Files
s3/weed/storage/needle/needle_read_page.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

97 lines
2.7 KiB
Go

package needle
import (
"fmt"
"io"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/storage/backend"
. "github.com/seaweedfs/seaweedfs/weed/storage/types"
"github.com/seaweedfs/seaweedfs/weed/util"
)
// ReadNeedleData uses a needle without n.Data to read the content
// volumeOffset: the offset within the volume
// needleOffset: the offset within the needle Data
func (n *Needle) ReadNeedleData(r backend.BackendStorageFile, volumeOffset int64, data []byte, needleOffset int64) (count int, err error) {
sizeToRead := min(int64(len(data)), int64(n.DataSize)-needleOffset)
if sizeToRead <= 0 {
return 0, io.EOF
}
startOffset := volumeOffset + NeedleHeaderSize + DataSizeSize + needleOffset
count, err = r.ReadAt(data[:sizeToRead], startOffset)
if err == io.EOF && int64(count) == sizeToRead {
err = nil
}
if err != nil {
fileSize, _, _ := r.GetStat()
glog.Errorf("%s read %d %d size %d at offset %d fileSize %d: %v", r.Name(), n.Id, needleOffset, sizeToRead, volumeOffset, fileSize, err)
}
return
}
// ReadNeedleMeta fills all metadata except the n.Data
func (n *Needle) ReadNeedleMeta(r backend.BackendStorageFile, offset int64, size Size, version Version) (err error) {
defer func() {
if r := recover(); r != nil {
err = fmt.Errorf("panic occurred: %+v", r)
}
}()
bytes := make([]byte, NeedleHeaderSize+DataSizeSize)
count, err := r.ReadAt(bytes, offset)
if err == io.EOF && count == NeedleHeaderSize+DataSizeSize {
err = nil
}
if count != NeedleHeaderSize+DataSizeSize || err != nil {
return err
}
n.ParseNeedleHeader(bytes)
if n.Size != size {
if OffsetSize == 4 && offset < int64(MaxPossibleVolumeSize) {
return ErrorSizeMismatch
}
return fmt.Errorf("size mismatch for entry at offset %d: found id %x size %d, expected size %d", offset, n.Id, n.Size, size)
}
n.DataSize = util.BytesToUint32(bytes[NeedleHeaderSize : NeedleHeaderSize+DataSizeSize])
startOffset := offset + NeedleHeaderSize
if size.IsValid() {
startOffset = offset + NeedleHeaderSize + DataSizeSize + int64(n.DataSize)
}
dataSize := GetActualSize(size, version)
stopOffset := offset + dataSize
metaSize := stopOffset - startOffset
if metaSize < 0 || metaSize > 128*1024 {
return fmt.Errorf("invalid needle meta size %d: DataSize=%d, size=%d, offset=%d", metaSize, n.DataSize, size, offset)
}
metaSlice := make([]byte, int(metaSize))
count, err = r.ReadAt(metaSlice, startOffset)
if err != nil && int64(count) == metaSize {
err = nil
}
if err != nil {
return err
}
var index int
if size.IsValid() {
index, err = n.readNeedleDataVersion2NonData(metaSlice)
}
err = n.readNeedleTail(metaSlice[index:], version)
return err
}
func min(x, y int64) int64 {
if x < y {
return x
}
return y
}