
# - name: Build with source maps
# run: npm run build
#
# - name: Download glitchtip-cli
# run: |
# curl -L "https://gitlab.com/glitchtip/glitchtip-cli/-/jobs/artifacts/v0.1.0/raw/artifacts/glitchtip-cli-linux-x86_64?job=build-linux-x86_64" \
# -o /usr/local/bin/glitchtip-cli
# chmod +x /usr/local/bin/glitchtip-cli
#
# - name: Inject debug IDs into build artifacts
# run: glitchtip-cli sourcemaps inject ./build
# env:
# SENTRY_URL: https://errors.libnovel.cc/
# SENTRY_AUTH_TOKEN: ${{ secrets.GLITCHTIP_AUTH_TOKEN }}
# SENTRY_ORG: libnovel
# SENTRY_PROJECT: libnovel-ui
#
# - name: Upload source maps to GlitchTip
# run: glitchtip-cli sourcemaps upload ./build --release ${{ gitea.ref_name }}
# env:
# SENTRY_URL: https://errors.libnovel.cc/
# SENTRY_AUTH_TOKEN: ${{ secrets.GLITCHTIP_AUTH_TOKEN }}
# SENTRY_ORG: libnovel
# SENTRY_PROJECT: libnovel-ui
# ── docker: ui ────────────────────────────────────────────────────────────────
docker-ui:
@@ -261,7 +260,7 @@ jobs:
release:
name: Gitea Release
runs-on: ubuntu-latest
needs: [docker-backend, docker-runner, docker-ui, docker-caddy, upload-sourcemaps]
needs: [docker-backend, docker-runner, docker-ui, docker-caddy]
steps:
- uses: actions/checkout@v4
with:

View File

@@ -152,6 +152,7 @@ func run() error {
OrchestratorWorkers: workers,
MetricsAddr: cfg.Runner.MetricsAddr,
CatalogueRefreshInterval: cfg.Runner.CatalogueRefreshInterval,
CatalogueRequestDelay: cfg.Runner.CatalogueRequestDelay,
SkipInitialCatalogueRefresh: cfg.Runner.SkipInitialCatalogueRefresh,
RedisAddr: cfg.Redis.Addr,
RedisPassword: cfg.Redis.Password,

View File

@@ -126,6 +126,11 @@ type Runner struct {
// is already indexed and a 24h walk would be wasteful.
// Controlled by RUNNER_SKIP_INITIAL_CATALOGUE_REFRESH=true.
SkipInitialCatalogueRefresh bool
// CatalogueRequestDelay is the base delay inserted between per-book metadata
// requests during a catalogue refresh. A random jitter of up to 50% is added
// on top. Defaults to 2s. Increase to reduce 429 pressure on novelfire.net.
// Controlled by RUNNER_CATALOGUE_REQUEST_DELAY (e.g. "3s", "500ms").
CatalogueRequestDelay time.Duration
}
// Config is the top-level configuration struct consumed by both binaries.
@@ -196,6 +201,7 @@ func Load() Config {
MetricsAddr: envOr("RUNNER_METRICS_ADDR", ":9091"),
CatalogueRefreshInterval: envDuration("RUNNER_CATALOGUE_REFRESH_INTERVAL", 0),
SkipInitialCatalogueRefresh: envBool("RUNNER_SKIP_INITIAL_CATALOGUE_REFRESH", false),
CatalogueRequestDelay: envDuration("RUNNER_CATALOGUE_REQUEST_DELAY", 2*time.Second),
},
Meilisearch: Meilisearch{

View File

@@ -13,6 +13,7 @@ import (
"errors"
"fmt"
"log/slog"
"math/rand"
"net/url"
"path"
"strconv"
@@ -55,6 +56,9 @@ func (s *Scraper) SourceName() string { return "novelfire.net" }
// ── CatalogueProvider ─────────────────────────────────────────────────────────
// ScrapeCatalogue streams all CatalogueEntry values across all catalogue pages.
// Each page fetch uses retryGet with 429-aware exponential backoff.
// A small inter-page delay (cataloguePageDelay) is inserted between requests to
// avoid hammering the server when paging through hundreds of catalogue pages.
func (s *Scraper) ScrapeCatalogue(ctx context.Context) (<-chan domain.CatalogueEntry, <-chan error) {
entries := make(chan domain.CatalogueEntry, 64)
errs := make(chan error, 16)
@@ -73,8 +77,18 @@ func (s *Scraper) ScrapeCatalogue(ctx context.Context) (<-chan domain.CatalogueE
default:
}
// Polite inter-page delay — skipped on the very first page.
if page > 1 {
jitter := time.Duration(500+rand.Intn(1000)) * time.Millisecond
select {
case <-ctx.Done():
return
case <-time.After(jitter):
}
}
s.log.Info("scraping catalogue page", "page", page, "url", pageURL)
raw, err := s.client.GetContent(ctx, pageURL)
raw, err := retryGet(ctx, s.log, s.client, pageURL, 9, 10*time.Second)
if err != nil {
errs <- fmt.Errorf("catalogue page %d: %w", page, err)
return
@@ -139,10 +153,11 @@ func (s *Scraper) ScrapeCatalogue(ctx context.Context) (<-chan domain.CatalogueE
// ── MetadataProvider ──────────────────────────────────────────────────────────
// ScrapeMetadata fetches and parses book metadata from the book's landing page.
// Uses retryGet with 429-aware exponential backoff (up to 9 attempts).
func (s *Scraper) ScrapeMetadata(ctx context.Context, bookURL string) (domain.BookMeta, error) {
s.log.Debug("metadata fetch starting", "url", bookURL)
raw, err := s.client.GetContent(ctx, bookURL)
raw, err := retryGet(ctx, s.log, s.client, bookURL, 9, 10*time.Second)
if err != nil {
return domain.BookMeta{}, fmt.Errorf("metadata fetch %s: %w", bookURL, err)
}

View File

@@ -6,17 +6,20 @@ package runner
//
// Design:
// - Runs on its own ticker (CatalogueRefreshInterval, default 24h) inside Run().
// - Also fires once on startup.
// - ScrapeCatalogue streams CatalogueEntry values over a channel — we iterate
// and call ScrapeMetadata for each entry.
// - Per-request random jitter (13s) prevents hammering novelfire.net.
// - Cover images are fetched from the URL embedded in BookMeta.Cover and
// stored in MinIO (browse bucket, key: covers/{slug}.jpg).
// - WriteMetadata + UpsertBook are called for every successfully scraped book.
// - Errors for individual books are logged and skipped; the loop continues.
// - The cover URL stored in BookMeta.Cover is rewritten to the internal proxy
// path (/api/cover/novelfire.net/{slug}) so the UI always fetches via the
// backend, which will serve from MinIO.
// - Also fires once on startup (unless SkipInitialCatalogueRefresh is set).
// - ScrapeCatalogue streams CatalogueEntry values over a channel — already has
// its own inter-page jitter + retryGet (see scraper.go).
// - Per-book: only metadata is scraped here (not chapters). Chapters are scraped
// on-demand when a user opens a book or via an explicit scrape task.
// - Between each metadata request a configurable base delay plus up to 50%
// random jitter is applied (CatalogueRequestDelay, default 2s). This keeps
// the request rate well below novelfire.net's rate limit even for ~15k books.
// - ScrapeMetadata itself uses retryGet with 429-aware exponential backoff
// (up to 9 attempts), so transient rate limits are handled gracefully.
// - Cover images are fetched and stored in MinIO on first sight; subsequent
// refreshes skip covers that already exist (CoverExists check).
// - Books already present in Meilisearch are skipped entirely (fast path).
// - Errors for individual books are logged and skipped; the loop never aborts.
import (
"context"
@@ -29,7 +32,7 @@ import (
// runCatalogueRefresh performs one full catalogue walk: scrapes metadata for
// every book on novelfire.net, downloads covers to MinIO, and upserts to
// Meilisearch. Errors for individual books are logged and skipped.
// Meilisearch. Individual book failures are logged and skipped.
func (r *Runner) runCatalogueRefresh(ctx context.Context) {
if r.deps.Novel == nil {
r.deps.Log.Warn("runner: catalogue refresh skipped — Novel scraper not configured")
@@ -40,8 +43,9 @@ func (r *Runner) runCatalogueRefresh(ctx context.Context) {
return
}
delay := r.cfg.CatalogueRequestDelay
log := r.deps.Log.With("op", "catalogue_refresh")
log.Info("runner: catalogue refresh starting")
log.Info("runner: catalogue refresh starting", "request_delay", delay)
entries, errCh := r.deps.Novel.ScrapeCatalogue(ctx)
@@ -51,26 +55,26 @@ func (r *Runner) runCatalogueRefresh(ctx context.Context) {
break
}
// Skip books already present in Meilisearch — they were indexed on a
// previous run. Re-indexing only happens when a scrape task is
// explicitly enqueued (e.g. via the admin UI or API).
// Fast path: skip books already indexed in Meilisearch.
if r.deps.SearchIndex.BookExists(ctx, entry.Slug) {
skipped++
continue
}
// Random jitter between books to avoid rate-limiting.
jitter := time.Duration(1000+rand.Intn(2000)) * time.Millisecond
// Polite delay between metadata requests: base + up to 50% jitter.
// This applies before every fetch so we never fire bursts.
jitter := time.Duration(rand.Int63n(int64(delay / 2)))
select {
case <-ctx.Done():
break
case <-time.After(jitter):
case <-time.After(delay + jitter):
}
// ScrapeMetadata internally retries on 429 with exponential back-off.
meta, err := r.deps.Novel.ScrapeMetadata(ctx, entry.URL)
if err != nil {
log.Warn("runner: catalogue refresh: metadata scrape failed",
"url", entry.URL, "err", err)
log.Warn("runner: catalogue refresh: metadata scrape failed — skipping book",
"slug", entry.Slug, "url", entry.URL, "err", err)
errCount++
continue
}
@@ -81,35 +85,32 @@ func (r *Runner) runCatalogueRefresh(ctx context.Context) {
// Persist to PocketBase.
if err := r.deps.BookWriter.WriteMetadata(ctx, meta); err != nil {
log.Warn("runner: catalogue refresh: WriteMetadata failed",
log.Warn("runner: catalogue refresh: WriteMetadata failed — skipping book",
"slug", meta.Slug, "err", err)
errCount++
continue
}
// Index in Meilisearch.
// Index in Meilisearch (non-fatal).
if err := r.deps.SearchIndex.UpsertBook(ctx, meta); err != nil {
log.Warn("runner: catalogue refresh: UpsertBook failed",
"slug", meta.Slug, "err", err)
// non-fatal — continue
}
// Download and store cover image in MinIO if we have a cover URL
// and a CoverStore is wired in.
// Download cover to MinIO if not already cached (non-fatal).
if r.deps.CoverStore != nil && originalCover != "" {
if !r.deps.CoverStore.CoverExists(ctx, meta.Slug) {
if err := r.downloadCover(ctx, meta.Slug, originalCover); err != nil {
log.Warn("runner: catalogue refresh: cover download failed",
"slug", meta.Slug, "url", originalCover, "err", err)
// non-fatal
}
}
}
ok++
if ok%100 == 0 {
if ok%50 == 0 {
log.Info("runner: catalogue refresh progress",
"scraped", ok, "errors", errCount)
"scraped", ok, "skipped", skipped, "errors", errCount)
}
}

View File

@@ -62,6 +62,10 @@ type Config struct {
// scrapes per-book metadata, downloads covers, and re-indexes everything in
// Meilisearch. Defaults to 24h (expensive — full catalogue walk).
CatalogueRefreshInterval time.Duration
// CatalogueRequestDelay is the base inter-request pause during a catalogue
// refresh metadata walk. Jitter of up to 50% is added on top.
// Defaults to 2s. Set via RUNNER_CATALOGUE_REQUEST_DELAY.
CatalogueRequestDelay time.Duration
// SkipInitialCatalogueRefresh suppresses the immediate catalogue walk that
// otherwise fires at startup. The periodic ticker (CatalogueRefreshInterval)
// still fires normally. Set RUNNER_SKIP_INITIAL_CATALOGUE_REFRESH=true for
@@ -145,6 +149,9 @@ func New(cfg Config, deps Dependencies) *Runner {
if cfg.CatalogueRefreshInterval <= 0 {
cfg.CatalogueRefreshInterval = 24 * time.Hour
}
if cfg.CatalogueRequestDelay <= 0 {
cfg.CatalogueRequestDelay = 2 * time.Second
}
if cfg.MetricsAddr == "" {
cfg.MetricsAddr = ":9091"
}

View File

@@ -434,16 +434,16 @@
<span>&copy; {new Date().getFullYear()} libnovel</span>
</div>
<!-- Build version / commit SHA -->
<div class="text-zinc-700 tabular-nums font-mono">
<div class="text-xs tabular-nums font-mono px-2 py-0.5 rounded bg-zinc-800 border border-zinc-700">
{#if env.PUBLIC_BUILD_VERSION && env.PUBLIC_BUILD_VERSION !== 'dev'}
<span title="Build version">{env.PUBLIC_BUILD_VERSION}</span>
<span class="text-zinc-300" title="Build version">{env.PUBLIC_BUILD_VERSION}</span>
{#if env.PUBLIC_BUILD_COMMIT && env.PUBLIC_BUILD_COMMIT !== 'unknown'}
<span class="text-zinc-800 select-all" title="Commit SHA"
<span class="text-zinc-500 select-all" title="Commit SHA"
>+{env.PUBLIC_BUILD_COMMIT.slice(0, 7)}</span
>
{/if}
{:else}
<span class="text-zinc-800">dev</span>
<span class="text-zinc-400">dev</span>
{/if}
</div>
</div>

View File

@@ -1,5 +1,6 @@
<script lang="ts">
import { enhance } from '$app/forms';
import { goto } from '$app/navigation';
import { navigating } from '$app/state';
import { untrack } from 'svelte';
import type { PageData, ActionData } from './$types';
@@ -7,6 +8,29 @@
let { data, form }: { data: PageData; form: ActionData } = $props();
// ── Local filter state (mirrors URL params) ──────────────────────────────
// These are separate from data.* so we can bind them to selects and keep
// the DOM in sync. They sync back from data whenever a navigation completes.
let filterSort = $state(untrack(() => data.sort));
let filterGenre = $state(untrack(() => data.genre));
let filterStatus = $state(untrack(() => data.status));
// Keep local state in sync whenever SvelteKit re-runs the load (URL changed).
$effect(() => {
filterSort = data.sort;
filterGenre = data.genre;
filterStatus = data.status;
});
function navigateWithFilters(overrides: { sort?: string; genre?: string; status?: string }) {
const params = new URLSearchParams();
params.set('sort', overrides.sort ?? filterSort);
params.set('genre', overrides.genre ?? filterGenre);
params.set('status', overrides.status ?? filterStatus);
params.set('page', '1');
goto(`/catalogue?${params.toString()}`);
}
// Track which novel card is currently being navigated to
let loadingSlug = $state<string | null>(null);
@@ -389,11 +413,12 @@
<select
id="filter-sort"
name="sort"
value={data.sort}
bind:value={filterSort}
onchange={() => navigateWithFilters({ sort: filterSort })}
class="bg-zinc-900 border border-zinc-700 text-zinc-200 text-sm rounded px-3 py-2 focus:outline-none focus:border-amber-400 w-full"
>
{#each sorts as s}
<option value={s.value}>{s.label}</option>
<option value={s.value} selected={s.value === filterSort}>{s.label}</option>
{/each}
</select>
</div>
@@ -403,12 +428,13 @@
<select
id="filter-genre"
name="genre"
value={data.genre}
bind:value={filterGenre}
onchange={() => navigateWithFilters({ genre: filterGenre })}
disabled={isRankView}
class="bg-zinc-900 border border-zinc-700 text-zinc-200 text-sm rounded px-3 py-2 focus:outline-none focus:border-amber-400 disabled:opacity-40 disabled:cursor-not-allowed w-full"
>
{#each genres as g}
<option value={g.value}>{g.label}</option>
<option value={g.value} selected={g.value === filterGenre}>{g.label}</option>
{/each}
</select>
</div>
@@ -418,12 +444,13 @@
<select
id="filter-status"
name="status"
value={data.status}
bind:value={filterStatus}
onchange={() => navigateWithFilters({ status: filterStatus })}
disabled={isRankView}
class="bg-zinc-900 border border-zinc-700 text-zinc-200 text-sm rounded px-3 py-2 focus:outline-none focus:border-amber-400 disabled:opacity-40 disabled:cursor-not-allowed w-full"
>
{#each statuses as st}
<option value={st.value}>{st.label}</option>
<option value={st.value} selected={st.value === filterStatus}>{st.label}</option>
{/each}
</select>
</div>
@@ -437,13 +464,6 @@
<a href="/catalogue" class="px-4 py-2 rounded bg-zinc-700 text-zinc-300 text-sm hover:bg-zinc-600 transition-colors">
Reset
</a>
<button
type="submit"
onclick={() => (filtersOpen = false)}
class="px-4 py-2 rounded bg-amber-400 text-zinc-900 text-sm font-semibold hover:bg-amber-300 transition-colors"
>
Apply
</button>
</div>
</form>
{/if}