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

Move chunks into the canonical source model

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-17 05:32:11 +00:00
parent 40709e4ad8
commit 075888c97f
33 changed files with 548 additions and 325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
internal/framework/pipeline/chunk_validation.go
View File

@@ -5,10 +5,9 @@ import (
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []contracts.SourceChunk) ([]contracts.SourceChunk, error) {
func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []source.Chunk) ([]source.Chunk, error) {
if len(chunks) == 0 {
return nil, fmt.Errorf("chunks must not be empty")
}
@@ -20,7 +19,7 @@ func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []con
sourceUnits[unit.ID] = unit
}
canonicalChunks := make([]contracts.SourceChunk, 0, len(chunks))
canonicalChunks := make([]source.Chunk, 0, len(chunks))
seenChunkIDs := make(map[string]struct{}, len(chunks))
for chunkIndex, chunk := range chunks {
if strings.TrimSpace(chunk.ID) == "" {
@@ -37,17 +36,6 @@ func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []con
if chunk.Index != chunkIndex {
return nil, fmt.Errorf("chunk %q index %d does not match returned order %d", chunk.ID, chunk.Index, chunkIndex)
}
startIndex, ok := sourceUnitIndexes[chunk.StartUnitID]
if !ok {
return nil, fmt.Errorf("chunk %q start_unit_id %d was not found in source document %q", chunk.ID, chunk.StartUnitID, doc.ID)
}
endIndex, ok := sourceUnitIndexes[chunk.EndUnitID]
if !ok {
return nil, fmt.Errorf("chunk %q end_unit_id %d was not found in source document %q", chunk.ID, chunk.EndUnitID, doc.ID)
}
if startIndex > endIndex {
return nil, fmt.Errorf("chunk %q start_unit_id %d appears after end_unit_id %d", chunk.ID, chunk.StartUnitID, chunk.EndUnitID)
}
if len(chunk.Units) == 0 {
return nil, fmt.Errorf("chunk %q units must not be empty", chunk.ID)
}
@@ -57,6 +45,9 @@ func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []con
if strings.TrimSpace(chunk.MediaType) == "" {
return nil, fmt.Errorf("chunk %q media_type must not be empty", chunk.ID)
}
if err := source.ValidateRef(doc, chunk.Ref); err != nil {
return nil, fmt.Errorf("chunk %q ref: %w", chunk.ID, err)
}
seenUnitIDs := make(map[int]struct{}, len(chunk.Units))
previousSourceIndex := -1
@@ -74,23 +65,33 @@ func validateAndCanonicalizeChunkResult(doc *source.SourceDocument, chunks []con
if !ok {
return nil, fmt.Errorf("chunk %q source unit %d was not found in source document %q", chunk.ID, unit.ID, doc.ID)
}
if sourceIndex <= previousSourceIndex {
return nil, fmt.Errorf("chunk %q source units must appear in source document order", chunk.ID)
if previousSourceIndex >= 0 && sourceIndex != previousSourceIndex+1 {
return nil, fmt.Errorf("chunk %q source units must form a contiguous range in source document order", chunk.ID)
}
if unit.Ref != sourceUnits[unit.ID].Ref {
return nil, fmt.Errorf("chunk %q source unit %d ref does not match source document", chunk.ID, unit.ID)
}
previousSourceIndex = sourceIndex
canonicalUnits = append(canonicalUnits, cloneSourceUnit(sourceUnits[unit.ID]))
}
expectedRef := source.SourceRef{
SourceID: doc.ID,
StartUnitID: canonicalUnits[0].Ref.StartUnitID,
EndUnitID: canonicalUnits[len(canonicalUnits)-1].Ref.EndUnitID,
}
if chunk.Ref != expectedRef {
return nil, fmt.Errorf("chunk %q ref %#v does not match unit span %#v", chunk.ID, chunk.Ref, expectedRef)
}
canonicalChunks = append(canonicalChunks, contracts.SourceChunk{
ID: chunk.ID,
SourceID: chunk.SourceID,
Index: chunk.Index,
StartUnitID: chunk.StartUnitID,
EndUnitID: chunk.EndUnitID,
Content: append([]byte(nil), chunk.Content...),
MediaType: chunk.MediaType,
Units: canonicalUnits,
Metadata: cloneMetadata(chunk.Metadata),
canonicalChunks = append(canonicalChunks, source.Chunk{
ID: chunk.ID,
SourceID: chunk.SourceID,
Index: chunk.Index,
Ref: expectedRef,
Content: append([]byte(nil), chunk.Content...),
MediaType: chunk.MediaType,
Units: canonicalUnits,
Metadata: cloneMetadata(chunk.Metadata),
})
}