feat: backfill hii_waterlevel from the HII waterlevel_graph archive

scripts/backfill_hii_waterlevel.py walks the api-v3 waterlevel_graph
endpoint (hourly wl_msl + discharge, archive back to ~2019) in full-year
windows per station and upserts into hii_waterlevel. Defaults to the
RID-mirror and key stations; --stations/--all/--start/--end/--chunk-days
override. History upserts touch only wl_msl and discharge so colliding
live-snapshot rows keep storage_percent/situation_level. Idempotent and
safe to re-run.

src/hii_backfill.py

@@ -0,0 +1,222 @@
+"""Backfill historical water levels from the HII waterlevel_graph endpoint.
+
+The api-v3 waterlevel_graph archive reaches back to ~2019 with hourly
+wl_msl + discharge. This module walks a date range in chunks per station and
+upserts into hii_waterlevel (idempotent; safe to re-run and to overlap with
+the live snapshot collector). Station metadata comes from a live
+waterlevel_load fetch, so hii_wl_stations is populated/refreshed as a side
+effect.
+
+Usage: python scripts/backfill_hii_waterlevel.py --start 2019-01-01
+"""
+
+import argparse
+import datetime
+import logging
+import time
+from typing import Dict, List, Optional
+
+from .hii_collector import (
+    HiiClient,
+    HiiStore,
+    PING_BASIN_CODE,
+    _parse_datetime,
+    _to_float,
+)
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_START = datetime.date(2019, 1, 1)
+DEFAULT_CHUNK_DAYS = 365  # full-year windows verified working (8,760 rows, ~700KB)
+DEFAULT_SLEEP_SECONDS = 1.0
+
+
+def parse_graph_rows(payload: Dict) -> List[Dict]:
+    """Extract history rows from a waterlevel_graph payload (skips empty rows)."""
+    rows = (payload.get("data") or {}).get("graph_data") or []
+    records = []
+    for row in rows:
+        timestamp = _parse_datetime(row.get("datetime"))
+        wl_msl = _to_float(row.get("value"))
+        discharge = _to_float(row.get("discharge"))
+        if timestamp is None or (wl_msl is None and discharge is None):
+            continue
+        records.append(
+            {"timestamp": timestamp, "wl_msl": wl_msl, "discharge": discharge}
+        )
+    return records
+
+
+def fetch_waterlevel_history(
+    client: HiiClient,
+    station_id: int,
+    start_date: datetime.date,
+    end_date: datetime.date,
+) -> List[Dict]:
+    """Hourly wl_msl + discharge history (archive reaches back to ~2019)."""
+    payload = client.get(
+        "waterlevel_graph",
+        params={
+            "station_type": "tele_waterlevel",
+            "station_id": station_id,
+            "start_date": start_date.isoformat(),
+            "end_date": end_date.isoformat(),
+        },
+    )
+    return parse_graph_rows(payload)
+
+
+def chunk_date_range(
+    start: datetime.date, end: datetime.date, chunk_days: int
+) -> List[tuple]:
+    """Split [start, end] into inclusive (start, end) windows."""
+    chunks = []
+    cursor = start
+    while cursor <= end:
+        chunk_end = min(cursor + datetime.timedelta(days=chunk_days - 1), end)
+        chunks.append((cursor, chunk_end))
+        cursor = chunk_end + datetime.timedelta(days=1)
+    return chunks
+
+
+def select_stations(
+    station_records: List[Dict],
+    codes: Optional[List[str]] = None,
+    all_stations: bool = False,
+) -> List[Dict]:
+    """Pick stations to backfill from parsed waterlevel_load records.
+
+    Default: stations that mirror a RID gauge (rid_code) or are flagged
+    is_key_station — the ones relevant to the flood model. Explicit codes
+    match rid_code or oldcode; --all takes every station in the basin.
+    """
+    if all_stations:
+        return station_records
+    if codes:
+        wanted = {c.strip().upper() for c in codes if c.strip()}
+        return [
+            r
+            for r in station_records
+            if (r.get("rid_code") or "").upper() in wanted
+            or (r.get("oldcode") or "").upper() in wanted
+        ]
+    return [r for r in station_records if r.get("rid_code") or r.get("is_key_station")]
+
+
+def backfill(
+    store: HiiStore,
+    client: Optional[HiiClient] = None,
+    start: datetime.date = DEFAULT_START,
+    end: Optional[datetime.date] = None,
+    codes: Optional[List[str]] = None,
+    all_stations: bool = False,
+    chunk_days: int = DEFAULT_CHUNK_DAYS,
+    sleep_seconds: float = DEFAULT_SLEEP_SECONDS,
+    basin_code: int = PING_BASIN_CODE,
+) -> Dict[str, int]:
+    """Run the backfill; returns {'stations': n, 'rows': n, 'errors': n}."""
+    client = client or HiiClient()
+    end = end or datetime.date.today()
+
+    logger.info("Fetching station catalog from waterlevel_load...")
+    station_records = client.fetch_waterlevel(basin_code)
+    # Refresh station metadata (and today's snapshot) while we have it
+    store.save_waterlevel(station_records)
+
+    stations = select_stations(station_records, codes=codes, all_stations=all_stations)
+    if not stations:
+        logger.error("No stations matched the selection")
+        return {"stations": 0, "rows": 0, "errors": 0}
+
+    chunks = chunk_date_range(start, end, chunk_days)
+    logger.info(
+        f"Backfilling {len(stations)} stations x {len(chunks)} windows "
+        f"({start} .. {end}, {chunk_days}-day chunks)"
+    )
+
+    totals = {"stations": len(stations), "rows": 0, "errors": 0}
+    for station in stations:
+        sid = station["station_id"]
+        label = station.get("rid_code") or station.get("oldcode") or str(sid)
+        station_rows = 0
+        for chunk_start, chunk_end in chunks:
+            try:
+                rows = fetch_waterlevel_history(client, sid, chunk_start, chunk_end)
+                station_rows += store.save_waterlevel_history(sid, rows)
+            except Exception as e:
+                totals["errors"] += 1
+                logger.warning(
+                    f"{label}: {chunk_start}..{chunk_end} failed: {e}"
+                )
+            time.sleep(sleep_seconds)
+        totals["rows"] += station_rows
+        logger.info(f"{label} (id {sid}): {station_rows} rows saved")
+
+    logger.info(
+        f"Backfill complete: {totals['rows']} rows across "
+        f"{totals['stations']} stations, {totals['errors']} failed windows"
+    )
+    return totals
+
+
+def main(argv: Optional[List[str]] = None) -> bool:
+    parser = argparse.ArgumentParser(
+        description="Backfill hii_waterlevel from the HII waterlevel_graph archive"
+    )
+    parser.add_argument(
+        "--start",
+        type=datetime.date.fromisoformat,
+        default=DEFAULT_START,
+        help=f"First date to fetch (default {DEFAULT_START})",
+    )
+    parser.add_argument(
+        "--end",
+        type=datetime.date.fromisoformat,
+        default=None,
+        help="Last date to fetch (default today)",
+    )
+    parser.add_argument(
+        "--stations",
+        help="Comma-separated codes (rid_code or oldcode, e.g. P.1,P.67,CHM004). "
+        "Default: all RID-mirror and key stations",
+    )
+    parser.add_argument(
+        "--all",
+        action="store_true",
+        help="Backfill every Ping-basin station (125+; slow)",
+    )
+    parser.add_argument(
+        "--chunk-days", type=int, default=DEFAULT_CHUNK_DAYS, help="Window size"
+    )
+    parser.add_argument(
+        "--sleep",
+        type=float,
+        default=DEFAULT_SLEEP_SECONDS,
+        help="Pause between requests in seconds",
+    )
+    args = parser.parse_args(argv)
+
+    logging.basicConfig(
+        level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+    )
+
+    from .config import Config
+
+    db_config = Config.get_database_config()
+    if db_config["type"] not in ("sqlite", "postgresql", "mysql"):
+        logger.error(f"Backfill requires a SQL DB_TYPE, got '{db_config['type']}'")
+        return False
+    store = HiiStore(db_config["connection_string"], db_config["type"])
+    if not store.connect():
+        return False
+
+    totals = backfill(
+        store,
+        start=args.start,
+        end=args.end,
+        codes=args.stations.split(",") if args.stations else None,
+        all_stations=args.all,
+        chunk_days=args.chunk_days,
+        sleep_seconds=args.sleep,
+    )
+    return totals["rows"] > 0 and totals["errors"] == 0