import nltk
from nltk import WordNetLemmatizer
from nltk.stem import PorterStemmer
from nltk.corpus import stopwords
from textblob import TextBlob
from nltk.tokenize import RegexpTokenizer

import re
import string

nltk.download('stopwords')
nltk.download('punkt')
nltk.download('omw-1.4')

from collections import OrderedDict

from wordcloud import WordCloud
from matplotlib import pyplot as plt

def join_countries(a_list):
    joined_string = "|".join(a_list)
    return joined_string

def join_columns(x):
    return ' '.join(x.dropna())


def remove_short_words(text, length):
    if text is None:
        text =  ''
    else:
        regex = '\W*\\b\w{1,' + str(length) +'}\\b'
        shortword = re.compile(regex)
        text = shortword.sub('', text)
    return text


def remove_duplicates_from_cell(text):
    if text is None:
        text =  ''
    else:
        text = text.split()
        text = ' '.join(OrderedDict.fromkeys(text).keys())
    return text


def make_lower_case(text):
    if text is None:
        text =  ''
    else:
        text = text.lower()
        return text


def remove_curly_brackets(text):
    if text is None:
        text = ''
    else:
        text = text.replace("{","").replace("}","")
    return text


def remove_double_quotes(text):
    if text is None:
        text = ''
    else:
        text = text.replace('"','')
    return text

def remove_and_semicolon(text):
    if text is None:
        text = ''
    else:
        text = re.sub(r'\&[^]]*\;', '', text)
    return text

def remove_slash_n(text):
    if text is None:
        text = ''
    else:
        text = text.replace('\n','')
    return text

def remove_urls(text):
    if text is None:
        text = ''
    else:
        text = re.sub(r'http\S+', '', text)
    return text

def remove_html_tags(text):
    if text is None:
        text = ''
    else:
        clean = re.compile('<.*?>')
        text = re.sub(clean, '', text)
    return text

def remove_forward_slash(text):
    if text is None:
        text = ''
    else:
        text = text.replace('/','')
    return text

def remove_and_sign(text):
    if text is None:
        text = ''
    else:
        text = text.replace('&','')
    return text

def remove_dash_sign(text):
    if text is None:
        text = ''
    else:
        text = text.replace('-','')
    return text

# Function for replacing | sign with comma
def replace_straight(text):
    if text is None:
        text = ''
    else:
        text = text.replace("|",",")
    return text


# Function for replacing | sign with space
def replace_straight_with_space(text):
    if text is None:
        text = ''
    else:
        text = text.replace("|"," ")
    return text


# Function for replace comma with | sign
def replace_comma_straight(text):
    if text is None:
        text = ''
    else:
        text = text.replace(",","|")
    return text

# Function for revoming non ascii symbols
def remove_non_ascii(s):
    if s is None:
        s = ''
    else:
        s = "".join(i for i in s if  ord(i)<128)
    return s


def remove_stop_words(text):
    if text is None:
        text = ''
    else:
        text = text.split()
        stops = set(stopwords.words("english"))
        text = [w for w in text if not w in stops]
        text = " ".join(text)
    return text


def remove_punctuation(text):
    if text is None:
        text = ''
    else:        
        tokenizer = RegexpTokenizer(r'\w+')
        text = tokenizer.tokenize(text)
        text = " ".join(text)
    return text


# Function for removing the html tags
def remove_html(text):
    if text is None:
        text = ''
    else:
        html_pattern = re.compile('<.*?>')
        text = html_pattern.sub(r'', text)
    return text


def draw_word_cloud(paragraph):

    # Create WordCloud 
    word_cloud = WordCloud(width = 1000, height = 800, 
                           background_color ='Black', 
                           #stopwords = stopword_list, 
                           min_font_size = 14).generate(paragraph) 
    
    # Set wordcloud figure size
    plt.figure(figsize = (10, 6)); 
    
    # Show image
    plt.imshow(word_cloud); 
    
    # Remove Axis
    plt.axis("off");  
    plt.show();
    
    
def tokenize(x):
    tokenizer = RegexpTokenizer(r'\w+')
    return tokenizer.tokenize(x)


def stemmer(x):
    stemmer = PorterStemmer()
    return ' '.join([stemmer.stem(word) for word in x])


def lemmatize(x):
    lemmatizer = WordNetLemmatizer()
    return ' '.join([lemmatizer.lemmatize(word) for word in x])