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;
021import java.util.Arrays;
022import java.util.Collections;
023import java.util.EnumSet;
024
025/**
026 * Translate XML numeric entities of the form &#[xX]?\d+;? to
027 * the specific codepoint.
028 *
029 * Note that the semi-colon is optional.
030 *
031 * @since 3.0
032 * @deprecated as of 3.6, use commons-text
033 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/translate/NumericEntityUnescaper.html">
034 * NumericEntityUnescaper</a> instead
035 */
036@Deprecated
037public class NumericEntityUnescaper extends CharSequenceTranslator {
038
039    public enum OPTION {
040        semiColonRequired, semiColonOptional, errorIfNoSemiColon
041    }
042
043    // TODO?: Create an OptionsSet class to hide some of the conditional logic below
044    private final EnumSet<OPTION> options;
045
046    /**
047     * Create a UnicodeUnescaper.
048     *
049     * The constructor takes a list of options, only one type of which is currently
050     * available (whether to allow, error or ignore the semi-colon on the end of a
051     * numeric entity to being missing).
052     *
053     * For example, to support numeric entities without a ';':
054     *    new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.semiColonOptional)
055     * and to throw an IllegalArgumentException when they're missing:
056     *    new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.errorIfNoSemiColon)
057     *
058     * Note that the default behavior is to ignore them.
059     *
060     * @param options to apply to this unescaper
061     */
062    public NumericEntityUnescaper(final OPTION... options) {
063        if (options.length > 0) {
064            this.options = EnumSet.copyOf(Arrays.asList(options));
065        } else {
066            this.options = EnumSet.copyOf(Collections.singletonList(OPTION.semiColonRequired));
067        }
068    }
069
070    /**
071     * Whether the passed in option is currently set.
072     *
073     * @param option to check state of
074     * @return whether the option is set
075     */
076    public boolean isSet(final OPTION option) {
077        return options != null && options.contains(option);
078    }
079
080    /**
081     * {@inheritDoc}
082     */
083    @Override
084    public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
085        final int seqEnd = input.length();
086        // Uses -2 to ensure there is something after the &#
087        if (input.charAt(index) == '&' && index < seqEnd - 2 && input.charAt(index + 1) == '#') {
088            int start = index + 2;
089            boolean isHex = false;
090
091            final char firstChar = input.charAt(start);
092            if (firstChar == 'x' || firstChar == 'X') {
093                start++;
094                isHex = true;
095
096                // Check there's more than just an x after the &#
097                if (start == seqEnd) {
098                    return 0;
099                }
100            }
101
102            int end = start;
103            // Note that this supports character codes without a ; on the end
104            while (end < seqEnd && ( input.charAt(end) >= '0' && input.charAt(end) <= '9' ||
105                                    input.charAt(end) >= 'a' && input.charAt(end) <= 'f' ||
106                                    input.charAt(end) >= 'A' && input.charAt(end) <= 'F' ) ) {
107                end++;
108            }
109
110            final boolean semiNext = end != seqEnd && input.charAt(end) == ';';
111
112            if (!semiNext) {
113                if (isSet(OPTION.semiColonRequired)) {
114                    return 0;
115                } else
116                if (isSet(OPTION.errorIfNoSemiColon)) {
117                    throw new IllegalArgumentException("Semi-colon required at end of numeric entity");
118                }
119            }
120
121            int entityValue;
122            try {
123                if (isHex) {
124                    entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 16);
125                } else {
126                    entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 10);
127                }
128            } catch(final NumberFormatException nfe) {
129                return 0;
130            }
131
132            if (entityValue > 0xFFFF) {
133                final char[] chars = Character.toChars(entityValue);
134                out.write(chars[0]);
135                out.write(chars[1]);
136            } else {
137                out.write(entityValue);
138            }
139
140            return 2 + end - start + (isHex ? 1 : 0) + (semiNext ? 1 : 0);
141        }
142        return 0;
143    }
144}