Files
s3/weed/storage/needle/needle_read_tail.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

50 lines
1.9 KiB
Go

package needle
import (
"fmt"
"github.com/seaweedfs/seaweedfs/weed/stats"
. "github.com/seaweedfs/seaweedfs/weed/storage/types"
"github.com/seaweedfs/seaweedfs/weed/util"
)
func (n *Needle) readNeedleTail(needleBody []byte, version Version) error {
// for all versions, we need to read the checksum
if len(n.Data) > 0 {
expectedChecksum := CRC(util.BytesToUint32(needleBody[0:NeedleChecksumSize]))
dataChecksum := NewCRC(n.Data)
if expectedChecksum != dataChecksum && uint32(expectedChecksum) != dataChecksum.Value() {
// crc.Value() is the deprecated legacy transform used before commit 056c480eb
// (volume server <3.09). Accept either encoding so .dat files written by older
// versions still verify after an upgrade.
stats.VolumeServerHandlerCounter.WithLabelValues(stats.ErrorCRC).Inc()
return fmt.Errorf("invalid CRC for needle %v (got %08x, want %08x), data on disk corrupted: %w", n.Id, dataChecksum, expectedChecksum, ErrorCorrupted)
}
n.Checksum = dataChecksum
} else {
// when data is skipped from reading, just read the checksum
n.Checksum = CRC(util.BytesToUint32(needleBody[0:NeedleChecksumSize]))
}
if version == Version3 {
tsOffset := NeedleChecksumSize
n.AppendAtNs = util.BytesToUint64(needleBody[tsOffset : tsOffset+TimestampSize])
}
return nil
}
func PaddingLength(needleSize Size, version Version) Size {
if version == Version3 {
// this is same value as version2, but just listed here for clarity
return NeedlePaddingSize - ((NeedleHeaderSize + needleSize + NeedleChecksumSize + TimestampSize) % NeedlePaddingSize)
}
return NeedlePaddingSize - ((NeedleHeaderSize + needleSize + NeedleChecksumSize) % NeedlePaddingSize)
}
func NeedleBodyLength(needleSize Size, version Version) int64 {
if version == Version3 {
return int64(needleSize) + NeedleChecksumSize + TimestampSize + int64(PaddingLength(needleSize, version))
}
return int64(needleSize) + NeedleChecksumSize + int64(PaddingLength(needleSize, version))
}