from heapq import nlargest
import spacy
from spacy.lang.en.stop_words import STOP_WORDS
from string import punctuation
import gradio as gr



# Stopwords
stopwords = list(STOP_WORDS)
nlp = spacy.load('en_core_web_sm')
punctuation = punctuation + '\n'
import spacy
from spacy.lang.en.stop_words import STOP_WORDS
from string import punctuation

# Prediction 
def prediction(text):
  doc = nlp(text)
  len1 = len(text)
  tokens = [token.text for token in doc]
  word_frequencies = {}
  for word in doc:
    if word.text.lower() not in stopwords:
      if word.text.lower() not in punctuation:
        if word.text not in word_frequencies.keys():
          word_frequencies[word.text] = 1
        else:
          word_frequencies[word.text] += 1
  max_frequency = max(word_frequencies.values())
  for word in word_frequencies.keys():
    word_frequencies[word] = word_frequencies[word]/max_frequency
  sentence_tokens = [sent for sent in doc.sents]
  sentence_scores = {}
  for sent in sentence_tokens:
    for word in sent:
      if word.text.lower() in word_frequencies.keys():
        if sent not in sentence_scores.keys():
          sentence_scores[sent] = word_frequencies[word.text.lower()]
        else:
          sentence_scores[sent] += word_frequencies[word.text.lower()]
  select_length = int(len(sentence_tokens)*0.3)
  summary = nlargest(select_length, sentence_scores, key = sentence_scores.get)
  org_len = len(text.split(' '))
  summary = (str(summary[0]))
  sum_len = len(summary.split(' '))
  return summary,org_len,sum_len


#predicted_label, score = occ_predict("img1.jpg")
#inputs = gr.inputs.text(label)
#label = gr.outputs.Label(num_top_classes=2)
#EXAMPLES = ["img1.png","img2.png","img3.png","img10.png","img8.png","img9.png"]
#DESCRIPTION = "Occlusion means the act of closing, blocking or shutting something or the state of being closed or blocked"
#summary = prediction(text)
#print(summary)
outputs = [
    gr.Textbox(lines =5,label = "Summarization of text"),
    gr.Number(label="Word Count of given Text"),
    gr.Number(label="Word Count of Summarized Text")
]

demo_app = gr.Interface(
    fn=prediction, 
    inputs=gr.Textbox(lines =10,label = " Enter the Text", max_lines = 20),
    outputs= outputs,
    title = "Text Summarization",
    #description = DESCRIPTION,
    #cache_example = True,
    #live = True,
    theme = 'huggingface'
)
#if __name__ == "__main__":
demo_app.launch() 
#demo_app.launch(debug=True, enable_queue = True)