Files
s3/weed/s3api/s3lifecycle/dailyrun/walk_buckets.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

77 lines
2.5 KiB
Go

package dailyrun
import (
"context"
"errors"
"fmt"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/bootstrap"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3lifecycle/engine"
)
// WalkBuckets runs bootstrap.Walk for each bucket using a per-bucket
// ListFunc wrapped to drop entries whose ShardID doesn't belong to
// shardID. Returns the first bucket error; remaining buckets log and
// continue so one bucket's filer error doesn't kill the whole walk.
//
// Composable shape: callers (the worker handler) supply a real
// filer-backed ListFunc and a real Dispatcher (WalkerDispatcher).
// Tests pass bootstrap.EntryCallback and a stub Dispatcher.
func WalkBuckets(ctx context.Context, view *engine.Snapshot, shardID int, buckets []string, list bootstrap.ListFunc, dispatch bootstrap.Dispatcher) error {
if view == nil {
return errors.New("WalkBuckets: nil view")
}
if list == nil {
return errors.New("WalkBuckets: nil list")
}
if dispatch == nil {
return errors.New("WalkBuckets: nil dispatch")
}
filtered := perShardListFunc(list, shardID)
var firstErr error
for _, b := range buckets {
if err := ctx.Err(); err != nil {
return err
}
if _, err := bootstrap.Walk(ctx, view, b, filtered, dispatch, bootstrap.WalkOptions{}); err != nil {
if firstErr == nil {
firstErr = fmt.Errorf("walk %s: %w", b, err)
} else {
glog.V(1).Infof("walker: additional bucket %s: %v", b, err)
}
}
}
return firstErr
}
// perShardListFunc wraps an inner ListFunc so only entries whose
// logical-key shard matches shardID reach the callback. The walker
// emits one entry per logical object — versioned siblings share the
// same logical key so they're either all in-shard or all out — and
// MPU init records carry the user's destination in DestKey, so the
// shard predicate must use DestKey there to match what the dispatcher
// will send.
func perShardListFunc(inner bootstrap.ListFunc, shardID int) bootstrap.ListFunc {
return func(ctx context.Context, bucket, start string, cb func(*bootstrap.Entry) error) error {
return inner(ctx, bucket, start, func(e *bootstrap.Entry) error {
if e == nil {
return nil
}
if entryShardID(bucket, e) != shardID {
return nil
}
return cb(e)
})
}
}
func entryShardID(bucket string, e *bootstrap.Entry) int {
key := e.Path
if e.IsMPUInit && e.DestKey != "" {
key = e.DestKey
}
return s3lifecycle.ShardID(bucket, key)
}