Move python implementation under python/ in preparation for the upcoming Go rewrite

python/tests/test_new_transcript_schema.py

@@ -0,0 +1,84 @@
+import json
+
+from audita.core.schemas import parse_source_transcript_json, parse_transcript_json, transcript_to_json
+
+
+SERIATIM_TRANSCRIPT = """
+{
+  "metadata": {
+    "application": "seriatim",
+    "version": "dev",
+    "input_reader": "json-files",
+    "input_files": ["eric.json", "mike.json"],
+    "preprocessing_modules": ["validate-raw", "normalize-speakers", "trim-text"],
+    "postprocessing_modules": ["detect-overlaps", "resolve-overlaps", "backchannel"],
+    "output_modules": ["json"]
+  },
+  "segments": [
+    {
+      "id": 1,
+      "source": "eric.json",
+      "source_segment_index": 0,
+      "speaker": "Eric Rakestraw",
+      "start": 1.25,
+      "end": 3.5,
+      "text": "Hello there.",
+      "overlap_group_id": 1
+    },
+    {
+      "id": 2,
+      "source": "eric.json",
+      "source_ref": "word-run:1:1:1",
+      "derived_from": ["eric.json#0"],
+      "speaker": "Eric Rakestraw",
+      "start": 4.0,
+      "end": 4.5,
+      "text": "Resolved word run",
+      "categories": ["backchannel"]
+    }
+  ],
+  "overlap_groups": [
+    {
+      "id": 1,
+      "start": 1.25,
+      "end": 4.0,
+      "segments": ["eric.json#0", "mike.json#0"],
+      "speakers": ["Eric Rakestraw", "Mike Brown"],
+      "class": "unknown",
+      "resolution": "unresolved"
+    }
+  ]
+}
+"""
+
+
+def test_parse_source_transcript_json_accepts_seriatim_transcript_object():
+    segments = parse_source_transcript_json(SERIATIM_TRANSCRIPT)
+
+    assert len(segments) == 2
+    assert segments[0].id == 1
+    assert segments[0].speaker == "Eric Rakestraw"
+    assert segments[0].start == 1.25
+    assert segments[0].end == 3.5
+    assert segments[0].text == "Hello there."
+    assert segments[1].text == "Resolved word run"
+    assert segments[0].categories is None
+    assert segments[1].categories == ["backchannel"]
+
+
+def test_parse_transcript_json_accepts_seriatim_transcript_object_and_ignores_unused_fields():
+    segments = parse_transcript_json(SERIATIM_TRANSCRIPT)
+
+    assert [segment.id for segment in segments] == [1, 2]
+    assert [segment.text for segment in segments] == ["Hello there.", "Resolved word run"]
+    assert segments[0].categories is None
+    assert segments[1].categories == ["backchannel"]
+
+
+def test_transcript_to_json_emits_categories_only_when_present():
+    segments = parse_transcript_json(SERIATIM_TRANSCRIPT)
+
+    payload = json.loads(transcript_to_json(segments))
+
+    assert "categories" not in payload[0]
+    assert payload[1]["categories"] == ["backchannel"]