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 * https://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.lang3.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 3.0
28 * @deprecated As of <a href="https://commons.apache.org/proper/commons-lang/changes-report.html#a3.6">3.6</a>, use Apache Commons Text
29 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/UnicodeUnescaper.html">
30 * UnicodeUnescaper</a>.
31 */
32 @Deprecated
33 public class UnicodeUnescaper extends CharSequenceTranslator {
34
35 /**
36 * Constructs a new instance.
37 */
38 public UnicodeUnescaper() {
39 // empty
40 }
41
42 /**
43 * {@inheritDoc}
44 */
45 @Override
46 public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
47 if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
48 // consume optional additional 'u' chars
49 int i = 2;
50 while (index + i < input.length() && input.charAt(index + i) == 'u') {
51 i++;
52 }
53
54 if (index + i < input.length() && input.charAt(index + i) == '+') {
55 i++;
56 }
57
58 if (index + i + 4 <= input.length()) {
59 // Get 4 hex digits
60 final CharSequence unicode = input.subSequence(index + i, index + i + 4);
61
62 try {
63 final int value = Integer.parseInt(unicode.toString(), 16);
64 out.write((char) value);
65 } catch (final NumberFormatException nfe) {
66 throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
67 }
68 return i + 4;
69 }
70 throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + input.subSequence(index, input.length())
71 + "' due to end of CharSequence");
72 }
73 return 0;
74 }
75 }