Add reproducible grayscale detector corpus

backend/tests/test_grayscale_yolo_dataset.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+from PIL import Image
+
+
+SCRIPT = Path(__file__).parents[2] / "scripts" / "build_grayscale_yolo_dataset.py"
+
+
+def test_grayscale_builder_preserves_labels_and_split(tmp_path: Path) -> None:
+    source = tmp_path / "source"
+    (source / "images" / "train").mkdir(parents=True)
+    (source / "labels" / "train").mkdir(parents=True)
+    image = source / "images" / "train" / "tile.png"
+    label = source / "labels" / "train" / "tile.txt"
+    Image.new("RGB", (8, 8), (255, 0, 0)).save(image)
+    label.write_text("0 0.5 0.5 0.5 0.5\n", encoding="utf-8")
+    summary = source / "yolo_tile_dataset_summary.json"
+    summary.write_text(
+        json.dumps(
+            {
+                "tiles": [
+                    {
+                        "split": "train",
+                        "image_path": str(image),
+                        "label_path": str(label),
+                    }
+                ]
+            }
+        ),
+        encoding="utf-8",
+    )
+    output = tmp_path / "gray"
+    subprocess.run(
+        [sys.executable, str(SCRIPT), "--summary", str(summary), "--output-dir", str(output)],
+        check=True,
+    )
+    converted = Image.open(output / "images" / "train" / "tile.png")
+    r, g, b = converted.getpixel((0, 0))
+    assert r == g == b
+    assert (output / "labels" / "train" / "tile.txt").read_text() == label.read_text()
+    evidence = json.loads((output / "grayscale-dataset-evidence.json").read_text())
+    assert evidence["converted_tile_count"] == 1