Unify trim selector projection across output schemas

This commit is contained in:
2026-05-24 14:52:08 +00:00
parent 332884f887
commit e9028e08a4
2 changed files with 277 additions and 109 deletions

View File

@@ -44,54 +44,29 @@ type MinimalResult struct {
RemovedIDs []int
}
type projection struct {
retainedIndexes []int
oldToNewID map[int]int
removedIDs []int
}
// Apply trims a full seriatim output transcript by segment ID.
func Apply(input schema.Transcript, opts Options) (Result, error) {
if err := validateMode(opts.Mode); err != nil {
return Result{}, err
}
selected := opts.Selector.IDs()
if len(selected) == 0 {
return Result{}, fmt.Errorf("selector cannot be empty")
}
inputIDs := make([]int, len(input.Segments))
for index, segment := range input.Segments {
inputIDs[index] = segment.ID
}
idIndex, err := validateInputIDs(inputIDs)
proj, err := projectSegmentIDs(inputIDs, opts)
if err != nil {
return Result{}, err
}
if err := validateSelectedIDsExist(selected, idIndex); err != nil {
return Result{}, err
}
kept := make([]schema.Segment, 0, len(input.Segments))
removed := make([]int, 0, len(input.Segments))
oldToNew := make(map[int]int, len(input.Segments))
for _, segment := range input.Segments {
keep := opts.Mode == ModeKeep && opts.Selector.Contains(segment.ID)
if opts.Mode == ModeRemove {
keep = !opts.Selector.Contains(segment.ID)
}
if !keep {
removed = append(removed, segment.ID)
continue
}
rewritten := copySegment(segment)
rewritten.ID = len(kept) + 1
kept := make([]schema.Segment, len(proj.retainedIndexes))
for outputIndex, inputIndex := range proj.retainedIndexes {
rewritten := copySegment(input.Segments[inputIndex])
rewritten.ID = outputIndex + 1
rewritten.OverlapGroupID = 0
kept = append(kept, rewritten)
oldToNew[segment.ID] = rewritten.ID
}
if len(kept) == 0 && !opts.AllowEmpty {
return Result{}, fmt.Errorf("trim operation produced an empty transcript; set AllowEmpty to true to permit this")
kept[outputIndex] = rewritten
}
kept, groups := recomputeOverlapGroups(kept)
@@ -104,62 +79,35 @@ func Apply(input schema.Transcript, opts Options) (Result, error) {
out.OverlapGroups = groups
return Result{
Transcript: out,
OldToNewID: oldToNew,
RemovedIDs: removed,
OldToNewID: proj.oldToNewID,
RemovedIDs: proj.removedIDs,
}, nil
}
// ApplyIntermediate trims an intermediate seriatim output transcript by
// segment ID.
func ApplyIntermediate(input schema.IntermediateTranscript, opts Options) (IntermediateResult, error) {
if err := validateMode(opts.Mode); err != nil {
return IntermediateResult{}, err
}
selected := opts.Selector.IDs()
if len(selected) == 0 {
return IntermediateResult{}, fmt.Errorf("selector cannot be empty")
}
inputIDs := make([]int, len(input.Segments))
for index, segment := range input.Segments {
inputIDs[index] = segment.ID
}
idIndex, err := validateInputIDs(inputIDs)
proj, err := projectSegmentIDs(inputIDs, opts)
if err != nil {
return IntermediateResult{}, err
}
if err := validateSelectedIDsExist(selected, idIndex); err != nil {
return IntermediateResult{}, err
}
kept := make([]schema.IntermediateSegment, 0, len(input.Segments))
removed := make([]int, 0, len(input.Segments))
oldToNew := make(map[int]int, len(input.Segments))
for _, segment := range input.Segments {
keep := opts.Mode == ModeKeep && opts.Selector.Contains(segment.ID)
if opts.Mode == ModeRemove {
keep = !opts.Selector.Contains(segment.ID)
}
if !keep {
removed = append(removed, segment.ID)
continue
}
kept := make([]schema.IntermediateSegment, len(proj.retainedIndexes))
for outputIndex, inputIndex := range proj.retainedIndexes {
segment := input.Segments[inputIndex]
rewritten := schema.IntermediateSegment{
ID: len(kept) + 1,
ID: outputIndex + 1,
Start: segment.Start,
End: segment.End,
Speaker: segment.Speaker,
Text: segment.Text,
Categories: append([]string(nil), segment.Categories...),
}
kept = append(kept, rewritten)
oldToNew[segment.ID] = rewritten.ID
}
if len(kept) == 0 && !opts.AllowEmpty {
return IntermediateResult{}, fmt.Errorf("trim operation produced an empty transcript; set AllowEmpty to true to permit this")
kept[outputIndex] = rewritten
}
return IntermediateResult{
@@ -171,60 +119,33 @@ func ApplyIntermediate(input schema.IntermediateTranscript, opts Options) (Inter
},
Segments: kept,
},
OldToNewID: oldToNew,
RemovedIDs: removed,
OldToNewID: proj.oldToNewID,
RemovedIDs: proj.removedIDs,
}, nil
}
// ApplyMinimal trims a minimal seriatim output transcript by segment ID.
func ApplyMinimal(input schema.MinimalTranscript, opts Options) (MinimalResult, error) {
if err := validateMode(opts.Mode); err != nil {
return MinimalResult{}, err
}
selected := opts.Selector.IDs()
if len(selected) == 0 {
return MinimalResult{}, fmt.Errorf("selector cannot be empty")
}
inputIDs := make([]int, len(input.Segments))
for index, segment := range input.Segments {
inputIDs[index] = segment.ID
}
idIndex, err := validateInputIDs(inputIDs)
proj, err := projectSegmentIDs(inputIDs, opts)
if err != nil {
return MinimalResult{}, err
}
if err := validateSelectedIDsExist(selected, idIndex); err != nil {
return MinimalResult{}, err
}
kept := make([]schema.MinimalSegment, 0, len(input.Segments))
removed := make([]int, 0, len(input.Segments))
oldToNew := make(map[int]int, len(input.Segments))
for _, segment := range input.Segments {
keep := opts.Mode == ModeKeep && opts.Selector.Contains(segment.ID)
if opts.Mode == ModeRemove {
keep = !opts.Selector.Contains(segment.ID)
}
if !keep {
removed = append(removed, segment.ID)
continue
}
kept := make([]schema.MinimalSegment, len(proj.retainedIndexes))
for outputIndex, inputIndex := range proj.retainedIndexes {
segment := input.Segments[inputIndex]
rewritten := schema.MinimalSegment{
ID: len(kept) + 1,
ID: outputIndex + 1,
Start: segment.Start,
End: segment.End,
Speaker: segment.Speaker,
Text: segment.Text,
}
kept = append(kept, rewritten)
oldToNew[segment.ID] = rewritten.ID
}
if len(kept) == 0 && !opts.AllowEmpty {
return MinimalResult{}, fmt.Errorf("trim operation produced an empty transcript; set AllowEmpty to true to permit this")
kept[outputIndex] = rewritten
}
return MinimalResult{
@@ -236,11 +157,53 @@ func ApplyMinimal(input schema.MinimalTranscript, opts Options) (MinimalResult,
},
Segments: kept,
},
OldToNewID: oldToNew,
RemovedIDs: removed,
OldToNewID: proj.oldToNewID,
RemovedIDs: proj.removedIDs,
}, nil
}
func projectSegmentIDs(ids []int, opts Options) (projection, error) {
if err := validateMode(opts.Mode); err != nil {
return projection{}, err
}
selected := opts.Selector.IDs()
if len(selected) == 0 {
return projection{}, fmt.Errorf("selector cannot be empty")
}
idIndex, err := validateInputIDs(ids)
if err != nil {
return projection{}, err
}
if err := validateSelectedIDsExist(selected, idIndex); err != nil {
return projection{}, err
}
result := projection{
retainedIndexes: make([]int, 0, len(ids)),
oldToNewID: make(map[int]int, len(ids)),
removedIDs: make([]int, 0, len(ids)),
}
for index, id := range ids {
keep := opts.Mode == ModeKeep && opts.Selector.Contains(id)
if opts.Mode == ModeRemove {
keep = !opts.Selector.Contains(id)
}
if !keep {
result.removedIDs = append(result.removedIDs, id)
continue
}
result.retainedIndexes = append(result.retainedIndexes, index)
result.oldToNewID[id] = len(result.retainedIndexes)
}
if len(result.retainedIndexes) == 0 && !opts.AllowEmpty {
return projection{}, fmt.Errorf("trim operation produced an empty transcript; set AllowEmpty to true to permit this")
}
return result, nil
}
func validateMode(mode Mode) error {
switch mode {
case ModeKeep, ModeRemove: