climperor/web/export_relations_site.py

"""Export the Climperor web site as a static bundle (no server needed).

Usage:
    python export_relations_site.py [--out dist/relations] [--with-videos]
        [--ability-video-base URL] [--static-asset-base URL] [--site-origin URL]

Copies web/frontend/ + a snapshot of the /api/data payload (data.json) +
the referenced image assets into one directory, ready for any static host
(GitHub Pages, Cloudflare Pages, nginx, ...).

Also runs seo_prerender: crawlable HTML for heroes/mechanics/top pages,
plus sitemap.xml / llms.txt / robots.txt / _redirects (History SPA).

Notes:
- Only already-cached assets are exported. For full ability-icon coverage
  run `python fetch_hero_abilities.py --icons-only` first.
- For patch-notes names/icons on the 版本 page, run `python fetch_patches.py`
  first (downloads referenced item + ability icons into assets/).
- Ability videos (several GB locally) are skipped unless --with-videos is
  given; production deploys point the UI at OSS via --ability-video-base
  (or ABILITY_VIDEO_BASE env) instead of bundling videos into Pages.
- When --static-asset-base is set, image dirs are omitted from dist/ and the
  UI loads icons/portraits from OSS (see _oss_static_assets.py to sync).
"""

from __future__ import annotations

import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1]))

import argparse
import json
import os
import shutil

from shared.http_utils import write_json_atomic
from shared.paths import (
    ABILITY_ICONS,
    ABILITY_VIDEOS,
    ATTR_ICONS,
    HERO_PORTRAITS,
    ITEM_CAT_ICONS,
    ITEM_ICONS,
    RANK_ICONS,
    ROLE_ICONS,
    ROOT,
    STREAMER_AVATARS,
    STREAMER_VIDEOS,
    UI_ICONS,
    WEB_DIST,
)

from seo_prerender import DEFAULT_SITE_ORIGIN, write_seo_bundle
from serve_relations import WEB_DIR, build_payload

SITE_VERSION = "0.6.57"
DEFAULT_OSS_BASE = "https://climperor.oss-cn-shanghai.aliyuncs.com"


def copy_glob(src: Path, dst: Path, pattern: str = "*.png") -> int:
    if not src.is_dir():
        return 0
    dst.mkdir(parents=True, exist_ok=True)
    n = 0
    for f in sorted(src.glob(pattern)):
        if f.is_file():
            shutil.copy2(f, dst / f.name)
            n += 1
    return n


def populate_static_assets(out: Path, payload: dict) -> dict[str, int]:
    """Copy web site image dirs into ``out`` (portrait/item/ability/...)."""
    counts = {
        "attr": copy_glob(ATTR_ICONS, out / "attr"),
        "role-icon": copy_glob(ROLE_ICONS, out / "role-icon"),
        "rank": copy_glob(RANK_ICONS, out / "rank", "rank*.png"),
        "item": copy_glob(ITEM_ICONS, out / "item"),
        "item-cat": copy_glob(ITEM_CAT_ICONS, out / "item-cat", "itemcat_*.png"),
        "ability": copy_glob(ABILITY_ICONS, out / "ability"),
        "ui-icon": copy_glob(UI_ICONS, out / "ui-icon"),
        "streamer-avatar": 0,
        "streamer-video": 0,
    }
    if STREAMER_AVATARS.is_dir():
        n_av = 0
        for pattern in ("*.jpg", "*.jpeg", "*.png", "*.webp"):
            n_av += copy_glob(STREAMER_AVATARS, out / "streamer-avatar", pattern)
        counts["streamer-avatar"] = n_av
    if STREAMER_VIDEOS.is_dir():
        n_vid = 0
        dst = out / "streamer-video"
        dst.mkdir(parents=True, exist_ok=True)
        for f in sorted(STREAMER_VIDEOS.iterdir()):
            if not f.is_file() or f.name.startswith("_"):
                continue
            name = f.name.lower()
            if not name.endswith(
                (".mp4", ".webm", ".jpg", ".jpeg", ".webp", ".png")
            ):
                continue
            shutil.copy2(f, dst / f.name)
            n_vid += 1
        counts["streamer-video"] = n_vid

    # Wide Heroes-page cards only — never fall back to pc/templates/cdn
    # (96×96 match crops). That fallback previously overwrote OSS portraits.
    portrait_dst = out / "portrait"
    portrait_dst.mkdir(exist_ok=True)
    n_portrait = 0
    missing: list[str] = []
    for hero in payload.get("heroes") or []:
        key = hero.get("key")
        if not key:
            continue
        src = HERO_PORTRAITS / f"{key}.png"
        if src.is_file():
            shutil.copy2(src, portrait_dst / f"{key}.png")
            n_portrait += 1
        else:
            missing.append(key)
    # Patch-only units (e.g. spirit_bear) are optional; copy when present.
    for cell in ((payload.get("patch_lookup") or {}).get("heroes") or {}).values():
        key = cell.get("key") if isinstance(cell, dict) else None
        if not key or (portrait_dst / f"{key}.png").is_file():
            continue
        src = HERO_PORTRAITS / f"{key}.png"
        if src.is_file():
            shutil.copy2(src, portrait_dst / f"{key}.png")
            n_portrait += 1
    counts["portrait"] = n_portrait
    if missing:
        sample = ", ".join(missing[:8])
        more = f" (+{len(missing) - 8} more)" if len(missing) > 8 else ""
        raise SystemExit(
            f"missing {len(missing)} wide hero portrait(s) under "
            f"{HERO_PORTRAITS}: {sample}{more}. "
            "Run: python web/fetch_hero_portraits.py"
        )
    return counts


def write_config_js(
    out: Path,
    *,
    ability_video_base: str,
    static_asset_base: str,
    site_version: str,
    site_origin: str,
    players_asset_base: str = "",
) -> None:
    """Write config.js consumed by app.js."""
    video = (ability_video_base or "").strip().rstrip("/")
    static = (static_asset_base or "").strip().rstrip("/")
    players = (players_asset_base or "").strip().rstrip("/") or static
    ver = (site_version or "").strip()
    origin = (site_origin or "").strip().rstrip("/")
    (out / "config.js").write_text(
        "/* generated by export_relations_site.py — do not edit */\n"
        f"var SITE_VERSION = {json.dumps(ver, ensure_ascii=False)};\n"
        f"var SITE_ORIGIN = {json.dumps(origin, ensure_ascii=False)};\n"
        f"var ABILITY_VIDEO_BASE = {json.dumps(video, ensure_ascii=False)};\n"
        f"var STATIC_ASSET_BASE = {json.dumps(static, ensure_ascii=False)};\n"
        f"var PLAYERS_ASSET_BASE = {json.dumps(players, ensure_ascii=False)};\n",
        encoding="utf-8",
    )


def main() -> None:
    ap = argparse.ArgumentParser(
        description="Export Climperor web site as a static bundle"
    )
    ap.add_argument("--out", default=str(WEB_DIST / "relations"))
    ap.add_argument(
        "--with-videos",
        action="store_true",
        help="also copy assets/ability_videos (several GB)",
    )
    ap.add_argument(
        "--ability-video-base",
        default=None,
        help="public base URL for ability demos (writes config.js); "
        "falls back to ABILITY_VIDEO_BASE env, else empty (same-origin)",
    )
    ap.add_argument(
        "--static-asset-base",
        default=None,
        help="public base URL for icons/portraits (writes config.js); "
        "when set, image dirs are not copied into dist; "
        "falls back to STATIC_ASSET_BASE env, else empty",
    )
    ap.add_argument(
        "--site-origin",
        default=None,
        help="canonical site origin for SEO (sitemap / og / config SITE_ORIGIN); "
        "falls back to SITE_ORIGIN env, else https://dota2.refining.dev",
    )
    args = ap.parse_args()

    video_base = (
        args.ability_video_base
        if args.ability_video_base is not None
        else os.environ.get("ABILITY_VIDEO_BASE", "")
    )
    static_base = (
        args.static_asset_base
        if args.static_asset_base is not None
        else os.environ.get("STATIC_ASSET_BASE", "")
    )
    site_origin = (
        args.site_origin
        if args.site_origin is not None
        else os.environ.get("SITE_ORIGIN", DEFAULT_SITE_ORIGIN)
    )

    out = Path(args.out).resolve()
    if out == ROOT.resolve() or out.parent == out:
        raise SystemExit(f"refusing unsafe --out: {out}")
    if out.exists():
        shutil.rmtree(out)
    out.mkdir(parents=True)

    for name in (
        "index.html",
        "router.js",
        "app.js",
        "style.css",
        "mobile-gate.js",
        "_headers",
        "_redirects",
        "robots.txt",
    ):
        src = WEB_DIR / name
        if src.is_file():
            shutil.copy2(src, out / name)
    fonts_src = WEB_DIR / "fonts"
    if fonts_src.is_dir():
        shutil.copytree(fonts_src, out / "fonts")
    # Cloudflare Pages Functions (functions/api/*.js -> /api/*).
    functions_src = WEB_DIR / "functions"
    n_functions = 0
    if functions_src.is_dir():
        shutil.copytree(functions_src, out / "functions")
        n_functions = sum(1 for f in (out / "functions").rglob("*") if f.is_file())
    write_config_js(
        out,
        ability_video_base=video_base,
        static_asset_base=static_base,
        site_version=SITE_VERSION,
        site_origin=site_origin,
    )

    payload = build_payload()
    refresh_run_id = os.environ.get("REFRESH_RUN_ID") or ""
    payload.setdefault("meta", {})["refresh_run_id"] = refresh_run_id
    write_json_atomic(
        out / "data.json",
        payload,
        indent=None,
        separators=(",", ":"),
    )

    template_html = (WEB_DIR / "index.html").read_text(encoding="utf-8")
    seo_counts = write_seo_bundle(
        out,
        template_html,
        payload,
        site_origin=site_origin,
    )

    if static_base:
        counts = {
            name: 0
            for name in (
                "attr",
                "item",
                "item-cat",
                "ability",
                "ui-icon",
                "portrait",
                "streamer-avatar",
                "streamer-video",
            )
        }
        print("  static assets: omitted (STATIC_ASSET_BASE set — served from OSS)")
    else:
        counts = populate_static_assets(out, payload)

    n_videos = 0
    if args.with_videos and ABILITY_VIDEOS.is_dir():
        shutil.copytree(ABILITY_VIDEOS, out / "ability-video")
        n_videos = sum(1 for f in (out / "ability-video").rglob("*") if f.is_file())

    total = sum(f.stat().st_size for f in out.rglob("*") if f.is_file())
    print(f"exported static site -> {out}")
    for name, n in counts.items():
        print(f"  {name}/: {n} files")
    print(
        f"  seo prerender: top={seo_counts['top']} "
        f"heroes={seo_counts['heroes']} mechanics={seo_counts['mechanics']} "
        f"(+ sitemap.xml / llms.txt / robots.txt)"
    )
    if n_functions:
        print(f"  functions/: {n_functions} files (Pages Functions)")
    if args.with_videos:
        print(f"  ability-video/: {n_videos} files")
    print(
        f"  config.js SITE_VERSION={SITE_VERSION!r} SITE_ORIGIN={site_origin!r} "
        f"ABILITY_VIDEO_BASE={video_base!r} STATIC_ASSET_BASE={static_base!r} "
        f"PLAYERS_ASSET_BASE={static_base!r}"
    )
    print(f"  total: {total / 1e6:.1f} MB")
    print(
        f"local Pages Function check:  npx wrangler pages dev . "
        f"--port 8789  (run from {out})"
    )
    print("deploy: upload the directory to any static host (Pages / nginx / ...)")


if __name__ == "__main__":
    main()