import re
import string
from textblob import TextBlob

stopword = ["i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", "yourself",
            "yourselves", "he", "him", "his", "himself", "she", "her", "hers", "herself", "it", "its", "itself", "they",
            "them", "their", "theirs", "themselves", "what", "which", "who", "whom", "this", "that", "these", "those",
            "am", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had", "having", "do", "does",
            "did", "doing", "a", "an", "the", "and", "but", "if", "or", "because", "as", "until", "while", "of", "at",
            "by", "for", "with", "about", "against", "between", "into", "through", "during", "before", "after", "above",
            "below", "to", "from", "up", "down", "in", "out", "on", "off", "over", "under", "again", "further", "then",
            "once", "here", "there", "when", "where", "why", "how", "all", "any", "both", "each", "few", "more", "most",
            "other", "some", "such", "no", "nor", "not", "only", "own", "same", "so", "than", "too", "very", "s", "t",
            "can", "will", "just", "don", "should", "now"]
punctuations = string.punctuation

def to_lower(text: str) -> str:
    return text.lower()


def remove_html_tags(text: str) -> str:
    pattern = re.compile('<.*?>')
    return pattern.sub(r'', text)


def remove_punctuations(text: str) -> str:
    return text.translate(str.maketrans('', '', punctuations))


def correct_spellings(text: str) -> str:
    return TextBlob(text).correct().string


def remove_stopwords(text: str) -> str:
    return " ".join([word for word in text.split() if word not in stopword])


def clean(text: str) -> str:
    return remove_stopwords(
        correct_spellings(remove_punctuations(remove_html_tags(to_lower(text))))
    )