mangaBookmark/backend/internal/latest/acquire.go

package latest

import (
	"context"
	"errors"
	"log"
	"sync"
	"time"

	"bookmarkmanager/backend/internal/store"
)

// acquireTimeout bounds one creation-time acquisition end to end: the series
// page plus the cover bytes. Nothing is waiting on it — the Reader's write has
// already returned — so this only stops a stalled Site from holding a
// goroutine and a connection open forever.
const acquireTimeout = 45 * time.Second

// Acquirer gives a Series its Latest Chapter and its Cover the moment the
// first Bookmark creates it, instead of leaving the Reader to wait out the
// poll queue — which is ordered by Reader count, so a Series with one Reader
// sits behind every popular one (ADR-0007).
//
// Both facts come from a single series-page fetch, which is also why no
// client-supplied cover hint is worth accepting: the page has to be fetched
// for the chapter signal regardless, so a hint would save no request while
// adding a client-controlled input to a server-side fetch.
//
// Every failure path is "log and move on". The Bookmark, its progress and its
// Latest Chapter are already committed; a Site that is down or a Cover that
// cannot be produced must not disturb any of them, and the Series is simply
// left blank until the poll's own cover pass (#61) fills it.
type Acquirer struct {
	Store *store.Store
	// Fetch retrieves the series page over plain TLS. Nil with a nil
	// BrowserFetch disables acquisition entirely.
	Fetch Fetcher
	// BrowserFetch retrieves kagane and novelfull pages through the browser
	// sidecar, the only thing that clears their Cloudflare challenge. The
	// per-site fallback policy lives in fetcherFor. Nil leaves those Sites
	// unacquired when no fallback applies.
	BrowserFetch Fetcher
	// Covers retrieves the cover bytes. Nil leaves the Cover blank and the
	// chapter half working.
	Covers CoverBytesFetcher
	// BrowserCoverFetch retrieves browser-claimed cover bytes through the
	// sidecar. Nil leaves those Covers blank; nothing falls back to a plain
	// fetch, which would only ever retrieve a challenge page.
	BrowserCoverFetch BrowserCoverFetcher
	// Ctx cancels in-flight acquisitions at shutdown. A hook signature has
	// nowhere to pass one, so it lives here; nil means context.Background.
	Ctx context.Context

	inflight sync.WaitGroup
}

// acquireSlots caps how many creation-time fetches run at once. A Reader whose
// userscript bulk-syncs creates many Series at once, and a burst of
// simultaneous requests from one server IP is the traffic shape most likely to
// move that IP's bot score — the same reason the poller staggers its batch.
var acquireSlots = make(chan struct{}, 2)

// Acquire starts one acquisition and returns immediately: a Reader's bookmark
// action may not block on a third-party Site's latency, nor fail with it. It
// is the store's OnSeriesCreated hook, so it only ever runs for a Series no
// Reader had bookmarked before.
func (a *Acquirer) Acquire(sr store.Series) {
	a.inflight.Add(1)
	go func() {
		defer a.inflight.Done()
		defer func() {
			if r := recover(); r != nil {
				log.Printf("acquire %q: recovered from panic: %v", sr.Key(), r)
			}
		}()
		parent := a.Ctx
		if parent == nil {
			parent = context.Background()
		}
		select {
		case acquireSlots <- struct{}{}:
			defer func() { <-acquireSlots }()
		case <-parent.Done():
			return
		}
		ctx, cancel := context.WithTimeout(parent, acquireTimeout)
		defer cancel()
		a.acquire(ctx, sr)
	}()
}

// Wait blocks until every started acquisition has finished. It exists for
// tests: an asynchronous side effect is otherwise unobservable without
// polling for it.
func (a *Acquirer) Wait() { a.inflight.Wait() }

func (a *Acquirer) acquire(ctx context.Context, sr store.Series) {
	if a.Fetch == nil && a.BrowserFetch == nil {
		return
	}
	facts, err := readSeriesPage(ctx, sr.Site, sr.SeriesURL, a.BrowserFetch, a.Fetch)
	if err != nil {
		switch {
		case errors.Is(err, errNotFetchable):
			// series_url arrives in a client-supplied PUT body, so without the
			// gate a token-holder chooses what the server fetches from its own
			// network position.
			log.Printf("acquire %q: not fetchable: site=%q url=%q", sr.Key(), sr.Site, sr.SeriesURL)
		case errors.Is(err, errNoFetcher):
			log.Printf("acquire %q: no fetcher for site %q", sr.Key(), sr.Site)
		default:
			log.Printf("acquire %q: %v", sr.Key(), err)
		}
		return
	}

	// This page just served the same purpose a poll tick would have; without
	// the stamp the row stays due and the poller refetches it immediately.
	//
	// Stamped after success — the reverse of the poller, which stamps before
	// the fetch: the Reader is here, watching the Series they just created, so
	// a failed acquisition must leave the row due for a fast retry rather than
	// consuming the rest. The stamp happens even when the page read
	// succeeded but produced no facts to persist.
	if err := a.Store.MarkLatestChecked(sr.Site, sr.SeriesID, time.Now().UnixMilli()); err != nil {
		log.Printf("acquire %q: mark checked: %v", sr.Key(), err)
	}

	if facts.HasLatest {
		if err := a.Store.SetLatestChapter(sr.Site, sr.SeriesID, facts.Latest.Label, facts.Latest.Num); err != nil {
			log.Printf("acquire %q: set latest chapter: %v", sr.Key(), err)
		}
	}

	if !facts.HasCover {
		return
	}
	bytes, contentType, err := fetchCoverBytes(ctx, facts.Cover, a.BrowserCoverFetch, a.Covers)
	if err != nil {
		log.Printf("acquire %q: fetch cover %s: %v", sr.Key(), facts.Cover, err)
		return
	}
	if err := a.Store.SetSeriesCover(sr.Site, sr.SeriesID, facts.Cover, bytes, contentType); err != nil {
		log.Printf("acquire %q: persist cover: %v", sr.Key(), err)
	}
}