Files
s3/weed/filer/abstract_sql/abstract_sql_store.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

419 lines
12 KiB
Go

package abstract_sql
import (
"context"
"database/sql"
"fmt"
"strings"
"sync"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/s3api/s3bucket"
"github.com/seaweedfs/seaweedfs/weed/util"
)
type SqlGenerator interface {
GetSqlInsert(tableName string) string
GetSqlUpdate(tableName string) string
GetSqlFind(tableName string) string
GetSqlDelete(tableName string) string
GetSqlDeleteFolderChildren(tableName string) string
GetSqlListExclusive(tableName string) string
GetSqlListInclusive(tableName string) string
GetSqlCreateTable(tableName string) string
GetSqlDropTable(tableName string) string
}
type AbstractSqlStore struct {
SqlGenerator
DB *sql.DB
SupportBucketTable bool
dbs map[string]bool
dbsLock sync.Mutex
RetryableErrorCallback func(err error) bool
}
var _ filer.BucketAware = (*AbstractSqlStore)(nil)
func (store *AbstractSqlStore) CanDropWholeBucket() bool {
return store.SupportBucketTable
}
func (store *AbstractSqlStore) OnBucketCreation(bucket string) {
store.dbsLock.Lock()
defer store.dbsLock.Unlock()
store.CreateTable(context.Background(), bucket)
if store.dbs == nil {
return
}
store.dbs[bucket] = true
}
func (store *AbstractSqlStore) OnBucketDeletion(bucket string) {
store.dbsLock.Lock()
defer store.dbsLock.Unlock()
store.deleteTable(context.Background(), bucket)
if store.dbs == nil {
return
}
delete(store.dbs, bucket)
}
const (
DEFAULT_TABLE = "filemeta"
)
type TxOrDB interface {
ExecContext(ctx context.Context, query string, args ...interface{}) (sql.Result, error)
QueryRowContext(ctx context.Context, query string, args ...interface{}) *sql.Row
QueryContext(ctx context.Context, query string, args ...interface{}) (*sql.Rows, error)
}
func (store *AbstractSqlStore) BeginTransaction(ctx context.Context) (context.Context, error) {
tx, err := store.DB.BeginTx(ctx, &sql.TxOptions{
Isolation: sql.LevelReadCommitted,
ReadOnly: false,
})
if err != nil {
return ctx, err
}
return context.WithValue(ctx, "tx", tx), nil
}
func (store *AbstractSqlStore) CommitTransaction(ctx context.Context) error {
if tx, ok := ctx.Value("tx").(*sql.Tx); ok {
return tx.Commit()
}
return nil
}
func (store *AbstractSqlStore) RollbackTransaction(ctx context.Context) error {
if tx, ok := ctx.Value("tx").(*sql.Tx); ok {
return tx.Rollback()
}
return nil
}
func (store *AbstractSqlStore) getTxOrDB(ctx context.Context, fullpath util.FullPath, isForChildren bool) (txOrDB TxOrDB, bucket string, shortPath util.FullPath, err error) {
shortPath = fullpath
bucket = DEFAULT_TABLE
if tx, ok := ctx.Value("tx").(*sql.Tx); ok {
txOrDB = tx
} else {
txOrDB = store.DB
}
if !store.SupportBucketTable {
return
}
if !strings.HasPrefix(string(fullpath), "/buckets/") {
return
}
// detect bucket
bucketAndObjectKey := string(fullpath)[len("/buckets/"):]
t := strings.Index(bucketAndObjectKey, "/")
if t < 0 && !isForChildren {
return
}
bucket = bucketAndObjectKey
shortPath = "/"
if t > 0 {
bucket = bucketAndObjectKey[:t]
shortPath = util.FullPath(bucketAndObjectKey[t:])
}
if isValidBucket(bucket) {
store.dbsLock.Lock()
defer store.dbsLock.Unlock()
if store.dbs == nil {
store.dbs = make(map[string]bool)
}
if _, found := store.dbs[bucket]; !found {
if err = store.CreateTable(ctx, bucket); err == nil {
store.dbs[bucket] = true
}
}
} else {
err = fmt.Errorf("invalid bucket name %s", bucket)
}
return
}
func (store *AbstractSqlStore) InsertEntry(ctx context.Context, entry *filer.Entry) (err error) {
// define the work to be done
var doInsert func() error
doInsert = func() error {
db, bucket, shortPath, err := store.getTxOrDB(ctx, entry.FullPath, false)
if err != nil {
return fmt.Errorf("findDB %s : %w", entry.FullPath, err)
}
dir, name := shortPath.DirAndName()
meta, err := entry.EncodeAttributesAndChunks()
if err != nil {
return fmt.Errorf("encode %s: %w", entry.FullPath, err)
}
if len(entry.GetChunks()) > filer.CountEntryChunksForGzip {
meta = util.MaybeGzipData(meta)
}
sqlInsert := "insert"
res, err := db.ExecContext(ctx, store.GetSqlInsert(bucket), util.HashStringToLong(dir), name, dir, meta)
if err != nil && strings.Contains(strings.ToLower(err.Error()), "duplicate entry") {
// now the insert failed possibly due to duplication constraints
sqlInsert = "falls back to update"
glog.V(1).InfofCtx(ctx, "insert %s %s: %v", entry.FullPath, sqlInsert, err)
res, err = db.ExecContext(ctx, store.GetSqlUpdate(bucket), meta, util.HashStringToLong(dir), name, dir)
}
if err != nil {
return fmt.Errorf("%s %s: %w", sqlInsert, entry.FullPath, err)
}
_, err = res.RowsAffected()
if err != nil {
return fmt.Errorf("%s %s but no rows affected: %w", sqlInsert, entry.FullPath, err)
}
return nil
}
if store.RetryableErrorCallback != nil {
if ctx.Value("tx") != nil {
return doInsert()
}
return util.RetryUntil("InsertEntry", doInsert, store.RetryableErrorCallback)
}
return doInsert()
}
func (store *AbstractSqlStore) UpdateEntry(ctx context.Context, entry *filer.Entry) (err error) {
var doUpdate func() error
doUpdate = func() error {
db, bucket, shortPath, err := store.getTxOrDB(ctx, entry.FullPath, false)
if err != nil {
return fmt.Errorf("findDB %s : %w", entry.FullPath, err)
}
dir, name := shortPath.DirAndName()
meta, err := entry.EncodeAttributesAndChunks()
if err != nil {
return fmt.Errorf("encode %s: %w", entry.FullPath, err)
}
res, err := db.ExecContext(ctx, store.GetSqlUpdate(bucket), meta, util.HashStringToLong(dir), name, dir)
if err != nil {
return fmt.Errorf("update %s: %w", entry.FullPath, err)
}
_, err = res.RowsAffected()
if err != nil {
return fmt.Errorf("update %s but no rows affected: %w", entry.FullPath, err)
}
return nil
}
if store.RetryableErrorCallback != nil {
if ctx.Value("tx") != nil {
return doUpdate()
}
return util.RetryUntil("UpdateEntry", doUpdate, store.RetryableErrorCallback)
}
return doUpdate()
}
func (store *AbstractSqlStore) FindEntry(ctx context.Context, fullpath util.FullPath) (*filer.Entry, error) {
db, bucket, shortPath, err := store.getTxOrDB(ctx, fullpath, false)
if err != nil {
return nil, fmt.Errorf("findDB %s : %v", fullpath, err)
}
dir, name := shortPath.DirAndName()
row := db.QueryRowContext(ctx, store.GetSqlFind(bucket), util.HashStringToLong(dir), name, dir)
var data []byte
if err := row.Scan(&data); err != nil {
if err == sql.ErrNoRows {
return nil, filer_pb.ErrNotFound
}
return nil, fmt.Errorf("find %s: %v", fullpath, err)
}
entry := &filer.Entry{
FullPath: fullpath,
}
if err := entry.DecodeAttributesAndChunks(util.MaybeDecompressData(data)); err != nil {
return entry, fmt.Errorf("decode %s : %v", entry.FullPath, err)
}
return entry, nil
}
func (store *AbstractSqlStore) DeleteEntry(ctx context.Context, fullpath util.FullPath) error {
var doDelete func() error
doDelete = func() error {
db, bucket, shortPath, err := store.getTxOrDB(ctx, fullpath, false)
if err != nil {
return fmt.Errorf("findDB %s : %w", fullpath, err)
}
dir, name := shortPath.DirAndName()
res, err := db.ExecContext(ctx, store.GetSqlDelete(bucket), util.HashStringToLong(dir), name, dir)
if err != nil {
return fmt.Errorf("delete %s: %w", fullpath, err)
}
_, err = res.RowsAffected()
if err != nil {
return fmt.Errorf("delete %s but no rows affected: %w", fullpath, err)
}
return nil
}
if store.RetryableErrorCallback != nil {
if ctx.Value("tx") != nil {
return doDelete()
}
return util.RetryUntil("DeleteEntry", doDelete, store.RetryableErrorCallback)
}
return doDelete()
}
func (store *AbstractSqlStore) DeleteFolderChildren(ctx context.Context, fullpath util.FullPath) error {
var doDeleteFolderChildren func() error
doDeleteFolderChildren = func() error {
db, bucket, shortPath, err := store.getTxOrDB(ctx, fullpath, true)
if err != nil {
return fmt.Errorf("findDB %s : %w", fullpath, err)
}
if isValidBucket(bucket) && shortPath == "/" {
if err = store.deleteTable(ctx, bucket); err == nil {
store.dbsLock.Lock()
delete(store.dbs, bucket)
store.dbsLock.Unlock()
return nil
} else {
return err
}
}
glog.V(4).InfofCtx(ctx, "delete %s SQL %s %d", string(shortPath), store.GetSqlDeleteFolderChildren(bucket), util.HashStringToLong(string(shortPath)))
res, err := db.ExecContext(ctx, store.GetSqlDeleteFolderChildren(bucket), util.HashStringToLong(string(shortPath)), string(shortPath))
if err != nil {
return fmt.Errorf("deleteFolderChildren %s: %w", fullpath, err)
}
_, err = res.RowsAffected()
if err != nil {
return fmt.Errorf("deleteFolderChildren %s but no rows affected: %w", fullpath, err)
}
return nil
}
if store.RetryableErrorCallback != nil {
if ctx.Value("tx") != nil {
return doDeleteFolderChildren()
}
return util.RetryUntil("DeleteFolderChildren", doDeleteFolderChildren, store.RetryableErrorCallback)
}
return doDeleteFolderChildren()
}
func (store *AbstractSqlStore) ListDirectoryPrefixedEntries(ctx context.Context, dirPath util.FullPath, startFileName string, includeStartFile bool, limit int64, prefix string, eachEntryFunc filer.ListEachEntryFunc) (lastFileName string, err error) {
db, bucket, shortPath, err := store.getTxOrDB(ctx, dirPath, true)
if err != nil {
return lastFileName, fmt.Errorf("findDB %s : %v", dirPath, err)
}
sqlText := store.GetSqlListExclusive(bucket)
if includeStartFile {
sqlText = store.GetSqlListInclusive(bucket)
}
rows, err := db.QueryContext(ctx, sqlText, util.HashStringToLong(string(shortPath)), startFileName, string(shortPath), prefix+"%", limit+1)
if err != nil {
return lastFileName, fmt.Errorf("list %s : %v", dirPath, err)
}
defer rows.Close()
for rows.Next() {
var name string
var data []byte
if err = rows.Scan(&name, &data); err != nil {
glog.V(0).InfofCtx(ctx, "scan %s : %v", dirPath, err)
return lastFileName, fmt.Errorf("scan %s: %v", dirPath, err)
}
lastFileName = name
entry := &filer.Entry{
FullPath: util.NewFullPath(string(dirPath), name),
}
if err = entry.DecodeAttributesAndChunks(util.MaybeDecompressData(data)); err != nil {
glog.V(0).InfofCtx(ctx, "scan decode %s : %v", entry.FullPath, err)
return lastFileName, fmt.Errorf("scan decode %s : %v", entry.FullPath, err)
}
resEachEntryFunc, resEachEntryFuncErr := eachEntryFunc(entry)
if resEachEntryFuncErr != nil {
err = fmt.Errorf("failed to process eachEntryFunc: %w", resEachEntryFuncErr)
break
}
if !resEachEntryFunc {
break
}
}
return lastFileName, err
}
func (store *AbstractSqlStore) ListDirectoryEntries(ctx context.Context, dirPath util.FullPath, startFileName string, includeStartFile bool, limit int64, eachEntryFunc filer.ListEachEntryFunc) (lastFileName string, err error) {
return store.ListDirectoryPrefixedEntries(ctx, dirPath, startFileName, includeStartFile, limit, "", eachEntryFunc)
}
func (store *AbstractSqlStore) Shutdown() {
store.DB.Close()
}
func isValidBucket(bucket string) bool {
if s3bucket.VerifyS3BucketName(bucket) != nil {
return false
}
return bucket != DEFAULT_TABLE && bucket != ""
}
func (store *AbstractSqlStore) CreateTable(ctx context.Context, bucket string) error {
if !store.SupportBucketTable {
return nil
}
_, err := store.DB.ExecContext(ctx, store.SqlGenerator.GetSqlCreateTable(bucket))
return err
}
func (store *AbstractSqlStore) deleteTable(ctx context.Context, bucket string) error {
if !store.SupportBucketTable {
return nil
}
_, err := store.DB.ExecContext(ctx, store.SqlGenerator.GetSqlDropTable(bucket))
return err
}