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.lang3.text.translate;
018
019import java.io.IOException;
020import java.io.Writer;
021import java.util.HashMap;
022import java.util.HashSet;
023
024/**
025 * Translates a value using a lookup table.
026 *
027 * @since 3.0
028 * @version $Id: LookupTranslator.java 1669520 2015-03-27 08:03:41Z britter $
029 */
030public class LookupTranslator extends CharSequenceTranslator {
031
032    private final HashMap<String, String> lookupMap;
033    private final HashSet<Character> prefixSet;
034    private final int shortest;
035    private final int longest;
036
037    /**
038     * Define the lookup table to be used in translation
039     *
040     * Note that, as of Lang 3.1, the key to the lookup table is converted to a
041     * java.lang.String. This is because we need the key to support hashCode and
042     * equals(Object), allowing it to be the key for a HashMap. See LANG-882.
043     *
044     * @param lookup CharSequence[][] table of size [*][2]
045     */
046    public LookupTranslator(final CharSequence[]... lookup) {
047        lookupMap = new HashMap<String, String>();
048        prefixSet = new HashSet<Character>();
049        int _shortest = Integer.MAX_VALUE;
050        int _longest = 0;
051        if (lookup != null) {
052            for (final CharSequence[] seq : lookup) {
053                this.lookupMap.put(seq[0].toString(), seq[1].toString());
054                this.prefixSet.add(seq[0].charAt(0));
055                final int sz = seq[0].length();
056                if (sz < _shortest) {
057                    _shortest = sz;
058                }
059                if (sz > _longest) {
060                    _longest = sz;
061                }
062            }
063        }
064        shortest = _shortest;
065        longest = _longest;
066    }
067
068    /**
069     * {@inheritDoc}
070     */
071    @Override
072    public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
073        // check if translation exists for the input at position index
074        if (prefixSet.contains(input.charAt(index))) {
075            int max = longest;
076            if (index + longest > input.length()) {
077                max = input.length() - index;
078            }
079            // implement greedy algorithm by trying maximum match first
080            for (int i = max; i >= shortest; i--) {
081                final CharSequence subSeq = input.subSequence(index, index + i);
082                final String result = lookupMap.get(subSeq.toString());
083
084                if (result != null) {
085                    out.write(result);
086                    return i;
087                }
088            }
089        }
090        return 0;
091    }
092}