| 1,11 → 1,12 |
|---|
| |
| package jomm.utils; |
| |
| import org.apache.lucene.analysis.Token; |
| import org.apache.lucene.analysis.TokenFilter; |
| import org.apache.lucene.analysis.TokenStream; |
| import org.apache.lucene.analysis.Token; |
| |
| import java.io.*; |
| import java.io.IOException; |
| import java.text.Normalizer; |
| |
| |
| /** |
| 30,6 → 31,12 |
|---|
| return new Token(clean(value),t.startOffset(),t.endOffset()); |
| } |
| |
| public static String stripAccents(String s) |
| { |
| s = Normalizer.normalize(s, Normalizer.Form.NFD); |
| s = s.replaceAll("[\\p{InCombiningDiacriticalMarks}]", ""); |
| return s; |
| } |
| public static String clean(String value) |
| { |
| StringBuilder finalTerm = new StringBuilder(); |