UnicodeUnpairedSurrogateRemover.java

  1. /*
  2.  * Licensed to the Apache Software Foundation (ASF) under one or more
  3.  * contributor license agreements.  See the NOTICE file distributed with
  4.  * this work for additional information regarding copyright ownership.
  5.  * The ASF licenses this file to You under the Apache License, Version 2.0
  6.  * (the "License"); you may not use this file except in compliance with
  7.  * the License.  You may obtain a copy of the License at
  8.  *
  9.  *      http://www.apache.org/licenses/LICENSE-2.0
  10.  *
  11.  * Unless required by applicable law or agreed to in writing, software
  12.  * distributed under the License is distributed on an "AS IS" BASIS,
  13.  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14.  * See the License for the specific language governing permissions and
  15.  * limitations under the License.
  16.  */
  17. package org.apache.commons.text.translate;

  18. import java.io.IOException;
  19. import java.io.Writer;

  20. /**
  21.  * Helper subclass to CharSequenceTranslator to remove unpaired surrogates.
  22.  *
  23.  * @since 1.0
  24.  */
  25. public class UnicodeUnpairedSurrogateRemover extends CodePointTranslator {

  26.     /**
  27.      * Creates a new instance.
  28.      */
  29.     public UnicodeUnpairedSurrogateRemover() {
  30.         // empty
  31.     }

  32.     /**
  33.      * Implements translate to throw out unpaired surrogates.
  34.      * {@inheritDoc}
  35.      */
  36.     @Override
  37.     public boolean translate(final int codePoint, final Writer writer) throws IOException {
  38.         // If true, it is a surrogate. Write nothing and say we've translated. Otherwise return false, and don't translate it.
  39.         return codePoint >= Character.MIN_SURROGATE && codePoint <= Character.MAX_SURROGATE;
  40.     }
  41. }