Move chunks into the canonical source model

This commit is contained in:
2026-07-17 05:32:11 +00:00
parent 40709e4ad8
commit 075888c97f
33 changed files with 548 additions and 325 deletions

View File

@@ -61,7 +61,7 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
}
step := opts.maxUnits - opts.overlapUnits
chunks := make([]contracts.SourceChunk, 0, (len(req.Source.Units)+step-1)/step)
chunks := make([]source.Chunk, 0, (len(req.Source.Units)+step-1)/step)
for start := 0; start < len(req.Source.Units); start += step {
end := start + opts.maxUnits
if end > len(req.Source.Units) {
@@ -72,15 +72,18 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
if err != nil {
return contracts.ChunkResult{}, err
}
chunks = append(chunks, contracts.SourceChunk{
ID: fmt.Sprintf("chunk-%06d", len(chunks)+1),
SourceID: req.Source.ID,
Index: len(chunks),
StartUnitID: units[0].ID,
EndUnitID: units[len(units)-1].ID,
Content: content,
MediaType: "application/json",
Units: units,
chunks = append(chunks, source.Chunk{
ID: fmt.Sprintf("chunk-%06d", len(chunks)+1),
SourceID: req.Source.ID,
Index: len(chunks),
Ref: source.SourceRef{
SourceID: req.Source.ID,
StartUnitID: units[0].Ref.StartUnitID,
EndUnitID: units[len(units)-1].Ref.EndUnitID,
},
Content: content,
MediaType: "application/json",
Units: units,
Metadata: map[string]any{
"start_unit_id": units[0].ID,
"end_unit_id": units[len(units)-1].ID,

View File

@@ -62,8 +62,8 @@ func TestChunkUsesDefaultsForSingleChunk(t *testing.T) {
if got := unitIDs(chunk.Units); !reflect.DeepEqual(got, []int{1, 2, 3}) {
t.Fatalf("unit IDs = %#v, want all units", got)
}
if chunk.StartUnitID != 1 || chunk.EndUnitID != 3 {
t.Fatalf("chunk boundaries = %d-%d, want 1-3", chunk.StartUnitID, chunk.EndUnitID)
if chunk.Ref != (source.SourceRef{SourceID: "source-1", StartUnitID: 1, EndUnitID: 3}) {
t.Fatalf("chunk ref = %#v, want source-1:1-3", chunk.Ref)
}
if chunk.MediaType != "application/json" || len(chunk.Content) == 0 {
t.Fatalf("chunk payload = media type %q length %d, want JSON content", chunk.MediaType, len(chunk.Content))
@@ -209,7 +209,7 @@ func zeroPad3(value int) string {
return fmt.Sprintf("%03d", value)
}
func chunkIDs(chunks []contracts.SourceChunk) []string {
func chunkIDs(chunks []source.Chunk) []string {
ids := make([]string, 0, len(chunks))
for _, chunk := range chunks {
ids = append(ids, chunk.ID)