app.py

"""Harbor Visualiser — FastAPI backend + Harbor Hub UI.

Serves a single-page "Harbor Hub" themed UI (static/) plus a JSON API that
reuses the existing loader/parser:

    GET /                       → the SPA (static/index.html)
    GET /api/hub/datasets       → live list of Harbor-tagged HF datasets
    GET /api/hub/count?id=      → task count for one Hub dataset (memoised)
    GET /api/dataset?uri=       → fetch a dataset, return its task ids + meta
    GET /api/task?uri=&task=    → one task's parsed spec (files + metadata)
    GET /healthz

Run locally:
    pip install -r requirements.txt
    uvicorn app:app --reload --port 7860      # → http://127.0.0.1:7860

On a Hugging Face Docker Space it runs via the Dockerfile (uvicorn :7860).
"""

from __future__ import annotations

import logging
from pathlib import Path

from fastapi import FastAPI, HTTPException, Query
from fastapi.responses import FileResponse, JSONResponse
from fastapi.staticfiles import StaticFiles

from viewer import fetch_dataset, fetch_hf_task, list_tasks, load_task, parse_dataset_uri
from viewer.hub import count_tasks, list_harbor_datasets, list_hf_tasks

logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s %(message)s")
logger = logging.getLogger("harbor-visualiser")

HERE = Path(__file__).resolve().parent
STATIC = HERE / "static"

app = FastAPI(title="Harbor Visualiser", docs_url="/api/docs")


# ---------------------------------------------------------------------------
# API
# ---------------------------------------------------------------------------

@app.get("/api/hub/datasets")
def api_hub_datasets(
    q: str | None = Query(None, description="substring filter on dataset id"),
    sort: str = Query("downloads"),
    limit: int = Query(500, ge=1, le=2000),
) -> JSONResponse:
    """Live list of Harbor-tagged datasets on the HF Hub (no stale cache)."""
    try:
        ds = list_harbor_datasets(query=q, sort=sort, limit=limit)
    except Exception as exc:  # noqa: BLE001
        raise HTTPException(502, f"HF Hub listing failed: {exc}") from exc
    return JSONResponse({"datasets": [d.as_dict() for d in ds], "count": len(ds)})


@app.get("/api/hub/count")
def api_hub_count(id: str = Query(..., description="dataset id, e.g. owner/name")) -> JSONResponse:
    """Task count for a single Hub dataset (one cheap list_repo_files call)."""
    return JSONResponse({"id": id, "tasks": count_tasks(id)})


@app.get("/api/dataset")
def api_dataset(
    uri: str = Query(..., description="owner/name | hf:// | gh:// | harbor:// | local path"),
    refresh: int = Query(0, description="1 = force re-fetch (bypass cache)"),
) -> JSONResponse:
    """Fetch a dataset and return its task ids + source metadata."""
    try:
        source = parse_dataset_uri(uri)
    except ValueError as exc:
        raise HTTPException(400, str(exc)) from exc
    try:
        if source.kind == "hf":
            # List task ids via the Hub API — no download. Critical for large
            # datasets (2k+ tasks) which would otherwise snapshot the whole repo.
            tasks = list_hf_tasks(source.ident, source.revision)
        else:
            root = fetch_dataset(source, force=bool(refresh))
            tasks = list_tasks(root)
    except Exception as exc:  # noqa: BLE001
        raise HTTPException(502, f"fetch failed: {exc}") from exc
    return JSONResponse({
        "uri": uri,
        "display": source.display,
        "kind": source.kind,
        "ident": source.ident,
        "revision": source.revision,
        "tasks": tasks,
        "count": len(tasks),
    })


@app.get("/api/task")
def api_task(
    uri: str = Query(...),
    task: str = Query(..., description="task id (directory name)"),
    refresh: int = Query(0),
) -> JSONResponse:
    """Return one task's full parsed spec — metadata + every file."""
    try:
        source = parse_dataset_uri(uri)
    except ValueError as exc:
        raise HTTPException(400, str(exc)) from exc
    try:
        if source.kind == "hf":
            # Pull just this one task's files, not the entire dataset.
            root = fetch_hf_task(source, task, force=bool(refresh))
        else:
            root = fetch_dataset(source, force=bool(refresh))
        t = load_task(root, task)
    except FileNotFoundError as exc:
        raise HTTPException(404, str(exc)) from exc
    except Exception as exc:  # noqa: BLE001
        raise HTTPException(502, f"load failed: {exc}") from exc
    return JSONResponse({
        "id": t.id,
        "name": t.name,
        "org": t.org,
        "version": t.version,
        "description": t.description,
        "instruction_inline": t.instruction_inline,
        "difficulty": t.difficulty,
        "category": t.category,
        "keywords": t.keywords,
        "agent_timeout_sec": t.agent_timeout_sec,
        "verifier_timeout_sec": t.verifier_timeout_sec,
        "repo2env": t.repo2env,
        "task_toml_raw": t.task_toml_raw,
        "files": t.files,
    })


@app.get("/api/config")
def api_config() -> JSONResponse:
    """Runtime config for the UI. On a Hugging Face Space, $SPACE_HOST is the
    public app host (e.g. owner-name.hf.space) — we surface it so the deep-link
    / badge examples show the real Space URL instead of localhost."""
    import os
    return JSONResponse({
        "space_host": os.environ.get("SPACE_HOST") or None,
        "space_id": os.environ.get("SPACE_ID") or None,
    })


@app.get("/healthz")
def healthz() -> dict:
    return {"ok": True}


# ---------------------------------------------------------------------------
# UI (static SPA)
# ---------------------------------------------------------------------------

@app.get("/")
def index() -> FileResponse:
    return FileResponse(STATIC / "index.html", media_type="text/html")


app.mount("/static", StaticFiles(directory=str(STATIC)), name="static")