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

123 lines
3.0 KiB
Go

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"
)
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 := earliestSourceIndex(doc, response.NPCs[i])
right, rightOK := earliestSourceIndex(doc, response.NPCs[j])
if leftOK != rightOK {
return leftOK
}
if !leftOK {
return false
}
return left < right
})
}
func canonicalizeNPC(npc *npcResponse) {
if npc == nil {
return
}
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 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 == right.StartUnitID && left.EndUnitID == right.EndUnitID
}
func earliestSourceIndex(doc *source.SourceDocument, npc npcResponse) (int, bool) {
earliest := 0
found := false
for _, ref := range npc.SourceRefs {
start := ref.StartUnitID
end := ref.EndUnitID
if start > 0 && end > 0 {
startIndex, startOK := source.UnitIndex(doc, start)
endIndex, endOK := source.UnitIndex(doc, end)
if !startOK || !endOK || startIndex > endIndex {
continue
}
if !found || startIndex < earliest {
earliest = startIndex
found = true
}
}
}
return earliest, found
}
func unitSortValue(value int) 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,
SourceRefs: canonicalSourceRefs(npc.SourceRefs, sourceID),
}
}
return dnd.NPCList{NPCs: npcs}
}
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,
EndUnitID: value.EndUnitID,
}
}
return out
}