View Javadoc
1   /*
2    * Licensed to the Apache Software Foundation (ASF) under one or more
3    * contributor license agreements.  See the NOTICE file distributed with
4    * this work for additional information regarding copyright ownership.
5    * The ASF licenses this file to You under the Apache License, Version 2.0
6    * (the "License"); you may not use this file except in compliance with
7    * the License.  You may obtain a copy of the License at
8    * 
9    *      http://www.apache.org/licenses/LICENSE-2.0
10   * 
11   * Unless required by applicable law or agreed to in writing, software
12   * distributed under the License is distributed on an "AS IS" BASIS,
13   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14   * See the License for the specific language governing permissions and
15   * limitations under the License.
16   */
17  package org.apache.commons.lang3.text.translate;
18  
19  import java.io.IOException;
20  import java.io.Writer;
21  import java.util.HashMap;
22  import java.util.HashSet;
23  
24  /**
25   * Translates a value using a lookup table.
26   *
27   * @since 3.0
28   * @version $Id$
29   */
30  public class LookupTranslator extends CharSequenceTranslator {
31  
32      private final HashMap<String, String> lookupMap;
33      private final HashSet<Character> prefixSet;
34      private final int shortest;
35      private final int longest;
36  
37      /**
38       * Define the lookup table to be used in translation
39       *
40       * Note that, as of Lang 3.1, the key to the lookup table is converted to a
41       * java.lang.String. This is because we need the key to support hashCode and
42       * equals(Object), allowing it to be the key for a HashMap. See LANG-882.
43       *
44       * @param lookup CharSequence[][] table of size [*][2]
45       */
46      public LookupTranslator(final CharSequence[]... lookup) {
47          lookupMap = new HashMap<String, String>();
48          prefixSet = new HashSet<Character>();
49          int _shortest = Integer.MAX_VALUE;
50          int _longest = 0;
51          if (lookup != null) {
52              for (final CharSequence[] seq : lookup) {
53                  this.lookupMap.put(seq[0].toString(), seq[1].toString());
54                  this.prefixSet.add(seq[0].charAt(0));
55                  final int sz = seq[0].length();
56                  if (sz < _shortest) {
57                      _shortest = sz;
58                  }
59                  if (sz > _longest) {
60                      _longest = sz;
61                  }
62              }
63          }
64          shortest = _shortest;
65          longest = _longest;
66      }
67  
68      /**
69       * {@inheritDoc}
70       */
71      @Override
72      public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
73          // check if translation exists for the input at position index
74          if (prefixSet.contains(input.charAt(index))) {
75              int max = longest;
76              if (index + longest > input.length()) {
77                  max = input.length() - index;
78              }
79              // implement greedy algorithm by trying maximum match first
80              for (int i = max; i >= shortest; i--) {
81                  final CharSequence subSeq = input.subSequence(index, index + i);
82                  final String result = lookupMap.get(subSeq.toString());
83  
84                  if (result != null) {
85                      out.write(result);
86                      return i;
87                  }
88              }
89          }
90          return 0;
91      }
92  }