feat(normalizer): row extraction, triage, canonical record

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

tools/import-normalizer/tests/test_documents.py

@@ -0,0 +1,31 @@
+import documents
+from documents import Triage
+
+def test_extract_row():
+    header = {"index": 0, "file": 1, "box": 2, "folder": 3, "sender": 4,
+              "receivers": 5, "date": 6, "location": 7, "tags": 8, "summary": 9}
+    cells = ["W-0001", r"..\__scan\W-0001.pdf", "V", "1", "Walter de Gruyter",
+             "Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "Geschäftsreise"]
+    raw = documents.extract_row(cells, header, source_row=3)
+    assert raw.index == "W-0001"
+    assert raw.sender == "Walter de Gruyter"
+    assert raw.date == "15.2.1888"
+    assert raw.source_row == 3
+
+def test_triage():
+    assert documents.triage(["", "", ""]) == Triage.EMPTY
+    assert documents.triage(["", "", "Walter"]) == Triage.BLANK_INDEX  # data but no index
+    assert documents.triage(["W-0001x", "x"]) == Triage.X_SUFFIX
+    assert documents.triage(["W-0001", "x"]) == Triage.OK
+
+def test_classify_blank_index():
+    header = {"sender": 4, "receivers": 5}
+    banner = ["", "", "", "", "Brautbriefe von Walter an Eugenie", ""]
+    data = ["", "", "V", "1", "", "Eugenie"]
+    assert documents.classify_blank_index(banner, header) == "section_banner"
+    assert documents.classify_blank_index(data, header) == "data_no_index"
+
+def test_index_file_mismatch():
+    assert documents.index_file_mismatch("W-0010x", r"..\__scan\W-0011x.pdf") is True
+    assert documents.index_file_mismatch("W-0001", r"..\__scan\W-0001.pdf") is False
+    assert documents.index_file_mismatch("W-0001", "") is False