Files
s3/weed/replication/sink/localsink/local_sink.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.

- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
  "Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
  SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
  (replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
  keep their upstream import paths with zero churn. Internal identifiers and
  import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
  help/usage/flag strings, shell autocomplete program name, and the product name
  in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
  (e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
  `cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
  updated to ignore the `s3` build output.
2026-06-18 23:41:25 -07:00

166 lines
4.5 KiB
Go

package localsink
import (
"context"
"fmt"
"os"
"path/filepath"
"strings"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/replication/repl_util"
"github.com/seaweedfs/seaweedfs/weed/replication/sink"
"github.com/seaweedfs/seaweedfs/weed/replication/source"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3_constants"
"github.com/seaweedfs/seaweedfs/weed/util"
)
type LocalSink struct {
Dir string
filerSource *source.FilerSource
isIncremental bool
}
func init() {
sink.Sinks = append(sink.Sinks, &LocalSink{})
}
func (localsink *LocalSink) SetSourceFiler(s *source.FilerSource) {
localsink.filerSource = s
}
func (localsink *LocalSink) GetName() string {
return "local"
}
func (localsink *LocalSink) isMultiPartEntry(key string) bool {
return strings.HasSuffix(key, ".part") && strings.Contains(key, "/"+s3_constants.MultipartUploadsFolder+"/")
}
func (localsink *LocalSink) initialize(dir string, isIncremental bool) error {
localsink.Dir = dir
localsink.isIncremental = isIncremental
return nil
}
func (localsink *LocalSink) Initialize(configuration util.Configuration, prefix string) error {
dir := configuration.GetString(prefix + "directory")
isIncremental := configuration.GetBool(prefix + "is_incremental")
glog.V(4).Infof("sink.local.directory: %v", dir)
return localsink.initialize(dir, isIncremental)
}
func (localsink *LocalSink) GetSinkToDirectory() string {
return localsink.Dir
}
func (localsink *LocalSink) IsIncremental() bool {
return localsink.isIncremental
}
func (localsink *LocalSink) DeleteEntry(key string, isDirectory, deleteIncludeChunks bool, signatures []int32) error {
key = sanitizeFsKey(key)
if localsink.isMultiPartEntry(key) {
return nil
}
glog.V(4).Infof("Delete Entry key: %s", key)
if err := os.Remove(key); err != nil {
glog.V(0).Infof("remove entry key %s: %s", key, err)
}
return nil
}
func (localsink *LocalSink) CreateEntry(key string, entry *filer_pb.Entry, signatures []int32) error {
key = sanitizeFsKey(key)
if entry.IsDirectory || localsink.isMultiPartEntry(key) {
return nil
}
glog.V(4).Infof("Create Entry key: %s", key)
totalSize := filer.FileSize(entry)
chunkViews := filer.ViewFromChunks(context.Background(), localsink.filerSource.LookupFileId, entry.GetChunks(), 0, int64(totalSize))
dir := filepath.Dir(key)
if _, err := os.Stat(dir); os.IsNotExist(err) {
glog.V(4).Infof("Create Directory key: %s", dir)
if err = os.MkdirAll(dir, 0755); err != nil {
return err
}
}
if entry.IsDirectory {
return os.Mkdir(key, os.FileMode(entry.Attributes.FileMode))
}
mode := os.FileMode(entry.Attributes.FileMode)
shortFileName := util.ToShortFileName(key)
// Write to a temp file in the same directory, then atomically rename
// on success. This prevents leaving a truncated/empty file if
// decryption or chunk copy fails.
tmpFile, err := os.CreateTemp(dir, ".seaweedfs-tmp-*")
if err != nil {
return err
}
tmpName := tmpFile.Name()
defer func() {
// Clean up temp file on any error (rename removes it on success)
if tmpFile != nil {
tmpFile.Close()
os.Remove(tmpName)
}
}()
if err := tmpFile.Chmod(mode); err != nil {
return err
}
writeFunc := func(data []byte) error {
_, writeErr := tmpFile.Write(data)
return writeErr
}
if len(entry.Content) > 0 {
content, err := repl_util.MaybeDecryptContent(entry.Content, entry)
if err != nil {
return fmt.Errorf("decrypt inline SSE content: %w", err)
}
if err := writeFunc(content); err != nil {
return err
}
} else {
if err := repl_util.CopyFromChunkViews(chunkViews, localsink.filerSource, writeFunc, entry); err != nil {
return err
}
}
// Close before rename so the data is flushed
if err := tmpFile.Close(); err != nil {
return err
}
tmpFile = nil // prevent deferred cleanup
// Atomic rename into final destination
if err := os.Rename(tmpName, shortFileName); err != nil {
os.Remove(tmpName)
return err
}
return nil
}
func (localsink *LocalSink) UpdateEntry(key string, oldEntry *filer_pb.Entry, newParentPath string, newEntry *filer_pb.Entry, deleteIncludeChunks bool, signatures []int32) (foundExistingEntry bool, err error) {
key = sanitizeFsKey(key)
if localsink.isMultiPartEntry(key) {
return true, nil
}
glog.V(4).Infof("Update Entry key: %s", key)
// do delete and create
foundExistingEntry = util.FileExists(key)
err = localsink.CreateEntry(key, newEntry, signatures)
return
}