Add Phase 2 fixtures and compatibility tests

internal/core/normalization/normalize_test.go

@@ -271,15 +271,417 @@ func TestNormalizationCategoryPreservation(t *testing.T) {
 	}
 }
 
-func TestNormalizationSummaryCounts(t *testing.T) {
+func TestNormalizationGoldenBareArrayTranscript(t *testing.T) {
 	config := NormalizationConfig{
-		MaxSegmentGap:      2.0,
-		EllipsisGap:        1.0,
-		MaxSegmentDuration: 60.0,
-		MaxSegmentTokens:   100,
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
 	}
 	normalizer := NewNormalizer(config)
 
+	raw, err := os.ReadFile("testdata/bare_array_transcript.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/bare_array_transcript.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenObjectWithSegmentsTranscript(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/object_with_segments_transcript.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/object_with_segments_transcript.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenTranscriptWithCategories(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/transcript_with_categories.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/transcript_with_categories.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenTranscriptWithOriginalIDs(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/transcript_with_original_ids.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/transcript_with_original_ids.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenSameSpeakerMerge(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/transcript_same_speaker_merge.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/transcript_same_speaker_merge.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenEllipsisMerge(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/transcript_ellipsis_merge.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/transcript_ellipsis_merge.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func TestNormalizationGoldenDifferentSpeakersNoMerge(t *testing.T) {
+	config := NormalizationConfig{
+		MaxSegmentGap:        2.0,
+		EllipsisGap:          1.0,
+		MaxSegmentDuration:   60.0,
+		MaxSegmentTokens:     100,
+	}
+	normalizer := NewNormalizer(config)
+
+	raw, err := os.ReadFile("testdata/transcript_different_speakers_no_merge.json")
+	if err != nil {
+		t.Fatalf("failed to read test fixture: %v", err)
+	}
+
+	transcript, err := schema.ParseSourceTranscriptJSON(raw)
+	if err != nil {
+		t.Fatalf("failed to parse source transcript: %v", err)
+	}
+
+	converted := &schema.Transcript{
+		Segments: make([]schema.Segment, len(transcript.Segments)),
+	}
+	for i, s := range transcript.Segments {
+		id := i + 1
+		if s.ID != nil {
+			id = *s.ID
+		}
+		converted.Segments[i] = schema.Segment{
+			ID:         id,
+			Speaker:    s.Speaker,
+			Start:      s.Start,
+			End:        s.End,
+			Text:       s.Text,
+			Categories: s.Categories,
+		}
+	}
+
+	normalized, _ := normalizer.Normalize(converted)
+
+	// Compare with golden output semantically
+	expectedRaw, err := os.ReadFile("testdata/transcript_different_speakers_no_merge.golden.json")
+	if err != nil {
+		t.Fatalf("failed to read golden fixture: %v", err)
+	}
+
+	var expectedTranscript schema.Transcript
+	if err := schema.ParseTranscriptJSON(expectedRaw); err != nil {
+		t.Fatalf("failed to parse golden transcript: %v", err)
+	}
+
+	assertTranscriptsEqual(t, normalized, &expectedTranscript)
+}
+
+func assertTranscriptsEqual(t *testing.T, actual, expected *schema.Transcript) {
+	t.Helper()
+
+	if len(actual.Segments) != len(expected.Segments) {
+		t.Errorf("segment count mismatch: expected %d, got %d", len(expected.Segments), len(actual.Segments))
+		return
+	}
+
+	for i := range actual.Segments {
+		a := actual.Segments[i]
+		e := expected.Segments[i]
+
+		if a.ID != e.ID {
+			t.Errorf("segment %d: ID mismatch: expected %d, got %d", i, e.ID, a.ID)
+		}
+		if a.Speaker != e.Speaker {
+			t.Errorf("segment %d: speaker mismatch: expected %q, got %q", i, e.Speaker, a.Speaker)
+		}
+		if a.Start != e.Start {
+			t.Errorf("segment %d: start mismatch: expected %f, got %f", i, e.Start, a.Start)
+		}
+		if a.End != e.End {
+			t.Errorf("segment %d: end mismatch: expected %f, got %f", i, e.End, a.End)
+		}
+		if a.Text != e.Text {
+			t.Errorf("segment %d: text mismatch: expected %q, got %q", i, e.Text, a.Text)
+		}
+		if len(a.Categories) != len(e.Categories) {
+			t.Errorf("segment %d: categories count mismatch: expected %d, got %d", i, len(e.Categories), len(a.Categories))
+			continue
+		}
+		for j, cat := range a.Categories {
+			if j >= len(e.Categories) || cat != e.Categories[j] {
+				t.Errorf("segment %d: category %d mismatch: expected %q, got %q", i, j, e.Categories[j], cat)
+			}
+		}
+	}
+}
+	normalizer := NewNormalizer(config)
+
 	transcript := &schema.Transcript{
 		Segments: []schema.Segment{
 			{ID: 1, Speaker: "Alice", Start: 0.0, End: 1.0, Text: "Hello"},

internal/core/normalization/testdata/bare_array_transcript.golden.json

@@ -0,0 +1,19 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.5,
+    "text": "Hello world."
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 2.0,
+    "end": 3.5,
+    "text": "Hi there.",
+    "categories": [
+      "greeting"
+    ]
+  }
+]

internal/core/normalization/testdata/bare_array_transcript.json

@@ -0,0 +1,17 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.5,
+    "text": "Hello world."
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 2.0,
+    "end": 3.5,
+    "text": "Hi there.",
+    "categories": ["greeting"]
+  }
+]

internal/core/normalization/testdata/comprehensive_glossary.yaml

@@ -0,0 +1,19 @@
+glossary:
+  - name: Jesters
+    category: faction
+    summary: A faction name.
+    aliases:
+      - Jester
+      - Jest
+  - name: Popov
+    category: character
+    summary: A character name.
+    aliases:
+      - Hrank
+      - Pop
+  - name: Audita
+    category: system
+    summary: The transcript polishing system.
+    aliases:
+      - Audit
+      - Auditor

internal/core/normalization/testdata/object_with_segments_transcript.golden.json

@@ -0,0 +1,19 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.5,
+    "text": "Hello world."
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 2.0,
+    "end": 3.5,
+    "text": "Hi there.",
+    "categories": [
+      "greeting"
+    ]
+  }
+]

internal/core/normalization/testdata/object_with_segments_transcript.json

@@ -0,0 +1,19 @@
+{
+  "segments": [
+    {
+      "id": 1,
+      "speaker": "Alice",
+      "start": 0.0,
+      "end": 1.5,
+      "text": "Hello world."
+    },
+    {
+      "id": 2,
+      "speaker": "Bob",
+      "start": 2.0,
+      "end": 3.5,
+      "text": "Hi there.",
+      "categories": ["greeting"]
+    }
+  ]
+}

internal/core/normalization/testdata/transcript_different_speakers_no_merge.golden.json

@@ -0,0 +1,16 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello"
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 1.5,
+    "end": 2.5,
+    "text": "Hi"
+  }
+]

internal/core/normalization/testdata/transcript_different_speakers_no_merge.json

@@ -0,0 +1,16 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello"
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 1.5,
+    "end": 2.5,
+    "text": "Hi"
+  }
+]

internal/core/normalization/testdata/transcript_ellipsis_merge.golden.json

@@ -0,0 +1,9 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 3.0,
+    "text": "Hello... world"
+  }
+]

internal/core/normalization/testdata/transcript_ellipsis_merge.json

@@ -0,0 +1,16 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello"
+  },
+  {
+    "id": 2,
+    "speaker": "Alice",
+    "start": 2.0,
+    "end": 3.0,
+    "text": "world"
+  }
+]

internal/core/normalization/testdata/transcript_same_speaker_merge.golden.json

@@ -0,0 +1,9 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 2.5,
+    "text": "Hello world"
+  }
+]

internal/core/normalization/testdata/transcript_same_speaker_merge.json

@@ -0,0 +1,16 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello"
+  },
+  {
+    "id": 2,
+    "speaker": "Alice",
+    "start": 1.2,
+    "end": 2.2,
+    "text": "world"
+  }
+]

internal/core/normalization/testdata/transcript_with_categories.golden.json

@@ -0,0 +1,24 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello world.",
+    "categories": [
+      "greeting",
+      "opening"
+    ]
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 2.0,
+    "end": 3.0,
+    "text": "Hi there.",
+    "categories": [
+      "response",
+      "opening"
+    ]
+  }
+]

internal/core/normalization/testdata/transcript_with_categories.json

@@ -0,0 +1,18 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello world.",
+    "categories": ["greeting", "opening"]
+  },
+  {
+    "id": 2,
+    "speaker": "Bob",
+    "start": 2.0,
+    "end": 3.0,
+    "text": "Hi there.",
+    "categories": ["response", "opening"]
+  }
+]

internal/core/normalization/testdata/transcript_with_original_ids.golden.json

@@ -0,0 +1,9 @@
+[
+  {
+    "id": 1,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 2.5,
+    "text": "Hello world"
+  }
+]

internal/core/normalization/testdata/transcript_with_original_ids.json

@@ -0,0 +1,16 @@
+[
+  {
+    "id": 10,
+    "speaker": "Alice",
+    "start": 0.0,
+    "end": 1.0,
+    "text": "Hello"
+  },
+  {
+    "id": 25,
+    "speaker": "Alice",
+    "start": 1.5,
+    "end": 2.5,
+    "text": "world"
+  }
+]