mirror of
https://github.com/hanzoai/s3.git
synced 2026-10-30 14:59:09 +00:00
zooqueen
dd74d3e6d6
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.
115 lines
2.9 KiB
Go
115 lines
2.9 KiB
Go
package weed_server
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"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/util"
|
|
"github.com/viant/ptrie"
|
|
)
|
|
|
|
func (fs *FilerServer) TraverseBfsMetadata(req *filer_pb.TraverseBfsMetadataRequest, stream filer_pb.SeaweedFiler_TraverseBfsMetadataServer) error {
|
|
|
|
glog.V(0).Infof("TraverseBfsMetadata %v", req)
|
|
|
|
excludedTrie := ptrie.New[bool]()
|
|
for _, excluded := range req.ExcludedPrefixes {
|
|
excludedTrie.Put([]byte(excluded), true)
|
|
}
|
|
|
|
ctx := stream.Context()
|
|
|
|
isExcluded := func(path util.FullPath) bool {
|
|
excluded := false
|
|
excludedTrie.MatchPrefix([]byte(path), func(key []byte, value bool) bool {
|
|
// Only exclude when the prefix ends on a path-component boundary,
|
|
// so /a/b does not also exclude a sibling like /a/bc.
|
|
if len(path) == len(key) || path[len(key)] == '/' {
|
|
excluded = true
|
|
return false
|
|
}
|
|
return true
|
|
})
|
|
return excluded
|
|
}
|
|
|
|
// Send each entry as it is visited and queue only directory paths to
|
|
// descend into. Queuing the entries themselves would hold the whole
|
|
// subtree in memory, including every file's chunk list, and can exhaust
|
|
// the filer on large trees (e.g. during a peer's first-time bootstrap).
|
|
sendEntry := func(entry *filer.Entry) error {
|
|
parent, _ := entry.FullPath.DirAndName()
|
|
if err := stream.Send(&filer_pb.TraverseBfsMetadataResponse{
|
|
Directory: parent,
|
|
Entry: entry.ToProtoEntry(),
|
|
}); err != nil {
|
|
return fmt.Errorf("send traverse bfs metadata response: %w", err)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
dirEntry, err := fs.filer.FindEntry(ctx, util.FullPath(req.Directory))
|
|
if err != nil {
|
|
return fmt.Errorf("find dir %s: %v", req.Directory, err)
|
|
}
|
|
if isExcluded(dirEntry.FullPath) {
|
|
return nil
|
|
}
|
|
if err := sendEntry(dirEntry); err != nil {
|
|
return err
|
|
}
|
|
|
|
queue := util.NewQueue[util.FullPath]()
|
|
if dirEntry.IsDirectory() {
|
|
queue.Enqueue(dirEntry.FullPath)
|
|
}
|
|
|
|
for queue.Len() > 0 {
|
|
dirPath := queue.Dequeue()
|
|
if err := fs.iterateDirectory(ctx, dirPath, func(entry *filer.Entry) error {
|
|
if isExcluded(entry.FullPath) {
|
|
return nil
|
|
}
|
|
if err := sendEntry(entry); err != nil {
|
|
return err
|
|
}
|
|
if entry.IsDirectory() {
|
|
queue.Enqueue(entry.FullPath)
|
|
}
|
|
return nil
|
|
}); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func (fs *FilerServer) iterateDirectory(ctx context.Context, dirPath util.FullPath, fn func(entry *filer.Entry) error) (err error) {
|
|
var lastFileName string
|
|
var listErr error
|
|
for {
|
|
var hasEntries bool
|
|
lastFileName, listErr = fs.filer.StreamListDirectoryEntries(ctx, dirPath, lastFileName, false, 1024, "", "", "", func(entry *filer.Entry) (bool, error) {
|
|
hasEntries = true
|
|
if fnErr := fn(entry); fnErr != nil {
|
|
err = fnErr
|
|
return false, err
|
|
}
|
|
return true, nil
|
|
})
|
|
if listErr != nil {
|
|
return listErr
|
|
}
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if !hasEntries {
|
|
return nil
|
|
}
|
|
}
|
|
}
|