thibaut-d

clean_corpus = function(x){
  # Replace redundant white spaces and line jumps such as \n
  x = replace_white(x)
  # Replace or remove non ASCII characters
  x = replace_non_ascii(x)
  # Replace contractions such as "you're" by expanded such as "you are"
  x = replace_contraction(x)
  # Replace elongations. Ex: "heyyyyy" is replaced by "Hey"
  x = replace_word_elongation(x)
  # Replace emoji by plain text