from bs4 import BeautifulSoup
from bs4.element import Comment
import requests
from transformers import pipeline


def tag_visible(element):
    if element.parent.name in ['style', 'script', 'head', 'title', 'meta', '[document]']:
        return False
    if isinstance(element, Comment):
        return False
    return True


def getTalkPage(wiki_page):
  if "wikipedia.org" in wiki_page:
      response = requests.get(wiki_page)
      soup = BeautifulSoup(response.content, 'html.parser')

      talk_url = soup.find_all("a", {"rel": "discussion"})
      if len(talk_url) > 0:
        talk_url = talk_url[0]["href"]
        try:
          talk_response = requests.get("https://en.wikipedia.org" + talk_url)
          talk_soup = BeautifulSoup(talk_response.content, 'html.parser')
          talk_texts = talk_soup.findAll(text=True)
          visible_texts = filter(tag_visible, talk_texts)
          return u" ".join(t.strip() for t in visible_texts)

        except Exception as error:
          print('Error occured: {}'.format(error))

classifier = pipeline(model="amitkayal/bert-finetuned-sem_eval-english", top_k=None)

def tone_talkpage(url):
    """This function goes through the content of the talk page, break it down into smaller parts.
    It then takes those smaller parts through the fine-tuned BERT tone detection model, then average out the results for the whole page
    Output: the 3 most likely tones of the page with its corresponding probability"""

    talk_content = getTalkPage(url)
    tone_labels = {'anger': 0, 'anticipation': 0, 'disgust': 0, 'fear': 0, 'joy': 0, 'love': 0, 'optimism': 0, 'pessimism': 0, 'sadness': 0, 'surprise': 0, 'trust': 0}
    if talk_content:
        breakdown = talk_content.split()
        n = 150 #because the max amount of sequence length is 512
        breakdown_lst = [' '.join(breakdown[i:i+n]) for i in range(0,len(talk_content),n)]
        for ele in breakdown_lst:
            res = classifier(ele)[0]
            for tone_res in res:
                tone_labels[tone_res["label"]] += tone_res["score"]
    
        lst_len = len(breakdown_lst)
    
        for key, val in tone_labels.items():
            tone_labels[key] = val/lst_len
    
    sorted_tones = sorted(tone_labels.items(), key=lambda x:x[1], reverse=True)
    return sorted_tones[:3]