#!/usr/bin/env python3
"""Backfill events.shape_* and shape_offset_* from each event's .h5 samples. Idempotent."""
from __future__ import annotations
import argparse, logging, sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
from sfm.database import SeismoDb
from sfm.waveform_store import WaveformStore
from sfm.shape_metrics import shape_from_h5, offset_from_h5

log = logging.getLogger("backfill_event_shape")

def backfill_shape(db: SeismoDb, store: WaveformStore, *, dry_run: bool = False) -> dict:
    counts = {"updated": 0, "skipped_no_h5": 0, "skipped_no_samples": 0,
              "cleared_stale": 0}
    for row in db.query_events(limit=1_000_000):
        serial, filename = row.get("serial"), row.get("blastware_filename")
        if not serial or not filename:
            counts["skipped_no_h5"] += 1; continue
        h5_path = store.hdf5_path_for(serial, filename)
        if not h5_path.exists():
            counts["skipped_no_h5"] += 1; continue
        shape = shape_from_h5(h5_path)
        offset = offset_from_h5(h5_path)
        if shape is None:
            # The .h5 can no longer yield a shape (fewer than 2 samples, or a
            # flat trace).  Clear any previously stored value rather than
            # leaving it behind — a stale shape outlives the decode it came
            # from and silently feeds the false-trigger detector.  Seen after
            # a decoder fix shrinks an event: 493 rows in the prod snapshot
            # were carrying metrics from a superseded decode (2026-08-25).
            if (row.get("shape_crest_factor") is not None
                    or row.get("shape_offset") is not None):
                if not dry_run:
                    with db._connect() as conn:
                        conn.execute(
                            "UPDATE events SET shape_crest_factor=NULL, "
                            "shape_near_peak_count=NULL, shape_sample_count=NULL, "
                            "shape_axis=NULL, shape_offset=NULL, shape_offset_axis=NULL, "
                            "shape_offset_pre=NULL, shape_offset_spread=NULL WHERE id=?",
                            (row["id"],))
                counts["cleared_stale"] += 1
            counts["skipped_no_samples"] += 1; continue
        if not dry_run:
            with db._connect() as conn:
                conn.execute(
                    "UPDATE events SET shape_crest_factor=?, shape_near_peak_count=?, "
                    "shape_sample_count=?, shape_axis=?, shape_offset=?, "
                    "shape_offset_axis=?, shape_offset_pre=?, shape_offset_spread=? "
                    "WHERE id=?",
                    (shape["crest_factor"], shape["near_peak_count"],
                     shape["sample_count"], shape["axis"],
                     (1 if offset["offset"] else 0) if offset else None,
                     offset["axis"] if offset else None,
                     offset["pre"] if offset else None,
                     offset["spread"] if offset else None,
                     row["id"]))
        counts["updated"] += 1
    log.info("backfill_shape: %s", counts)
    return counts

def main(argv=None) -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--db-path", required=True)
    ap.add_argument("--store-root", required=True)
    ap.add_argument("--dry-run", action="store_true")
    a = ap.parse_args(argv)
    logging.basicConfig(level=logging.INFO)
    counts = backfill_shape(SeismoDb(a.db_path), WaveformStore(a.store_root), dry_run=a.dry_run)
    print(counts)
    return 0

if __name__ == "__main__":
    raise SystemExit(main())