1   /*
2    * Copyright (C) 2009 The Guava Authors
3    *
4    * Licensed under the Apache License, Version 2.0 (the "License");
5    * you may not use this file except in compliance with the License.
6    * You may obtain a copy of the License at
7    *
8    * http://www.apache.org/licenses/LICENSE-2.0
9    *
10   * Unless required by applicable law or agreed to in writing, software
11   * distributed under the License is distributed on an "AS IS" BASIS,
12   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   * See the License for the specific language governing permissions and
14   * limitations under the License.
15   */
16  
17  package com.google.common.escape;
18  
19  import static com.google.common.base.Preconditions.checkNotNull;
20  
21  import com.google.common.annotations.Beta;
22  import com.google.common.annotations.GwtCompatible;
23  import com.google.common.annotations.VisibleForTesting;
24  
25  import java.util.Collections;
26  import java.util.Map;
27  
28  /**
29   * An implementation-specific parameter class suitable for initializing
30   * {@link ArrayBasedCharEscaper} or {@link ArrayBasedUnicodeEscaper} instances.
31   * This class should be used when more than one escaper is created using the
32   * same character replacement mapping to allow the underlying (implementation
33   * specific) data structures to be shared.
34   *
35   * <p>The size of the data structure used by ArrayBasedCharEscaper and
36   * ArrayBasedUnicodeEscaper is proportional to the highest valued character that
37   * has a replacement. For example a replacement map containing the single
38   * character '{@literal \}u1000' will require approximately 16K of memory.
39   * As such sharing this data structure between escaper instances is the primary
40   * goal of this class.
41   *
42   * @author David Beaumont
43   * @since 15.0
44   */
45  @Beta
46  @GwtCompatible
47  public final class ArrayBasedEscaperMap {
48    /**
49     * Returns a new ArrayBasedEscaperMap for creating ArrayBasedCharEscaper or
50     * ArrayBasedUnicodeEscaper instances.
51     *
52     * @param replacements a map of characters to their escaped representations
53     */
54    public static ArrayBasedEscaperMap create(
55        Map<Character, String> replacements) {
56      return new ArrayBasedEscaperMap(createReplacementArray(replacements));
57    }
58  
59    // The underlying replacement array we can share between multiple escaper
60    // instances.
61    private final char[][] replacementArray;
62  
63    private ArrayBasedEscaperMap(char[][] replacementArray) {
64      this.replacementArray = replacementArray;
65    }
66  
67    // Returns the non-null array of replacements for fast lookup.
68    char[][] getReplacementArray() {
69      return replacementArray;
70    }
71  
72    // Creates a replacement array from the given map. The returned array is a
73    // linear lookup table of replacement character sequences indexed by the
74    // original character value.
75    @VisibleForTesting
76    static char[][] createReplacementArray(Map<Character, String> map) {
77      checkNotNull(map);  // GWT specific check (do not optimize)
78      if (map.isEmpty()) {
79        return EMPTY_REPLACEMENT_ARRAY;
80      }
81      char max = Collections.max(map.keySet());
82      char[][] replacements = new char[max + 1][];
83      for (char c : map.keySet()) {
84        replacements[c] = map.get(c).toCharArray();
85      }
86      return replacements;
87    }
88  
89    // Immutable empty array for when there are no replacements.
90    private static final char[][] EMPTY_REPLACEMENT_ARRAY = new char[0][0];
91  }