1
1
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-10-06 07:32:38 +02:00
Files
MarginaliaSearch/code/functions/language-processing/java/nu/marginalia/segmentation/BasicSentenceExtractor.java

17 lines
503 B
Java
Raw Normal View History

package nu.marginalia.segmentation;
import ca.rmen.porterstemmer.PorterStemmer;
import org.apache.commons.lang3.StringUtils;
public class BasicSentenceExtractor {
private static PorterStemmer porterStemmer = new PorterStemmer();
public static String[] getStemmedParts(String sentence) {
String[] parts = StringUtils.split(sentence, ' ');
for (int i = 0; i < parts.length; i++) {
parts[i] = porterStemmer.stemWord(parts[i]);
}
return parts;
}
}