Implement integer source units and chunk payloads

This commit is contained in:
2026-07-07 18:34:23 +00:00
parent 4f057b99ac
commit 9e3f8809b3
45 changed files with 618 additions and 451 deletions

View File

@@ -2,6 +2,7 @@ package scenes
import (
"context"
"encoding/json"
"fmt"
"strings"
@@ -142,7 +143,7 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
return nil, fmt.Errorf("scenes must not be empty")
}
unitIndexes := make(map[string]int, len(doc.Units))
unitIndexes := make(map[int]int, len(doc.Units))
for i, unit := range doc.Units {
unitIndexes[unit.ID] = i
}
@@ -157,18 +158,18 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
startIndex, ok := unitIndexes[normalized.StartUnitID]
if !ok {
return nil, fmt.Errorf("scene[%d] start_unit_id %q was not found", i, normalized.StartUnitID)
return nil, fmt.Errorf("scene[%d] start_unit_id %d was not found", i, normalized.StartUnitID)
}
endIndex, ok := unitIndexes[normalized.EndUnitID]
if !ok {
return nil, fmt.Errorf("scene[%d] end_unit_id %q was not found", i, normalized.EndUnitID)
return nil, fmt.Errorf("scene[%d] end_unit_id %d was not found", i, normalized.EndUnitID)
}
if startIndex > endIndex {
return nil, fmt.Errorf("scene[%d] start_unit_id %q appears after end_unit_id %q", i, normalized.StartUnitID, normalized.EndUnitID)
return nil, fmt.Errorf("scene[%d] start_unit_id %d appears after end_unit_id %d", i, normalized.StartUnitID, normalized.EndUnitID)
}
if i == 0 && startIndex != 0 {
return nil, fmt.Errorf("first scene must start at first source unit %q", doc.Units[0].ID)
return nil, fmt.Errorf("first scene must start at first source unit %d", doc.Units[0].ID)
}
if i > 0 {
if startIndex <= previousEnd {
@@ -181,11 +182,19 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
previousEnd = endIndex
units := cloneUnits(doc.Units[startIndex : endIndex+1])
content, err := chunkContent(units)
if err != nil {
return nil, err
}
chunks = append(chunks, contracts.SourceChunk{
ID: fmt.Sprintf("scene-%06d", i+1),
SourceID: doc.ID,
Index: i,
Units: units,
ID: fmt.Sprintf("scene-%06d", i+1),
SourceID: doc.ID,
Index: i,
StartUnitID: units[0].ID,
EndUnitID: units[len(units)-1].ID,
Content: content,
MediaType: "application/json",
Units: units,
Metadata: map[string]any{
"scene_title": normalized.ShortTitle,
"primary_mode": normalized.PrimaryMode,
@@ -201,11 +210,23 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
}
if previousEnd != len(doc.Units)-1 {
return nil, fmt.Errorf("final scene must end at final source unit %q", doc.Units[len(doc.Units)-1].ID)
return nil, fmt.Errorf("final scene must end at final source unit %d", doc.Units[len(doc.Units)-1].ID)
}
return chunks, nil
}
func chunkContent(units []source.SourceUnit) ([]byte, error) {
content, err := json.Marshal(struct {
Units []source.SourceUnit `json:"units"`
}{
Units: units,
})
if err != nil {
return nil, fmt.Errorf("encode chunk content: %w", err)
}
return content, nil
}
func normalizeScene(doc *source.SourceDocument, index int, scene sceneResponse) (normalizedScene, error) {
startUnitID, err := dnd.ResolveUnitID(doc, "start_unit_id", scene.StartUnitID)
if err != nil {
@@ -226,9 +247,16 @@ func normalizeScene(doc *source.SourceDocument, index int, scene sceneResponse)
BoundaryConfidence: strings.TrimSpace(scene.BoundaryConfidence),
}
requiredInts := map[string]int{
"start_unit_id": out.StartUnitID,
"end_unit_id": out.EndUnitID,
}
for field, value := range requiredInts {
if value <= 0 {
return normalizedScene{}, fmt.Errorf("scene[%d] %s must be positive", index, field)
}
}
required := map[string]string{
"start_unit_id": out.StartUnitID,
"end_unit_id": out.EndUnitID,
"short_title": out.ShortTitle,
"primary_mode": out.PrimaryMode,
"summary": out.Summary,