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