object StopwordRemover {
// A stopwords list is a collection of commonly used words in a language
// that are often removed during text processing tasks.
val stopWords: Array[String] = Array(
"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", "to", "from", "in", "out", "on", "off", "over", "further",
"then", "here", "there", "when", "where", "why", "how", "all", "any", "both", "each",
"few", "more", "most", "other", "some", "such", "no", "nor", "not", "only", "own",
"so", "than", "too", "very", "can", "will", "just", "don", "should", "now"
)
def isStopWord(word: String): Boolean = stopWords.contains(word)
def splitWords(input: String): Array[String] = input.trim.split("\\s+")
def removeStopWords(words: Array[String]): String = {
words.filterNot(isStopWord).mkString(" ")
}
def main(args: Array[String]): Unit = {
val input = "a scala and java to python a we if c# then a and aa"
println(s"Original: $input")
val words = splitWords(input)
val filtered = removeStopWords(words)
println(s"Filtered: $filtered")
}
}
/*
run:
Original: a scala and java to python a we if c# then a and aa
Filtered: scala java python c# aa
*/
