infra/reingest_canonical_ids.sh

@@ -58,6 +58,35 @@ run_sql "SELECT count(*) AS papers, count(*) FILTER (WHERE starts_with(id, 'http
 echo "   sample ids:"
 run_sql "SELECT id FROM papers ORDER BY added_at LIMIT 3"
 
+# ── 2b. Preflight: verify the schema is re-ingestable BEFORE wiping anything ──
+# ingest writes chunks.section (F-16). On a live DB that predates it the column
+# is missing, and the app user cannot ALTER tables owned by 'postgres' (audit
+# M-1). Check FIRST so we never TRUNCATE and then fail mid-re-ingest.
+echo "── Preflight: schema readiness ───────────────────────────────"
+SECTION_OK="$("$PY" - <<'PYEOF'
+import os, psycopg
+try:
+    with psycopg.connect(os.environ["DATABASE_URL"], connect_timeout=10) as c:
+        cols = [r[0] for r in c.execute(
+            "SELECT column_name FROM information_schema.columns WHERE table_name='chunks'").fetchall()]
+        print("yes" if "section" in cols else "no")
+except Exception:
+    print("error")
+PYEOF
+)"
+if [[ "$SECTION_OK" != "yes" ]]; then
+  echo "ABORT — schema not ready: chunks.section is missing (audit M-1)."
+  echo "The app user cannot add it (chunks is owned by 'postgres'). Apply it as"
+  echo "the table owner, then re-run this script:"
+  echo ""
+  echo "    ssh alfred@192.168.178.103 \\"
+  echo "      \"sudo -u postgres psql -d papers -c \\\\\"ALTER TABLE chunks ADD COLUMN IF NOT EXISTS section TEXT;\\\\\"\""
+  echo ""
+  echo "Nothing was changed — no TRUNCATE was issued."
+  exit 1
+fi
+echo "   chunks.section present — schema OK."
+
 # ── 3. Confirmation gate (destructive) ───────────────────────────────────────
 echo ""
 echo "This TRUNCATEs papers CASCADE (papers/chunks/citations/formulas/figures/"