"""Hugging Face 儲存庫同步：commit 並上傳程式碼與量測結果到 EPM model repo。

用法：

    # commit + 上傳（需要 HF_TOKEN，或 ~/.cache/huggingface/token）
    python -m sdq.hf_sync push -m "說明這次改了什麼"

    # 只看本地狀態（給接手的人 / AI）
    python -m sdq.hf_sync status

    # 只下載 HF 上的 code（給 demo.py 用）
    python -m sdq.hf_sync pull --dest /path/to/dir

    # 從 patch 重新產生 patches/0001-sdq-expert-pager.patch
    python -m sdq.hf_sync regen-patch --src /path/to/llama.cpp

`push` 會尊重 `.gitignore`：模型權重、建置產物與 `tools/epq_lock.so`
（由 `tools/strict8g.py` 在執行時編譯）不會被上傳。
"""

from __future__ import annotations

import argparse
import os
import subprocess
from pathlib import Path

REPO_DIR = Path(__file__).resolve().parent.parent

DEFAULT_HF_REPO = os.environ.get(
    "EPM_HF_REPO",
    os.environ.get("SDQ_HF_REPO", "HelloSun/minicpm47woek"),
)

# demo.py fetch_code() 下載的檔案類型。新增檔案時這裡也要跟著改，否則
# 使用者從 HF 拉下來的 code 會缺東西。
CODE_PATTERNS = [
    "*.py", "*.md", "*.c",
    "cpp/*", "docs/*", "patches/*", "tools/*", "sdq/*.py",
    "bench/expert_index.json",
]


def git(*args: str) -> str:
    return subprocess.run(
        ["git", *args], cwd=REPO_DIR, check=True, capture_output=True, text=True
    ).stdout.strip()


def _git_optional(*args: str) -> str:
    r = subprocess.run(["git", *args], cwd=REPO_DIR, capture_output=True, text=True)
    return r.stdout.strip() if r.returncode == 0 else ""


def _token() -> str | None:
    token = os.environ.get("HF_TOKEN")
    if token:
        return token
    p = Path.home() / ".cache" / "huggingface" / "token"
    return p.read_text().strip() if p.exists() else None


def push(message: str, hf_repo: str = DEFAULT_HF_REPO) -> None:
    git("add", "-A")
    if not git("diff", "--cached", "--name-only"):
        print("[sync] 沒有變更，略過 commit")
    else:
        git("commit", "-m", message)
        print(f"[sync] 已 commit：{message}")

    from huggingface_hub import HfApi

    api = HfApi(token=_token())
    try:
        api.create_repo(hf_repo, repo_type="model", exist_ok=True)
    except Exception as exc:
        print(f"[sync] create_repo: {exc}")
    ignore = REPO_DIR / ".gitignore"
    patterns = ([ln.strip() for ln in ignore.read_text().splitlines() if ln.strip()]
                if ignore.exists() else [])
    api.upload_folder(
        folder_path=str(REPO_DIR),
        repo_id=hf_repo,
        repo_type="model",
        ignore_patterns=patterns or None,
        commit_message=message,
    )
    print(f"[sync] 已上傳到 https://huggingface.co/{hf_repo}")


def status() -> None:
    print(f"[sync] repo：{REPO_DIR}")
    print(f"[sync] 遠端：{_git_optional('remote', '-v').splitlines()[:1]}")
    log = _git_optional("log", "--oneline", "-10")
    print(f"\n最近提交：\n{log or '（無）'}")
    print(f"\n工作區狀態：\n{_git_optional('status', '--short') or '（乾淨）'}")
    docs = sorted(p.name for p in (REPO_DIR / "docs").glob("*.md"))
    print(f"\ndocs/：{', '.join(docs) if docs else '（空）'}")


def pull(dest: str) -> None:
    from huggingface_hub import snapshot_download

    path = snapshot_download(
        repo_id=DEFAULT_HF_REPO, repo_type="model", local_dir=dest,
        token=_token(), allow_patterns=CODE_PATTERNS,
    )
    print(f"[sync] 已下載 code 到 {path}")


def regen_patch(src_dir: str) -> None:
    """把 cpp/ 的引擎檔重新產生成 llama.cpp 可套用的 patch。

    `patches/` 裡的 patch 是給 `demo.py` 從零重建 llama.cpp 用的。改了
    `cpp/*.cpp` 之後一定要重跑這個指令，否則從 HF 下載的使用者會拿到舊引擎。
    """
    from sdq.config import PATCH_FILE, SDQ_SOURCE_FILES

    src = Path(src_dir).resolve()
    if not (src / ".git").exists():
        raise SystemExit(f"{src} 不是 git 工作目錄")
    if not (src / "src").exists():
        raise SystemExit(f"{src}/src 不存在")
    for f in SDQ_SOURCE_FILES:
        cur = REPO_DIR / "cpp" / f
        dst = src / "src" / f
        if cur.exists() and dst.exists() and cur.read_bytes() != dst.read_bytes():
            dst.write_bytes(cur.read_bytes())
            print(f"[sync] 已同步 cpp/{f} → {src}/src/{f}")

    out = REPO_DIR / PATCH_FILE
    # `git diff` does not see untracked files. The engine sources are new files in
    # the llama.cpp tree, so mark them intent-to-add first -- without this the
    # patch would carry only the small edits to CMakeLists/llama-graph/llama-model
    # and a fresh clone would build without any of the pager code.
    subprocess.run(["git", "add", "-N", *[f"src/{f}" for f in SDQ_SOURCE_FILES]],
                   cwd=src, check=True, capture_output=True)
    diff = subprocess.run(
        ["git", "diff", "--binary", "--", "src/CMakeLists.txt", "src/llama-graph.cpp",
         "src/llama-model.cpp", *[f"src/{f}" for f in SDQ_SOURCE_FILES]],
        cwd=src, capture_output=True, text=True, check=True,
    ).stdout
    if not diff.strip():
        raise SystemExit("diff 是空的：llama.cpp 樹裡已經沒有 EPM 的改動？")
    out.write_text(diff, encoding="utf-8")
    print(f"[sync] 已重新產生 {out}（{len(diff)} bytes）")


def main() -> None:
    ap = argparse.ArgumentParser(description="Hugging Face 同步")
    sub = ap.add_subparsers(dest="cmd", required=True)

    p_push = sub.add_parser("push", help="commit 並上傳 HF")
    p_push.add_argument("-m", "--message", default=None)
    p_push.add_argument("--repo", default=DEFAULT_HF_REPO)

    sub.add_parser("status", help="印出目前狀態")
    p_pull = sub.add_parser("pull", help="下載 HF 上的 code")
    p_pull.add_argument("--dest", required=True)
    p_patch = sub.add_parser("regen-patch", help="從 cpp/ 重新產生 llama.cpp patch")
    p_patch.add_argument("--src", required=True, help="已套用 patch 的 llama.cpp 原始碼目錄")

    args = ap.parse_args()
    if args.cmd == "push":
        push(args.message or "update", args.repo)
    elif args.cmd == "status":
        status()
    elif args.cmd == "pull":
        pull(args.dest)
    elif args.cmd == "regen-patch":
        regen_patch(args.src)


if __name__ == "__main__":
    main()