Add canonical source unit provenance

internal/modules/seriatim/input/transcript/adapter.go

@@ -65,18 +65,21 @@ func (a *Adapter) Parse(ctx context.Context, req contracts.ParseRequest) (*sourc
 		ID:       documentID(req.SourceID, parsed.Metadata, rawDigest),
 		Kind:     DocumentKind,
 		Format:   Format,
-		Digest:   rawDigest,
 		Metadata: copyMetadata(parsed.Metadata),
 	}
 
 	seenSegmentIDs := make(map[int]struct{}, len(parsed.Segments))
 	for i, segment := range parsed.Segments {
-		unit, err := sourceUnit(segment, i, seenSegmentIDs)
+		unit, err := sourceUnit(doc.ID, segment, i, seenSegmentIDs)
 		if err != nil {
 			return nil, err
 		}
 		doc.Units = append(doc.Units, unit)
 	}
+	doc.Digest, err = source.DigestDocument(doc)
+	if err != nil {
+		return nil, inputErrorf("digest source document: %w", err)
+	}
 
 	if err := source.ValidateDocument(doc); err != nil {
 		return nil, inputErrorf("validate source document: %w", err)
@@ -98,7 +101,7 @@ func Register(registry *pipeline.InputAdapterRegistry) error {
 	})
 }
 
-func sourceUnit(segment segment, index int, seen map[int]struct{}) (source.SourceUnit, error) {
+func sourceUnit(sourceID string, segment segment, index int, seen map[int]struct{}) (source.SourceUnit, error) {
 	segmentLabel := fmt.Sprintf("segment[%d]", index)
 	if segment.ID <= 0 {
 		return source.SourceUnit{}, inputErrorf("%s id must be positive", segmentLabel)
@@ -133,6 +136,11 @@ func sourceUnit(segment segment, index int, seen map[int]struct{}) (source.Sourc
 		ID:   segment.ID,
 		Kind: UnitKind,
 		Text: segment.Text,
+		Ref: source.SourceRef{
+			SourceID:    sourceID,
+			StartUnitID: segment.ID,
+			EndUnitID:   segment.ID,
+		},
 		Metadata: map[string]any{
 			MetadataSpeaker: segment.Speaker,
 			MetadataStart:   segment.Start,

internal/modules/seriatim/input/transcript/adapter_test.go

@@ -30,8 +30,8 @@ func TestParseValidMinimalTranscript(t *testing.T) {
 	if doc.Format != Format {
 		t.Fatalf("doc.Format = %q, want %q", doc.Format, Format)
 	}
-	if doc.Digest != testDigest(raw) {
-		t.Fatalf("doc.Digest = %q, want %q", doc.Digest, testDigest(raw))
+	if doc.Digest == testDigest(raw) || !strings.HasPrefix(doc.Digest, "sha256:") {
+		t.Fatalf("doc.Digest = %q, want canonical source digest distinct from raw input digest", doc.Digest)
 	}
 	if got := doc.Metadata["title"]; got != "Synthetic session transcript" {
 		t.Fatalf("doc.Metadata[title] = %#v, want Synthetic session transcript", got)
@@ -39,6 +39,12 @@ func TestParseValidMinimalTranscript(t *testing.T) {
 	if len(doc.Units) != 2 {
 		t.Fatalf("len(doc.Units) = %d, want 2", len(doc.Units))
 	}
+	for i, unit := range doc.Units {
+		want := source.SourceRef{SourceID: doc.ID, StartUnitID: unit.ID, EndUnitID: unit.ID}
+		if unit.Ref != want {
+			t.Fatalf("doc.Units[%d].Ref = %#v, want %#v", i, unit.Ref, want)
+		}
+	}
 
 	first := doc.Units[0]
 	if first.ID != 1 {
@@ -89,6 +95,12 @@ func TestParseAcceptsNumericSegmentIDs(t *testing.T) {
 	if doc.Units[0].ID != 1 || doc.Units[1].ID != 2 {
 		t.Fatalf("unit IDs = %#v, want numeric IDs", []int{doc.Units[0].ID, doc.Units[1].ID})
 	}
+	for i, unit := range doc.Units {
+		want := source.SourceRef{SourceID: doc.ID, StartUnitID: unit.ID, EndUnitID: unit.ID}
+		if unit.Ref != want {
+			t.Fatalf("doc.Units[%d].Ref = %#v, want %#v", i, unit.Ref, want)
+		}
+	}
 	ref := source.SourceRef{
 		SourceID:    doc.ID,
 		StartUnitID: 1,