"""Vendor highlight.js (common bundle + extra languages + themes) into static/.

Run: python3 scripts/vendor_hljs.py
Fetches from cdnjs 11.9.0 (pinned for stability) and writes:
  static/js/highlight.min.js        (common bundle, ~40 languages)
  static/js/highlight-extra.min.js  (extra languages concatenated)
  static/css/highlight.css          (github light + github-dark scoped on [data-theme])
"""
import re
import urllib.request

VERSION = "11.9.0"
BASE = f"https://cdnjs.cloudflare.com/ajax/libs/highlight.js/{VERSION}"

COMMON_JS = f"{BASE}/highlight.min.js"
LANG_URL = BASE + "/languages/{lang}.min.js"
LIGHT_CSS = BASE + "/styles/github.min.css"
DARK_CSS = BASE + "/styles/github-dark.min.css"

# Extra languages NOT in the common bundle, covering a maximum of file types.
# NOTE (verified 11.9.0): "fish", "toml" and "cobol" have NO standalone grammar
# on cdnjs for this version — code-highlight.js maps them to the closest
# bundled grammar (fish→shell, toml→ini, cobol→plaintext).
EXTRA_LANGS = [
    # shells / ops
    "powershell", "dos", "fish",
    # build / containers / config
    "dockerfile", "cmake", "toml", "graphql", "protobuf", "thrift",
    # web servers / protocols (absent du bundle common cdnjs 11.9.0)
    "apache", "http", "nginx",
    # JVM / functional / misc popular
    "scala", "groovy", "haskell", "elixir", "erlang", "clojure",
    "ocaml", "fsharp", "nim", "d", "julia", "matlab",
    "dart", "latex", "vim", "awk", "delphi",
    # asm / hdl / legacy
    "armasm", "x86asm", "vhdl", "verilog", "ada", "fortran", "cobol",
    "gcode", "stata", "stan",
]


def fetch(url: str) -> str:
    req = urllib.request.Request(url, headers={"User-Agent": "FlowDeck-vendor/1.0"})
    with urllib.request.urlopen(req, timeout=30) as r:
        return r.read().decode("utf-8", "replace")


def scope_css(css: str, scope: str) -> str:
    """Prefix every rule whose selector mentions .hljs with the theme scope."""
    out = []
    for chunk in css.split("}"):
        if "{" not in chunk:
            out.append(chunk)
            continue
        selectors, body = chunk.split("{", 1)
        parts = []
        for sel in selectors.split(","):
            sel = sel.strip()
            if not sel:
                continue
            if ".hljs" in sel:
                parts.append(f"{scope} {sel}")
            else:
                parts.append(sel)
        out.append(", ".join(parts) + "{" + body)
    return "}".join(out)


def main() -> None:
    from pathlib import Path

    root = Path(__file__).resolve().parent.parent
    js_dir = root / "static" / "js"
    css_dir = root / "static" / "css"

    common = fetch(COMMON_JS)
    (js_dir / "highlight.min.js").write_text(common, encoding="utf-8")
    print(f"highlight.min.js: {len(common)} bytes")

    extra_parts = []
    missing = []
    for lang in EXTRA_LANGS:
        try:
            code = fetch(LANG_URL.format(lang=lang))
            extra_parts.append(f"\n/* hljs lang: {lang} */\n" + code)
            print(f"  + {lang}: {len(code)} bytes")
        except Exception as exc:  # noqa: BLE001
            missing.append(lang)
            print(f"  ! {lang} missing: {exc}")
    (js_dir / "highlight-extra.min.js").write_text(
        "/* FlowDeck — highlight.js extra languages (cdnjs %s) */\n" % VERSION
        + "\n".join(extra_parts),
        encoding="utf-8",
    )

    light = fetch(LIGHT_CSS)
    dark = fetch(DARK_CSS)
    css = (
        "/* FlowDeck — highlight.js themes (cdnjs %s): github (light) + "
        "github-dark scoped on html[data-theme=\"dark\"] */\n" % VERSION
        + light
        + "\n"
        + scope_css(dark, 'html[data-theme="dark"]')
        + "\n/* FlowDeck tweaks: keep code blocks integrated with app surfaces */\n"
        + ".hljs{background:transparent;}\n"
    )
    (css_dir / "highlight.css").write_text(css, encoding="utf-8")
    print(f"highlight.css: {len(css)} bytes")
    if missing:
        print("MISSING:", missing)


if __name__ == "__main__":
    main()