"""Extract the SUBJECT company from SC 13D filing headers.

The EDGAR full index lists the FILER (the activist) in the CIK/company
columns; the target company appears only inside the document. For Schedule
13D filings the SGML header's first COMPANY block is the subject company
(verified on samples: FTE Networks, 30DC, Helius Medical, Genco). This
fetcher reads data/research/edgar_13d.csv, keeps SC 13D originals, and for
each one fetches the .txt header, extracting the first company name + CIK.

Writes data/research/edgar_13d_targets.csv (resume-safe: paths already
extracted are skipped).

    PYTHONPATH=. uv run python -m research.lab.fetch_13d_targets [--limit N]
"""
from __future__ import annotations

import os
import re
import sys
import time
from concurrent.futures import ThreadPoolExecutor, as_completed

import pandas as pd
import requests

from research.lab.fetch_us import _proxy_env

IN = "data/research/edgar_13d.csv"
OUT = "data/research/edgar_13d_targets.csv"
UA = {"User-Agent": "quant-research/0.1 gahow@example.com", "Accept-Encoding": "gzip"}
NAME_RE = re.compile(r"COMPANY CONFORMED NAME:\s*(.+)")
CIK_RE = re.compile(r"CENTRAL INDEX KEY:\s*(\d+)")
WORKERS = 5


def fetch_target(path: str) -> tuple[str, str, int] | None:
    url = "https://www.sec.gov/Archives/" + path
    for attempt in range(3):
        try:
            r = requests.get(url, headers=UA, timeout=60)
            if r.status_code == 404:
                return path, "", 0
            r.raise_for_status()
            head = r.text[:20000]
            name = NAME_RE.search(head)
            cik = CIK_RE.search(head)
            return path, (name.group(1).strip() if name else ""), int(cik.group(1)) if cik else 0
        except Exception:  # noqa: BLE001
            time.sleep(1.0 * (attempt + 1))
    print(f"  FAILED {path}")
    return None


def main() -> None:
    _proxy_env()
    limit = None
    if "--limit" in sys.argv:
        limit = int(sys.argv[sys.argv.index("--limit") + 1])
    ev = pd.read_csv(IN)
    ev = ev[ev["form"] == "SC 13D"].copy()
    done: set[str] = set()
    frames = []
    if os.path.exists(OUT):
        prev = pd.read_csv(OUT)
        frames.append(prev)
        done = set(prev["path"])
    todo = ev[~ev["path"].isin(done)]
    if limit:
        todo = todo.head(limit)
    print(f"13D originals: {len(ev)}, done: {len(done)}, fetching: {len(todo)}")
    rows = []
    with ThreadPoolExecutor(max_workers=WORKERS) as ex:
        futs = {ex.submit(fetch_target, p): p for p in todo["path"]}
        n = 0
        for fut in as_completed(futs):
            res = fut.result()
            n += 1
            if res is not None:
                path, name, cik = res
                rows.append({"path": path, "target_name": name, "target_cik": cik})
            if n % 500 == 0:
                print(f"  {n}/{len(todo)}")
    df = pd.DataFrame(rows)
    if len(df):
        meta = todo.set_index("path")[["filed", "cik", "company"]]
        df = df.join(meta, on="path")
    allrows = pd.concat(frames + [df]) if frames or len(df) else pd.DataFrame()
    allrows.to_csv(OUT, index=False)
    print(f"stored {len(allrows)} rows -> {OUT}")


if __name__ == "__main__":
    main()