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.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 1.0
28 */
29 public class LookupTranslator extends CharSequenceTranslator {
30
31 private final HashMap<String, String> lookupMap;
32 private final HashSet<Character> prefixSet;
33 private final int shortest;
34 private final int longest;
35
36 /**
37 * Define the lookup table to be used in translation
38 *
39 * Note that, as of Lang 3.1, the key to the lookup table is converted to a
40 * java.lang.String. This is because we need the key to support hashCode and
41 * equals(Object), allowing it to be the key for a HashMap. See LANG-882.
42 *
43 * @param lookup CharSequence[][] table of size [*][2]
44 */
45 public LookupTranslator(final CharSequence[]... lookup) {
46 lookupMap = new HashMap<>();
47 prefixSet = new HashSet<>();
48 int _shortest = Integer.MAX_VALUE;
49 int _longest = 0;
50 if (lookup != null) {
51 for (final CharSequence[] seq : lookup) {
52 this.lookupMap.put(seq[0].toString(), seq[1].toString());
53 this.prefixSet.add(seq[0].charAt(0));
54 final int sz = seq[0].length();
55 if (sz < _shortest) {
56 _shortest = sz;
57 }
58 if (sz > _longest) {
59 _longest = sz;
60 }
61 }
62 }
63 shortest = _shortest;
64 longest = _longest;
65 }
66
67 /**
68 * {@inheritDoc}
69 */
70 @Override
71 public int translate(final CharSequence input, final int index, final Writer out) throws IOException {
72 // check if translation exists for the input at position index
73 if (prefixSet.contains(input.charAt(index))) {
74 int max = longest;
75 if (index + longest > input.length()) {
76 max = input.length() - index;
77 }
78 // implement greedy algorithm by trying maximum match first
79 for (int i = max; i >= shortest; i--) {
80 final CharSequence subSeq = input.subSequence(index, index + i);
81 final String result = lookupMap.get(subSeq.toString());
82
83 if (result != null) {
84 out.write(result);
85 return i;
86 }
87 }
88 }
89 return 0;
90 }
91 }