Add D&D NPC extraction and validation

internal/modules/dnd/extract/npcs/canonicalize.go

@@ -0,0 +1,153 @@
+package npcs
+
+import (
+	"sort"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+func canonicalizeResponse(response *extractionResponse, doc *source.SourceDocument) {
+	if response == nil {
+		return
+	}
+	for index := range response.NPCs {
+		canonicalizeNPC(&response.NPCs[index])
+	}
+	sort.SliceStable(response.NPCs, func(i, j int) bool {
+		left, leftOK := earliestSourceUnit(doc, response.NPCs[i])
+		right, rightOK := earliestSourceUnit(doc, response.NPCs[j])
+		if leftOK != rightOK {
+			return leftOK
+		}
+		if !leftOK {
+			return false
+		}
+		return left < right
+	})
+}
+
+func canonicalizeNPC(npc *npcResponse) {
+	if npc == nil {
+		return
+	}
+	for index := range npc.SourceRefs {
+		npc.SourceRefs[index].StartUnitID = canonicalUnitRef(npc.SourceRefs[index].StartUnitID)
+		npc.SourceRefs[index].EndUnitID = canonicalUnitRef(npc.SourceRefs[index].EndUnitID)
+	}
+	sort.SliceStable(npc.SourceRefs, func(i, j int) bool {
+		left := npc.SourceRefs[i]
+		right := npc.SourceRefs[j]
+		if unitSortValue(left.StartUnitID) != unitSortValue(right.StartUnitID) {
+			return unitSortValue(left.StartUnitID) < unitSortValue(right.StartUnitID)
+		}
+		return unitSortValue(left.EndUnitID) < unitSortValue(right.EndUnitID)
+	})
+	npc.SourceRefs = dedupeSourceRefs(npc.SourceRefs)
+}
+
+func canonicalUnitRef(ref shared.UnitRef) shared.UnitRef {
+	value := ref.Int()
+	if value <= 0 {
+		return ref
+	}
+	return shared.UnitRefFromInt(value)
+}
+
+func dedupeSourceRefs(refs []npcSourceRefResponse) []npcSourceRefResponse {
+	if len(refs) < 2 {
+		return refs
+	}
+	out := refs[:0]
+	var previous npcSourceRefResponse
+	for index, ref := range refs {
+		if index > 0 && sameSourceRef(previous, ref) {
+			continue
+		}
+		out = append(out, ref)
+		previous = ref
+	}
+	return out
+}
+
+func sameSourceRef(left npcSourceRefResponse, right npcSourceRefResponse) bool {
+	return left.StartUnitID.Int() == right.StartUnitID.Int() &&
+		left.EndUnitID.Int() == right.EndUnitID.Int()
+}
+
+func earliestSourceUnit(doc *source.SourceDocument, npc npcResponse) (int, bool) {
+	for _, ref := range npc.SourceRefs {
+		start := ref.StartUnitID.Int()
+		end := ref.EndUnitID.Int()
+		if start > 0 && end > 0 {
+			startIndex, startOK := source.UnitIndex(doc, start)
+			endIndex, endOK := source.UnitIndex(doc, end)
+			if !startOK || !endOK || startIndex > endIndex {
+				continue
+			}
+			return start, true
+		}
+	}
+	return 0, false
+}
+
+func unitSortValue(ref shared.UnitRef) int {
+	value := ref.Int()
+	if value <= 0 {
+		return int(^uint(0) >> 1)
+	}
+	return value
+}
+
+func canonicalNPCList(response extractionResponse, sourceID string) dnd.NPCList {
+	if response.NPCs == nil {
+		return dnd.NPCList{NPCs: nil}
+	}
+	npcs := make([]dnd.NPC, len(response.NPCs))
+	for index, npc := range response.NPCs {
+		npcs[index] = dnd.NPC{
+			ID:            identity.DeriveID(npc.Name),
+			Name:          npc.Name,
+			Aliases:       cloneStrings(npc.Aliases),
+			Description:   npc.Description,
+			Relationships: cloneRelationships(npc.Relationships),
+			SourceRefs:    canonicalSourceRefs(npc.SourceRefs, sourceID),
+		}
+	}
+	return dnd.NPCList{NPCs: npcs}
+}
+
+func cloneStrings(values []string) []string {
+	if values == nil {
+		return nil
+	}
+	return append([]string{}, values...)
+}
+
+func cloneRelationships(values []npcRelationshipResponse) []dnd.NPCRelationship {
+	if values == nil {
+		return nil
+	}
+	out := make([]dnd.NPCRelationship, len(values))
+	for index, value := range values {
+		out[index] = dnd.NPCRelationship{Target: value.Target, Relationship: value.Relationship}
+	}
+	return out
+}
+
+func canonicalSourceRefs(values []npcSourceRefResponse, sourceID string) []source.SourceRef {
+	if values == nil {
+		return nil
+	}
+	out := make([]source.SourceRef, len(values))
+	for index, value := range values {
+		out[index] = source.SourceRef{
+			SourceID:    sourceID,
+			StartUnitID: value.StartUnitID.Int(),
+			EndUnitID:   value.EndUnitID.Int(),
+		}
+	}
+	return out
+}