app.py

#!/usr/bin/env python

import os

import gradio as gr
import pandas as pd
from gradio_calendar import Calendar

from papers import PaperList, get_df
from update_scheduler import UpdateScheduler

DESCRIPTION = "# [Daily Papers](https://huggingface.co/papers)"

paper_list = PaperList(get_df("papers.csv"))

if (SPACE_ID := os.getenv("SPACE_ID")) is not None:
    CRON_HOUR = os.getenv("CRON_HOUR", "*/4")
    CRON_MINUTE = os.getenv("CRON_MINUTE", "0")
    scheduler = UpdateScheduler(space_id=SPACE_ID, cron_hour=CRON_HOUR, cron_minute=CRON_MINUTE)
    scheduler.start()


def update_num_papers(df: pd.DataFrame) -> str:
    return f"{len(df)} / {len(paper_list.df_raw)}"


with gr.Blocks(css="style.css") as demo:
    gr.Markdown(DESCRIPTION)
    with gr.Group():
        with gr.Row():
            start_date = Calendar(label="Start date", type="datetime", value="2023-05-05")
            end_date = Calendar(label="End date", type="datetime")
        search_title = gr.Textbox(label="Search by title")

    num_papers = gr.Textbox(label="Number of papers", value=update_num_papers(paper_list.df_raw), interactive=False)
    df = gr.Dataframe(
        value=paper_list.df_prettified,
        datatype=paper_list.column_datatype,
        type="pandas",
        interactive=False,
        height=1000,
        elem_id="table",
        column_widths=["10%", "10%", "60%", "10%", "10%"],
        wrap=True,
    )

    gr.on(
        triggers=[start_date.change, end_date.change, search_title.submit],
        fn=paper_list.search,
        inputs=[start_date, end_date, search_title],
        outputs=df,
        api_name=False,
    ).then(
        fn=update_num_papers,
        inputs=df,
        outputs=num_papers,
        queue=False,
        api_name=False,
    )

if __name__ == "__main__":
    demo.queue(api_open=False).launch(show_api=False)