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 *      https://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
018package org.apache.commons.lang3.text.translate;
019
020import java.io.IOException;
021import java.io.Writer;
022
023import org.apache.commons.lang3.CharUtils;
024
025/**
026 * Translates escaped Unicode values of the form \\u+\d\d\d\d back to Unicode. It supports multiple 'u' characters and will work with or without the +.
027 * <p>
028 * Only ASCII hexadecimal digits ({@code [0-9a-fA-F]}) are accepted in the four-digit value. Malformed sequences - non-ASCII-hex digits, sign characters,
029 * or an escape truncated by the end of the input - are not translated and pass through unchanged.
030 * </p>
031 *
032 * @since 3.0
033 * @deprecated As of <a href="https://commons.apache.org/proper/commons-lang/changes-report.html#a3.6">3.6</a>, use Apache Commons Text
034 *             <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/UnicodeUnescaper.html">
035 *             UnicodeUnescaper</a>.
036 */
037@Deprecated
038public class UnicodeUnescaper extends CharSequenceTranslator {
039
040    /**
041     * Constructs a new instance.
042     */
043    public UnicodeUnescaper() {
044        // empty
045    }
046
047    /**
048     * {@inheritDoc}
049     */
050    @Override
051    public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
052        if (input.charAt(index) == '\\' && index + 1 < input.length() && input.charAt(index + 1) == 'u') {
053            // consume optional additional 'u' chars
054            int i = 2;
055            while (index + i < input.length() && input.charAt(index + i) == 'u') {
056                i++;
057            }
058            if (index + i < input.length() && input.charAt(index + i) == '+') {
059                i++;
060            }
061            if (index + i + 4 <= input.length()) {
062                // Get 4 hex digits
063                final CharSequence unicode = input.subSequence(index + i, index + i + 4);
064                // Pre-validate that all four characters are ASCII hexadecimal digits, mirroring
065                // NumericEntityUnescaper's CharUtils.isHex discipline. Integer.parseInt is looser than
066                // the \\uXXXX format: it accepts a leading sign and, via Character.digit, decimal digits
067                // from any Unicode script and fullwidth Latin hex letters. Anything that is not a
068                // well-formed escape is not translated and passes through verbatim.
069                for (int j = 0; j < 4; j++) {
070                    if (!CharUtils.isHex(unicode.charAt(j))) {
071                        return 0;
072                    }
073                }
074                out.write((char) Integer.parseInt(unicode.toString(), 16));
075                return i + 4;
076            }
077            // Truncated escape at the end of the input: not a well-formed escape, pass through verbatim.
078            return 0;
079        }
080        return 0;
081    }
082}