Fix D&D extraction issues and retire the completed audit

internal/core/source/validation.go

@@ -5,6 +5,46 @@ import (
 	"strings"
 )
 
+// DocumentIndex is an immutable snapshot of a source document's identity and
+// unit positions for repeated source-reference operations.
+type DocumentIndex struct {
+	documentID  string
+	positions   map[int]int
+	hasDocument bool
+}
+
+// NewDocumentIndex snapshots doc without retaining or mutating it.
+func NewDocumentIndex(doc *SourceDocument) DocumentIndex {
+	if doc == nil {
+		return DocumentIndex{}
+	}
+	positions := make(map[int]int, len(doc.Units))
+	for position, unit := range doc.Units {
+		if _, exists := positions[unit.ID]; !exists {
+			positions[unit.ID] = position
+		}
+	}
+	return DocumentIndex{
+		documentID:  doc.ID,
+		positions:   positions,
+		hasDocument: true,
+	}
+}
+
+// Position returns the indexed document position for unitID.
+func (i DocumentIndex) Position(unitID int) (int, bool) {
+	position, ok := i.positions[unitID]
+	return position, ok
+}
+
+// ValidateRef validates ref against the indexed document snapshot.
+func (i DocumentIndex) ValidateRef(ref SourceRef) error {
+	if !i.hasDocument {
+		return fmt.Errorf("source document must not be nil")
+	}
+	return validateRef(i.documentID, i.Position, ref)
+}
+
 func ValidateDocument(doc *SourceDocument) error {
 	if doc == nil {
 		return fmt.Errorf("source document must not be nil")
@@ -60,6 +100,12 @@ func ValidateRef(doc *SourceDocument, ref SourceRef) error {
 	if doc == nil {
 		return fmt.Errorf("source document must not be nil")
 	}
+	return validateRef(doc.ID, func(unitID int) (int, bool) {
+		return UnitIndex(doc, unitID)
+	}, ref)
+}
+
+func validateRef(documentID string, position func(int) (int, bool), ref SourceRef) error {
 	if isBlank(ref.SourceID) {
 		return fmt.Errorf("source ref source_id must not be empty")
 	}
@@ -72,15 +118,15 @@ func ValidateRef(doc *SourceDocument, ref SourceRef) error {
 	if ref.EndUnitID <= 0 {
 		return fmt.Errorf("source ref end_unit_id must be positive")
 	}
-	if ref.SourceID != doc.ID {
-		return fmt.Errorf("source ref source_id %q does not match document id %q", ref.SourceID, doc.ID)
+	if ref.SourceID != documentID {
+		return fmt.Errorf("source ref source_id %q does not match document id %q", ref.SourceID, documentID)
 	}
 
-	startIndex, ok := UnitIndex(doc, ref.StartUnitID)
+	startIndex, ok := position(ref.StartUnitID)
 	if !ok {
 		return fmt.Errorf("source ref start_unit_id %d was not found", ref.StartUnitID)
 	}
-	endIndex, ok := UnitIndex(doc, ref.EndUnitID)
+	endIndex, ok := position(ref.EndUnitID)
 	if !ok {
 		return fmt.Errorf("source ref end_unit_id %d was not found", ref.EndUnitID)
 	}