feat(extract): Beschriftungsmasken, Gitternetz und Entfernen mit Bericht

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

tools/extract/tests/test_annotations_remove.py

@@ -0,0 +1,172 @@
+import numpy as np
+from shapely.geometry import box
+
+from leonida.annotations import (Annotation, AnnotationList, Grid, annotation_mask, candidates, grid_mask,
+                                 mark_generated, remove_annotations)
+from leonida.classify import CLASSES, classify
+
+PARK, ROAD, URBAN = (192, 216, 128), (80, 80, 80), (216, 216, 216)
+WHITE, OUTLINE = (248, 248, 248), (80, 88, 96)
+
+
+def picture(h=200, w=300, colour=URBAN):
+    img = np.zeros((h, w, 3), dtype=np.uint8)
+    img[:] = colour
+    return img
+
+
+def entry(kind, rows, cols, index=1, name="Test"):
+    """Eintrag, dessen Rahmen genau die Pixelzeilen rows und -spalten cols umfasst (halboffen)."""
+    (r0, r1), (c0, c1) = rows, cols
+    return Annotation(index, name, kind, (-1000.0 + c0, 2500.0 - (r1 - 1), -1000.0 + c1 - 1, 2500.0 - r0), None)
+
+
+def letter(img, rows, cols, outline=3):
+    (r0, r1), (c0, c1) = rows, cols
+    img[r0 - outline:r1 + outline, c0 - outline:c1 + outline] = OUTLINE
+    img[r0:r1, c0:c1] = WHITE
+
+
+def test_candidates_follow_the_colour_rules():
+    colours = {"white": WHITE, "urban": URBAN, "red": (248, 112, 112), "speculative": (160, 72, 72),
+               "magenta": (200, 0, 200), "black": (20, 20, 20), "water": (48, 144, 192), "road": ROAD,
+               "park": PARK, "light": (230, 230, 230), "building": (176, 176, 176)}
+    img = np.array([list(colours.values())], dtype=np.uint8)
+    names = list(colours)
+
+    def hits(kind):
+        return {name for name, hit in zip(names, candidates(img, kind)[0]) if hit}
+
+    assert hits("text_white") == {"white"}
+    assert hits("text_red") == {"red"}
+    assert hits("marker") == {"magenta", "black"}
+    assert hits("symbol") == {"white", "magenta", "black"}
+    assert hits("street_name") == {"white", "urban", "light"}
+
+
+def test_white_text_is_masked_together_with_its_outline():
+    img = picture(colour=PARK)
+    img[:, 140:160] = ROAD
+    letter(img, (80, 120), (120, 180))
+    found = annotation_mask(img, entry("text_white", (60, 141), (100, 201)))
+    mask = np.zeros(img.shape[:2], dtype=bool)
+    mask[found.rows, found.cols] = found.mask
+    assert found.applied and found.warning is None
+    assert mask[77:123, 117:183].all()                      # Füllung und Kontur
+    assert not mask[80:120, 107].any()                      # 10 m neben der Kontur ist wieder Karte
+
+
+def test_text_filling_most_of_its_frame_after_growing_is_not_overfull():
+    img = picture()
+    for left in range(60, 240, 30):
+        letter(img, (60, 140), (left, left + 12))           # sechs Buchstabenstriche, Rahmen mit 10 m Luft
+    found = annotation_mask(img, entry("text_white", (47, 154), (47, 244)))
+    assert found.mask.mean() > 0.6
+    assert found.applied and found.warning is None
+
+
+def test_street_names_do_not_warn_about_urban_ground_at_the_frame_edge():
+    img = picture()
+    img[:, 140:160] = ROAD
+    img[80:120, 146:150] = WHITE                            # helle Schrift auf der Fahrbahn
+    found = annotation_mask(img, entry("street_name", (70, 131), (130, 171)))
+    assert found.applied and found.warning is None
+    assert found.mask[20, 17] and not found.mask[20, 2]
+
+
+def test_colour_touching_the_frame_edge_stays_and_is_reported():
+    img = picture()
+    letter(img, (80, 120), (60, 90))
+    letter(img, (80, 120), (180, 240))                      # ragt über den rechten Rahmenrand
+    found = annotation_mask(img, entry("text_white", (60, 141), (40, 211)))
+    assert found.applied
+    assert found.warning == "angeschnitten: Rahmen prüfen"
+    assert found.mask[30, 35]                               # Buchstabe innen
+    assert not found.mask[30, 160]                          # Buchstabe am Rand bleibt
+
+
+def test_letter_counters_are_filled_but_large_enclosed_areas_stay():
+    img = picture(420, 420)
+    img[20:80, 20:80] = WHITE
+    img[41:59, 41:59] = URBAN                               # 18 x 18 m großes „O"-Innere
+    img[150:290, 150:290] = WHITE
+    img[195:245, 195:245] = URBAN                           # 50 x 50 m: echte Fläche
+    small = annotation_mask(img, entry("text_white", (0, 130), (0, 130)))
+    large = annotation_mask(img, entry("text_white", (110, 331), (110, 331)))
+    assert small.applied and large.applied
+    assert small.mask[50, 50]
+    assert not large.mask[220 - 110, 220 - 110]
+
+
+def test_region_masks_exactly_its_polygon():
+    img = picture()
+    triangle = ((-950.0, 2450.0), (-850.0, 2450.0), (-950.0, 2350.0))
+    found = annotation_mask(img, Annotation(1, "Rest", "region", None, triangle))
+    assert found.applied
+    assert abs(int(found.mask.sum()) - 5000) <= 200
+    mask = np.zeros(img.shape[:2], dtype=bool)
+    mask[found.rows, found.cols] = found.mask
+    assert mask[60, 60] and not mask[140, 140]
+
+
+def test_empty_and_overfull_frames_are_skipped_with_a_warning():
+    park = annotation_mask(picture(colour=PARK), entry("text_white", (50, 100), (50, 100)))
+    assert not park.applied and park.warning == "leer: keine Pixel der Art text_white im Rahmen"
+    img = picture()
+    img[52:98, 52:98] = WHITE
+    full = annotation_mask(img, entry("text_white", (50, 100), (50, 100)))
+    assert not full.applied and full.warning.startswith("randvoll: Farbpixel füllen")
+
+
+def test_grid_mask_puts_a_stripe_on_every_line():
+    mask, lines = grid_mask((30, 30), Grid(10, 2))
+    assert lines == 8
+    for index in (0, 9, 10, 19, 20, 29):
+        assert mask[:, index].all() and mask[index, :].all()
+    assert not mask[5, 5] and not mask[15, 25]
+
+
+def test_removal_without_entries_changes_nothing():
+    labels = classify(picture())
+    removal = remove_annotations(picture(), labels, AnnotationList())
+    assert (removal.labels == labels).all() and removal.generated == []
+    assert removal.report() == "Beschriftungen: 0 angewendet, 0 übersprungen · Gitternetz: 0 Linien"
+
+
+def test_removal_rebuilds_a_road_under_white_text():
+    img = picture()
+    img[:, 140:160] = ROAD
+    letter(img, (80, 120), (60, 240))
+    removal = remove_annotations(img, classify(img), AnnotationList([entry("text_white", (60, 141), (40, 261))]))
+    assert (removal.labels[80:120, 141:159] == CLASSES["strasse"]).all()
+    assert not (removal.labels[80:120, 60:137] == CLASSES["strasse"]).any()
+    report = removal.report()
+    assert "#1 Test · A1 · Maske" in report and "Straßen 1 verbunden" in report
+
+
+def test_the_grid_is_closed_before_anything_is_rebuilt():
+    img = picture()
+    img[:, 98:102] = (140, 140, 140)                        # abgedunkelte Gitterlinie über Stadtfläche
+    labels = classify(img)
+    assert (labels[:, 99] == CLASSES["gebaeude"]).all()
+    removal = remove_annotations(img, labels, AnnotationList(grid=Grid(100, 6)))
+    assert (removal.labels == CLASSES["stadt"]).all()
+    assert removal.grid_lines == 7                          # Spalten 0, 100, 200, 300 und Zeilen 0, 100, 200
+
+
+def test_entries_sharing_one_mask_are_reported_together():
+    img = picture()
+    img[:, 140:160] = ROAD
+    letter(img, (80, 120), (60, 150))
+    letter(img, (80, 120), (155, 240))
+    first = entry("text_white", (60, 141), (40, 153), index=1, name="Links")
+    second = entry("text_white", (60, 141), (152, 261), index=2, name="Rechts")
+    report = remove_annotations(img, classify(img), AnnotationList([first, second])).report()
+    assert "#2 Rechts · A1 · Maske" in report and "gemeinsam mit #1" in report
+
+
+def test_buildings_mostly_inside_added_rectangles_are_marked():
+    heights = [{"height": 9.0, "source": "district"}, {"height": 12.0, "source": "district"}]
+    marked = mark_generated([box(1, 1, 9, 9), box(6, 0, 16, 10)], heights, [box(0, 0, 10, 10)])
+    assert marked == 1
+    assert [h["source"] for h in heights] == ["annotation", "district"]