Fix D&D extraction issues and retire the completed audit

internal/core/source/source_test.go

@@ -249,6 +249,9 @@ func TestValidateRefValid(t *testing.T) {
 	if err := ValidateRef(doc, ref); err != nil {
 		t.Fatalf("ValidateRef() error = %v, want nil", err)
 	}
+	if err := NewDocumentIndex(doc).ValidateRef(ref); err != nil {
+		t.Fatalf("DocumentIndex.ValidateRef() error = %v, want nil", err)
+	}
 }
 
 func TestValidateRefRejectsMalformedReferences(t *testing.T) {
@@ -301,13 +304,56 @@ func TestValidateRefRejectsMalformedReferences(t *testing.T) {
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			err := ValidateRef(validDocument(), tt.ref)
-
-			requireErrorFragments(t, err, tt.fragments...)
+			doc := validDocument()
+			validators := []struct {
+				name     string
+				validate func(SourceRef) error
+			}{
+				{name: "document", validate: func(ref SourceRef) error { return ValidateRef(doc, ref) }},
+				{name: "index", validate: NewDocumentIndex(doc).ValidateRef},
+			}
+			for _, validator := range validators {
+				t.Run(validator.name, func(t *testing.T) {
+					requireErrorFragments(t, validator.validate(tt.ref), tt.fragments...)
+				})
+			}
 		})
 	}
 }
 
+func TestDocumentIndexSnapshotsIdentityAndUnitPositions(t *testing.T) {
+	doc := &SourceDocument{
+		ID: "source-1",
+		Units: []SourceUnit{
+			{ID: 30},
+			{ID: 10},
+			{ID: 30},
+		},
+	}
+	index := NewDocumentIndex(doc)
+	doc.ID = "changed"
+	doc.Units[0].ID = 99
+
+	if position, ok := index.Position(30); !ok || position != 0 {
+		t.Fatalf("Position(30) = %d, %t, want 0, true", position, ok)
+	}
+	if position, ok := index.Position(10); !ok || position != 1 {
+		t.Fatalf("Position(10) = %d, %t, want 1, true", position, ok)
+	}
+	ref := SourceRef{SourceID: "source-1", StartUnitID: 30, EndUnitID: 10}
+	if err := index.ValidateRef(ref); err != nil {
+		t.Fatalf("ValidateRef() error = %v, want nil", err)
+	}
+}
+
+func TestZeroDocumentIndexIsSafe(t *testing.T) {
+	var index DocumentIndex
+	if position, ok := index.Position(1); ok || position != 0 {
+		t.Fatalf("Position(1) = %d, %t, want 0, false", position, ok)
+	}
+	requireErrorFragments(t, index.ValidateRef(SourceRef{}), "source document must not be nil")
+}
+
 func TestUnitIndex(t *testing.T) {
 	doc := validDocument()
 

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)
 	}