Files
SaveAny-Bot/core/tasks/batchtfile/task.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

141 lines
3.5 KiB
Go

package batchtfile
import (
"context"
"fmt"
"path/filepath"
"sync"
"sync/atomic"
"github.com/krau/SaveAny-Bot/common/utils/tgutil"
"github.com/krau/SaveAny-Bot/config"
"github.com/krau/SaveAny-Bot/core"
"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
"github.com/krau/SaveAny-Bot/pkg/tfile"
"github.com/krau/SaveAny-Bot/storage"
"github.com/rs/xid"
)
var _ core.Executable = (*Task)(nil)
type TaskElement struct {
ID string
Storage storage.Storage
Path string
File tfile.TGFile
localPath string
stream bool
sourceGroupKey string
sourceCaption string
preserveCaption bool
}
type Task struct {
ID string
ctx context.Context
elems []TaskElement
Progress ProgressTracker
IgnoreErrors bool // if true, errors during processing will be ignored
downloaded atomic.Int64
totalSize int64
uploadTotalSize atomic.Int64
processing map[string]TaskElementInfo
processingMu sync.RWMutex
itemStates []itemProgressState
itemIndex map[string]int
itemMu sync.RWMutex
uploadOnce sync.Once
uploadMu sync.Mutex
uploaded map[string]int64
}
// Title implements core.Exectable.
func (t *Task) Title() string {
return fmt.Sprintf("[%s](%d files/%.2fMB)", t.Type(), len(t.elems), float64(t.totalSize)/(1024*1024))
}
func (t *Task) Type() tasktype.TaskType {
return tasktype.TaskTypeTgfiles
}
func NewTaskElement(
stor storage.Storage,
path string,
file tfile.TGFile,
) (*TaskElement, error) {
id := xid.New().String()
groupKey, caption, preserveCaption := sourceMetadata(file)
_, ok := stor.(storage.StorageCannotStream)
if !config.C().Stream || ok {
cachePath, err := filepath.Abs(filepath.Join(config.C().Temp.BasePath, fmt.Sprintf("%s_%s", id, file.Name())))
if err != nil {
return nil, fmt.Errorf("failed to get absolute path for cache: %w", err)
}
return &TaskElement{
ID: id,
Storage: stor,
Path: path,
File: file,
localPath: cachePath,
sourceGroupKey: groupKey,
sourceCaption: caption,
preserveCaption: preserveCaption,
}, nil
}
return &TaskElement{
ID: id,
Storage: stor,
Path: path,
File: file,
stream: true,
sourceGroupKey: groupKey,
sourceCaption: caption,
preserveCaption: preserveCaption,
}, nil
}
func sourceMetadata(file tfile.TGFile) (groupKey, caption string, preserveCaption bool) {
messageFile, ok := file.(tfile.TGFileMessage)
if !ok || messageFile.Message() == nil {
return "", "", false
}
msg := messageFile.Message()
groupID, grouped := msg.GetGroupedID()
if !grouped || groupID == 0 {
return "", "", false
}
chatID := tgutil.ChatIdFromPeer(msg.GetPeerID())
return fmt.Sprintf("%T:%d:%d", msg.GetPeerID(), chatID, groupID), msg.GetMessage(), true
}
func NewBatchTGFileTask(
id string,
ctx context.Context,
files []TaskElement,
progress ProgressTracker,
ignoreErrors bool,
) *Task {
itemStates, itemIndex := newItemProgressStates(files)
task := &Task{
ID: id,
ctx: ctx,
elems: files,
Progress: progress,
downloaded: atomic.Int64{},
totalSize: func() int64 {
var total int64
for _, elem := range files {
total += elem.File.Size()
}
return total
}(),
processing: make(map[string]TaskElementInfo),
itemStates: itemStates,
itemIndex: itemIndex,
uploaded: make(map[string]int64),
IgnoreErrors: ignoreErrors,
processingMu: sync.RWMutex{},
}
return task
}