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