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     */
017    package org.apache.commons.lang3.text.translate;
018    
019    import java.io.IOException;
020    import 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 1146554 2011-07-14 04:43:15Z bayard $
029     */
030    public class UnicodeUnescaper extends CharSequenceTranslator {
031    
032        /**
033         * {@inheritDoc}
034         */
035        @Override
036        public int translate(CharSequence input, int index, Writer out) throws IOException {
037            if(input.charAt(index) == '\\') {
038                if( (index + 1 < input.length()) && input.charAt(index + 1) == 'u') {
039                    // consume optional additional 'u' chars
040                    int i=2;
041                    while( (index + i < input.length()) && input.charAt(index + i) == 'u') {
042                        i++;
043                    }
044    
045                    if( (index + i < input.length()) && (input.charAt(index + i) == '+') ) {
046                        i++;
047                    }
048    
049                    if( (index + i + 4 <= input.length()) ) {
050                        // Get 4 hex digits
051                        CharSequence unicode = input.subSequence(index + i, index + i + 4);
052    
053                        try {
054                            int value = Integer.parseInt(unicode.toString(), 16);
055                            out.write((char) value);
056                        } catch (NumberFormatException nfe) {
057                            throw new IllegalArgumentException("Unable to parse unicode value: " + unicode, nfe);
058                        }
059                        return i + 4;
060                    } else {
061                        throw new IllegalArgumentException("Less than 4 hex digits in unicode value: '" + 
062                                                           input.subSequence(index, input.length()) +
063                                                           "' due to end of CharSequence");
064                    }
065                }
066            }
067            return 0;
068        }
069    }