Files
SaveAny-Bot/core/tasks/batchtfile/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

469 lines
14 KiB
Go

package batchtfile
import (
"context"
"errors"
"fmt"
"io"
"os"
"path"
"sync"
"time"
"github.com/charmbracelet/log"
"github.com/duke-git/lancet/v2/retry"
"github.com/krau/SaveAny-Bot/common/tdler"
"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/storagetypes"
"github.com/krau/SaveAny-Bot/pkg/taskevent"
"github.com/krau/SaveAny-Bot/storage"
"golang.org/x/sync/errgroup"
)
type executionGroup struct {
elems []*TaskElement
batchSaver storage.StorageBatchSaver
}
func (g executionGroup) usesBatchSaver() bool {
return g.batchSaver != nil
}
func (t *Task) Execute(ctx context.Context) error {
logger := log.FromContext(ctx).WithPrefix(fmt.Sprintf("batch_file[%s]", t.ID))
logger.Info("Starting batch file task")
if t.Progress != nil {
t.Progress.OnStart(ctx, t)
}
groups := t.executionGroups()
var err error
for i := 0; i < len(groups); {
if groups[i].usesBatchSaver() {
err = t.processBatch(ctx, groups[i])
i++
} else {
end := i + 1
for end < len(groups) && !groups[end].usesBatchSaver() {
end++
}
elems := make([]*TaskElement, 0, end-i)
for _, group := range groups[i:end] {
elems = append(elems, group.elems...)
}
err = t.processElements(ctx, elems)
i = end
}
if err != nil {
if !t.IgnoreErrors || errors.Is(err, context.Canceled) {
break
}
logger.Warnf("Group processing failed (ignored): %v", err)
err = nil
}
}
if err != nil {
logger.Errorf("Error during batch file processing: %v", err)
} else {
logger.Info("Batch file task completed successfully")
}
t.finishItems(err)
if t.Progress != nil {
t.Progress.OnDone(ctx, t, err)
}
return err
}
// notifyProgress reports a progress update to the optional tracker.
func (t *Task) notifyProgress(ctx context.Context) {
if t.Progress != nil {
t.Progress.OnProgress(ctx, t)
}
}
func (t *Task) executionGroups() []executionGroup {
groups := make([]executionGroup, 0, len(t.elems))
for i := 0; i < len(t.elems); {
elem := &t.elems[i]
batchSaver, batchCapable := elem.Storage.(storage.StorageBatchSaver)
if !batchCapable || elem.sourceGroupKey == "" {
groups = append(groups, executionGroup{elems: []*TaskElement{elem}})
i++
continue
}
end := i + 1
for end < len(t.elems) {
next := &t.elems[end]
if next.Storage != elem.Storage || next.sourceGroupKey != elem.sourceGroupKey {
break
}
end++
}
elems := make([]*TaskElement, 0, end-i)
for j := i; j < end; j++ {
elems = append(elems, &t.elems[j])
}
groups = append(groups, executionGroup{elems: elems, batchSaver: batchSaver})
i = end
}
return groups
}
func (t *Task) processElements(ctx context.Context, elems []*TaskElement) error {
eg, gctx := errgroup.WithContext(ctx)
eg.SetLimit(config.C().Workers)
for _, elem := range elems {
eg.Go(func() error {
if err := t.markProcessing(ctx, elem); err != nil {
return err
}
defer t.unmarkProcessing(elem.ID)
err := t.processElement(gctx, *elem)
if err != nil && t.IgnoreErrors && !errors.Is(err, context.Canceled) {
// Per-item failure: keep siblings running.
log.FromContext(ctx).Warnf("Element %s failed (ignored): %v", elem.ID, err)
return nil
}
return err
})
}
return eg.Wait()
}
func (t *Task) processBatch(ctx context.Context, group executionGroup) error {
defer func() {
for _, elem := range group.elems {
if err := os.Remove(elem.localPath); err != nil && !os.IsNotExist(err) {
log.FromContext(ctx).Warnf("Failed to cleanup batch cache file %s: %v", elem.localPath, err)
}
}
}()
type downloadResult struct {
elem *TaskElement
err error
}
results := make([]downloadResult, len(group.elems))
var resultsMu sync.Mutex
eg, gctx := errgroup.WithContext(ctx)
eg.SetLimit(config.C().Workers)
for i, elem := range group.elems {
eg.Go(func() error {
if err := t.markProcessing(ctx, elem); err != nil {
return err
}
defer t.unmarkProcessing(elem.ID)
err := t.downloadElement(gctx, elem)
// Store by original index.
resultsMu.Lock()
results[i] = downloadResult{elem: elem, err: err}
resultsMu.Unlock()
if err != nil && t.IgnoreErrors && !errors.Is(err, context.Canceled) {
// Per-item failure: keep siblings running.
log.FromContext(ctx).Warnf("Element %s failed (ignored): %v", elem.ID, err)
return nil
}
return err
})
}
if err := eg.Wait(); err != nil {
return err
}
// Upload only successfully downloaded elements.
successElems := make([]*TaskElement, 0, len(group.elems))
for _, r := range results {
if r.err == nil {
successElems = append(successElems, r.elem)
}
}
if len(successElems) == 0 {
return fmt.Errorf("all elements failed to download")
}
items := make([]storagetypes.BatchItem, 0, len(successElems))
openFiles := make([]*os.File, 0, len(successElems))
defer func() {
for _, file := range openFiles {
if err := file.Close(); err != nil {
log.FromContext(ctx).Warnf("Failed to close batch cache file %s: %v", file.Name(), err)
}
}
}()
for _, elem := range successElems {
file, err := os.Open(elem.localPath)
if err != nil {
t.markItemFailed(elem.ID, FailureStageCache, err)
return fmt.Errorf("failed to open cache file: %w", err)
}
stat, err := file.Stat()
if err != nil {
file.Close()
t.markItemFailed(elem.ID, FailureStageCache, err)
return fmt.Errorf("failed to get cache file stat: %w", err)
}
openFiles = append(openFiles, file)
items = append(items, storagetypes.BatchItem{
Reader: file,
StoragePath: elem.Path,
Size: stat.Size(),
SourceGroupKey: elem.sourceGroupKey,
Caption: elem.sourceCaption,
PreserveCaption: elem.preserveCaption,
})
}
for index, item := range items {
t.recordDownloadComplete(successElems[index].ID, item.Size)
}
return t.saveBatchItems(ctx, successElems, items)
}
func (t *Task) saveBatchItems(ctx context.Context, successElems []*TaskElement, items []storagetypes.BatchItem) error {
t.startUpload(ctx)
if progressSaver, ok := successElems[0].Storage.(storage.StorageBatchProgressSaver); ok {
err := progressSaver.SaveBatchWithProgress(ctx, items, func(index int, uploaded, total int64) {
if index < 0 || index >= len(successElems) {
return
}
t.uploadCallback(ctx, successElems[index].ID)(uploaded, total)
})
if err != nil {
for _, elem := range successElems {
t.markItemFailed(elem.ID, FailureStageBatchUpload, err)
}
t.notifyStateChange(ctx)
return fmt.Errorf("failed to save batch: %w", err)
}
for index, elem := range successElems {
t.uploadCallback(ctx, elem.ID)(items[index].Size, items[index].Size)
t.markItemCompleted(elem.ID)
}
t.notifyStateChange(ctx)
return nil
}
for i := range items {
items[i].Reader = ioutil.NewProgressReader(
items[i].Reader,
items[i].Size,
t.uploadCallback(ctx, successElems[i].ID),
)
}
if err := successElems[0].Storage.(storage.StorageBatchSaver).SaveBatch(ctx, items); err != nil {
for _, elem := range successElems {
t.markItemFailed(elem.ID, FailureStageBatchUpload, err)
}
t.notifyStateChange(ctx)
return fmt.Errorf("failed to save batch: %w", err)
}
for index, elem := range successElems {
t.uploadCallback(ctx, elem.ID)(items[index].Size, items[index].Size)
t.markItemCompleted(elem.ID)
}
t.notifyStateChange(ctx)
return nil
}
func (t *Task) markProcessing(ctx context.Context, elem *TaskElement) error {
t.processingMu.Lock()
if t.processing[elem.ID] != nil {
t.processingMu.Unlock()
return fmt.Errorf("element with ID %s is already being processed", elem.ID)
}
t.processing[elem.ID] = elem
t.processingMu.Unlock()
t.markItemActive(elem.ID, elem.stream, time.Now())
t.notifyProgress(ctx)
return nil
}
func (t *Task) unmarkProcessing(id string) {
t.processingMu.Lock()
delete(t.processing, id)
t.processingMu.Unlock()
}
func (t *Task) downloadElement(ctx context.Context, elem *TaskElement) error {
logger := log.FromContext(ctx).WithPrefix(fmt.Sprintf("file[%s]", elem.File.Name()))
logger.Info("Starting file download")
localFile, err := fsutil.CreateFile(elem.localPath)
if err != nil {
t.markItemFailed(elem.ID, FailureStageCache, err)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to create local file: %w", err)
}
wrAt := ioutil.NewProgressWriterAt(localFile, func(n int) {
t.recordItemDownload(elem.ID, int64(n), time.Now())
downloaded := t.downloaded.Add(int64(n))
t.notifyProgress(ctx)
taskevent.Emit(ctx, taskevent.Event{
TaskID: t.ID,
Phase: taskevent.PhaseProgress,
TotalBytes: t.totalSize,
DownloadedBytes: downloaded,
})
})
_, downloadErr := tdler.NewDownloader(elem.File).Parallel(ctx, wrAt)
closeErr := localFile.Close()
if downloadErr != nil {
t.markItemFailed(elem.ID, FailureStageDownload, downloadErr)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to download file: %w", downloadErr)
}
if closeErr != nil {
t.markItemFailed(elem.ID, FailureStageCache, closeErr)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to close cache file: %w", closeErr)
}
logger.Info("File downloaded successfully")
if path.Ext(elem.FileName()) == "" {
if ext := fsutil.DetectFileExt(elem.localPath); ext != "" {
elem.Path += ext
}
}
t.markItemDownloaded(elem.ID)
t.notifyProgress(ctx)
return nil
}
func (t *Task) processElement(ctx context.Context, elem TaskElement) error {
logger := log.FromContext(ctx).WithPrefix(fmt.Sprintf("file[%s]", elem.File.Name()))
if elem.stream {
pr, pw := io.Pipe()
defer pr.Close()
errg, uploadCtx := errgroup.WithContext(ctx)
errg.Go(func() error {
err := elem.Storage.Save(uploadCtx, pr, elem.Path)
if err != nil {
t.markItemFailed(elem.ID, FailureStageUpload, err)
t.notifyStateChange(ctx)
}
return err
})
wr := ioutil.NewProgressWriter(pw, func(n int) {
t.recordItemDownload(elem.ID, int64(n), time.Now())
downloaded := t.downloaded.Add(int64(n))
t.notifyProgress(ctx)
taskevent.Emit(ctx, taskevent.Event{
TaskID: t.ID,
Phase: taskevent.PhaseProgress,
TotalBytes: t.totalSize,
DownloadedBytes: downloaded,
})
})
errg.Go(func() error {
defer pw.Close()
logger.Info("Starting file download in stream mode")
_, err := tdler.NewDownloader(elem.File).Stream(uploadCtx, wr)
if err != nil {
logger.Errorf("Failed to download file: %v", err)
t.markItemFailed(elem.ID, FailureStageDownload, err)
t.notifyStateChange(ctx)
pw.CloseWithError(err)
}
return err
})
if err := errg.Wait(); err != nil {
return fmt.Errorf("failed to download file in stream mode: %w", err)
}
// Streamed bytes are the uploaded bytes.
var streamedBytes int64
t.updateItem(elem.ID, func(item *itemProgressState) {
streamedBytes = item.downloaded
})
t.recordDownloadComplete(elem.ID, streamedBytes)
t.markItemCompleted(elem.ID)
t.notifyStateChange(ctx)
logger.Info("File downloaded successfully in stream mode")
return nil
}
logger.Info("Starting file download")
localFile, err := fsutil.CreateFile(elem.localPath)
if err != nil {
t.markItemFailed(elem.ID, FailureStageCache, err)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to create local file: %w", err)
}
defer func() {
if err := localFile.CloseAndRemove(); err != nil {
logger.Errorf("Failed to close local file: %v", err)
}
}()
wrAt := ioutil.NewProgressWriterAt(localFile, func(n int) {
t.recordItemDownload(elem.ID, int64(n), time.Now())
downloaded := t.downloaded.Add(int64(n))
t.notifyProgress(ctx)
taskevent.Emit(ctx, taskevent.Event{
TaskID: t.ID,
Phase: taskevent.PhaseProgress,
TotalBytes: t.totalSize,
DownloadedBytes: downloaded,
})
})
_, err = tdler.NewDownloader(elem.File).Parallel(ctx, wrAt)
if err != nil {
t.markItemFailed(elem.ID, FailureStageDownload, err)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to download file: %w", err)
}
logger.Info("File downloaded successfully")
if path.Ext(elem.FileName()) == "" {
ext := fsutil.DetectFileExt(elem.localPath)
if ext != "" {
elem.Path = elem.Path + ext
}
}
var fileStat os.FileInfo
fileStat, err = os.Stat(elem.localPath)
if err != nil {
t.markItemFailed(elem.ID, FailureStageCache, err)
t.notifyStateChange(ctx)
return fmt.Errorf("failed to get file stat: %w", err)
}
t.recordDownloadComplete(elem.ID, fileStat.Size())
vctx := context.WithValue(ctx, ctxkey.ContentLength, fileStat.Size())
t.startUpload(vctx)
onProgress := t.uploadCallback(vctx, elem.ID)
attempt := 0
retryLimit := int(config.C().Retry)
lastFailureStage := FailureStageUpload
err = retry.Retry(func() error {
attempt++
var file *os.File
file, err = os.Open(elem.localPath)
if err != nil {
lastFailureStage = FailureStageCache
t.markItemRetry(elem.ID, lastFailureStage, attempt, retryLimit, err)
t.notifyStateChange(vctx)
return fmt.Errorf("failed to open cache file: %w", err)
}
defer file.Close()
onProgress(0, fileStat.Size())
if progressSaver, ok := elem.Storage.(storage.StorageProgressSaver); ok {
err = progressSaver.SaveWithProgress(vctx, file, elem.Path, onProgress)
} else {
err = elem.Storage.Save(vctx, ioutil.NewProgressReader(file, fileStat.Size(), onProgress), elem.Path)
}
if err != nil {
logger.Errorf("Failed to save file: %s, retrying...", err)
lastFailureStage = t.itemFailureStage(elem.ID)
t.markItemRetry(elem.ID, lastFailureStage, attempt, retryLimit, err)
t.notifyStateChange(vctx)
return err
}
return nil
}, retry.Context(vctx), retry.RetryTimes(uint(config.C().Retry)))
if err == nil {
onProgress(fileStat.Size(), fileStat.Size())
t.markItemCompleted(elem.ID)
t.notifyStateChange(vctx)
} else {
t.markItemFailed(elem.ID, lastFailureStage, err)
t.notifyStateChange(vctx)
}
return err
}