feat(normalizer): overrides loader + xlsx/csv writers

Recovered from an entangled commit: these files were correct but had been
bundled into an unrelated reader-dashboard commit by a concurrent session.

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

tools/import-normalizer/writers.py

@@ -0,0 +1,73 @@
+"""Write canonical .xlsx outputs and review .csv files."""
+import csv
+import datetime
+from pathlib import Path
+import openpyxl
+
+_PIPE = "|"
+# Pinned workbook metadata so reruns are content-deterministic (NFR-IDEM-01); openpyxl
+# otherwise stamps docProps with the current time on every save.
+_FIXED_TS = datetime.datetime(2020, 1, 1, 0, 0, 0)
+
+
+def _join(value):
+    if isinstance(value, list):
+        return _PIPE.join(str(v) for v in value)
+    return "" if value is None else str(value)
+
+
+def _csv_safe(value):
+    """Neutralise spreadsheet formula injection (CWE-1236) in human-opened review CSVs."""
+    s = "" if value is None else str(value)
+    return "'" + s if s[:1] in ("=", "+", "-", "@", "\t", "\r") else s
+
+
+DOC_COLUMNS = ["index", "box", "folder", "sender_person_id", "sender_name",
+               "receiver_person_ids", "receiver_names", "date_iso", "date_raw",
+               "date_precision", "location", "tags", "summary", "source_row", "needs_review"]
+
+PERSON_COLUMNS = ["person_id", "last_name", "first_name", "maiden_name", "title", "nickname",
+                  "birth_date", "birth_date_raw", "birth_place", "death_date", "death_date_raw",
+                  "death_place", "spouse", "generation", "notes", "aliases", "provisional"]
+
+
+def _write_xlsx(records, columns, path: Path):
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.append(columns)
+    for rec in records:
+        ws.append([_join(getattr(rec, col)) for col in columns])
+    wb.properties.created = _FIXED_TS
+    wb.properties.modified = _FIXED_TS
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    wb.save(path)
+
+
+def write_documents_xlsx(docs, path: Path):
+    _write_xlsx(docs, DOC_COLUMNS, path)
+
+
+def write_persons_xlsx(people, path: Path):
+    _write_xlsx(people, PERSON_COLUMNS, path)
+
+
+def write_review_csv(path: Path, header: list[str], rows: list[list]):
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    with open(path, "w", encoding="utf-8", newline="") as f:
+        w = csv.writer(f)
+        w.writerow(header)
+        for row in rows:
+            w.writerow([_csv_safe(c) for c in row])
+
+
+def write_summary(path: Path, stats: dict):
+    """Render a grouped, scannable summary. Keys beginning with '#' are section headers."""
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    lines = []
+    for k, v in stats.items():
+        if k.startswith("#"):
+            lines.append("")
+            lines.append(k[1:].strip() + ":")
+        else:
+            lines.append(f"  {k}: {v}")
+    Path(path).write_text("\n".join(lines).strip() + "\n", encoding="utf-8")