Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| import lexrank as lr | |
| import nltk | |
| import metrics | |
| def summarize(in_text): | |
| if len(in_text)==0: | |
| return 'Error: No text provided', None | |
| nltk_file = '/home/user/nltk_data/tokenizers/punkt.zip' | |
| if os.path.exists(nltk_file): | |
| print('nltk punkt file exists in ', nltk_file) | |
| else: | |
| print("downloading punkt file") | |
| nltk.download('punkt') | |
| in_longtext = [] | |
| # Discard all senteces that have less than 10 words in them | |
| in_text_sentenses = in_text.split('.') | |
| print(in_text_sentenses) | |
| for sen in in_text_sentenses: | |
| if len(sen.split()) > 10: | |
| in_longtext.append(sen) | |
| in_text = '.'.join(in_longtext)+'.' | |
| # The size of the summary is limited to 1024 | |
| # The Lexrank algorith accepts only sentences as a limit | |
| # We start with one sentece and check the token size | |
| # Then increase the number of sentences until the tokensize | |
| # of the next sentence exceed the limit | |
| target_tokens = 1024 | |
| in_sents = metrics.num_sentences(in_text) | |
| out_text = lr.get_Summary(in_text,1) | |
| n_tokens= metrics.num_tokens(out_text) | |
| prev_n_tokens=0 | |
| for sen in range(2, in_sents): | |
| if n_tokens >= target_tokens: | |
| n_tokens = prev_n_tokens | |
| break | |
| else: | |
| out_text = lr.get_Summary(in_text,sen) | |
| prev_n_tokens = n_tokens | |
| n_tokens= metrics.num_tokens(out_text) | |
| n_sents = metrics.num_sentences(out_text) | |
| n_words = metrics.num_words(out_text) | |
| n_chars = metrics.num_chars(out_text) | |
| return out_text, n_words, n_sents, n_chars, n_tokens | |
| demo = gr.Interface(summarize, | |
| inputs=["text"] , | |
| outputs=[gr.Textbox(label="Extractive Summary"), | |
| gr.Number(label="Number of Words"), | |
| gr.Number(label="Number of Sentences"), | |
| gr.Number(label="Number of Characters"), | |
| gr.Number(label="Number of Tokens")], | |
| allow_flagging="never", queue = True) | |
| if __name__ == "__main__": | |
| demo.launch() | |