mangaBookmark/backend/internal/latest/read.go

package latest

import (
	"context"
	"errors"
	"fmt"
)

// seriesRead carries the facts the poll and the acquirer both extract from a
// series page. Persistence, stamps and scheduling stay with the callers, so
// the policies that keep the two flows distinct (stamp order, rests) are not
// swallowed by the module.
type seriesRead struct {
	Latest    latestChapter
	HasLatest bool
	Cover     string
	HasCover  bool
	// SiteCompleted is whether the Site's own completed value was on the page.
	// A challenge body and a redesign both read false — an absent hint, never
	// a claim (issue #168).
	SiteCompleted bool
	// BodyLen is the fetched body's length, surfaced because the no-chapter
	// log uses it to tell a markup change from a body the size cap cut short.
	BodyLen int
}

// errNotFetchable and errNoFetcher separate the gate and the route from fetch
// failures so each caller keeps its own distinct log line for all three.
// errChallengeHeld (browser.go) is the outcome of a Site that answered with
// its interstitial — status 403 (cf-mitigated) or a challenge page body — and
// is how a Lane tells a refusal from an ordinary failure (issue #100).
// errNotFound marks any other 4xx: the page is gone — a fact the owner can act
// on — as distinct from a Site or database that is merely unwell (issue #164).
var (
	errNotFetchable = errors.New("series url not fetchable")
	errNoFetcher    = errors.New("no fetcher for site")
	errNotFound     = errors.New("series page not found")
)

// readSeriesPage performs the series-page read the poll and the acquirer have
// in common: gate the address, choose the route, fetch the page, extract the
// Latest Chapter, the Cover address and the Site's completed value. It
// persists nothing and stamps nothing.
//
// series_url arrives in a client-supplied PUT body (PUT /bookmarks/{key}
// accepts any string), so the gate is not an optimisation against burning a
// request on an unknown site: without it, the server would issue a GET from
// its own network position to whatever URL a token-holder writes, including
// link-local/internal addresses or non-https schemes.
func readSeriesPage(ctx context.Context, site, seriesURL string, browser, tls Fetcher) (seriesRead, error) {
	if !FetchableSeriesURL(site, seriesURL) {
		return seriesRead{}, fmt.Errorf("%w: site=%q url=%q", errNotFetchable, site, seriesURL)
	}
	f := fetcherFor(site, browser, tls)
	if f == nil {
		return seriesRead{}, fmt.Errorf("%w: site %q", errNoFetcher, site)
	}
	body, status, err := f.Get(ctx, seriesURL)
	if err != nil {
		return seriesRead{}, fmt.Errorf("fetch %s: %w", seriesURL, err)
	}
	if status == 403 {
		// Cloudflare's challenge response for these Sites (cf-mitigated). The
		// browser fetcher returns exactly this on a held interstitial, and a
		// plain-TLS 403 means the same: the Site is refusing.
		return seriesRead{}, fmt.Errorf("%w: fetch %s: status %d", errChallengeHeld, seriesURL, status)
	}
	if status != 200 {
		if status >= 400 && status < 500 {
			return seriesRead{}, fmt.Errorf("%w: fetch %s: status %d", errNotFound, seriesURL, status)
		}
		return seriesRead{}, fmt.Errorf("fetch %s: status %d", seriesURL, status)
	}
	if isInterstitial(body) {
		// A 200 that is the challenge page, not the payload: the TLS route can
		// receive this where the browser would have kept re-reading. Same
		// refusal as the 403.
		return seriesRead{}, fmt.Errorf("%w: fetch %s: interstitial body", errChallengeHeld, seriesURL)
	}
	latest, hasLatest := latestChapterFrom(site, seriesURL, body)
	cover, hasCover := coverFrom(site, seriesURL, body)
	return seriesRead{
		Latest:        latest,
		HasLatest:     hasLatest,
		Cover:         cover,
		HasCover:      hasCover,
		SiteCompleted: siteCompletedFrom(site, seriesURL, body),
		BodyLen:       len(body),
	}, nil
}