feat(normalizer): orchestrator + end-to-end integration test

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

tools/import-normalizer/tests/test_normalize.py

@@ -0,0 +1,59 @@
+import openpyxl
+import normalize
+
+
+def _doc_wb(tmp_path):
+    wb = openpyxl.Workbook(); ws = wb.active; ws.title = "Familienarchiv"
+    ws.append(["Index", "Datei", "Box", "Mappe", "BriefeschreiberIn", "EmpfängerIn",
+               "Datum des Briefes", "Ort", "Schlagwort", "Inhalt"])
+    ws.append(["W-0001", r"..\__scan\W-0001.pdf", "V", "1", "Walter de Gruyter",
+               "Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "Geschäftsreise"])
+    ws.append(["W-0001x", r"..\__scan\W-0001x.pdf", "", "", "Walter de Gruyter", "Eugenie Müller", "", "", "", ""])
+    ws.append(["", "", "", "", "Section banner row", "", "", "", "", ""])
+    ws.append(["C-0001", "", "", "", "Hans Wittkopf", "", "Freitag 1919", "", "", ""])
+    ws.append(["W-0001", r"..\__scan\W-0001.pdf", "V", "1", "Walter de Gruyter",
+               "Eugenie Müller", "15.2.1888", "Rotterdam", "Brautbriefe", "dup"])
+    p = tmp_path / "docs.xlsx"; wb.save(p); return p
+
+
+def _person_wb(tmp_path):
+    wb = openpyxl.Workbook(); ws = wb.active; ws.title = "Tabelle1"
+    ws.append(["Generation", "Familienname", "Vorname", "geb als", "Geburtsdatum",
+               "Geburtsort", "Todesdatum", "Sterbeort", "verheiratet mit", "Bemerkung"])
+    ws.append(["G 1", "de Gruyter", "Walter", "", "", "", "", "", "", ""])
+    ws.append(["G 1", "de Gruyter", "Eugenie", "Müller", "", "", "", "", "", ""])
+    p = tmp_path / "persons.xlsx"; wb.save(p); return p
+
+
+def test_run_end_to_end(tmp_path):
+    out_dir = tmp_path / "out"; review_dir = tmp_path / "review"
+    stats = normalize.run(
+        document_workbook=_doc_wb(tmp_path), document_sheet="Familienarchiv",
+        person_workbook=_person_wb(tmp_path), person_sheet="Tabelle1",
+        out_dir=out_dir, review_dir=review_dir,
+        date_overrides={}, name_overrides={})
+    assert (out_dir / "canonical-documents.xlsx").exists()
+    assert (out_dir / "canonical-persons.xlsx").exists()
+    assert stats["documents_emitted"] == 3        # W-0001, C-0001, W-0001 (dup) — x and blank excluded
+    assert stats["skipped_x_suffix"] == 1
+    assert stats["blank_index_rows"] == 1
+    assert stats["duplicate_index_rows"] == 2
+    assert (review_dir / "skipped-x-suffix.csv").exists()
+    assert (review_dir / "unparsed-dates.csv").exists()
+    # C-0001's "Freitag 1919" is unparseable -> must appear in the review file (NFR-DATA-01)
+    assert "Freitag 1919" in (review_dir / "unparsed-dates.csv").read_text(encoding="utf-8")
+
+    # determinism (NFR-IDEM-01): a second run yields identical canonical content + review files
+    def _matrix(p):
+        wb = openpyxl.load_workbook(p)
+        return [[c.value for c in row] for row in wb.active.iter_rows()]
+    docs1 = _matrix(out_dir / "canonical-documents.xlsx")
+    persons1 = _matrix(out_dir / "canonical-persons.xlsx")
+    unparsed1 = (review_dir / "unparsed-dates.csv").read_text(encoding="utf-8")
+    normalize.run(document_workbook=_doc_wb(tmp_path), document_sheet="Familienarchiv",
+                  person_workbook=_person_wb(tmp_path), person_sheet="Tabelle1",
+                  out_dir=out_dir, review_dir=review_dir, date_overrides={}, name_overrides={})
+    assert _matrix(out_dir / "canonical-documents.xlsx") == docs1
+    assert _matrix(out_dir / "canonical-persons.xlsx") == persons1
+    assert (review_dir / "unparsed-dates.csv").read_text(encoding="utf-8") == unparsed1
+    assert len(docs1) == 4  # header + 3 docs