feat(extract): Beschriftungen suchen, Liste auf Vollständigkeit prüfen, Prüfbilder

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tools/extract/tests/test_find_annotations.py

@@ -0,0 +1,56 @@
+import numpy as np
+from PIL import Image
+from shapely.geometry import box
+
+import find_annotations as fa
+from leonida.annotations import Annotation, AnnotationList, Keep, parse_annotations
+
+URBAN, WHITE, MAGENTA = (216, 216, 216), (248, 248, 248), (200, 0, 200)
+WATER, COAST = np.array([48, 144, 192]), np.array([0, 200, 240])
+
+
+def picture():
+    img = np.zeros((200, 300, 3), dtype=np.uint8)
+    img[:] = URBAN
+    img[40:70, 30:120] = WHITE                                   # Schriftzug
+    for left in range(40, 100, 12):
+        img[120:140, left:left + 4] = MAGENTA                    # Markerschrift, harte Kanten
+    for offset in range(80):                                     # weicher Küstenverlauf
+        weight = 1 - abs(offset - 40) / 40
+        img[:, 200 + offset] = np.round(WATER * (1 - weight) + COAST * weight).astype(np.uint8)
+    return img
+
+
+def test_scan_finds_text_and_markers_but_not_a_soft_coast_gradient():
+    spots = fa.scan(picture())
+    assert sorted(s.kind for s in spots) == ["marker", "text_white"]
+    assert all(s.cols[1] <= 200 for s in spots)
+    text = next(s for s in spots if s.kind == "text_white")
+    assert (text.rows, text.cols) == ((40, 70), (30, 120))
+    assert text.chunk == "A1"
+
+
+def test_uncovered_respects_annotation_and_keep_frames():
+    spots = fa.scan(picture())
+    text = next(s for s in spots if s.kind == "text_white")
+    marker = next(s for s in spots if s.kind == "marker")
+    covering = Annotation(1, "Text", "text_white", box(*text.centre, *text.centre).buffer(5).bounds, None)
+    keep = Keep(1, box(*marker.centre, *marker.centre).buffer(5).bounds, "echt")
+    assert fa.uncovered(spots, AnnotationList([covering], [keep])) == []
+    assert fa.uncovered(spots, AnnotationList([covering])) == [marker]
+
+
+def test_proposal_is_a_valid_list_with_padded_frames():
+    spots = fa.scan(picture())
+    parsed = parse_annotations(fa.propose_toml(spots))
+    assert [a.kind for a in parsed.annotations] == [s.kind for s in spots]
+    text = next(a for a in parsed.annotations if a.kind == "text_white")
+    assert text.box == (-980.0, 2421.0, -871.0, 2470.0)          # Pixel 30–119 / 40–69 plus 10 m Luft
+
+
+def test_review_writes_one_page_per_entry_and_an_overview(tmp_path):
+    img = picture()
+    entry = Annotation(1, "Text", "text_white", (-980.0, 2420.0, -870.0, 2470.0), None)
+    written = fa.review(img, AnnotationList([entry]), Image.fromarray(img), tmp_path)
+    assert [p.name for p in written] == ["001-Text.png"]
+    assert (tmp_path / "uebersicht.png").exists()