001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3.text.translate;
018
019import java.io.IOException;
020import java.io.Writer;
021
022/**
023 * Translates escaped Unicode values of the form \\u+\d\d\d\d back to
024 * Unicode. It supports multiple 'u' characters and will work with or
025 * without the +.
026 *
027 * @since 3.0
028 * @deprecated As of 3.6, use Apache Commons Text
029 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/UnicodeUnescaper.html">
030 * UnicodeUnescaper</a> instead
031 */
032@Deprecated
033public class UnicodeUnescaper extends CharSequenceTranslator {
034
035    /**
036     * Constructs a new instance.
037     */
038    public UnicodeUnescaper() {
039        // empty
040    }
041
042    /**
043     * {@inheritDoc}
044     */
045    @Override
046    public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
047        if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
048            // consume optional additional 'u' chars
049            int i = 2;
050            while (index + i < input.length() && input.charAt(index + i) == 'u') {
051                i++;
052            }
053
054            if (index + i < input.length() && input.charAt(index + i) == '+') {
055                i++;
056            }
057
058            if (index + i + 4 <= input.length()) {
059                // Get 4 hex digits
060                final CharSequence unicode = input.subSequence(index + i, index + i + 4);
061
062                try {
063                    final int value = Integer.parseInt(unicode.toString(), 16);
064                    out.write((char) value);
065                } catch (final NumberFormatException nfe) {
066                    throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
067                }
068                return i + 4;
069            }
070            throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + input.subSequence(index, input.length())
071                    + "' due to end of CharSequence");
072        }
073        return 0;
074    }
075}