Files
s3/weed/util/compression.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

154 lines
3.0 KiB
Go

package util
import (
"bytes"
"fmt"
"strings"
"github.com/seaweedfs/seaweedfs/weed/glog"
// "github.com/klauspost/compress/zstd"
)
var (
UnsupportedCompression = fmt.Errorf("unsupported compression")
)
func MaybeGzipData(input []byte) []byte {
if IsGzippedContent(input) {
return input
}
gzipped, err := GzipData(input)
if err != nil {
return input
}
if len(gzipped)*10 > len(input)*9 {
return input
}
return gzipped
}
func MaybeDecompressData(input []byte) []byte {
uncompressed, err := DecompressData(input)
if err != nil {
if err != UnsupportedCompression {
glog.Errorf("decompressed data: %v", err)
}
return input
}
return uncompressed
}
func GzipData(input []byte) ([]byte, error) {
w := new(bytes.Buffer)
_, err := GzipStream(w, bytes.NewReader(input))
if err != nil {
return nil, err
}
return w.Bytes(), nil
}
func ungzipData(input []byte) ([]byte, error) {
w := new(bytes.Buffer)
_, err := GunzipStream(w, bytes.NewReader(input))
if err != nil {
return nil, err
}
return w.Bytes(), nil
}
func DecompressData(input []byte) ([]byte, error) {
if IsGzippedContent(input) {
return ungzipData(input)
}
/*
if IsZstdContent(input) {
return unzstdData(input)
}
*/
return input, UnsupportedCompression
}
func IsGzippedContent(data []byte) bool {
if len(data) < 2 {
return false
}
return data[0] == 31 && data[1] == 139
}
/*
var zstdEncoder, _ = zstd.NewWriter(nil)
func ZstdData(input []byte) ([]byte, error) {
return zstdEncoder.EncodeAll(input, nil), nil
}
var decoder, _ = zstd.NewReader(nil)
func unzstdData(input []byte) ([]byte, error) {
return decoder.DecodeAll(input, nil)
}
func IsZstdContent(data []byte) bool {
if len(data) < 4 {
return false
}
return data[3] == 0xFD && data[2] == 0x2F && data[1] == 0xB5 && data[0] == 0x28
}
*/
/*
* Default not to compressed since compression can be done on client side.
*/func IsCompressableFileType(ext, mtype string) (shouldBeCompressed, iAmSure bool) {
// text
if strings.HasPrefix(mtype, "text/") {
return true, true
}
// images
switch ext {
case ".svg", ".bmp", ".wav":
return true, true
}
if strings.HasPrefix(mtype, "image/") {
return false, true
}
// by file name extension
switch ext {
case ".zip", ".rar", ".gz", ".bz2", ".xz", ".zst", ".br":
return false, true
case ".pdf", ".txt", ".html", ".htm", ".css", ".js", ".json":
return true, true
case ".php", ".java", ".go", ".rb", ".c", ".cpp", ".h", ".hpp":
return true, true
case ".png", ".jpg", ".jpeg":
return false, true
}
// by mime type
if strings.HasPrefix(mtype, "application/") {
if strings.HasSuffix(mtype, "zstd") {
return false, true
}
if strings.HasSuffix(mtype, "xml") {
return true, true
}
if strings.HasSuffix(mtype, "script") {
return true, true
}
if strings.HasSuffix(mtype, "vnd.rar") {
return false, true
}
}
if strings.HasPrefix(mtype, "audio/") {
switch strings.TrimPrefix(mtype, "audio/") {
case "wave", "wav", "x-wav", "x-pn-wav":
return true, true
}
}
return false, false
}