Files
s3/weed/shell/command_fs_meta_load.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

177 lines
4.1 KiB
Go

package shell
import (
"compress/gzip"
"context"
"flag"
"fmt"
"io"
"os"
"strings"
"sync"
"time"
"google.golang.org/protobuf/proto"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/util"
)
func init() {
Commands = append(Commands, &commandFsMetaLoad{})
}
type commandFsMetaLoad struct {
dirPrefix *string
}
func (c *commandFsMetaLoad) Name() string {
return "fs.meta.load"
}
func (c *commandFsMetaLoad) Help() string {
return `load saved filer meta data to restore the directory and file structure
fs.meta.load <filer_host>-<port>-<time>.meta
fs.meta.load -v=false <filer_host>-<port>-<time>.meta // skip printing out the verbose output
fs.meta.load -concurrency=1 <filer_host>-<port>-<time>.meta // number of parallel meta load to filer
fs.meta.load -dirPrefix=/buckets/important <filer_host>.meta // load any dirs with prefix "important"
`
}
func (c *commandFsMetaLoad) HasTag(CommandTag) bool {
return false
}
func (c *commandFsMetaLoad) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
if len(args) == 0 {
fmt.Fprintf(writer, "missing a metadata file\n")
return nil
}
fileName := util.ResolvePath(args[len(args)-1])
metaLoadCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
c.dirPrefix = metaLoadCommand.String("dirPrefix", "", "load entries only with directories matching prefix")
concurrency := metaLoadCommand.Int("concurrency", 1, "number of parallel meta load to filer")
verbose := metaLoadCommand.Bool("v", true, "verbose mode")
if err = metaLoadCommand.Parse(args[0 : len(args)-1]); err != nil {
return nil
}
var dst io.Reader
f, err := os.OpenFile(fileName, os.O_RDONLY, 0644)
if err != nil {
return fmt.Errorf("failed to open file %s: %v", fileName, err)
}
defer f.Close()
dst = f
if strings.HasSuffix(fileName, ".gz") || strings.HasSuffix(fileName, ".gzip") {
var gr *gzip.Reader
gr, err = gzip.NewReader(dst)
if err != nil {
return err
}
defer func() {
err1 := gr.Close()
if err == nil {
err = err1
}
}()
dst = gr
}
var dirCount, fileCount uint64
lastLogTime := time.Now()
err = commandEnv.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
sizeBuf := make([]byte, 4)
waitChan := make(chan struct{}, *concurrency)
defer close(waitChan)
var wg sync.WaitGroup
for {
if _, err := io.ReadFull(dst, sizeBuf); err != nil {
if err == io.EOF {
return nil
}
return err
}
size := util.BytesToUint32(sizeBuf)
data := make([]byte, int(size))
if _, err := io.ReadFull(dst, data); err != nil {
return err
}
fullEntry := &filer_pb.FullEntry{}
if err = proto.Unmarshal(data, fullEntry); err != nil {
return err
}
// check collection name pattern
entryFullName := string(util.FullPath(fullEntry.Dir).Child(fullEntry.Entry.Name))
if *c.dirPrefix != "" {
if !strings.HasPrefix(fullEntry.Dir, *c.dirPrefix) {
if *verbose {
fmt.Fprintf(writer, "not match dir prefix %s\n", entryFullName)
}
continue
}
}
if *verbose || lastLogTime.Add(time.Second).Before(time.Now()) {
if !*verbose {
lastLogTime = time.Now()
}
fmt.Fprintf(writer, "load %s\n", entryFullName)
}
fullEntry.Entry.Name = strings.ReplaceAll(fullEntry.Entry.Name, "/", "x")
if fullEntry.Entry.IsDirectory {
wg.Wait()
if errEntry := filer_pb.CreateEntry(context.Background(), client, &filer_pb.CreateEntryRequest{
Directory: fullEntry.Dir,
Entry: fullEntry.Entry,
}); errEntry != nil {
return errEntry
}
dirCount++
} else {
wg.Add(1)
waitChan <- struct{}{}
go func(entry *filer_pb.FullEntry) {
if errEntry := filer_pb.CreateEntry(context.Background(), client, &filer_pb.CreateEntryRequest{
Directory: entry.Dir,
Entry: entry.Entry,
}); errEntry != nil {
err = errEntry
}
defer wg.Done()
<-waitChan
}(fullEntry)
if err != nil {
return err
}
fileCount++
}
}
})
if err == nil {
fmt.Fprintf(writer, "\ntotal %d directories, %d files", dirCount, fileCount)
fmt.Fprintf(writer, "\n%s is loaded.\n", fileName)
}
return err
}