Fix D&D extraction issues and retire the completed audit

This commit is contained in:
2026-07-25 12:30:42 +00:00
parent 84a2854b5e
commit e4471fc300
15 changed files with 295 additions and 1782 deletions

View File

@@ -2,7 +2,6 @@ package shared
import (
"sort"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
)
@@ -10,8 +9,8 @@ import (
// SourceRefOrder provides a stable snapshot of a source document's unit
// ordering for source-reference comparison and canonicalization.
type SourceRefOrder struct {
sourceID string
positions map[int]int
sourceID string
index source.DocumentIndex
}
// NewSourceRefOrder captures the source identity and unit positions from doc.
@@ -19,13 +18,7 @@ func NewSourceRefOrder(doc *source.SourceDocument) SourceRefOrder {
if doc == nil {
return SourceRefOrder{}
}
positions := make(map[int]int, len(doc.Units))
for position, unit := range doc.Units {
if _, exists := positions[unit.ID]; !exists {
positions[unit.ID] = position
}
}
return SourceRefOrder{sourceID: doc.ID, positions: positions}
return SourceRefOrder{sourceID: doc.ID, index: source.NewDocumentIndex(doc)}
}
// Less orders references by source identity, then document positions when
@@ -34,14 +27,13 @@ func (o SourceRefOrder) Less(left, right source.SourceRef) bool {
if left.SourceID != right.SourceID {
return left.SourceID < right.SourceID
}
positions := o.positionsFor(left.SourceID)
if lessEndpoint(positions, left.StartUnitID, right.StartUnitID) {
if o.lessEndpoint(left.SourceID, left.StartUnitID, right.StartUnitID) {
return true
}
if lessEndpoint(positions, right.StartUnitID, left.StartUnitID) {
if o.lessEndpoint(left.SourceID, right.StartUnitID, left.StartUnitID) {
return false
}
return lessEndpoint(positions, left.EndUnitID, right.EndUnitID)
return o.lessEndpoint(left.SourceID, left.EndUnitID, right.EndUnitID)
}
// EarliestValid returns the earliest document position among valid refs.
@@ -52,14 +44,10 @@ func (o SourceRefOrder) EarliestValid(refs []source.SourceRef) (int, bool) {
found := false
earliest := 0
for _, ref := range refs {
if ref.SourceID != o.sourceID || strings.TrimSpace(ref.SourceID) != ref.SourceID || ref.StartUnitID <= 0 || ref.EndUnitID <= 0 {
continue
}
start, startOK := o.positions[ref.StartUnitID]
end, endOK := o.positions[ref.EndUnitID]
if !startOK || !endOK || start > end {
if o.index.ValidateRef(ref) != nil {
continue
}
start, _ := o.index.Position(ref.StartUnitID)
if !found || start < earliest {
earliest = start
found = true
@@ -87,16 +75,9 @@ func (o SourceRefOrder) Canonicalize(refs []source.SourceRef) []source.SourceRef
return unique
}
func (o SourceRefOrder) positionsFor(sourceID string) map[int]int {
if o.sourceID == "" || sourceID != o.sourceID {
return nil
}
return o.positions
}
func lessEndpoint(positions map[int]int, left, right int) bool {
leftPosition, leftOK := positions[left]
rightPosition, rightOK := positions[right]
func (o SourceRefOrder) lessEndpoint(sourceID string, left, right int) bool {
leftPosition, leftOK := o.position(sourceID, left)
rightPosition, rightOK := o.position(sourceID, right)
if leftOK != rightOK {
return leftOK
}
@@ -105,3 +86,10 @@ func lessEndpoint(positions map[int]int, left, right int) bool {
}
return left < right
}
func (o SourceRefOrder) position(sourceID string, unitID int) (int, bool) {
if o.sourceID == "" || sourceID != o.sourceID {
return 0, false
}
return o.index.Position(unitID)
}