001/*
002 * Copyright (C) 2009 The Guava Authors
003 *
004 * Licensed under the Apache License, Version 2.0 (the "License");
005 * you may not use this file except in compliance with the License.
006 * You may obtain a copy of the License at
007 *
008 * http://www.apache.org/licenses/LICENSE-2.0
009 *
010 * Unless required by applicable law or agreed to in writing, software
011 * distributed under the License is distributed on an "AS IS" BASIS,
012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
013 * See the License for the specific language governing permissions and
014 * limitations under the License.
015 */
016
017package com.google.common.escape;
018
019import static com.google.common.base.Preconditions.checkNotNull;
020
021import com.google.common.annotations.Beta;
022import com.google.common.annotations.GwtCompatible;
023import com.google.common.annotations.VisibleForTesting;
024
025import java.util.Collections;
026import java.util.Map;
027
028/**
029 * An implementation-specific parameter class suitable for initializing
030 * {@link ArrayBasedCharEscaper} or {@link ArrayBasedUnicodeEscaper} instances.
031 * This class should be used when more than one escaper is created using the
032 * same character replacement mapping to allow the underlying (implementation
033 * specific) data structures to be shared.
034 *
035 * <p>The size of the data structure used by ArrayBasedCharEscaper and
036 * ArrayBasedUnicodeEscaper is proportional to the highest valued character that
037 * has a replacement. For example a replacement map containing the single
038 * character '{@literal \}u1000' will require approximately 16K of memory.
039 * As such sharing this data structure between escaper instances is the primary
040 * goal of this class.
041 *
042 * @author David Beaumont
043 * @since 15.0
044 */
045@Beta
046@GwtCompatible
047public final class ArrayBasedEscaperMap {
048  /**
049   * Returns a new ArrayBasedEscaperMap for creating ArrayBasedCharEscaper or
050   * ArrayBasedUnicodeEscaper instances.
051   *
052   * @param replacements a map of characters to their escaped representations
053   */
054  public static ArrayBasedEscaperMap create(
055      Map<Character, String> replacements) {
056    return new ArrayBasedEscaperMap(createReplacementArray(replacements));
057  }
058
059  // The underlying replacement array we can share between multiple escaper
060  // instances.
061  private final char[][] replacementArray;
062
063  private ArrayBasedEscaperMap(char[][] replacementArray) {
064    this.replacementArray = replacementArray;
065  }
066
067  // Returns the non-null array of replacements for fast lookup.
068  char[][] getReplacementArray() {
069    return replacementArray;
070  }
071
072  // Creates a replacement array from the given map. The returned array is a
073  // linear lookup table of replacement character sequences indexed by the
074  // original character value.
075  @VisibleForTesting
076  static char[][] createReplacementArray(Map<Character, String> map) {
077    checkNotNull(map);  // GWT specific check (do not optimize)
078    if (map.isEmpty()) {
079      return EMPTY_REPLACEMENT_ARRAY;
080    }
081    char max = Collections.max(map.keySet());
082    char[][] replacements = new char[max + 1][];
083    for (char c : map.keySet()) {
084      replacements[c] = map.get(c).toCharArray();
085    }
086    return replacements;
087  }
088
089  // Immutable empty array for when there are no replacements.
090  private static final char[][] EMPTY_REPLACEMENT_ARRAY = new char[0][0];
091}