#!/usr/bin/env python3
"""Daily external-link liveness check.

Runs lychee over every http/https link in the site's content/*.md and prints a
concise report of the ones that failed (dead / 4xx / 5xx). Designed for a
scheduled job: read-only (HTTP GET only), always exits 0 so the job never
"fails" — the report is the output.

Defaults are absolute to the repo, so it runs from ANY working directory
(including a cron scheduler). Override with flags if the repo lives elsewhere.

Usage:
  python3 scripts/check_external_links.py
  python3 scripts/check_external_links.py --timeout 20 --retries 1

Report goes to stdout and to linkcheck/external_dead.txt (one dead URL per line
with its source file:line).
"""
import argparse
import json
import shutil
import subprocess
from pathlib import Path

DEFAULT_REPO = Path("/home/noether/libertytoolsio")
LYCHEE_CANDIDATES = ["lychee", str(Path.home() / ".local/bin/lychee")]


def find_lychee() -> str:
    for c in LYCHEE_CANDIDATES:
        p = shutil.which(c) if "/" not in c else (c if Path(c).exists() else None)
        if p:
            return p
    raise SystemExit("lychee not found. Install it first (plan Task 7a).")


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--repo", default=str(DEFAULT_REPO))
    ap.add_argument("--timeout", type=int, default=20)
    ap.add_argument("--retries", type=int, default=1)
    ap.add_argument("--threads", type=int, default="8")
    args = ap.parse_args()

    repo = Path(args.repo).resolve()
    content = repo / "content"
    md_files = sorted(str(p) for p in content.rglob("*.md"))
    if not md_files:
        print(f"No markdown files under {content}/")
        return

    lychee = find_lychee()
    cmd = [
        lychee, "--format", "json",
        "--scheme", "http", "--scheme", "https",     # web links only
        "--exclude", "mailto:", "--exclude", "tel:",
        "--timeout", str(args.timeout), "--max-retries", str(args.retries),
        "--threads", str(args.threads),
    ] + md_files

    proc = subprocess.run(cmd, capture_output=True, text=True)
    # lychee exits non-zero when it finds dead links; we still parse the JSON.
    try:
        data = json.loads(proc.stdout)
    except json.JSONDecodeError:
        print("Could not parse lychee output. stderr:\n", (proc.stderr or "")[-2000:])
        return

    dead = []
    for src, items in data.get("error_map", {}).items():
        for it in items:
            url = it.get("url", "")
            if url.startswith(("http://", "https://")):
                status = it.get("status", {}).get("text", "")
                span = it.get("span", {})
                # report the source path relative to the repo for readability
                try:
                    rel = Path(src).resolve().relative_to(repo)
                except ValueError:
                    rel = src
                dead.append((str(rel), span.get("line"), url, status))

    total_checked = data.get("total", 0)
    ok = data.get("successful", 0)

    outdir = repo / "linkcheck"
    outdir.mkdir(exist_ok=True)
    with (outdir / "external_dead.txt").open("w") as f:
        for src, line, url, status in sorted(dead):
            f.write(f"{src}:{line}\t{url}\t[{status}]\n")

    print(f"External link check: {total_checked} links checked, {ok} ok, {len(dead)} dead.")
    if dead:
        print("\nDead external links:")
        for src, line, url, status in sorted(dead):
            print(f"  {src}:{line}  {url}  [{status}]")
        print(f"\nFull list written to {outdir/'external_dead.txt'}")
    else:
        print("No dead external links found.")


if __name__ == "__main__":
    main()