Tighten NPC interaction validation and consistency

internal/modules/dnd/normalize/npcinteractions/normalizer.go

@@ -5,13 +5,12 @@ import (
 	"context"
 	"fmt"
 	"sort"
-	"strconv"
-	"strings"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	interactionmodel "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcinteractions"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
 	npcregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/registry"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
@@ -20,13 +19,14 @@ import (
 
 const (
 	Key                 = "dnd/npc-interactions"
-	normalizationPolicy = "dnd.npc_interactions.normalize.v1"
+	normalizationPolicy = "dnd.npc_interactions.normalize.v2"
 	NormalizationPolicy = normalizationPolicy
 
 	ReasonCodeNameCanonicalized     = "npc_interaction_name_canonicalized"
 	ReasonCodeSourceRefsNormalized  = "source_references_normalized"
 	ReasonCodeInteractionsReordered = "npc_interactions_reordered"
 	ReasonCodeDuplicateCollapsed    = "duplicate_npc_interaction_collapsed"
+	ReasonCodeWarningsOmitted       = "npc_interaction_normalization_warnings_omitted"
 )
 
 const (
@@ -125,8 +125,6 @@ func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalize
 type normalizedRecord struct {
 	interaction dnd.NPCInteraction
 	inputIndex  int
-	earliest    int
-	hasEvidence bool
 }
 
 type nameCanonicalization struct {
@@ -143,8 +141,7 @@ func normalizeList(input dnd.NPCInteractionList, doc *source.SourceDocument, reg
 	warnings := make([]contracts.Warning, 0)
 	for index, inputInteraction := range input.Interactions {
 		interaction, nameChange, refsChanged := normalizeInteraction(inputInteraction, doc, registry)
-		earliest, hasEvidence := earliestSourcePosition(doc, interaction)
-		records[index] = normalizedRecord{interaction: interaction, inputIndex: index, earliest: earliest, hasEvidence: hasEvidence}
+		records[index] = normalizedRecord{interaction: interaction, inputIndex: index}
 		if nameChange != nil {
 			warnings = append(warnings, contracts.Warning{
 				Scope:      interactionScope(index),
@@ -163,7 +160,9 @@ func normalizeList(input dnd.NPCInteractionList, doc *source.SourceDocument, reg
 		}
 	}
 
-	sort.SliceStable(records, func(left, right int) bool { return recordLess(doc, records[left], records[right]) })
+	sort.SliceStable(records, func(left, right int) bool {
+		return interactionmodel.Less(doc, records[left].interaction, records[right].interaction)
+	})
 	for position, record := range records {
 		if position == record.inputIndex {
 			continue
@@ -177,7 +176,8 @@ func normalizeList(input dnd.NPCInteractionList, doc *source.SourceDocument, reg
 
 	output, duplicateWarnings := collapseDuplicates(records, doc)
 	warnings = append(warnings, duplicateWarnings...)
-	return dnd.NPCInteractionList{Interactions: output}, warnings
+	return dnd.NPCInteractionList{Interactions: output},
+		diagnostics.LimitWarnings(warnings, "npc_interactions", ReasonCodeWarningsOmitted)
 }
 
 func normalizeInteraction(input dnd.NPCInteraction, doc *source.SourceDocument, registry *npcregistry.Registry) (dnd.NPCInteraction, *nameCanonicalization, bool) {
@@ -189,8 +189,8 @@ func normalizeInteraction(input dnd.NPCInteraction, doc *source.SourceDocument,
 	if input.Name != output.Name {
 		nameChange = &nameCanonicalization{from: input.Name, to: output.Name}
 	}
-	output.SourceRefs = canonicalizeSourceRefs(doc, input.SourceRefs)
-	return output, nameChange, !sourceRefsEqual(input.SourceRefs, output.SourceRefs)
+	output.SourceRefs = interactionmodel.CanonicalizeSourceRefs(doc, input.SourceRefs)
+	return output, nameChange, !interactionmodel.SourceRefsEqual(input.SourceRefs, output.SourceRefs)
 }
 
 func cloneInteraction(input dnd.NPCInteraction) dnd.NPCInteraction {
@@ -201,107 +201,6 @@ func cloneInteraction(input dnd.NPCInteraction) dnd.NPCInteraction {
 	return output
 }
 
-func canonicalizeSourceRefs(doc *source.SourceDocument, input []source.SourceRef) []source.SourceRef {
-	if input == nil {
-		return nil
-	}
-	canonical := append([]source.SourceRef(nil), input...)
-	sort.SliceStable(canonical, func(left, right int) bool { return sourceRefLess(doc, canonical[left], canonical[right]) })
-	unique := make([]source.SourceRef, 0, len(canonical))
-	for _, ref := range canonical {
-		if len(unique) == 0 || unique[len(unique)-1] != ref {
-			unique = append(unique, ref)
-		}
-	}
-	return unique
-}
-
-func sourceRefsEqual(left, right []source.SourceRef) bool {
-	if (left == nil) != (right == nil) || len(left) != len(right) {
-		return false
-	}
-	for index := range left {
-		if left[index] != right[index] {
-			return false
-		}
-	}
-	return true
-}
-
-func sourceRefLess(doc *source.SourceDocument, left, right source.SourceRef) bool {
-	if left.SourceID != right.SourceID {
-		return left.SourceID < right.SourceID
-	}
-	leftStart, leftStartOK := source.UnitIndex(doc, left.StartUnitID)
-	rightStart, rightStartOK := source.UnitIndex(doc, right.StartUnitID)
-	if leftStartOK != rightStartOK {
-		return leftStartOK
-	}
-	if leftStartOK && leftStart != rightStart {
-		return leftStart < rightStart
-	}
-	if left.StartUnitID != right.StartUnitID {
-		return left.StartUnitID < right.StartUnitID
-	}
-	leftEnd, leftEndOK := source.UnitIndex(doc, left.EndUnitID)
-	rightEnd, rightEndOK := source.UnitIndex(doc, right.EndUnitID)
-	if leftEndOK != rightEndOK {
-		return leftEndOK
-	}
-	if leftEndOK && leftEnd != rightEnd {
-		return leftEnd < rightEnd
-	}
-	return left.EndUnitID < right.EndUnitID
-}
-
-func earliestSourcePosition(doc *source.SourceDocument, interaction dnd.NPCInteraction) (int, bool) {
-	found := false
-	earliest := 0
-	for _, ref := range interaction.SourceRefs {
-		if source.ValidateRef(doc, ref) != nil {
-			continue
-		}
-		position, ok := source.UnitIndex(doc, ref.StartUnitID)
-		if !ok || (found && position >= earliest) {
-			continue
-		}
-		earliest = position
-		found = true
-	}
-	return earliest, found
-}
-
-func recordLess(doc *source.SourceDocument, left, right normalizedRecord) bool {
-	if left.hasEvidence != right.hasEvidence {
-		return left.hasEvidence
-	}
-	if left.hasEvidence && left.earliest != right.earliest {
-		return left.earliest < right.earliest
-	}
-	leftKey := identity.ComparisonKey(left.interaction.Name)
-	rightKey := identity.ComparisonKey(right.interaction.Name)
-	if leftKey != rightKey {
-		return leftKey < rightKey
-	}
-	if left.interaction.Name != right.interaction.Name {
-		return left.interaction.Name < right.interaction.Name
-	}
-	if left.interaction.Kind != right.interaction.Kind {
-		return left.interaction.Kind < right.interaction.Kind
-	}
-	return sourceRefsLess(doc, left.interaction.SourceRefs, right.interaction.SourceRefs)
-}
-
-func sourceRefsLess(doc *source.SourceDocument, left, right []source.SourceRef) bool {
-	for index := 0; index < len(left) && index < len(right); index++ {
-		if left[index] == right[index] {
-			continue
-		}
-		return sourceRefLess(doc, left[index], right[index])
-	}
-	return len(left) < len(right)
-}
-
 type duplicateGroup struct {
 	retainedIndex int
 	removed       []int
@@ -315,11 +214,11 @@ func collapseDuplicates(records []normalizedRecord, doc *source.SourceDocument)
 	groups := make([]duplicateGroup, 0)
 	groupByKey := make(map[string]int)
 	for index, record := range records {
-		key, eligible := duplicateKey(record.interaction, doc)
-		if !eligible {
+		if !interactionmodel.ValidSourceRefs(doc, record.interaction.SourceRefs) {
 			keep[index] = true
 			continue
 		}
+		key := interactionmodel.ExactIdentity(record.interaction)
 		groupIndex, exists := groupByKey[key]
 		if !exists {
 			groupByKey[key] = len(groups)
@@ -344,37 +243,6 @@ func collapseDuplicates(records []normalizedRecord, doc *source.SourceDocument)
 	return output, warnings
 }
 
-func duplicateKey(interaction dnd.NPCInteraction, doc *source.SourceDocument) (string, bool) {
-	if len(interaction.SourceRefs) == 0 {
-		return "", false
-	}
-	for _, ref := range interaction.SourceRefs {
-		if source.ValidateRef(doc, ref) != nil {
-			return "", false
-		}
-	}
-	var key strings.Builder
-	writeKeyString(&key, interaction.Name)
-	writeKeyString(&key, string(interaction.Kind))
-	for _, ref := range interaction.SourceRefs {
-		writeKeyString(&key, ref.SourceID)
-		writeKeyInt(&key, ref.StartUnitID)
-		writeKeyInt(&key, ref.EndUnitID)
-	}
-	return key.String(), true
-}
-
-func writeKeyString(builder *strings.Builder, value string) {
-	builder.WriteString(strconv.Itoa(len(value)))
-	builder.WriteByte(':')
-	builder.WriteString(value)
-}
-
-func writeKeyInt(builder *strings.Builder, value int) {
-	builder.WriteString(strconv.Itoa(value))
-	builder.WriteByte(';')
-}
-
 func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
 	issues := make([]string, len(removed))
 	for index, removedIndex := range removed {