feat(normalizer): person resolution context + to_canonical

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

tools/import-normalizer/documents.py

@@ -2,6 +2,8 @@
 from dataclasses import dataclass, field
 from enum import Enum, auto
 
+import dates as _dates
+
 
 class Triage(Enum):
     OK = auto()
@@ -84,3 +86,33 @@ def index_file_mismatch(index: str, file_path: str) -> bool:
     basename = file_path.replace("\\", "/").rsplit("/", 1)[-1]
     stem = basename.rsplit(".", 1)[0]
     return stem != index
+
+
+def to_canonical(raw, ctx, date_overrides: dict) -> CanonicalDocument:
+    pd = _dates.parse_date(raw.date, date_overrides)
+    flags = []
+
+    sender_id, sender_name, sender_matched, sender_multi = ctx.resolve_sender(raw.sender, raw.source_row)
+    if raw.sender.strip() and not sender_matched:
+        flags.append("unmatched_sender")
+    if sender_multi:
+        flags.append("multi_sender")
+
+    receivers = ctx.resolve_receivers(raw.receivers, raw.source_row)
+    if any(not matched for _, _, matched in receivers):
+        flags.append("unmatched_receiver")
+
+    if raw.date.strip() and pd.precision == _dates.Precision.UNKNOWN:
+        flags.append("unparsed_date")
+    if index_file_mismatch(raw.index, raw.file):
+        flags.append("index_file_mismatch")
+
+    return CanonicalDocument(
+        index=raw.index, box=raw.box, folder=raw.folder,
+        sender_person_id=sender_id, sender_name=sender_name,
+        receiver_person_ids=[r[0] for r in receivers],
+        receiver_names=[r[1] for r in receivers],
+        date_iso=pd.iso or "", date_raw=raw.date, date_precision=str(pd.precision),
+        location=raw.location, tags=[raw.tags] if raw.tags else [], summary=raw.summary,
+        source_row=raw.source_row, needs_review=flags,
+    )