import gradio as gr
import re
import textstat
from transformers import pipeline
from langdetect import detect

# Load a summarization model
summarizer = pipeline("summarization")

def text_analysis_and_summarization(text):
    # Analyze text: word count, character count, language detection, and readability
    words = re.findall(r'\w+', text.lower())
    sentences = re.split(r'[.!?]+', text)
    num_sentences = len(sentences) - 1
    num_words = len(words)
    num_chars = len("".join(words))
    reading_ease = textstat.flesch_reading_ease(text)
    language = detect(text)

    # Summarize text using the transformer model
    summary = summarizer(text, max_length=130, min_length=30, do_sample=False)[0]['summary_text']

    # Format the results
    return {
        "Language": language,
        "Sentences": num_sentences,
        "Words": num_words,
        "Characters": num_chars,
        "Readability (Flesch Reading Ease)": reading_ease,
        "Summary": summary
    }

# Define an interface for text analysis and summarization
text_analysis_and_summarization_interface = gr.Interface(fn=text_analysis_and_summarization, 
                                                        inputs=gr.Textbox(lines=4, placeholder="Type something here..."), 
                                                        outputs=gr.JSON(label="Text Analysis and Summarization"))

# Launch the interface
if __name__ == "__main__":
    text_analysis_and_summarization_interface.launch()