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.text.translate;
018
019import java.io.IOException;
020import java.io.Writer;
021import java.util.Arrays;
022import java.util.Collections;
023import java.util.EnumSet;
024
025import org.apache.commons.lang3.ArrayUtils;
026
027/**
028 * Translates XML numeric entities of the form &#[xX]?\d+;? to
029 * the specific code point.
030 *
031 * Note that the semicolon is optional.
032 *
033 * @since 1.0
034 */
035public class NumericEntityUnescaper extends CharSequenceTranslator {
036
037    /** Enumerates NumericEntityUnescaper options for unescaping. */
038    public enum OPTION {
039
040        /**
041         * Requires a semicolon.
042         */
043        semiColonRequired,
044
045        /**
046         * Does not require a semicolon.
047         */
048        semiColonOptional,
049
050        /**
051         * Throws an exception if a semicolon is missing.
052         */
053        errorIfNoSemiColon
054    }
055
056    /** Default options. */
057    private static final EnumSet<OPTION> DEFAULT_OPTIONS = EnumSet
058        .copyOf(Collections.singletonList(OPTION.semiColonRequired));
059
060    /** EnumSet of OPTIONS, given from the constructor, read-only. */
061    private final EnumSet<OPTION> options;
062
063    /**
064     * Creates a UnicodeUnescaper.
065     *
066     * The constructor takes a list of options, only one type of which is currently
067     * available (whether to allow, error or ignore the semicolon on the end of a
068     * numeric entity to being missing).
069     *
070     * For example, to support numeric entities without a ';':
071     *    new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.semiColonOptional)
072     * and to throw an IllegalArgumentException when they're missing:
073     *    new NumericEntityUnescaper(NumericEntityUnescaper.OPTION.errorIfNoSemiColon)
074     *
075     * Note that the default behavior is to ignore them.
076     *
077     * @param options to apply to this unescaper
078     */
079    public NumericEntityUnescaper(final OPTION... options) {
080        this.options = ArrayUtils.isEmpty(options) ? DEFAULT_OPTIONS : EnumSet.copyOf(Arrays.asList(options));
081    }
082
083    /**
084     * Tests whether the passed in option is currently set.
085     *
086     * @param option to check state of
087     * @return whether the option is set
088     */
089    public boolean isSet(final OPTION option) {
090        return options.contains(option);
091    }
092
093    /**
094     * {@inheritDoc}
095     */
096    @Override
097    public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
098        final int seqEnd = input.length();
099        // Uses -2 to ensure there is something after the &#
100        if (input.charAt(index) == '&' && index < seqEnd - 2 && input.charAt(index + 1) == '#') {
101            int start = index + 2;
102            boolean isHex = false;
103
104            final char firstChar = input.charAt(start);
105            if (firstChar == 'x' || firstChar == 'X') {
106                start++;
107                isHex = true;
108
109                // Check there's more than just an x after the &#
110                if (start == seqEnd) {
111                    return 0;
112                }
113            }
114
115            int end = start;
116            // Note that this supports character codes without a ; on the end
117            while (end < seqEnd && (input.charAt(end) >= '0' && input.charAt(end) <= '9'
118                                    || input.charAt(end) >= 'a' && input.charAt(end) <= 'f'
119                                    || input.charAt(end) >= 'A' && input.charAt(end) <= 'F')) {
120                end++;
121            }
122
123            final boolean semiNext = end != seqEnd && input.charAt(end) == ';';
124
125            if (!semiNext) {
126                if (isSet(OPTION.semiColonRequired)) {
127                    return 0;
128                }
129                if (isSet(OPTION.errorIfNoSemiColon)) {
130                    throw new IllegalArgumentException("Semi-colon required at end of numeric entity");
131                }
132            }
133
134            final int entityValue;
135            try {
136                if (isHex) {
137                    entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 16);
138                } else {
139                    entityValue = Integer.parseInt(input.subSequence(start, end).toString(), 10);
140                }
141            } catch (final NumberFormatException nfe) {
142                return 0;
143            }
144
145            if (entityValue > 0xFFFF) {
146                final char[] chrs = Character.toChars(entityValue);
147                writer.write(chrs[0]);
148                writer.write(chrs[1]);
149            } else {
150                writer.write(entityValue);
151            }
152
153            return 2 + end - start + (isHex ? 1 : 0) + (semiNext ? 1 : 0);
154        }
155        return 0;
156    }
157}