main: dedupe followed .torrent files by infohash

a .torrent fetched over http is added to the shared client in a second
pass (followUps); two that name the same torrent would share one torrent
on the refcount-less client, and the first to finish would Drop it out
from under the other, stranding it at 0%. dedupe the followed files by
infohash, the guard build() already applies to pass-1 sources.
This commit is contained in:
2026-06-20 19:28:32 +09:00
parent 554beb6b48
commit 7336f9c95e
2 changed files with 115 additions and 12 deletions

51
main.go
View File

@@ -224,6 +224,24 @@ func dedupeTorrents(uris []string, follow bool) map[string]string {
return dup
}
// markInfoHash records the v1 infohash of the .torrent at path in seen and
// reports whether it repeats one already seen, returning the path first recorded
// under that infohash. Callers fail the duplicate rather than let two jobs share
// one torrent on the client (see bt.SourceInfoHash for why that aliasing is
// unsafe). A v2-only or unreadable infohash is never a duplicate — the dedup
// can't see it, so it runs.
func markInfoHash(seen map[metainfo.Hash]string, path string) (first string, dup bool) {
h, ok := bt.SourceInfoHash(path, true)
if !ok {
return "", false
}
if first, dup = seen[h]; dup {
return first, true
}
seen[h] = path
return "", false
}
func build(opts *cli.Options, targets []target) ([]job, *torrent.Client, error) {
flat := allURIs(targets)
// Two sources naming the same torrent (a magnet and its own .torrent, say)
@@ -358,6 +376,7 @@ func runJobs(ctx context.Context, eng *download.Engine, jobs []job) []download.R
// so a regular download that merely ends in ".torrent" is left alone.
func followUps(jobs []job, client *torrent.Client, bo bt.Options) []job {
var out []job
seen := map[metainfo.Hash]string{}
for _, j := range jobs {
h, ok := j.dl.(*httpdl.Download)
if !ok || j.dl.Stat().Status != download.Complete {
@@ -373,6 +392,17 @@ func followUps(jobs []job, client *torrent.Client, bo bt.Options) []job {
if _, err := bt.Files(path); err != nil {
continue // downloaded file is not a valid torrent
}
// Two fetched .torrent files that name the same torrent would share one
// torrent on the refcount-less client: the first to finish Drops it out
// from under the other, stranding it at 0%. build() dedupes pass-1 sources
// but cannot reach a not-yet-fetched HTTP .torrent, so dedupe here too.
if first, dup := markInfoHash(seen, path); dup {
out = append(out, job{source: path, dl: failedDownload{
name: path,
err: fmt.Errorf("%w: same torrent as %s", errDuplicate, first),
}})
continue
}
out = append(out, job{source: path, dl: bt.New(client, path, true, bo)})
}
return out
@@ -408,22 +438,23 @@ func allURIs(ts []target) []string {
// gatherURIs collects download targets from the command line, --torrent-file,
// and --input-file. Plain command-line http/https URIs are grouped into ONE
// mirrored download by default (every command-line URI names the same file);
// -Z/--force-sequential makes each its own download. Torrents and magnets
// are always one target each; --input-file groups TAB-separated URIs per line.
// -Z/--force-sequential makes each its own download. Torrents, magnets, and
// .torrent URLs (fetched over HTTP then followed) are always one target each,
// since distinct torrents are not mirrors of one another; --input-file groups
// TAB-separated URIs per line.
func gatherURIs(opts *cli.Options, cmdURIs []string) []target {
var ts []target
follow := opts.Bool("follow-torrent")
seq := opts.Bool("force-sequential")
var httpGroup []string
for _, u := range cmdURIs {
switch uriKind(u, follow) {
case kindHTTP, kindFollow:
if seq {
ts = append(ts, target{uris: []string{u}})
} else {
httpGroup = append(httpGroup, u)
}
default:
// Only plain HTTP URLs collapse into one mirror download (alternate sources
// for the same file); -Z opts out. A .torrent URL (kindFollow), like a
// torrent or magnet, is its own download — distinct torrents are never
// mirrors of one another.
if uriKind(u, follow) == kindHTTP && !seq {
httpGroup = append(httpGroup, u)
} else {
ts = append(ts, target{uris: []string{u}})
}
}