Files
SaveAny-Bot/core/tasks/directlinks/execute.go
T
Krau c2f8ab3c01 refactor: quality overhaul (#234)
* fix: prevent queue deadlock after cancelling tasks

Get no longer recurses while holding the mutex.
Cancelled queued tasks leave the map, making their IDs reusable.
Closed empty queues return ErrQueueClosed.

* fix: init task queue lazily and close on shutdown

AddTask is safe before Run by initializing the queue once.
Close unblocks workers waiting in Get.

* fix: make resource fingerprints deterministic

Sort map keys before hashing so Resource.ID is stable.

* fix: harden per-item processing tracking in tasks

Use the resource fingerprint as the dedup key on insert and delete.
Check and set processing entries atomically instead of TOCTOU.
Count only successful downloads.

* fix: honor IgnoreErrors in batch tasks

Element failures no longer cancel sibling elements or stop later groups.

* fix: report streamed upload bytes in batch tasks

Stream downloads report their byte count as the upload total.

* fix: validate i18n key parity across locales

geni18n fails when a language file misses any key.
Align the syncpeers completion key between en and zh-Hans.
Translate three untranslated parse keys in zh-Hans.

* refactor: share progress throttling helpers

Move size-tiered and count-based throttling into progressutil.
Localize hardcoded Chinese progress strings.
Drop five duplicated implementations and dead local copies.

* refactor: share unique filename logic

Storage backends use fsutil.UniquePath instead of local loops.

* fix: sanitize local storage paths

Reject absolute paths and dot-dot escapes in Save.
Check close errors and wrap creation failures.

* fix: preserve webdav error causes

Wrap mkdir and write failures with %w and drop dead error values.

* fix: kill rclone subprocess on reader close

Prevent cat processes from hanging after the pipe is closed.

* fix: fail alist init instead of exiting

Replace log.Fatalf with wrapped errors so a bad alist cannot kill the bot.
Cancel token refresh with the init context and re-login on 401.

* fix: enforce telegram album limits and track saved paths

Use tglimit.MaxAlbumItems for album batching and video splitting.
Exists now reports previously saved paths instead of always false.

* fix: guard storage registry maps

Protect Storages and UserStorages with mutexes and expose read accessors.

* fix: harden JS parser plugin runtime

Validate semver instead of panicking and require canHandle.
Recover plugin worker panics and time out CanHandle calls.
Return a copy from the registry and sanitize install filenames.

* fix: guard kemono parser against nil fields

Skip sparse preview and attachment entries instead of panicking.

* refactor: remove commented-out dead code

Drop unused kemono legacy types and commented response structs.

* test: cover invalid plugin version rejection

* fix: show all queued tasks in /task list

Render up to ten tasks and append the truncation note once.

* fix: guard callback data parsing

Reject malformed callback payloads before indexing split parts.

* fix: isolate media groups per user

Key pending groups by chat, user and group id.

* fix: require permission for callback handlers

* fix: initialize userbot context once

Replace the racy lazy init with sync.OnceValue.

* fix: avoid leaking raw errors in /dir reply

* fix: notify users on invalid update version

* fix: fail fast when API listen fails

Bind synchronously and surface errors instead of logging them.

* fix: add timeouts and backoff to webhook delivery

* refactor: remove dead code from api and bot

Drop the empty ProgressTracker shim, unused token context key and a redundant SetBotCommands call.

* fix: load remote config without local lookup

Skip the local file search after reading a config URL and add a timeout.

* refactor: drop unused hook config

* docs: document parser plugin config

* ci: fix BuildTime formatting and align checkout

Actions format does not format dates; pass the raw timestamp.

* chore: ignore cache directory

* fix: make cache init idempotent

* fix: upload only downloaded batch elements

Failed elements keep partial cache files and never reach the backend.
Successfully downloaded siblings still upload when one element fails.

* fix: record telegram saved paths only after upload

Skip-large returns a sentinel so skipped files are not marked as saved.

* fix: deduplicate alist token refreshes

Guard token access with a mutex and merge concurrent logins.
Reuse a recent refresh to avoid login storms.

* test: cover concurrent alist 401 retry

Ten parallel uploads share a single re-login under -race.

* fix: count parsed resources in progress text

* fix: localize storage lookup errors in /dir

Use the shared i18n key and escape the dynamic error.

* fix: deduplicate concurrent storage initialization

singleflight merges first-time inits so side effects are not duplicated.

* fix: guard nil progress trackers in api-created tasks

Batch, telegraph and transfer tasks run without a Telegram tracker
when created through the API; their callbacks must not panic.

* fix: keep album order when filtering failed batch items

Download results are stored by original index so surviving
elements keep their source order.

* test: cover nil-tracker task execution

* fix: report partial failure in batch done message

IgnoreErrors runs with failed elements show success and failed
counts instead of claiming every file completed.

* fix: skip login refresh for token-only alist storage

401 responses surface the auth error instead of sending a
credential-less login; the refresh window never exceeds TokenExp.

* test: cover alist refresh semantics

Concurrent refresh uses username/password; token-only storage
never attempts a login on 401.

* fix: call tracker from notifyProgress instead of recursing

The helper called itself, overflowing the stack on any batch
task with a progress tracker.

* fix: propagate cancellation past IgnoreErrors

Cancelled tasks must not be reported as successful: only
ordinary element failures are ignored.

* test: cover notifyProgress tracker call

* test: cover cancellation with IgnoreErrors

* fix: refresh alist token after startup 401s

The init login no longer satisfies the dedup window, so an
early 401 triggers a real refresh; later 401s reuse it.
Clarify that streaming uploads cannot replay their body.

* test: exercise the alist 401 refresh path

Concurrent uploads now reject the init token, share one
refresh and retry with the new token; token-only stays inert.

* style: trim verbose comments

Drop process-style explanations; keep one-line behavior notes.

* style: gofmt test files

* fix: drop unbounded saved-path cache in telegram storage

Telegram cannot reliably query remote file existence, so the
cache answered a question it could not answer and grew without
bound. Exists returns false again, as before.

* style: format codes
2026-08-17 19:10:03 +08:00

182 lines
5.2 KiB
Go

package directlinks
import (
"context"
"errors"
"fmt"
"io"
"net/http"
"path/filepath"
"sync/atomic"
"github.com/charmbracelet/log"
"github.com/duke-git/lancet/v2/retry"
"github.com/krau/SaveAny-Bot/common/utils/fsutil"
"github.com/krau/SaveAny-Bot/common/utils/ioutil"
"github.com/krau/SaveAny-Bot/config"
"github.com/krau/SaveAny-Bot/pkg/enums/ctxkey"
"github.com/krau/SaveAny-Bot/pkg/taskevent"
"golang.org/x/sync/errgroup"
)
func (t *Task) Execute(ctx context.Context) error {
logger := log.FromContext(ctx)
logger.Infof("Starting directlinks task %s", t.ID)
if t.Progress != nil {
t.Progress.OnStart(ctx, t)
}
// head all links to get file info
eg, gctx := errgroup.WithContext(ctx)
eg.SetLimit(config.C().Workers)
fetchedTotalBytes := atomic.Int64{}
for _, file := range t.files {
eg.Go(func() error {
req, err := http.NewRequestWithContext(ctx, http.MethodHead, file.URL, nil)
if err != nil {
return fmt.Errorf("failed to create HEAD request for %s: %w", file.URL, err)
}
resp, err := t.client.Do(req)
if err != nil {
return fmt.Errorf("failed to HEAD %s: %w", file.URL, err)
}
defer resp.Body.Close()
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return fmt.Errorf("HEAD %s returned status %d", file.URL, resp.StatusCode)
}
fetchedTotalBytes.Add(resp.ContentLength)
file.Size = resp.ContentLength
if name := resp.Header.Get("Content-Disposition"); name != "" {
filename := parseFilename(name)
if filename != "" {
file.Name = filename
}
}
// extract filename from URL if Content-Disposition is empty or invalid
if file.Name == "" {
file.Name = parseFilenameFromURL(file.URL)
}
if file.Name == "" {
return fmt.Errorf("failed to determine filename for %s: Content-Disposition header is empty and URL does not contain a valid filename", file.URL)
}
return nil
})
}
err := eg.Wait()
if err != nil {
logger.Errorf("Error during HEAD requests: %v", err)
if t.Progress != nil {
t.Progress.OnDone(ctx, t, err)
}
return err
}
t.totalBytes = fetchedTotalBytes.Load()
// start downloading
eg, gctx = errgroup.WithContext(ctx)
eg.SetLimit(config.C().Workers)
for _, file := range t.files {
eg.Go(func() error {
t.processingMu.Lock()
if _, ok := t.processing[file.URL]; ok {
t.processingMu.Unlock()
return fmt.Errorf("file %s is already being processed", file.URL)
}
t.processing[file.URL] = file
t.processingMu.Unlock()
defer func() {
t.processingMu.Lock()
delete(t.processing, file.URL)
t.processingMu.Unlock()
}()
err := t.processLink(gctx, file)
if errors.Is(err, context.Canceled) {
logger.Debug("Link processing canceled")
return err
}
if err != nil {
logger.Errorf("Error processing link %s: %v", file.URL, err)
return fmt.Errorf("failed to process link %s: %w", file.URL, err)
}
t.downloaded.Add(1)
return nil
})
}
err = eg.Wait()
if err != nil {
logger.Errorf("Error during directlinks task execution: %v", err)
} else {
logger.Infof("Directlinks task %s completed successfully", t.ID)
}
if t.Progress != nil {
t.Progress.OnDone(ctx, t, err)
}
return err
}
func (t *Task) processLink(ctx context.Context, file *File) error {
logger := log.FromContext(ctx)
err := retry.Retry(func() error {
req, err := http.NewRequestWithContext(ctx, http.MethodGet, file.URL, nil)
if err != nil {
return fmt.Errorf("failed to create GET request for %s: %w", file.URL, err)
}
resp, err := t.client.Do(req)
if err != nil {
return fmt.Errorf("failed to GET %s: %w", file.URL, err)
}
defer resp.Body.Close()
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return fmt.Errorf("GET %s returned status %d", file.URL, resp.StatusCode)
}
ctx = context.WithValue(ctx, ctxkey.ContentLength, file.Size)
if t.stream {
return t.Storage.Save(ctx, resp.Body, filepath.Join(t.StorPath, file.Name))
}
cacheFile, err := fsutil.CreateFile(filepath.Join(config.C().Temp.BasePath,
fmt.Sprintf("direct_%s_%s", t.ID, file.Name)))
if err != nil {
return fmt.Errorf("failed to create temp file: %w", err)
}
defer func() {
if err := cacheFile.CloseAndRemove(); err != nil {
logger.Errorf("Failed to close and remove cache file: %v", err)
}
}()
wr := ioutil.NewProgressWriter(cacheFile, func(n int) {
downloaded := t.downloadedBytes.Add(int64(n))
if t.Progress != nil {
t.Progress.OnProgress(ctx, t)
}
taskevent.Emit(ctx, taskevent.Event{
TaskID: t.ID,
Phase: taskevent.PhaseProgress,
TotalBytes: t.totalBytes,
DownloadedBytes: downloaded,
})
})
copyResultCh := make(chan error, 1)
go func() {
_, err := io.Copy(wr, resp.Body)
copyResultCh <- err
}()
select {
case err := <-copyResultCh:
if err != nil {
return fmt.Errorf("failed to copy file %s to cache file: %w", file.URL, err)
}
case <-ctx.Done():
return ctx.Err()
}
_, err = cacheFile.Seek(0, 0)
if err != nil {
return fmt.Errorf("failed to seek cache file for resource %s: %w", file.URL, err)
}
return t.Storage.Save(ctx, cacheFile, filepath.Join(t.StorPath, file.Name))
}, retry.RetryTimes(uint(config.C().Retry)), retry.Context(ctx))
if ctx.Err() != nil {
return ctx.Err()
}
return err
}