Added a module to coalesce adjacent same-speaker segments

internal/coalesce/coalesce.go

@@ -0,0 +1,118 @@
+package coalesce
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/model"
+)
+
+// Summary records deterministic counters for a coalesce pass.
+type Summary struct {
+	OriginalSegmentsMerged int
+	CoalescedSegments      int
+}
+
+// Apply merges adjacent same-speaker segments in the transcript's current order.
+func Apply(in model.MergedTranscript, gap float64) (model.MergedTranscript, Summary) {
+	if len(in.Segments) < 2 {
+		return in, Summary{}
+	}
+
+	out := model.MergedTranscript{
+		Segments:      make([]model.Segment, 0, len(in.Segments)),
+		OverlapGroups: in.OverlapGroups,
+	}
+	summary := Summary{}
+	coalescedID := 0
+
+	current := newRun(in.Segments[0])
+	for _, segment := range in.Segments[1:] {
+		if current.canMerge(segment, gap) {
+			current.add(segment)
+			continue
+		}
+
+		coalescedID = appendRun(&out, current, coalescedID, &summary)
+		current = newRun(segment)
+	}
+	appendRun(&out, current, coalescedID, &summary)
+
+	return out, summary
+}
+
+type run struct {
+	segments []model.Segment
+}
+
+func newRun(segment model.Segment) run {
+	return run{
+		segments: []model.Segment{segment},
+	}
+}
+
+func (r run) canMerge(next model.Segment, gap float64) bool {
+	current := r.segments[len(r.segments)-1]
+	return current.Speaker == next.Speaker && next.Start-current.End <= gap
+}
+
+func (r *run) add(segment model.Segment) {
+	r.segments = append(r.segments, segment)
+}
+
+func appendRun(out *model.MergedTranscript, current run, coalescedID int, summary *Summary) int {
+	if len(current.segments) == 1 {
+		out.Segments = append(out.Segments, current.segments[0])
+		return coalescedID
+	}
+
+	coalescedID++
+	out.Segments = append(out.Segments, current.coalescedSegment(coalescedID))
+	summary.OriginalSegmentsMerged += len(current.segments)
+	summary.CoalescedSegments++
+	return coalescedID
+}
+
+func (r run) coalescedSegment(id int) model.Segment {
+	first := r.segments[0]
+	merged := model.Segment{
+		Source:      first.Source,
+		SourceRef:   fmt.Sprintf("coalesce:%d", id),
+		DerivedFrom: make([]string, 0, len(r.segments)),
+		Speaker:     first.Speaker,
+		Start:       first.Start,
+		End:         first.End,
+		Words:       make([]model.Word, 0),
+	}
+
+	text := make([]string, 0, len(r.segments))
+	for _, segment := range r.segments {
+		if segment.Start < merged.Start {
+			merged.Start = segment.Start
+		}
+		if segment.End > merged.End {
+			merged.End = segment.End
+		}
+		if segment.Source != merged.Source {
+			merged.Source = "derived"
+		}
+		if trimmed := strings.TrimSpace(segment.Text); trimmed != "" {
+			text = append(text, trimmed)
+		}
+		merged.Words = append(merged.Words, segment.Words...)
+		merged.DerivedFrom = append(merged.DerivedFrom, segmentRef(segment))
+	}
+
+	merged.Text = strings.Join(text, " ")
+	return merged
+}
+
+func segmentRef(segment model.Segment) string {
+	if segment.SourceSegmentIndex != nil {
+		return fmt.Sprintf("%s#%d", segment.Source, *segment.SourceSegmentIndex)
+	}
+	if segment.SourceRef != "" {
+		return segment.SourceRef
+	}
+	return segment.Source
+}