from pprint import pformat

import spacy
import gradio as gr
from textacy import preprocessing

import en_ethicalads_topics


ea_nlp = en_ethicalads_topics.load()

preprocessor = preprocessing.make_pipeline(
    preprocessing.normalize.unicode,
    preprocessing.remove.punctuation,
    preprocessing.normalize.whitespace,
)


def classify(input_text):
    processed_input = preprocessor(input_text)
    ea_output = ea_nlp(processed_input)
    return pformat(sorted(ea_output.cats.items(), key=lambda x: x[1], reverse=True))


iface = gr.Interface(
    fn=classify,
    inputs=gr.Textbox(lines=5, placeholder="Input text to detect the topic classification. Works best on inputs of 100+ words."),
    outputs="text",
)
iface.launch()