app.py

import json

import gradio as gr
import pandas as pd


def read_json(file_name):
    with open(file_name, "r") as f:
        json_data = json.load(f)
    return json_data


json_file = "awesome-japanese-nlp-resources-search.json"
json_data = read_json(json_file)
data = {"project_name": [], "source": [], "description": [], "languages": []}

for data_json in json_data:
    url = data_json["url"]
    description = data_json["description"]
    project_name = data_json["project_name"]
    source = data_json["source"]
    languages = data_json["languages"]

    data["project_name"].append(f"[{project_name}]({url})")
    data["source"].append(source)
    data["description"].append(description)
    data["languages"].append(", ".join(languages))

data = pd.DataFrame(data)


def show_search_results(language_filter, queries, source_checkbox):
    queries = queries.lower()
    queries = queries.split()

    df_search = data

    if language_filter:
        regex_pattern = r"\b" + language_filter + r"\b"
        df_search = df_search[
            df_search["languages"].str.contains(
                regex_pattern, case=False, regex=True, na=False
            )
        ]

    if "GitHub" not in source_checkbox:
        df_search = df_search[df_search["source"] != "GitHub"]

    if "Hugging Face" not in source_checkbox:
        df_search = df_search[df_search["source"] != "Hugging Face"]

    for query in queries:
        contained_description = data["description"].str.contains(query)

        contained_project_name = data["project_name"].str.contains(query)
        df_search = df_search[contained_description | contained_project_name]
    return df_search


with gr.Blocks() as demo:
    gr.Markdown(
        """
    # Awesome Japanese NLP resources search 🔎
    You can search for open-source software from [1250+ Japanese NLP repositories](https://github.com/taishi-i/awesome-japanese-nlp-resources).
    """
    )

    query = gr.Textbox(
        label="Search English or Japanese words", placeholder="llm"
    )
    languages = [
        "Python",
        "Jupyter Notebook",
        "Java",
        "C++",
        "JavaScript",
        "TypeScript",
        "C#",
        "Rust",
        "Go",
        "C",
        "Kotlin",
        "Ruby",
        "Perl",
        "Lua",
        "PHP",
        "Julia",
        "R",
        "Swift",
        "Haskell",
        "Scala",
    ]

    language_selector = gr.Dropdown(
        label="Programming Language",
        choices=languages,
    )

    source_checkbox = gr.CheckboxGroup(
        ["GitHub", "Hugging Face"],
        value=["GitHub", "Hugging Face"],
        label="Source",
    )

    df = gr.DataFrame(
        value=data, type="pandas", datatype="markdown", height=1000
    )

    query.change(
        fn=show_search_results,
        inputs=[language_selector, query, source_checkbox],
        outputs=df,
    )
    language_selector.change(
        fn=show_search_results,
        inputs=[language_selector, query, source_checkbox],
        outputs=df,
    )
    source_checkbox.change(
        fn=show_search_results,
        inputs=[language_selector, query, source_checkbox],
        outputs=df,
    )

demo.launch()