fn main() {
let input = "a rust and java to python a we if c# then a and aa";
println!("Original: {}", input);
let words: Vec<&str> = split_words(input);
let filtered = remove_stop_words(&words);
println!("Filtered: {}", filtered);
}
// A stopwords list is a collection of commonly used words in a language
// that are often removed during text processing tasks.
fn stop_words() -> &'static [&'static str] {
&[
"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",
]
}
fn is_stop_word(word: &str) -> bool {
stop_words().contains(&word)
}
fn split_words(input: &str) -> Vec<&str> {
input.trim().split_whitespace().collect()
}
fn remove_stop_words(words: &[&str]) -> String {
words
.iter()
.filter(|word| !is_stop_word(word))
.cloned()
.collect::<Vec<&str>>()
.join(" ")
}
/*
run:
Original: a rust and java to python a we if c# then a and aa
Filtered: rust java python c# aa
*/
