Unicode Normalization

gistfile1.scala

import java.text.Normalizer


/**
 * Problem: Characters with accents or other adornments can be encoded in several different ways in Unicode
 * However, from a user point of view if they logically mean the same, text search should make no distinction 
 * between the different notations. So it's important to store text in normalized unicode form.  Code below shows
 * how to check if text is normalized and how you can normalize it.
 **/
object NormalizationTest {
  def main(args: Array[String]) {
    val text = "16-bit transceiver with direction pin, 30 Ω series termination resistors;"
    println(text)
    println(Normalizer.isNormalized(text, Normalizer.Form.NFC))
    val normalizedText = Normalizer.normalize(text, Normalizer.Form.NFC)
    println(normalizedText)
    println(Normalizer.isNormalized(normalizedText, Normalizer.Form.NFC))
  }
}


/**
 * Output printed to console:
 * -------------------------------
 * 
 * 16-bit transceiver with direction pin, 30 Ω series termination resistors;
 * false
 * 16-bit transceiver with direction pin, 30 Ω series termination resistors;
 * true
 */