scripts/backfill_record_type.py

@@ -0,0 +1,150 @@
+"""
+scripts/backfill_record_type.py — fix `record_type` on legacy event
+rows whose value was hardcoded to "Waveform" regardless of actual type.
+
+Why this is needed
+──────────────────
+Pre-v0.16.1 the BW file importer (`event_file_io.read_blastware_file`)
+hardcoded `ev.record_type = "Waveform"` for every imported event.  Fixed
+in commit aac1c8e — new ingests now derive the type from the Blastware
+filename's extension last character (H=Histogram, W=Waveform, M=Manual,
+E=Event, C=Combo) per the V10.72+ MiniMate Plus AB0T filename scheme.
+
+Effect on a server that imported events under the old code: every
+events row has `record_type = "Waveform"`, even for histograms,
+manuals, etc.  Visible in terra-view's event-detail modal under the
+"Record Type" field.  Terra-view also has a client-side workaround
+that derives the type from the filename for display purposes, so
+operators see the correct type in the UI even before this backfill.
+This script makes the DB column match what the UI is already showing,
+which matters for reporting and any downstream consumer that reads
+events.record_type directly.
+
+This script
+───────────
+Walks the `events` table and updates each row's `record_type` to the
+derived value from its `blastware_filename`.  Old S338 firmware files
+(3-char extensions ending in `0`) and any unrecognized suffix get
+left at the existing value (defaults to "Waveform").
+
+Idempotent: re-running after a successful backfill finds zero rows
+needing updates and exits cleanly (it always re-derives but only
+writes when the value would change).
+
+Usage
+─────
+  # Dry-run (default): print what would change, don't touch the DB
+  python -m scripts.backfill_record_type --db bridges/captures/seismo_relay.db
+
+  # Apply the backfill
+  python -m scripts.backfill_record_type --db bridges/captures/seismo_relay.db --apply
+"""
+
+from __future__ import annotations
+
+import argparse
+import sqlite3
+import sys
+from collections import Counter
+from pathlib import Path
+
+
+# Must stay in sync with minimateplus.event_file_io._RECORD_TYPE_BY_EXT_SUFFIX.
+_TYPE_FROM_SUFFIX = {
+    "H": "Histogram",
+    "W": "Waveform",
+    "M": "Manual",
+    "E": "Event",
+    "C": "Combo",
+}
+
+
+def derive_record_type(filename: str | None, default: str = "Waveform") -> str:
+    """Mirror of minimateplus.event_file_io.derive_record_type_from_filename.
+
+    Vendored here so this script runs without needing the seismo-relay
+    package on the Python path (useful on prod where you might be
+    running it via `docker exec` against a container's DB volume).
+    """
+    if not filename:
+        return default
+    name = Path(filename).name
+    if "." not in name:
+        return default
+    ext = name.rsplit(".", 1)[1]
+    if not ext:
+        return default
+    return _TYPE_FROM_SUFFIX.get(ext[-1].upper(), default)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description=__doc__)
+    ap.add_argument("--db", required=True, help="Path to seismo_relay.db")
+    ap.add_argument("--apply", action="store_true",
+                    help="Actually write changes (default is dry-run).")
+    ap.add_argument("--default", default="Waveform",
+                    help="Fallback record_type when filename doesn't encode one. "
+                         "Default: Waveform (matches the pre-fix bug's behavior).")
+    args = ap.parse_args()
+
+    db_path = Path(args.db)
+    if not db_path.exists():
+        print(f"ERROR: database not found at {db_path}", file=sys.stderr)
+        return 1
+
+    conn = sqlite3.connect(str(db_path))
+    conn.row_factory = sqlite3.Row
+    cur = conn.cursor()
+
+    cur.execute("""
+        SELECT id, blastware_filename, record_type
+        FROM events
+        WHERE blastware_filename IS NOT NULL
+          AND blastware_filename != ''
+    """)
+    rows = cur.fetchall()
+    total = len(rows)
+    print(f"Scanning {total:,} event rows…")
+    print()
+
+    # Tally proposed changes.
+    transitions: Counter[tuple[str, str]] = Counter()
+    update_ids: list[tuple[str, str]] = []
+    unrecognized = 0
+
+    for row in rows:
+        derived = derive_record_type(row["blastware_filename"], default=args.default)
+        current = row["record_type"] or ""
+        if derived == current:
+            continue
+        transitions[(current, derived)] += 1
+        update_ids.append((row["id"], derived))
+
+    if not update_ids:
+        print("Nothing to update — all rows already match.")
+        conn.close()
+        return 0
+
+    print(f"{len(update_ids):,} row(s) need updating:")
+    for (old, new), count in sorted(transitions.items(), key=lambda x: -x[1]):
+        print(f"  {count:>6,}  {old!r:14s} → {new!r}")
+    print()
+
+    if not args.apply:
+        print("(dry-run — re-run with --apply to write changes)")
+        conn.close()
+        return 0
+
+    print("Applying changes…")
+    cur.executemany(
+        "UPDATE events SET record_type = ? WHERE id = ?",
+        [(new, eid) for eid, new in update_ids],
+    )
+    conn.commit()
+    print(f"Done. Updated {cur.rowcount:,} row(s).")
+    conn.close()
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())