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

@@ -33,3 +33,33 @@ func DigestDocument(doc *SourceDocument) (string, error) {
sum := sha256.Sum256(encoded)
return "sha256:" + hex.EncodeToString(sum[:]), nil
}
// DigestChunk returns a deterministic digest of a chunk, including its source
// provenance, content, units, and metadata.
func DigestChunk(chunk Chunk) (string, error) {
payload := struct {
ID string `json:"id"`
SourceID string `json:"source_id"`
Index int `json:"index"`
Ref SourceRef `json:"ref"`
Content []byte `json:"content"`
MediaType string `json:"media_type"`
Units []SourceUnit `json:"units"`
Metadata map[string]any `json:"metadata,omitempty"`
}{
ID: chunk.ID,
SourceID: chunk.SourceID,
Index: chunk.Index,
Ref: chunk.Ref,
Content: chunk.Content,
MediaType: chunk.MediaType,
Units: chunk.Units,
Metadata: chunk.Metadata,
}
encoded, err := json.Marshal(payload)
if err != nil {
return "", fmt.Errorf("encode source chunk for digest: %w", err)
}
sum := sha256.Sum256(encoded)
return "sha256:" + hex.EncodeToString(sum[:]), nil
}