app.py

from __future__ import annotations

import json
import tempfile
from pathlib import Path

import gradio as gr
from huggingface_hub import hf_hub_download

from modular_graph_and_candidates import (
    build_graph_json,
    generate_html,
    build_timeline_json,
    generate_timeline_html,
    filter_graph_by_threshold,
)

def _escape_srcdoc(text: str) -> str:
    return (
        text.replace("&", "&")
            .replace("\"", """)
            .replace("'", "'")
            .replace("<", "&lt;")
            .replace(">", "&gt;")
    )

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, *, height_vh: int = 85):
    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}-m{int(multimodal)}"
    json_fp = hf_hub_download(repo_id=repo_id, filename=f"{kind}/{key}.json", repo_type="dataset")

    raw_data = json.loads(Path(json_fp).read_text(encoding="utf-8"))
    filtered_data = filter_graph_by_threshold(raw_data, threshold)

    if kind == "timeline":
        raw_html = generate_timeline_html(filtered_data)
    else:
        raw_html = generate_html(filtered_data)

    iframe_html = f'<iframe style="width:100%;height:{height_vh}vh;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.dumps(filtered_data), encoding="utf-8")
    return iframe_html, str(tmp)

def run_loc(sim_method: str, multimodal: bool, *, height_vh: int = 85):
    latest_fp = hf_hub_download(repo_id=CACHE_REPO, filename="latest.json", repo_type="dataset")
    info = json.loads(Path(latest_fp).read_text(encoding="utf-8"))
    sha = info["sha"]
    key = f"{sha}/{sim_method}-m{int(multimodal)}"
    html_fp = hf_hub_download(repo_id=CACHE_REPO, filename=f"loc/{key}.html", repo_type="dataset")
    raw_html = Path(html_fp).read_text(encoding="utf-8")
    iframe_html = f'<iframe style="width:100%;height:{height_vh}vh;border:none;" srcdoc="{_escape_srcdoc(raw_html)}"></iframe>'
    return iframe_html

def run_graph(repo_url: str, threshold: float, multimodal: bool, sim_method: str, *, height_vh: int = 85):
    return _fetch_from_cache_repo("graph", sim_method, threshold, multimodal, height_vh=height_vh)

def run_timeline(repo_url: str, threshold: float, multimodal: bool, sim_method: str, *, height_vh: int = 85):
    return _fetch_from_cache_repo("timeline", sim_method, threshold, multimodal, height_vh=height_vh)

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

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

TAB_INDEX = {"timeline": 0, "loc": 1, "graph": 2}

with gr.Blocks() as demo:
    html = gr.HTML()
    def _load():
        return run_loc(sim_method="jaccard", multimodal=False)
    demo.load(_load, outputs=[html])

if __name__ == "__main__":
    demo.launch()