fix(bib): discover_docket prefers the Proposed Rule document over a later-closing final rule (refs #615 #680)

src/bib/regulations_gov.py

@@ -898,15 +898,28 @@ def upsert_comment_status(
 def discover_docket(client: Client, docket_id: str, *, rule_cms_id: str = "") -> Docket:
     """One ``/documents`` listing → the docket's commentable document.
 
-    Picks the document that has an ``objectId`` and a ``commentEndDate``
-    (latest close date wins when several qualify). Called once per
-    docket; the result is persisted so later runs make no API call.
+    Picks the Proposed Rule that has an ``objectId`` and a
+    ``commentEndDate`` — latest close date wins among proposed rules;
+    falls back to any commentable document. Called once per docket; the
+    result is persisted so later runs make no API call.
     """
-    best: dict | None = None
+    qualifying: list[dict] = []
     for fr_doc in client.find_documents_in_docket(docket_id):
         attrs = fr_doc.get("attributes") or {}
         if not attrs.get("objectId") or not attrs.get("commentEndDate"):
             continue
+        qualifying.append(fr_doc)
+
+    proposed_rules = [
+        fr_doc
+        for fr_doc in qualifying
+        if (fr_doc.get("attributes") or {}).get("documentType") == "Proposed Rule"
+    ]
+    candidates = proposed_rules or qualifying
+
+    best: dict | None = None
+    for fr_doc in candidates:
+        attrs = fr_doc.get("attributes") or {}
         if (
             best is None
             or attrs["commentEndDate"]

tests/bib/test_walk_docket.py

@@ -66,6 +66,44 @@ def test_discover_docket_picks_commentable_doc():
     api.find_documents_in_docket.assert_called_once_with(D)
 
 
+def test_discover_docket_prefers_proposed_rule():
+    api = MagicMock()
+    api.find_documents_in_docket.return_value = [
+        {
+            "id": "CMS-2019-0111-41991",
+            "attributes": {
+                "objectId": "o-rule",
+                "commentEndDate": "2020-01-03T03:59:59Z",
+                "documentType": "Rule",
+            },
+        },
+        {
+            "id": "CMS-2019-0111-0092",
+            "attributes": {
+                "objectId": "o-nprm",
+                "commentEndDate": "2019-09-28T03:59:59Z",
+                "documentType": "Proposed Rule",
+            },
+        },
+        {
+            "id": "CMS-2019-0111-0001",
+            "attributes": {
+                "objectId": "o-display",
+                "commentEndDate": "2019-08-14T03:59:59Z",
+                "documentType": "Proposed Rule",
+            },
+        },
+    ]
+    d = discover_docket(api, "CMS-2019-0111", rule_cms_id="CMS-1738-P")
+    assert d == Docket(
+        id="CMS-2019-0111",
+        rule_cms_id="CMS-1738-P",
+        fr_document_id="CMS-2019-0111-0092",
+        fr_object_id="o-nprm",
+        comment_end_date="2019-09-28",
+    )
+
+
 def test_walk_creates_counts_and_advances_watermark():
     s = _store()
     s.docket_upsert(_docket())