Improve D&D registry normalization efficiency

internal/modules/dnd/locations/identity/identity.go

@@ -5,7 +5,6 @@ import (
 	"crypto/sha256"
 	"encoding/hex"
 	"encoding/json"
-	"sort"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
@@ -58,9 +57,13 @@ func ComparisonKey(value string) string {
 // available, leaving validation to report the problem instead of manufacturing
 // an ID.
 func DeriveID(name string, refs []source.SourceRef) string {
-	comparisonName := ComparisonKey(name)
 	anchor, ok := earliestReference(refs)
-	if comparisonName == "" || !ok {
+	return deriveIDFromAnchor(name, anchor, ok)
+}
+
+func deriveIDFromAnchor(name string, anchor source.SourceRef, hasAnchor bool) string {
+	comparisonName := ComparisonKey(name)
+	if comparisonName == "" || !hasAnchor {
 		return ""
 	}
 
@@ -111,13 +114,14 @@ func ValidateRegistry(locations []dnd.Location) []Issue {
 		if ComparisonKey(location.Name) == "" {
 			issues = append(issues, Issue{Code: IssueEmptyCanonicalName, RecordIndex: recordIndex, Value: location.Name})
 		}
-		if _, ok := earliestReference(location.SourceRefs); !ok {
+		anchor, hasAnchor := earliestReference(location.SourceRefs)
+		if !hasAnchor {
 			issues = append(issues, Issue{Code: IssueMissingEvidence, RecordIndex: recordIndex})
 		}
 
 		if !IsValidID(location.ID) {
 			issues = append(issues, Issue{Code: IssueInvalidID, RecordIndex: recordIndex, Value: location.ID})
-		} else if expected := DeriveID(location.Name, location.SourceRefs); location.ID != expected {
+		} else if expected := deriveIDFromAnchor(location.Name, anchor, hasAnchor); location.ID != expected {
 			issues = append(issues, Issue{Code: IssueIDMismatch, RecordIndex: recordIndex, Value: location.ID})
 		}
 		if location.ID != "" {
@@ -135,36 +139,28 @@ func ValidateRegistry(locations []dnd.Location) []Issue {
 }
 
 func earliestReference(refs []source.SourceRef) (source.SourceRef, bool) {
-	canonical := canonicalReferences(refs)
-	if len(canonical) == 0 {
-		return source.SourceRef{}, false
+	var earliest source.SourceRef
+	found := false
+	for _, ref := range refs {
+		if !validIdentityReference(ref) {
+			continue
+		}
+		if !found || referenceLess(ref, earliest) {
+			earliest = ref
+			found = true
+		}
 	}
-	return canonical[0], true
+	return earliest, found
 }
 
-func canonicalReferences(refs []source.SourceRef) []source.SourceRef {
-	canonical := make([]source.SourceRef, 0, len(refs))
-	for _, ref := range refs {
-		if validIdentityReference(ref) {
-			canonical = append(canonical, ref)
-		}
+func referenceLess(left, right source.SourceRef) bool {
+	if left.SourceID != right.SourceID {
+		return left.SourceID < right.SourceID
 	}
-	sort.Slice(canonical, func(left, right int) bool {
-		if canonical[left].SourceID != canonical[right].SourceID {
-			return canonical[left].SourceID < canonical[right].SourceID
-		}
-		if canonical[left].StartUnitID != canonical[right].StartUnitID {
-			return canonical[left].StartUnitID < canonical[right].StartUnitID
-		}
-		return canonical[left].EndUnitID < canonical[right].EndUnitID
-	})
-	unique := canonical[:0]
-	for _, ref := range canonical {
-		if len(unique) == 0 || unique[len(unique)-1] != ref {
-			unique = append(unique, ref)
-		}
+	if left.StartUnitID != right.StartUnitID {
+		return left.StartUnitID < right.StartUnitID
 	}
-	return unique
+	return left.EndUnitID < right.EndUnitID
 }
 
 func validIdentityReference(ref source.SourceRef) bool {