feat: port blobindex package from go-libstoracha#14
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR ports a blobindex package into libforge, adding an in-memory sharded DAG index representation plus CAR-based archive/extract support using a CBOR/DAG-JSON datamodel (with generated codecs).
Changes:
- Add
blobindexAPIs (ShardedDagIndex,MapShardedDagIndex) and multihash-keyed map helpers. - Implement CAR decoding/encoding for sharded DAG indexes (
Extract,Archive) with deterministic output ordering. - Introduce the
blobindex/datamodelschema + generated CBOR/DAG-JSON codecs and add round-trip/determinism tests.
Reviewed changes
Copilot reviewed 7 out of 12 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| go.mod | Adds new direct/indirect dependencies needed for CAR + block/CID handling. |
| go.sum | Updates dependency lockfile for the newly introduced modules. |
| blobindex/types.go | Defines core blobindex interfaces/types (e.g., ShardedDagIndex, Range). |
| blobindex/multihashmap.go | Adds constructor helper for multihash-keyed maps. |
| blobindex/shardeddagindex.go | Implements CAR extract/archive + in-memory sharded DAG index implementation. |
| blobindex/shardeddagindex_test.go | Adds round-trip and determinism coverage for archive/extract behavior. |
| blobindex/datamodel/shardeddagindex.go | Defines the CBOR/DAG-JSON data model structs for the index format. |
| blobindex/datamodel/gen/main.go | Adds generator entrypoint for CBOR/DAG-JSON encoder/decoder generation. |
| blobindex/datamodel/cbor_gen.maps.go | Generated CBOR map encoders/decoders for the datamodel. |
| blobindex/datamodel/cbor_gen.tuples.go | Generated CBOR tuple encoders/decoders for the datamodel. |
| blobindex/datamodel/json_gen.maps.go | Generated DAG-JSON map encoders/decoders for the datamodel. |
| blobindex/datamodel/json_gen.tuples.go | Generated DAG-JSON tuple encoders/decoders for the datamodel. |
Files not reviewed (4)
- blobindex/datamodel/cbor_gen.maps.go: Language not supported
- blobindex/datamodel/cbor_gen.tuples.go: Language not supported
- blobindex/datamodel/json_gen.maps.go: Language not supported
- blobindex/datamodel/json_gen.tuples.go: Language not supported
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+179
to
+183
| b := buf.Bytes() | ||
| l, err := cid.V1Builder{Codec: cid.DagCBOR, MhType: mh.SHA2_256}.Sum(b) | ||
| if err != nil { | ||
| return nil, err | ||
| } |
Comment on lines
+30
to
+34
| // BlobIndexModel is the golang structure for encoding a shard of CIDs in a block | ||
| type BlobIndexModel struct { | ||
| Digest multihash.Multihash | ||
| Slices []BlobSliceModel | ||
| } |
| slices.SortFunc(list, func(a, b E) int { | ||
| decodedA := decodeds.Get(getDigest(a)) | ||
| decodedB := decodeds.Get(getDigest(b)) | ||
| return bytes.Compare(decodedA.Digest, decodedB.Digest) |
Comment on lines
+127
to
+132
| return fmt.Errorf(fmt.Sprintf("unknown format: %s", reason), args...) | ||
| } | ||
|
|
||
| // NewDecodeFailureError returns an error for a decode failure. | ||
| func NewDecodeFailureError(reason string, args ...any) error { | ||
| return fmt.Errorf(fmt.Sprintf("decode failure: %s", reason), args...) |
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
frrist
approved these changes
May 13, 2026
Comment on lines
+136
to
+224
| func Archive(index ShardedDagIndex) (io.Reader, error) { | ||
| // assemble blob index shards | ||
| blobIndexDatas, err := toList(index.Shards(), func(shardHash mh.Multihash, shard MultihashMap[Range]) (dm.BlobIndexModel, error) { | ||
| // assemble blob slices | ||
| blobSliceDatas, err := toList(shard, func(sliceHash mh.Multihash, byteRange Range) (dm.BlobSliceModel, error) { | ||
| return dm.BlobSliceModel{Digest: sliceHash, Range: byteRange}, nil | ||
| }) | ||
| if err != nil { | ||
| return dm.BlobIndexModel{}, err | ||
| } | ||
| // sort blob slices | ||
| if err := sortByDigest(blobSliceDatas, func(bsm dm.BlobSliceModel) mh.Multihash { | ||
| return bsm.Digest | ||
| }); err != nil { | ||
| return dm.BlobIndexModel{}, err | ||
| } | ||
| return dm.BlobIndexModel{ | ||
| Digest: shardHash, | ||
| Slices: blobSliceDatas, | ||
| }, nil | ||
| }) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| // sort blob index shards | ||
| if err := sortByDigest(blobIndexDatas, func(bim dm.BlobIndexModel) mh.Multihash { | ||
| return bim.Digest | ||
| }); err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| // initialize root sharded dag index | ||
| shardedDagIndex := dm.ShardedDagIndexModel_0_1{ | ||
| Shards: make([]cid.Cid, 0, len(blobIndexDatas)), | ||
| } | ||
| // encode blob index shards to blocks and add links to sharded dag index | ||
| blks := make([]blocks.Block, 0, len(blobIndexDatas)+1) | ||
| for _, shard := range blobIndexDatas { | ||
| var buf bytes.Buffer | ||
| err := shard.MarshalCBOR(&buf) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| b := buf.Bytes() | ||
| l, err := cid.V1Builder{Codec: cid.DagCBOR, MhType: mh.SHA2_256}.Sum(b) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| blk, err := blocks.NewBlockWithCid(b, l) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| blks = append(blks, blk) | ||
| shardedDagIndex.Shards = append(shardedDagIndex.Shards, l) | ||
| } | ||
|
|
||
| // encode the root block | ||
| model := dm.ShardedDagIndexModel{DagO_1: &shardedDagIndex} | ||
| var rootData bytes.Buffer | ||
| if err := model.MarshalCBOR(&rootData); err != nil { | ||
| return nil, err | ||
| } | ||
| root, err := cid.V1Builder{Codec: cid.DagCBOR, MhType: mh.SHA2_256}.Sum(rootData.Bytes()) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| rootBlock, err := blocks.NewBlockWithCid(rootData.Bytes(), root) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| reader, writer := io.Pipe() | ||
| go func() { | ||
| err := car.WriteHeader(&car.CarHeader{Roots: []cid.Cid{root}, Version: 1}, writer) | ||
| if err != nil { | ||
| writer.CloseWithError(fmt.Errorf("writing CAR header: %w", err)) | ||
| return | ||
| } | ||
| for _, block := range append(blks, rootBlock) { | ||
| err = util.LdWrite(writer, block.Cid().Bytes(), block.RawData()) | ||
| if err != nil { | ||
| writer.CloseWithError(fmt.Errorf("writing CAR blocks: %w", err)) | ||
| return | ||
| } | ||
| } | ||
| writer.Close() | ||
| }() | ||
| return reader, nil | ||
| } |
Member
There was a problem hiding this comment.
I'd really like to remove this go routine at the end, sorry this comment has to land here I realize you're just porting things. Could we instead flip the signature?:
func Archive(index ShardedDagIndex, w io.Writer) errorCallers that want streaming pass a pipe writer (and run the goroutine on their side), or if they want a buffer pass a bytes.Buffer. Ditto that for files, and http.ResponseWriters
Then we could wrap this like:
func ArchiveReader(index ShardedDagIndex) io.Reader {
r, w := io.Pipe()
go func() {
w.CloseWithError(Archive(index, w))
}()
return r
}to enable the current style if we need it.
Member
Author
There was a problem hiding this comment.
Yep, done. Also switched to new CAR library that doesn't bring in the whole of boxo and benchmarks seem to suggest it's faster than ipld/go-car and makes fewer allocations.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I'm not super happy that
go-carpulls in boxo, maybe I'll write a simple CAR reader/writer for Go at some point.