#!/usr/bin/env python3
"""Backfill full_text for unrated drafts that are missing it.

The fetch pipeline sometimes leaves new IETF drafts without full text (the per-source
text download can skip them). Analysis quality depends on full text, so this script
downloads it directly from the IETF archive using the draft's recorded revision, with
a fallback that probes nearby revisions if the recorded one 404s.

Usage:
    PYTHONPATH=src python3 scripts/backfill-unrated-text.py [--all] [--limit N]

    --all    Backfill ALL drafts missing full_text (not just unrated ones).
    --limit  Cap the number of drafts processed.
"""
from __future__ import annotations

import argparse
import sqlite3
import sys
import time

sys.path.insert(0, "src")

import httpx

from ietf_analyzer.config import Config

TEXT_BASE = "https://www.ietf.org/archive/id"


def candidate_urls(name: str, rev: str) -> list[str]:
    """URLs to try, in order: recorded rev, then 00..09, then bare name."""
    urls = [f"{TEXT_BASE}/{name}-{rev}.txt"] if rev else []
    for r in (f"{i:02d}" for i in range(10)):
        if r != rev:
            urls.append(f"{TEXT_BASE}/{name}-{r}.txt")
    urls.append(f"{TEXT_BASE}/{name}.txt")
    return urls


def main() -> int:
    ap = argparse.ArgumentParser()
    ap.add_argument("--all", action="store_true", help="all drafts missing text, not just unrated")
    ap.add_argument("--limit", type=int, default=0)
    args = ap.parse_args()

    cfg = Config.load()
    conn = sqlite3.connect(cfg.db_path)
    conn.row_factory = sqlite3.Row

    where_unrated = "" if args.all else (
        "AND NOT EXISTS (SELECT 1 FROM ratings r WHERE r.draft_name = d.name)"
    )
    sql = f"""
        SELECT name, rev FROM drafts d
        WHERE (full_text IS NULL OR full_text = '')
          AND source = 'ietf'
          {where_unrated}
        ORDER BY name
    """
    rows = conn.execute(sql).fetchall()
    if args.limit:
        rows = rows[: args.limit]

    print(f"Backfilling text for {len(rows)} drafts...")
    client = httpx.Client(timeout=30, follow_redirects=True)
    ok = fail = 0
    for i, row in enumerate(rows, 1):
        name, rev = row["name"], row["rev"] or "00"
        text = None
        for url in candidate_urls(name, rev):
            try:
                resp = client.get(url)
                if resp.status_code == 200 and len(resp.text) > 200:
                    text = resp.text[:500_000]  # cap 500K
                    break
            except httpx.HTTPError:
                continue
        if text:
            conn.execute("UPDATE drafts SET full_text = ? WHERE name = ?", (text, name))
            conn.commit()
            ok += 1
            print(f"  [{i}/{len(rows)}] OK   {name} ({len(text)} chars)")
        else:
            fail += 1
            print(f"  [{i}/{len(rows)}] FAIL {name}")
        time.sleep(0.3)

    print(f"\nDone. {ok} downloaded, {fail} failed.")
    conn.close()
    return 0


if __name__ == "__main__":
    raise SystemExit(main())