Implement integer source units and chunk payloads
This commit is contained in:
@@ -68,11 +68,19 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
|
||||
end = len(req.Source.Units)
|
||||
}
|
||||
units := cloneUnits(req.Source.Units[start:end])
|
||||
content, err := chunkContent(units)
|
||||
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),
|
||||
Units: units,
|
||||
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,
|
||||
Metadata: map[string]any{
|
||||
"start_unit_id": units[0].ID,
|
||||
"end_unit_id": units[len(units)-1].ID,
|
||||
@@ -87,6 +95,18 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
|
||||
return contracts.ChunkResult{Chunks: chunks}, nil
|
||||
}
|
||||
|
||||
func chunkContent(units []source.SourceUnit) ([]byte, error) {
|
||||
content, err := json.Marshal(struct {
|
||||
Units []source.SourceUnit `json:"units"`
|
||||
}{
|
||||
Units: units,
|
||||
})
|
||||
if err != nil {
|
||||
return nil, chunkerErrorf("encode chunk content: %w", err)
|
||||
}
|
||||
return content, nil
|
||||
}
|
||||
|
||||
func ModuleSpec() pipeline.ModuleSpec {
|
||||
return pipeline.ModuleSpec{
|
||||
Key: Key,
|
||||
|
||||
Reference in New Issue
Block a user