Add Phase 2 fixtures and compatibility tests

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"
+  }
+]