#!/usr/bin/env python3
"""Bulk-apply 'dedup' corrections for the same-date/same-amount cross-file
double-listings found by scripts/scan_double_listing.py.

Mechanism (verified against official filings for JLPSX, GDEUX, GSOUX,
FAEVX, CVSIX, FZAGX): Yahoo lists the (usually year-end) distribution in
both the dividend and capitalGains event maps; one copy is spurious. The
'dedup' invariant keeps at most one copy, layout-agnostically.

Skips symbols that already have a correction file (their pairs are handled
by explicit, officially-verified ops). Read the scan report first
(reports/double_listing/scan.md) — this applies the mechanism-inferred
correction to every symbol with at least one same-amount pair.

Usage:  python3 scripts/apply_dedup_corrections.py [--dry-run]
"""
import argparse
import json
import subprocess
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
CORR = ROOT / "overrides" / "corrections"
SCAN = ROOT / "reports" / "double_listing" / "scan.json"

NOTE = ("Bulk correction from the double-listing scan "
        "(scripts/scan_double_listing.py): Yahoo listed this distribution in "
        "both the dividend and capitalGains event files (same date, same "
        "amount); one copy is spurious. The 'dedup' invariant keeps at most "
        "one copy, layout-agnostically. Mechanism verified against official "
        "filings for JLPSX/GDEUX/GSOUX/FAEVX/CVSIX/FZAGX; mechanism-inferred "
        "for this symbol (no per-fund official check). Revert the entry if a "
        "future official cross-check shows both rows were real.")


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--dry-run", action="store_true")
    args = ap.parse_args()

    scan = json.loads(SCAN.read_text())
    written = skipped = 0
    for sym, r in sorted(scan["symbols"].items()):
        pairs = r.get("same_amt") or []
        if not pairs:
            continue
        f = CORR / f"{sym.upper()}.json"
        if f.exists():
            skipped += 1
            continue
        entry = {"symbol": sym, "dedup": [[x["date"], x["amount"]] for x in pairs],
                 "note": NOTE}
        if not args.dry_run:
            f.write_text(json.dumps(entry, indent=2) + "\n")
        written += 1
    print(f"{'would write' if args.dry_run else 'wrote'} {written} correction files, "
          f"skipped {skipped} (existing corrections)")
    if not args.dry_run:
        subprocess.run([sys.executable, str(ROOT / "scripts" / "check_corrections.py")],
                       check=False)
    return 0


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