View Javadoc
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  
19  import java.io.IOException;
20  import java.io.Writer;
21  
22  /**
23   * Translates escaped Unicode values of the form \\u+\d\d\d\d back to
24   * Unicode. It supports multiple 'u' characters and will work with or
25   * without the +.
26   *
27   * @since 1.0
28   */
29  public class UnicodeUnescaper extends CharSequenceTranslator {
30  
31      /**
32       * Constructs a new instance.
33       */
34      public UnicodeUnescaper() {
35          // empty
36      }
37  
38      /**
39       * {@inheritDoc}
40       */
41      @Override
42      public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
43          if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
44              // consume optional additional 'u' chars
45              int i = 2;
46              while (index + i < input.length() && input.charAt(index + i) == 'u') {
47                  i++;
48              }
49  
50              if (index + i < input.length() && input.charAt(index + i) == '+') {
51                  i++;
52              }
53  
54              if (index + i + 4 <= input.length()) {
55                  // Get 4 hex digits
56                  final CharSequence unicode = input.subSequence(index + i, index + i + 4);
57  
58                  try {
59                      final int value = Integer.parseInt(unicode.toString(), 16);
60                      writer.write((char) value);
61                  } catch (final NumberFormatException nfe) {
62                      throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
63                  }
64                  return i + 4;
65              }
66              throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '"
67                      + input.subSequence(index, input.length())
68                      + "' due to end of CharSequence");
69          }
70          return 0;
71      }
72  }