kevinjqliu commented on code in PR #332:
URL: https://github.com/apache/iceberg-go/pull/332#discussion_r1997684054
##########
manifest.go:
##########
@@ -146,25 +158,66 @@ type fallbackManifestFileV1 struct {
AddedSnapshotID *int64 `avro:"added_snapshot_id"`
}
-func (f *fallbackManifestFileV1) toManifest() *manifestFileV1 {
- f.manifestFileV1.AddedSnapshotID = *f.AddedSnapshotID
+func (f *fallbackManifestFileV1) toFile() *manifestFile {
+ if f.AddedSnapshotID == nil {
+ f.manifestFileV1.AddedSnapshotID = -1
+ }
- return &f.manifestFileV1
+ return f.manifestFileV1.toFile()
}
type manifestFileV1 struct {
- Path string `avro:"manifest_path"`
- Len int64 `avro:"manifest_length"`
- SpecID int32 `avro:"partition_spec_id"`
- AddedSnapshotID int64 `avro:"added_snapshot_id"`
- AddedFilesCount *int32 `avro:"added_files_count"`
- ExistingFilesCount *int32 `avro:"existing_files_count"`
- DeletedFilesCount *int32 `avro:"deleted_files_count"`
- AddedRowsCount *int64 `avro:"added_rows_count"`
- ExistingRowsCount *int64 `avro:"existing_rows_count"`
- DeletedRowsCount *int64 `avro:"deleted_rows_count"`
- PartitionList *[]FieldSummary `avro:"partitions"`
- Key []byte `avro:"key_metadata"`
+ manifestFile
+ AddedFilesCount *int32 `avro:"added_files_count"`
+ ExistingFilesCount *int32 `avro:"existing_files_count"`
+ DeletedFilesCount *int32 `avro:"deleted_files_count"`
+ AddedRowsCount *int64 `avro:"added_rows_count"`
+ ExistingRowsCount *int64 `avro:"existing_rows_count"`
+ DeletedRowsCount *int64 `avro:"deleted_rows_count"`
+}
+
+func (m *manifestFileV1) toFile() *manifestFile {
+ m.manifestFile.version = 1
+ m.Content = ManifestContentData
+ m.SeqNumber, m.MinSeqNumber = 0, 0
Review Comment:
should this be 0 or -1?
0 should represent the INITIAL_SEQUENCE_NUMBER
-1 should represent unassigned
##########
manifest.go:
##########
@@ -593,42 +624,29 @@ func ReadManifestList(in io.Reader) ([]ManifestFile,
error) {
return nil, err
}
- var fallbackAddedSnapshot bool
- for _, f := range sc.(*avro.RecordSchema).Fields() {
- if f.Name() == "added_snapshot_id" {
- if f.Type().Type() == avro.Union {
- fallbackAddedSnapshot = true
- }
-
- break
- }
+ version, err := strconv.Atoi(string(dec.Metadata()["format-version"]))
+ if err != nil {
+ return nil, fmt.Errorf("invalid format-version: %w", err)
}
- out := make([]ManifestFile, 0)
- for dec.HasNext() {
- var file ManifestFile
- if string(dec.Metadata()["format-version"]) == "2" {
- file = &manifestFileV2{}
- } else {
- if fallbackAddedSnapshot {
- file = &fallbackManifestFileV1{}
- } else {
- file = &manifestFileV1{}
- }
- }
-
- if err := dec.Decode(file); err != nil {
- return nil, err
- }
+ if version == 1 {
+ for _, f := range sc.(*avro.RecordSchema).Fields() {
+ if f.Name() == "added_snapshot_id" {
+ if f.Type().Type() == avro.Union {
+ return
decodeManifestsWithFallback[*fallbackManifestFileV1](dec)
+ }
Review Comment:
is there a corresponding test for this part?
##########
manifest.go:
##########
@@ -146,25 +158,66 @@ type fallbackManifestFileV1 struct {
AddedSnapshotID *int64 `avro:"added_snapshot_id"`
}
-func (f *fallbackManifestFileV1) toManifest() *manifestFileV1 {
- f.manifestFileV1.AddedSnapshotID = *f.AddedSnapshotID
+func (f *fallbackManifestFileV1) toFile() *manifestFile {
+ if f.AddedSnapshotID == nil {
+ f.manifestFileV1.AddedSnapshotID = -1
+ }
- return &f.manifestFileV1
+ return f.manifestFileV1.toFile()
}
type manifestFileV1 struct {
- Path string `avro:"manifest_path"`
- Len int64 `avro:"manifest_length"`
- SpecID int32 `avro:"partition_spec_id"`
- AddedSnapshotID int64 `avro:"added_snapshot_id"`
- AddedFilesCount *int32 `avro:"added_files_count"`
- ExistingFilesCount *int32 `avro:"existing_files_count"`
- DeletedFilesCount *int32 `avro:"deleted_files_count"`
- AddedRowsCount *int64 `avro:"added_rows_count"`
- ExistingRowsCount *int64 `avro:"existing_rows_count"`
- DeletedRowsCount *int64 `avro:"deleted_rows_count"`
- PartitionList *[]FieldSummary `avro:"partitions"`
- Key []byte `avro:"key_metadata"`
+ manifestFile
+ AddedFilesCount *int32 `avro:"added_files_count"`
+ ExistingFilesCount *int32 `avro:"existing_files_count"`
+ DeletedFilesCount *int32 `avro:"deleted_files_count"`
+ AddedRowsCount *int64 `avro:"added_rows_count"`
+ ExistingRowsCount *int64 `avro:"existing_rows_count"`
+ DeletedRowsCount *int64 `avro:"deleted_rows_count"`
+}
+
+func (m *manifestFileV1) toFile() *manifestFile {
+ m.manifestFile.version = 1
+ m.Content = ManifestContentData
+ m.SeqNumber, m.MinSeqNumber = 0, 0
Review Comment:
In `NewManifestFile`, V1 table's seqNum is null
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
