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.security.InvalidParameterException;
022import java.util.BitSet;
023import java.util.HashMap;
024import java.util.Map;
025
026/**
027 * Translates a value using a lookup table.
028 *
029 * @since 1.0
030 */
031public class LookupTranslator extends CharSequenceTranslator {
032
033    /** The mapping to be used in translation. */
034    private final Map<String, String> lookupMap;
035
036    /** The first character of each key in the lookupMap. */
037    private final BitSet prefixSet;
038
039    /** The length of the shortest key in the lookupMap. */
040    private final int shortest;
041
042    /** The length of the longest key in the lookupMap. */
043    private final int longest;
044
045    /**
046     * Constructs the lookup table to be used in translation
047     *
048     * Note that, as of Lang 3.1 (the origin of this code), the key to the lookup
049     * table is converted to a java.lang.String. This is because we need the key
050     * to support hashCode and equals(Object), allowing it to be the key for a
051     * HashMap. See LANG-882.
052     *
053     * @param lookupMap Map&lt;CharSequence, CharSequence&gt; table of translator
054     *                  mappings
055     */
056    public LookupTranslator(final Map<CharSequence, CharSequence> lookupMap) {
057        if (lookupMap == null) {
058            throw new InvalidParameterException("lookupMap cannot be null");
059        }
060        this.lookupMap = new HashMap<>();
061        this.prefixSet = new BitSet();
062        int currentShortest = Integer.MAX_VALUE;
063        int currentLongest = 0;
064
065        for (final Map.Entry<CharSequence, CharSequence> pair : lookupMap.entrySet()) {
066            this.lookupMap.put(pair.getKey().toString(), pair.getValue().toString());
067            this.prefixSet.set(pair.getKey().charAt(0));
068            final int sz = pair.getKey().length();
069            if (sz < currentShortest) {
070                currentShortest = sz;
071            }
072            if (sz > currentLongest) {
073                currentLongest = sz;
074            }
075        }
076        this.shortest = currentShortest;
077        this.longest = currentLongest;
078    }
079
080    /**
081     * {@inheritDoc}
082     */
083    @Override
084    public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
085        // check if translation exists for the input at position index
086        if (prefixSet.get(input.charAt(index))) {
087            int max = longest;
088            if (index + longest > input.length()) {
089                max = input.length() - index;
090            }
091            // implement greedy algorithm by trying maximum match first
092            for (int i = max; i >= shortest; i--) {
093                final CharSequence subSeq = input.subSequence(index, index + i);
094                final String result = lookupMap.get(subSeq.toString());
095
096                if (result != null) {
097                    writer.write(result);
098                    return Character.codePointCount(subSeq, 0, subSeq.length());
099                }
100            }
101        }
102        return 0;
103    }
104}