Add core source model validation

internal/core/source/validation.go

@@ -0,0 +1,95 @@
+package source
+
+import (
+	"fmt"
+	"strings"
+)
+
+func ValidateDocument(doc *SourceDocument) error {
+	if doc == nil {
+		return fmt.Errorf("source document must not be nil")
+	}
+	if isBlank(doc.ID) {
+		return fmt.Errorf("source document id must not be empty")
+	}
+	if isBlank(doc.Kind) {
+		return fmt.Errorf("source document kind must not be empty")
+	}
+	if isBlank(doc.Format) {
+		return fmt.Errorf("source document format must not be empty")
+	}
+	if isBlank(doc.Digest) {
+		return fmt.Errorf("source document digest must not be empty")
+	}
+	if len(doc.Units) == 0 {
+		return fmt.Errorf("source document units must not be empty")
+	}
+
+	seenUnitIDs := make(map[string]struct{}, len(doc.Units))
+	for i, unit := range doc.Units {
+		unitID := strings.TrimSpace(unit.ID)
+		if unitID == "" {
+			return fmt.Errorf("source unit[%d].id must not be empty", i)
+		}
+		if isBlank(unit.Kind) {
+			return fmt.Errorf("source unit[%d].kind must not be empty", i)
+		}
+		if isBlank(unit.Text) {
+			return fmt.Errorf("source unit[%d].text must not be empty", i)
+		}
+		if _, ok := seenUnitIDs[unitID]; ok {
+			return fmt.Errorf("source unit id %q is duplicated", unitID)
+		}
+		seenUnitIDs[unitID] = struct{}{}
+	}
+
+	return nil
+}
+
+func ValidateRef(doc *SourceDocument, ref SourceRef) error {
+	if doc == nil {
+		return fmt.Errorf("source document must not be nil")
+	}
+	if isBlank(ref.SourceID) {
+		return fmt.Errorf("source ref source_id must not be empty")
+	}
+	if isBlank(ref.StartUnitID) {
+		return fmt.Errorf("source ref start_unit_id must not be empty")
+	}
+	if isBlank(ref.EndUnitID) {
+		return fmt.Errorf("source ref end_unit_id must not be empty")
+	}
+	if ref.SourceID != doc.ID {
+		return fmt.Errorf("source ref source_id %q does not match document id %q", ref.SourceID, doc.ID)
+	}
+
+	startIndex, ok := UnitIndex(doc, ref.StartUnitID)
+	if !ok {
+		return fmt.Errorf("source ref start_unit_id %q was not found", ref.StartUnitID)
+	}
+	endIndex, ok := UnitIndex(doc, ref.EndUnitID)
+	if !ok {
+		return fmt.Errorf("source ref end_unit_id %q was not found", ref.EndUnitID)
+	}
+	if startIndex > endIndex {
+		return fmt.Errorf("source ref start_unit_id %q appears after end_unit_id %q", ref.StartUnitID, ref.EndUnitID)
+	}
+
+	return nil
+}
+
+func UnitIndex(doc *SourceDocument, unitID string) (int, bool) {
+	if doc == nil {
+		return 0, false
+	}
+	for i, unit := range doc.Units {
+		if unit.ID == unitID {
+			return i, true
+		}
+	}
+	return 0, false
+}
+
+func isBlank(value string) bool {
+	return strings.TrimSpace(value) == ""
+}