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 * https://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
18 package org.apache.commons.text.translate;
19
20 import java.io.IOException;
21 import java.io.Writer;
22 import java.util.BitSet;
23 import java.util.HashMap;
24 import java.util.Map;
25 import java.util.Objects;
26
27 /**
28 * Translates a value using a lookup table.
29 *
30 * @since 1.0
31 */
32 public class LookupTranslator extends CharSequenceTranslator {
33
34 /** The mapping to be used in translation. */
35 private final Map<String, String> lookupMap;
36 /** The first character of each key in the lookupMap. */
37 private final BitSet prefixSet;
38 /** The length of the shortest key in the lookupMap. */
39 private final int shortest;
40 /** The length of the longest key in the lookupMap. */
41 private final int longest;
42
43 /**
44 * Constructs the lookup table to be used in translation.
45 *
46 * Note that, as of Lang 3.1 (the origin of this code), the key to the lookup table is converted to a java.lang.String. This is because we need the key to
47 * support hashCode and equals(Object), allowing it to be the key for a HashMap. See LANG-882.
48 *
49 * @param lookupMap Map<CharSequence, CharSequence> table of translator mappings, may not be null.
50 */
51 public LookupTranslator(final Map<CharSequence, CharSequence> lookupMap) {
52 Objects.requireNonNull(lookupMap, "lookupMap");
53 this.lookupMap = new HashMap<>();
54 this.prefixSet = new BitSet();
55 int currentShortest = Integer.MAX_VALUE;
56 int currentLongest = 0;
57 for (final Map.Entry<CharSequence, CharSequence> pair : lookupMap.entrySet()) {
58 this.lookupMap.put(pair.getKey().toString(), pair.getValue().toString());
59 this.prefixSet.set(pair.getKey().charAt(0));
60 final int sz = pair.getKey().length();
61 if (sz < currentShortest) {
62 currentShortest = sz;
63 }
64 if (sz > currentLongest) {
65 currentLongest = sz;
66 }
67 }
68 this.shortest = currentShortest;
69 this.longest = currentLongest;
70 }
71
72 /**
73 * {@inheritDoc}
74 */
75 @Override
76 public int translate(final CharSequence input, final int index, final Writer writer) throws IOException {
77 // check if translation exists for the input at position index
78 if (prefixSet.get(input.charAt(index))) {
79 int max = longest;
80 if (index + longest > input.length()) {
81 max = input.length() - index;
82 }
83 // implement greedy algorithm by trying maximum match first
84 for (int i = max; i >= shortest; i--) {
85 final CharSequence subSeq = input.subSequence(index, index + i);
86 final String result = lookupMap.get(subSeq.toString());
87 if (result != null) {
88 writer.write(result);
89 return Character.codePointCount(subSeq, 0, subSeq.length());
90 }
91 }
92 }
93 return 0;
94 }
95 }