#!/usr/bin/env python3
"""Fundamental screener + enrichment with point-in-time notes.

  screen.py --filters "pe<15,fcf_yield>0.06" [--sort fcf_yield:desc] [--as-of 2020-03-20] [--limit 25]
            [--quarters 3] [--no-enrich] [--out screen.csv]
  screen.py --tickers AAPL MSFT --quarters 4          # enrich only
"""
from __future__ import annotations

import argparse
import sys
from datetime import date
from pathlib import Path

import pandas as pd

sys.path.insert(0, str(Path(__file__).parent))
import hfmd  # noqa: E402

KEY_RATIOS = ["pe", "pb", "ev_ebitda", "fcf_yield", "dividend_yield", "roe", "roa", "gross_margin", "operating_margin", "net_margin", "debt_to_equity", "current_ratio", "revenue_growth", "eps_growth", "market_cap"]
INCOME_COLS = ["period_end", "fiscal_period", "revenue", "operating_income", "net_income", "eps_diluted", "filed_at", "form"]


def pit_note(q: pd.DataFrame) -> str:
    if q.empty or "filed_at" not in q:
        return "no quarterly statements available"
    q = q.copy()
    q["filed_at"] = pd.to_datetime(q["filed_at"], errors="coerce")
    q["period_end"] = pd.to_datetime(q.get("period_end"), errors="coerce")
    latest = q.sort_values("filed_at").iloc[-1]
    lag = (latest["filed_at"] - latest["period_end"]).days if pd.notna(latest["filed_at"]) and pd.notna(latest["period_end"]) else None
    age = (pd.Timestamp(date.today()) - latest["filed_at"]).days if pd.notna(latest["filed_at"]) else None
    return (f"latest period {latest['period_end'].date() if pd.notna(latest['period_end']) else '?'} became public on "
            f"{latest['filed_at'].date() if pd.notna(latest['filed_at']) else '?'} ({lag} days after period end; {age} days ago)"
            + (" — a newer quarter has ended but is not filed yet" if age is not None and age > 100 else ""))


def main() -> int:
    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument("--filters", help='e.g. "pe<15,roe>0.15,fcf_yield>0.06"')
    ap.add_argument("--sort", help="metric:asc|desc")
    ap.add_argument("--as-of", help="point-in-time date YYYY-MM-DD")
    ap.add_argument("--limit", type=int, default=25)
    ap.add_argument("--tickers", nargs="*", help="skip the screener, enrich these tickers")
    ap.add_argument("--quarters", type=int, default=3)
    ap.add_argument("--no-enrich", action="store_true")
    ap.add_argument("--out")
    a = ap.parse_args()
    if not a.filters and not a.tickers:
        ap.error("--filters or --tickers required")

    hits = pd.DataFrame()
    if a.filters:
        try:
            hits, meta = hfmd.screener(a.filters, a.sort, a.as_of, a.limit)
        except hfmd.HfmdError as e:
            print(e, file=sys.stderr)
            if e.status == 404:
                print("→ the fundamentals module is not deployed on this server yet (v2 rollout). Nothing to screen.", file=sys.stderr)
                return 2
            return 1
        print(f"screen `{a.filters}`{' as of ' + a.as_of if a.as_of else ''}: {meta.get('count', len(hits))} match(es)"
              + (f" (universe {meta['universe']})" if 'universe' in meta else ""))
        if hits.empty:
            return 0
        with pd.option_context("display.width", 200, "display.max_columns", 30, "display.float_format", "{:.3f}".format):
            print(hits.head(a.limit).to_string(index=False))
        tickers = list(hits["ticker"].head(a.limit)) if "ticker" in hits else []
    else:
        tickers = [t.upper() for t in a.tickers]

    if a.no_enrich or not tickers:
        if a.out and not hits.empty:
            hits.to_csv(a.out, index=False)
            print(f"wrote {a.out}")
        return 0

    if not hfmd.API_KEY and len(tickers) > 8:
        hfmd.log(f"keyless mode: enriching {len(tickers)} tickers needs {2 * len(tickers)} requests (30/h quota) — set HFMD_API_KEY or use --limit 8")

    enriched = []
    for t in tickers:
        print(f"\n=== {t} ===")
        try:
            r = hfmd.ratios(t)
            line = "  ".join(f"{k}={r[k]:.3g}" for k in KEY_RATIOS if isinstance(r.get(k), (int, float)))
            print("ratios:", line or r)
            if r.get("as_of") or r.get("period_end"):
                print(f"  based on period {r.get('period_end')} · filed {r.get('filed_at')} · price as of {r.get('as_of')}")
        except hfmd.HfmdError as e:
            r = {}
            print(f"ratios: {e}")
        try:
            q = hfmd.statements(t, "income", "quarterly", a.quarters)
            cols = [c for c in INCOME_COLS if c in q.columns] or list(q.columns)[:8]
            with pd.option_context("display.width", 200, "display.float_format", "{:,.0f}".format):
                print(q[cols].to_string(index=False) if not q.empty else "  no statements")
            print("  point-in-time:", pit_note(q))
        except hfmd.HfmdError as e:
            q = pd.DataFrame()
            print(f"statements: {e}")
        enriched.append({"ticker": t, **{k: r.get(k) for k in KEY_RATIOS}, "latest_filed_at": (q["filed_at"].max() if "filed_at" in q else None)})

    if a.out:
        out = pd.DataFrame(enriched)
        if not hits.empty and "ticker" in hits:
            out = hits.merge(out, on="ticker", how="left", suffixes=("", "_latest"))
        out.to_csv(a.out, index=False)
        print(f"\nwrote {a.out}")
    return 0


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