eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reuse canonical item occurrence evidence

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-09 02:36:53 +00:00
parent b3ebfcef37
commit d28d1062e0
6 changed files with 97 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
internal/modules/dnd/normalize/itemoccurrences/normalizer.go
View File

@@ -113,6 +113,7 @@ func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalize
type normalizedRecord struct {
occurrence dnd.ItemOccurrence
identity string
inputIndex int
}
@@ -125,7 +126,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
warnings := make([]contracts.Warning, 0)
for index, inputOccurrence := range input.Occurrences {
occurrence, changedFields, found, refsChanged := normalizeOccurrence(inputOccurrence, order, registry)
records[index] = normalizedRecord{occurrence: occurrence, inputIndex: index}
records[index] = normalizedRecord{occurrence: occurrence, identity: itemoccurrencemodel.CanonicalExactIdentity(occurrence), inputIndex: index}
if len(changedFields) != 0 {
warnings = append(warnings, contracts.Warning{
Scope: occurrenceScope(index),
@@ -153,7 +154,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
}
sort.SliceStable(records, func(left, right int) bool {
return itemoccurrencemodel.Less(order, records[left].occurrence, records[right].occurrence)
return itemoccurrencemodel.CanonicalLess(order, records[left].occurrence, records[right].occurrence)
})
for position, record := range records {
if position == record.inputIndex {
@@ -166,7 +167,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
})
}
output, duplicateWarnings := collapseDuplicates(records, index, order)
output, duplicateWarnings := collapseDuplicates(records, index)
warnings = append(warnings, duplicateWarnings...)
return dnd.ItemOccurrenceList{Occurrences: output}, diagnostics.LimitWarnings(warnings, "item_occurrences", ReasonCodeWarningsOmitted)
}
@@ -208,28 +209,35 @@ func cloneOccurrence(input dnd.ItemOccurrence) dnd.ItemOccurrence {
}
type duplicateGroup struct {
retainedIndex int
removed []int
retainedIndex int
retainedRecord int
removed []int
}
func collapseDuplicates(records []normalizedRecord, index source.DocumentIndex, order shared.SourceRefOrder) ([]dnd.ItemOccurrence, []contracts.Warning) {
func collapseDuplicates(records []normalizedRecord, index source.DocumentIndex) ([]dnd.ItemOccurrence, []contracts.Warning) {
if len(records) == 0 {
return make([]dnd.ItemOccurrence, 0), nil
}
keep := make([]bool, len(records))
groups := make([]duplicateGroup, 0)
groupByKey := make(map[string]int)
groupByKey := make(map[string][]int)
for recordIndex, record := range records {
if !itemoccurrencemodel.ValidSourceRefs(index, record.occurrence.SourceRefs) {
keep[recordIndex] = true
continue
}
key := itemoccurrencemodel.ExactIdentity(order, record.occurrence)
groupIndex, exists := groupByKey[key]
if !exists {
groupByKey[key] = len(groups)
groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex})
groupIndex := -1
for _, candidate := range groupByKey[record.identity] {
if itemoccurrencemodel.CanonicalExactEqual(records[groups[candidate].retainedRecord].occurrence, record.occurrence) {
groupIndex = candidate
break
}
}
if groupIndex < 0 {
groupIndex = len(groups)
groupByKey[record.identity] = append(groupByKey[record.identity], groupIndex)
groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex, retainedRecord: recordIndex})
keep[recordIndex] = true
continue
}