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 * @version $Id: UnicodeUnescaper.java 1606060 2014-06-27 12:33:07Z ggregory $
029 */
030public class UnicodeUnescaper extends CharSequenceTranslator {
031
032    /**
033     * {@inheritDoc}
034     */
035    @Override
036    public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
037        if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
038            // consume optional additional 'u' chars
039            int i = 2;
040            while (index + i < input.length() && input.charAt(index + i) == 'u') {
041                i++;
042            }
043
044            if (index + i < input.length() && input.charAt(index + i) == '+') {
045                i++;
046            }
047
048            if (index + i + 4 <= input.length()) {
049                // Get 4 hex digits
050                final CharSequence unicode = input.subSequence(index + i, index + i + 4);
051
052                try {
053                    final int value = Integer.parseInt(unicode.toString(), 16);
054                    out.write((char) value);
055                } catch (final NumberFormatException nfe) {
056                    throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
057                }
058                return i + 4;
059            }
060            throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + input.subSequence(index, input.length())
061                    + "' due to end of CharSequence");
062        }
063        return 0;
064    }
065}