import scala.collection.mutable
import scala.util.matching.Regex
object WordDeduplicator:
/** Removes duplicate words from a free-text string containing Unicode characters.
* Preserves word order and the case of the first occurrence.
*
* @param input The input string containing text and punctuation.
* @return Space-separated unique words.
*/
def removeDuplicateWords(input: String): String =
if input == null || input.trim.isEmpty then return ""
// 1. Regex pattern using Unicode property escapes:
// \p{L} matches any Unicode letter, \p{N} matches numbers.
val wordRegex: Regex = """[\p{L}\p{N}_]+""".r
// 2. Mutable Set for O(1) case-insensitive duplicate tracking
val seenWords = mutable.HashSet[String]()
// 3. Extract word strings and filter sequentially
val uniqueWords = wordRegex
.findAllIn(input)
.filter { word =>
val lower = word.toLowerCase
// HashSet.add returns true if the element was NOT present
seenWords.add(lower)
}
.toList
// 4. Join unique words with a single space
uniqueWords.mkString(" ")
def main(args: Array[String]): Unit =
val input = "Hello! こんにちは, ,hello こんにちは Bună ziua; Γεια σας Bună ziua *HELLO* Γεια σας"
val result = removeDuplicateWords(input)
println(result)
/*
run:
Hello こんにちは Bună ziua Γεια σας
*/
