Minor updates to overlap detection and segment coalescing logic

internal/cli/merge_test.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
+	"reflect"
 	"strings"
 	"testing"
 
@@ -317,7 +318,7 @@ func TestMergeResolvesOverlapGroupsWithWordRuns(t *testing.T) {
 		t.Fatalf("segment count = %d, want %d", got, want)
 	}
 
-	wantTexts := []string{"hello there", "bob reply", "later"}
+	wantTexts := []string{"outside hello there", "bob reply", "later"}
 	wantSpeakers := []string{"Alice", "Bob", "Alice"}
 	wantRefs := []string{"word-run:1:1:1", "word-run:1:2:1", "word-run:1:1:2"}
 	for index, segment := range transcript.Segments {
@@ -1496,6 +1497,86 @@ func TestMergeResolutionPreservesUntimedWordText(t *testing.T) {
 	}
 }
 
+func TestMergeResolveOverlapsAbsorbsNearbyContext(t *testing.T) {
+	dir := t.TempDir()
+	inputA := writeJSONFile(t, dir, "a.json", `{
+		"segments": [
+			{
+				"start": 9,
+				"end": 9.95,
+				"text": "before",
+				"words": [
+					{"word": "before", "start": 9.7, "end": 9.9}
+				]
+			},
+			{
+				"start": 10,
+				"end": 11,
+				"text": "inside",
+				"words": [
+					{"word": "inside", "start": 10.5, "end": 10.7}
+				]
+			},
+			{
+				"start": 11.1,
+				"end": 12,
+				"text": "after",
+				"words": [
+					{"word": "after", "start": 11.2, "end": 11.3}
+				]
+			}
+		]
+	}`)
+	inputB := writeJSONFile(t, dir, "b.json", `{
+		"segments": [
+			{
+				"start": 10.2,
+				"end": 11,
+				"text": "bob",
+				"words": [
+					{"word": "bob", "start": 10.4, "end": 10.6}
+				]
+			}
+		]
+	}`)
+	speakers := writeYAMLFile(t, dir, "speakers.yml", `match:
+  - speaker: Alice
+    match: ["a.json"]
+  - speaker: Bob
+    match: ["b.json"]
+`)
+	output := filepath.Join(dir, "merged.json")
+
+	err := executeMerge(
+		"--input-file", inputA,
+		"--input-file", inputB,
+		"--speakers", speakers,
+		"--output-file", output,
+	)
+	if err != nil {
+		t.Fatalf("merge failed: %v", err)
+	}
+
+	var transcript model.FinalTranscript
+	readJSON(t, output, &transcript)
+
+	var aliceSegments []model.Segment
+	for _, segment := range transcript.Segments {
+		if segment.Speaker == "Alice" {
+			aliceSegments = append(aliceSegments, segment)
+		}
+	}
+	if len(aliceSegments) != 1 {
+		t.Fatalf("Alice segment count = %d, want 1: %#v", len(aliceSegments), aliceSegments)
+	}
+	if aliceSegments[0].Text != "before inside after" {
+		t.Fatalf("Alice text = %q", aliceSegments[0].Text)
+	}
+	if !reflect.DeepEqual(aliceSegments[0].DerivedFrom, []string{inputA + "#0", inputA + "#1", inputA + "#2"}) {
+		t.Fatalf("Alice derived_from = %v", aliceSegments[0].DerivedFrom)
+	}
+}
+
 func TestInvalidTimingFails(t *testing.T) {
 	tests := []struct {
 		name string