sulthan
d998f8725c
Restore two review findings against spec claims 'the Poll keeps its own Cover policy' and 'pinning is the only behavioural change': prefetchCover now also runs on ticks where the page fetch itself fails (the heal is independent of the page read, and its source may answer while the origin does not), and the no-chapter log surfaces the fetched body length again via a BodyLen fact on seriesRead. Browser dispatch iterates the sorted browser site list so its outcome cannot depend on map order.
59 lines
2.2 KiB
Go
59 lines
2.2 KiB
Go
package latest
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
)
|
|
|
|
// seriesRead carries the two 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,
|
|
// cooldowns) are not swallowed by the module.
|
|
type seriesRead struct {
|
|
Latest latestChapter
|
|
HasLatest bool
|
|
Cover string
|
|
HasCover 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.
|
|
var (
|
|
errNotFetchable = errors.New("series url not fetchable")
|
|
errNoFetcher = errors.New("no fetcher for site")
|
|
)
|
|
|
|
// 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 and the Cover address. 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 != 200 {
|
|
return seriesRead{}, fmt.Errorf("fetch %s: status %d", seriesURL, status)
|
|
}
|
|
latest, hasLatest := latestChapterFrom(site, seriesURL, body)
|
|
cover, hasCover := coverFrom(site, seriesURL, body)
|
|
return seriesRead{Latest: latest, HasLatest: hasLatest, Cover: cover, HasCover: hasCover, BodyLen: len(body)}, nil
|
|
}
|