Aggregate coverage paper counts once per snapshot

paper_atlas/audits/coverage.py

@@ -47,6 +47,16 @@ def report(db, registry, *, pg_service=None, pg_schema=None):
             database, schema = str(Path(db).resolve()), None
         latest = _status_counts(connection, latest=True)
         observations = _status_counts(connection, latest=False)
+        # Aggregate the paper join once for the whole snapshot. Repeating it
+        # for each registry target caused repeated scans on the production DB.
+        edition_counts = {}
+        for row in connection.execute('''SELECT s.edition_id,count(s.id) AS submissions,
+                count(DISTINCT s.paper_id) AS papers,
+                count(DISTINCT CASE WHEN p.abstract IS NULL OR p.abstract='' THEN s.paper_id END)
+                    AS papers_without_abstract_text
+                FROM submissions s LEFT JOIN papers p ON p.id=s.paper_id GROUP BY s.edition_id'''):
+            entry = dict(row)
+            edition_counts[entry.pop('edition_id')] = entry
         source_counts = defaultdict(list)
         for row in connection.execute('''SELECT s.edition_id,so.name AS source,
                 count(DISTINCT sr.id) AS source_records,
@@ -63,14 +73,12 @@ def report(db, registry, *, pg_service=None, pg_schema=None):
             params = (acronym, acronym)
             editions = []
             for row in connection.execute('''SELECT e.id,v.id AS venue_id,v.acronym AS canonical_venue,
-                    e.year,e.track,count(s.id) AS submissions,count(DISTINCT s.paper_id) AS papers,
-                    count(DISTINCT CASE WHEN p.abstract IS NULL OR p.abstract='' THEN s.paper_id END)
-                        AS papers_without_abstract_text
-                    FROM editions e JOIN venues v ON v.id=e.venue_id
-                    LEFT JOIN submissions s ON s.edition_id=e.id LEFT JOIN papers p ON p.id=s.paper_id
-                    WHERE ''' + scope + ''' GROUP BY e.id,v.id,v.acronym,e.year,e.track
+                    e.year,e.track FROM editions e JOIN venues v ON v.id=e.venue_id
+                    WHERE ''' + scope + '''
                     ORDER BY e.year,e.track,v.acronym''', params):
                 edition = dict(row)
+                edition.update(edition_counts.get(row['id'], {
+                    'submissions': 0, 'papers': 0, 'papers_without_abstract_text': 0}))
                 covered_venue_ids.add(edition['venue_id'])
                 edition['latest_observed_status_counts'] = {status: latest[row['id']].get(status, 0) for status in STATUSES}
                 edition['decision_observation_counts'] = {status: observations[row['id']].get(status, 0) for status in STATUSES}

tests/test_coverage_report.py

@@ -87,5 +87,18 @@ class CoverageTests(unittest.TestCase):
             report(path, self.registry)
         self.assertFalse(path.exists())
 
+    def test_empty_editions_remain_visible_after_shared_aggregation(self):
+        self.store.conn.execute("INSERT INTO venues(acronym,name,field,venue_type) VALUES('AAAI','AAAI','general_ai','conference')")
+        venue = self.store.conn.execute("SELECT id FROM venues WHERE acronym='AAAI'").fetchone()[0]
+        self.store.conn.execute("INSERT INTO editions(venue_id,year,track) VALUES(?,2026,'main')", (venue,))
+        self.store.conn.commit()
+        aaai = report(self.db, self.registry)['venues'][1]
+        self.assertEqual(aaai['history_status'], 'no_imported_records')
+        self.assertEqual(len(aaai['editions']), 1)
+        edition = aaai['editions'][0]
+        self.assertEqual((edition['submissions'], edition['papers'], edition['papers_without_abstract_text']), (0, 0, 0))
+        self.assertEqual(sum(edition['latest_observed_status_counts'].values()), 0)
+        self.assertEqual(edition['source_record_counts'], [])
+
 
 if __name__=='__main__':unittest.main()