Unify trim selector projection across output schemas

2026-05-24 14:52:08 +00:00
parent 332884f887
commit e9028e08a4
2 changed files with 277 additions and 109 deletions
--- a/internal/trim/apply_test.go
+++ b/internal/trim/apply_test.go
@@ -399,6 +399,106 @@ func TestApplyMinimalDoesNotIncludeOverlapGroups(t *testing.T) {
 	}
 }

+func TestApplySelectorPolicyIsSharedAcrossSchemas(t *testing.T) {
+	type testCase struct {
+		name               string
+		opts               Options
+		wantTexts          []string
+		wantOldToNew       map[int]int
+		wantRemoved        []int
+		wantSegmentCount   int
+		wantErrorSubstring string
+	}
+
+	cases := []testCase{
+		{
+			name:             "keep preserves input order regardless of selector order",
+			opts:             Options{Mode: ModeKeep, Selector: mustParseSelector(t, "4,1,3")},
+			wantTexts:        []string{"alpha", "gamma", "delta"},
+			wantOldToNew:     map[int]int{1: 1, 3: 2, 4: 3},
+			wantRemoved:      []int{2},
+			wantSegmentCount: 3,
+		},
+		{
+			name:             "remove reports deterministic renumbering metadata",
+			opts:             Options{Mode: ModeRemove, Selector: mustParseSelector(t, "2,4")},
+			wantTexts:        []string{"alpha", "gamma"},
+			wantOldToNew:     map[int]int{1: 1, 3: 2},
+			wantRemoved:      []int{2, 4},
+			wantSegmentCount: 2,
+		},
+		{
+			name:               "missing selected id returns error",
+			opts:               Options{Mode: ModeKeep, Selector: mustParseSelector(t, "9")},
+			wantErrorSubstring: "does not exist",
+		},
+		{
+			name:               "empty selector returns error",
+			opts:               Options{Mode: ModeKeep, Selector: Selector{}},
+			wantErrorSubstring: "selector cannot be empty",
+		},
+		{
+			name:               "invalid mode returns error",
+			opts:               Options{Mode: Mode("bad"), Selector: mustParseSelector(t, "1")},
+			wantErrorSubstring: `invalid trim mode "bad"`,
+		},
+		{
+			name:               "empty output blocked when allow empty is false",
+			opts:               Options{Mode: ModeRemove, Selector: mustParseSelector(t, "1-4")},
+			wantErrorSubstring: "empty transcript",
+		},
+		{
+			name:             "empty output allowed when allow empty is true",
+			opts:             Options{Mode: ModeRemove, Selector: mustParseSelector(t, "1-4"), AllowEmpty: true},
+			wantTexts:        []string{},
+			wantOldToNew:     map[int]int{},
+			wantRemoved:      []int{1, 2, 3, 4},
+			wantSegmentCount: 0,
+		},
+	}
+
+	for _, test := range cases {
+		t.Run(test.name, func(t *testing.T) {
+			fullInput := fullTranscriptFixture()
+			intermediateInput := intermediateFixture()
+			minimalInput := minimalFixture()
+
+			fullResult, fullErr := Apply(fullInput, test.opts)
+			intermediateResult, intermediateErr := ApplyIntermediate(intermediateInput, test.opts)
+			minimalResult, minimalErr := ApplyMinimal(minimalInput, test.opts)
+
+			if test.wantErrorSubstring != "" {
+				assertErrorContains(t, fullErr, test.wantErrorSubstring)
+				assertErrorContains(t, intermediateErr, test.wantErrorSubstring)
+				assertErrorContains(t, minimalErr, test.wantErrorSubstring)
+				return
+			}
+			if fullErr != nil {
+				t.Fatalf("apply full failed: %v", fullErr)
+			}
+			if intermediateErr != nil {
+				t.Fatalf("apply intermediate failed: %v", intermediateErr)
+			}
+			if minimalErr != nil {
+				t.Fatalf("apply minimal failed: %v", minimalErr)
+			}
+
+			assertIntSlice(t, extractFullIDs(fullResult.Transcript.Segments), extractSequentialIDs(test.wantSegmentCount))
+			assertIntSlice(t, extractIntermediateIDs(intermediateResult.Transcript.Segments), extractSequentialIDs(test.wantSegmentCount))
+			assertIntSlice(t, extractMinimalIDs(minimalResult.Transcript.Segments), extractSequentialIDs(test.wantSegmentCount))
+			assertStringSlice(t, extractFullTexts(fullResult.Transcript.Segments), test.wantTexts)
+			assertStringSlice(t, extractIntermediateTexts(intermediateResult.Transcript.Segments), test.wantTexts)
+			assertStringSlice(t, extractMinimalTexts(minimalResult.Transcript.Segments), test.wantTexts)
+			assertIntMap(t, fullResult.OldToNewID, test.wantOldToNew)
+			assertIntMap(t, intermediateResult.OldToNewID, test.wantOldToNew)
+			assertIntMap(t, minimalResult.OldToNewID, test.wantOldToNew)
+			assertIntSlice(t, fullResult.RemovedIDs, test.wantRemoved)
+			assertIntSlice(t, intermediateResult.RemovedIDs, test.wantRemoved)
+			assertIntSlice(t, minimalResult.RemovedIDs, test.wantRemoved)
+		})
+	}
+}
+
 func TestApplyOutputInvariantsValidAfterRenumberAndOverlapRecompute(t *testing.T) {
 	input := overlapTranscriptFixture()
 	selector := mustParseSelector(t, "2,1")
@@ -666,3 +766,108 @@ func equalStringSlices(got []string, want []string) bool {
 	}
 	return true
 }
+
+func assertErrorContains(t *testing.T, err error, substring string) {
+	t.Helper()
+	if err == nil {
+		t.Fatalf("expected error containing %q", substring)
+	}
+	if !strings.Contains(err.Error(), substring) {
+		t.Fatalf("error %q does not contain %q", err.Error(), substring)
+	}
+}
+
+func assertStringSlice(t *testing.T, got []string, want []string) {
+	t.Helper()
+	if !equalStringSlices(got, want) {
+		t.Fatalf("slice = %v, want %v", got, want)
+	}
+}
+
+func extractSequentialIDs(count int) []int {
+	ids := make([]int, count)
+	for index := range ids {
+		ids[index] = index + 1
+	}
+	return ids
+}
+
+func extractFullIDs(segments []schema.Segment) []int {
+	ids := make([]int, len(segments))
+	for index, segment := range segments {
+		ids[index] = segment.ID
+	}
+	return ids
+}
+
+func extractIntermediateIDs(segments []schema.IntermediateSegment) []int {
+	ids := make([]int, len(segments))
+	for index, segment := range segments {
+		ids[index] = segment.ID
+	}
+	return ids
+}
+
+func extractMinimalIDs(segments []schema.MinimalSegment) []int {
+	ids := make([]int, len(segments))
+	for index, segment := range segments {
+		ids[index] = segment.ID
+	}
+	return ids
+}
+
+func extractFullTexts(segments []schema.Segment) []string {
+	texts := make([]string, len(segments))
+	for index, segment := range segments {
+		texts[index] = segment.Text
+	}
+	return texts
+}
+
+func extractIntermediateTexts(segments []schema.IntermediateSegment) []string {
+	texts := make([]string, len(segments))
+	for index, segment := range segments {
+		texts[index] = segment.Text
+	}
+	return texts
+}
+
+func extractMinimalTexts(segments []schema.MinimalSegment) []string {
+	texts := make([]string, len(segments))
+	for index, segment := range segments {
+		texts[index] = segment.Text
+	}
+	return texts
+}
+
+func intermediateFixture() schema.IntermediateTranscript {
+	return schema.IntermediateTranscript{
+		Metadata: schema.IntermediateMetadata{
+			Application:  "seriatim",
+			Version:      "v-test",
+			OutputSchema: schema.OutputSchemaIntermediate,
+		},
+		Segments: []schema.IntermediateSegment{
+			{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "alpha", Categories: []string{"word-run"}},
+			{ID: 2, Start: 2, End: 3, Speaker: "Bob", Text: "beta", Categories: []string{"filler", "backchannel"}},
+			{ID: 3, Start: 3, End: 4, Speaker: "Carol", Text: "gamma", Categories: []string{"normal"}},
+			{ID: 4, Start: 4, End: 5, Speaker: "Dan", Text: "delta", Categories: []string{"normal"}},
+		},
+	}
+}
+
+func minimalFixture() schema.MinimalTranscript {
+	return schema.MinimalTranscript{
+		Metadata: schema.MinimalMetadata{
+			Application:  "seriatim",
+			Version:      "v-test",
+			OutputSchema: schema.OutputSchemaMinimal,
+		},
+		Segments: []schema.MinimalSegment{
+			{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "alpha"},
+			{ID: 2, Start: 2, End: 3, Speaker: "Bob", Text: "beta"},
+			{ID: 3, Start: 3, End: 4, Speaker: "Carol", Text: "gamma"},
+			{ID: 4, Start: 4, End: 5, Speaker: "Dan", Text: "delta"},
+		},
+	}
+}