feat(extract): Chunk-Zuordnung in Python und Beschriftungsliste lesen

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

tools/extract/tests/test_annotations_load.py

@@ -0,0 +1,88 @@
+import pytest
+
+from leonida.annotations import KINDS, AnnotationError, load_annotations, parse_annotations
+
+
+def test_missing_file_and_comment_only_file_mean_no_entries_and_no_grid(tmp_path):
+    assert load_annotations(tmp_path / "fehlt.toml").annotations == []
+    (tmp_path / "leer.toml").write_text("# nur Kommentare\n")
+    parsed = load_annotations(tmp_path / "leer.toml")
+    assert parsed.annotations == [] and parsed.keep == [] and parsed.grid is None
+
+
+def test_all_spec_kinds_are_known():
+    assert set(KINDS) == {"text_white", "text_red", "marker", "symbol", "street_name", "region"}
+
+
+def test_entries_parse_with_normalised_boxes_and_chunk_names():
+    parsed = parse_annotations("""
+[grid]
+spacing = 500
+width = 6
+
+[[annotation]]
+name = "VICE BEACH (MIAMI BEACH)"
+kind = "text_white"
+box = [[1900, 705], [1350, 870]]
+
+[[annotation]]
+name = "Rest am Marker S2/32"
+kind = "region"
+polygon = [[1905, 640], [1925, 640], [1925, 615], [1905, 615]]
+reason = "vom Nutzer markiert"
+
+[[keep]]
+box = [[-856, 194], [-794, -1]]
+reason = "knallrotes Gebäude, echt"
+""")
+    first, second = parsed.annotations
+    assert (first.index, first.kind, first.box) == (1, "text_white", (1350.0, 705.0, 1900.0, 870.0))
+    assert first.chunk == "K7"
+    assert second.polygon[0] == (1905.0, 640.0) and second.box is None and second.reason == "vom Nutzer markiert"
+    assert second.chunk == "L8"
+    assert parsed.keep[0].box == (-856.0, -1.0, -794.0, 194.0)
+    assert (parsed.grid.spacing, parsed.grid.width) == (500.0, 6.0)
+
+
+@pytest.mark.parametrize("body, message", [
+    ('name = "X"\nkind = "banner"\nbox = [[0, 0], [10, 10]]', "unbekanntes kind 'banner'"),
+    ('kind = "marker"\nbox = [[0, 0], [10, 10]]', "Feld 'name' fehlt oder ist leer"),
+    ('name = "X"\nkind = "marker"\nbox = [[0, 0], [10, 10]]\nhight = 3', "Feld 'hight' gibt es nicht"),
+    ('name = "X"\nkind = "marker"', "Feld 'box' fehlt"),
+    ('name = "X"\nkind = "marker"\nbox = [1, 2]', "Feld 'box' muss zwei Ecken"),
+    ('name = "X"\nkind = "marker"\nbox = [[0, 0], [1, 5]]', "mindestens 2 m"),
+    ('name = "X"\nkind = "marker"\nbox = [[1900, 0], [2100, 50]]', "außerhalb des Ausschnitts"),
+    ('name = "X"\nkind = "marker"\npolygon = [[0, 0], [10, 0], [10, 10]]', "Feld 'polygon' gibt es nur bei region"),
+    ('name = "X"\nkind = "region"\nbox = [[0, 0], [10, 10]]\npolygon = [[0, 0], [10, 0], [10, 10]]', "genau eines der Felder"),
+    ('name = "X"\nkind = "region"\npolygon = [[0, 0], [10, 10], [10, 0], [0, 10]]', "ohne sich schneidende Kanten"),
+    ('name = "X"\nkind = "region"\npolygon = [[0, 0], [10, 10]]', "mindestens 3 Punkte"),
+    ('name = "X"\nkind = "marker"\nbox = [[0, 0], [10, 10]]\nreason = 7', "reason muss Text sein"),
+])
+def test_form_errors_stop_with_entry_number_and_field(body, message):
+    text = ('[[annotation]]\nname = "OK"\nkind = "marker"\nbox = [[0, 0], [10, 10]]\n\n'
+            f'[[annotation]]\n{body}\n')
+    with pytest.raises(AnnotationError, match="Beschriftung 2") as err:
+        parse_annotations(text)
+    assert message in str(err.value)
+
+
+def test_keep_needs_a_reason():
+    with pytest.raises(AnnotationError, match="Ausnahme 1: Feld 'reason' fehlt oder ist leer"):
+        parse_annotations("[[keep]]\nbox = [[0, 0], [10, 10]]\n")
+
+
+@pytest.mark.parametrize("body, message", [
+    ("spacing = 0\nwidth = 6", "Gitternetz: Feld 'spacing' muss eine Zahl größer als 0 sein"),
+    ("spacing = 500", "Gitternetz: Feld 'width' fehlt"),
+    ("spacing = 500\nwidth = 6\ncolour = 1", "Gitternetz: Feld 'colour' gibt es nicht"),
+])
+def test_grid_form_errors(body, message):
+    with pytest.raises(AnnotationError, match=message):
+        parse_annotations(f"[grid]\n{body}\n")
+
+
+def test_broken_toml_and_unknown_sections_are_form_errors():
+    with pytest.raises(AnnotationError, match="kein gültiges TOML"):
+        parse_annotations("[[annotation]\n")
+    with pytest.raises(AnnotationError, match="unbekannter Abschnitt 'label'"):
+        parse_annotations('[[label]]\nname = "X"\n')