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.text.translate;
019
020import java.io.IOException;
021import java.io.Writer;
022import java.util.BitSet;
023import java.util.HashMap;
024import java.util.Map;
025import java.util.Objects;
026
027/**
028 * Translates a value using a lookup table.
029 *
030 * @since 1.0
031 */
032public class LookupTranslator extends CharSequenceTranslator {
033
034    /** The mapping to be used in translation. */
035    private final Map<String, String> lookupMap;
036
037    /** The first character of each key in the lookupMap. */
038    private final BitSet prefixSet;
039
040    /** The length of the shortest key in the lookupMap. */
041    private final int shortest;
042
043    /** The length of the longest key in the lookupMap. */
044    private final int longest;
045
046    /**
047     * Constructs the lookup table to be used in translation.
048     * <p>
049     * Note that, as of Lang 3.1 (the origin of this code), the key to the lookup table is converted to a {@link String}. This is because we need the key to
050     * support hashCode and equals(Object), allowing it to be the key for a HashMap. See LANG-882.
051     * </p>
052     *
053     * @param lookupMap Map&lt;CharSequence, CharSequence&gt; table of translator mappings, may not be null.
054     */
055    public LookupTranslator(final Map<CharSequence, CharSequence> lookupMap) {
056        Objects.requireNonNull(lookupMap, "lookupMap");
057        this.lookupMap = new HashMap<>();
058        this.prefixSet = new BitSet();
059        int currentShortest = Integer.MAX_VALUE;
060        int currentLongest = 0;
061        for (final Map.Entry<CharSequence, CharSequence> pair : lookupMap.entrySet()) {
062            this.lookupMap.put(pair.getKey().toString(), pair.getValue().toString());
063            this.prefixSet.set(pair.getKey().charAt(0));
064            final int sz = pair.getKey().length();
065            if (sz < currentShortest) {
066                currentShortest = sz;
067            }
068            if (sz > currentLongest) {
069                currentLongest = sz;
070            }
071        }
072        this.shortest = currentShortest;
073        this.longest = currentLongest;
074    }
075
076    /**
077     * {@inheritDoc}
078     */
079    @Override
080    public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
081        // check if translation exists for the input at position index
082        if (prefixSet.get(input.charAt(index))) {
083            int max = longest;
084            if (index + longest > input.length()) {
085                max = input.length() - index;
086            }
087            // implement greedy algorithm by trying maximum match first
088            for (int i = max; i >= shortest; i--) {
089                final CharSequence subSeq = input.subSequence(index, index + i);
090                final String result = lookupMap.get(subSeq.toString());
091                if (result != null) {
092                    writer.write(result);
093                    return Character.codePointCount(subSeq, 0, subSeq.length());
094                }
095            }
096        }
097        return 0;
098    }
099}