"""Backfill: enqueue publicly-fetchable open missing_precedents for auto-fetch.

The citation graph records cited-but-absent rulings in ``missing_precedents``.
The ones with a public source — Supreme serial (בג"ץ/בר"מ/עע"מ NNNN/YY) → Tier-0
supremedecisions; district/Supreme with a נט-format triple → Tier-1 נט המשפט —
can be fetched + ingested automatically. ועדת-ערר (needs Nevo) and serial cases
with no public record are left for the chair.

This stamps a ``court_fetch_jobs`` row for each fetchable gap; the court-fetch
drainer (``drain_court_fetch.py`` / pm2 cron) then fetches, ingests, and closes
the gap. Idempotent (upsert on the canonical case number).

    scripts/backfill_missing_precedents.py            # dry-run (report only)
    scripts/backfill_missing_precedents.py --apply    # enqueue
"""

import asyncio
import os
import sys

sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "mcp-server", "src"))

from legal_mcp.services import court_citation, db


async def main() -> int:
    apply = "--apply" in sys.argv
    gaps = await db.list_missing_precedents(status="open", limit=2000)
    enq = skipped = 0
    by_tier: dict[str, int] = {}
    for g in gaps:
        cit = court_citation.classify(g.get("citation", ""))
        net = bool(cit.file_number and cit.month and cit.year)
        # Fetchable: Supreme serial (Tier-0) or anything with a נט triple (Tier-1).
        if cit.tier == "supreme" or (cit.tier == "admin" and net):
            route = "Tier-0/supreme" if (cit.tier == "supreme" and not net) else "Tier-1/net"
            by_tier[route] = by_tier.get(route, 0) + 1
            if apply:
                await db.court_fetch_job_upsert(
                    case_number_norm=cit.case_number_norm,
                    citation_raw=g.get("citation", ""),
                    tier=cit.tier, court=cit.court_prefix,
                )
            enq += 1
        else:
            skipped += 1
    verb = "enqueued" if apply else "would enqueue"
    print(f"{verb}: {enq}  (routes: {by_tier})", flush=True)
    print(f"skipped (ועדת-ערר/serial-no-record/unrecognized): {skipped}", flush=True)
    if not apply:
        print("dry-run — re-run with --apply to enqueue.", flush=True)
    return 0


if __name__ == "__main__":
    sys.exit(asyncio.run(main()))