app.py

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
from huggingface_hub import hf_hub_download

import gradio as gr

from modular_graph_and_candidates import build_graph_json, generate_html, build_timeline_json, generate_timeline_html

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

CACHE_REPO = "Molbap/hf_cached_embeds_log"

def _fetch_from_cache_repo(kind: str, sim_method: str, threshold: float, multimodal: bool):
    repo_id = CACHE_REPO
    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)


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 run_graph(repo_url: str, threshold: float, multimodal: bool, sim_method: str):
    return _fetch_from_cache_repo("graph", sim_method, threshold, multimodal)


def run_timeline(repo_url: str, threshold: float, multimodal: bool, sim_method: str):
    return _fetch_from_cache_repo("timeline", sim_method, threshold, multimodal)



# ───────────────────────────── 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"])