# app.py – Gradio Space wrapper for modular_graph_and_candidates

from __future__ import annotations

import json
import shutil
import subprocess
import tempfile
from datetime import datetime, timedelta
from functools import lru_cache
from pathlib import Path
import os, json, tempfile
from pathlib import Path
from huggingface_hub import hf_hub_download
import gradio as gr

# —— refactored helpers ——
from modular_graph_and_candidates import build_graph_json, generate_html, build_timeline_json, generate_timeline_html

def _escape_srcdoc(text: str) -> str:
    """Escape for inclusion inside an <iframe srcdoc="…"> attribute."""
    return (
        text.replace("&", "&amp;")
            .replace("\"", "&quot;")
            .replace("'", "&#x27;")
            .replace("<", "&lt;")
            .replace(">", "&gt;")
    )

def _fetch_from_cache_repo(kind: str, sim_method: str, threshold: float, multimodal: bool):
    repo_id = "Molbap/hf_cached_embeds_log"
    try:
        latest_fp = hf_hub_download(repo_id=repo_id, filename="latest.json", repo_type="dataset")
        info = json.loads(Path(latest_fp).read_text(encoding="utf-8"))
        sha = info.get("sha")
        key = f"{sha}/{sim_method}-{threshold:.2f}-m{int(multimodal)}"
        html_fp = hf_hub_download(repo_id=repo_id, filename=f"{kind}/{key}.html", repo_type="dataset")
        json_fp = hf_hub_download(repo_id=repo_id, filename=f"{kind}/{key}.json", repo_type="dataset")
        raw_html = Path(html_fp).read_text(encoding="utf-8")
        json_text = Path(json_fp).read_text(encoding="utf-8")
        iframe_html = f'<iframe style="width:100%;height:85vh;border:none;" srcdoc="{_escape_srcdoc(raw_html)}"></iframe>'
        tmp = Path(tempfile.mkstemp(suffix=("_timeline.json" if kind == "timeline" else ".json"))[1])
        tmp.write_text(json_text, encoding="utf-8")
        return iframe_html, str(tmp)
    except Exception:
        return None


HF_MAIN_REPO = "https://github.com/huggingface/transformers"

# ───────────────────────────── cache repo once per 24 h ───────────────────────────

@lru_cache(maxsize=4)
def clone_or_cache(repo_url: str) -> Path:
    """Shallow‑clone *repo_url* and reuse it for 24 h."""
    tmp_root = Path(tempfile.gettempdir())
    cache_dir = tmp_root / f"repo_{abs(hash(repo_url))}"
    stamp = cache_dir / ".cloned_at"

    if cache_dir.exists() and stamp.exists():
        try:
            if datetime.utcnow() - datetime.fromisoformat(stamp.read_text().strip()) < timedelta(days=1):
                return cache_dir
        except Exception:
            pass  # fall through → reclone
        shutil.rmtree(cache_dir, ignore_errors=True)

    subprocess.check_call(["git", "clone", "--depth", "1", repo_url, str(cache_dir)])
    stamp.write_text(datetime.utcnow().isoformat())
    return cache_dir

# ───────────────────────────── main callback ─────────────────────────────────────


def run_graph(repo_url: str, threshold: float, multimodal: bool, sim_method: str):
    """Generate the dependency graph visualization."""
    hit = _fetch_from_cache_repo("graph", sim_method, threshold, multimodal)
    if hit:
        return hit

    repo_path = clone_or_cache(repo_url)

    graph = build_graph_json(
        transformers_dir=repo_path,
        threshold=threshold,
        multimodal=multimodal,
        sim_method=sim_method,
    )

    raw_html = generate_html(graph)

    iframe_html = (
        f'<iframe style="width:100%;height:85vh;border:none;" '
        f'srcdoc="{_escape_srcdoc(raw_html)}"></iframe>'
    )

    tmp_json = Path(tempfile.mktemp(suffix=".json"))
    tmp_json.write_text(json.dumps(graph), encoding="utf-8")
    return iframe_html, str(tmp_json)

def run_timeline(repo_url: str, threshold: float, multimodal: bool, sim_method: str):
    """Generate the chronological timeline visualization."""
    hit = _fetch_from_cache_repo("timeline", sim_method, threshold, multimodal)
    if hit:
        return hit

    repo_path = clone_or_cache(repo_url)

    timeline = build_timeline_json(
        transformers_dir=repo_path,
        threshold=threshold,
        multimodal=multimodal,
        sim_method=sim_method,
    )

    raw_html = generate_timeline_html(timeline)

    iframe_html = (
        f'<iframe style="width:100%;height:85vh;border:none;" '
        f'srcdoc="{_escape_srcdoc(raw_html)}"></iframe>'
    )

    tmp_json = Path(tempfile.mktemp(suffix="_timeline.json"))
    tmp_json.write_text(json.dumps(timeline), encoding="utf-8")
    return iframe_html, str(tmp_json)

# ───────────────────────────── UI ────────────────────────────────────────────────

CUSTOM_CSS = """
#graph_html iframe, #timeline_html iframe {height:85vh !important; width:100% !important; border:none;}
"""

with gr.Blocks(css=CUSTOM_CSS) as demo:
    gr.Markdown("## 🔍 Modular‑candidate explorer for 🤗 Transformers")

    with gr.Tabs():
        with gr.Tab("Dependency Graph"):
            with gr.Row():
                repo_in   = gr.Text(value=HF_MAIN_REPO, label="Repo / fork URL")
                thresh    = gr.Slider(0.50, 0.95, value=0.5, step=0.01, label="Similarity ≥")
                multi_cb  = gr.Checkbox(label="Only multimodal models")
                sim_radio = gr.Radio(["jaccard", "embedding"], value="jaccard", label="Similarity metric")
                go_btn    = gr.Button("Build graph")

            graph_html_out  = gr.HTML(elem_id="graph_html", show_label=False)
            graph_json_out  = gr.File(label="Download graph.json")

            go_btn.click(run_graph, [repo_in, thresh, multi_cb, sim_radio], [graph_html_out, graph_json_out])

        with gr.Tab("Chronological Timeline"):
            with gr.Row():
                timeline_repo_in = gr.Text(value=HF_MAIN_REPO, label="Repo / fork URL")
                timeline_thresh = gr.Slider(0.50, 0.95, value=0.5, step=0.01, label="Similarity ≥")
                timeline_multi_cb = gr.Checkbox(label="Only multimodal models")
                timeline_sim_radio = gr.Radio(["jaccard", "embedding"], value="jaccard", label="Similarity metric")
                timeline_btn = gr.Button("Build timeline")

            timeline_html_out = gr.HTML(elem_id="timeline_html", show_label=False)
            timeline_json_out = gr.File(label="Download timeline.json")

            timeline_btn.click(run_timeline, [timeline_repo_in, timeline_thresh, timeline_multi_cb, timeline_sim_radio], [timeline_html_out, timeline_json_out])

if __name__ == "__main__":
    demo.launch(allowed_paths=["static"])