001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.collections4.trie.analyzer;
018
019import org.apache.commons.collections4.trie.KeyAnalyzer;
020
021/**
022 * An {@link KeyAnalyzer} for {@link String}s.
023 * <p>
024 * This class is stateless.
025 * </p>
026 * @since 4.0
027 */
028public class StringKeyAnalyzer extends KeyAnalyzer<String> {
029
030    private static final long serialVersionUID = -7032449491269434877L;
031
032    /** A singleton instance of {@link StringKeyAnalyzer}. */
033    public static final StringKeyAnalyzer INSTANCE = new StringKeyAnalyzer();
034
035    /** The number of bits per {@link Character}. */
036    public static final int LENGTH = Character.SIZE;
037
038    /** A bit mask where the first bit is 1 and the others are zero. */
039    private static final int MSB = 0x8000;
040
041    /** Returns a bit mask where the given bit is set. */
042    private static int mask(final int bit) {
043        return MSB >>> bit;
044    }
045
046    /**
047     * Constructs a new instance.
048     *
049     * @deprecated Use {@link #INSTANCE}.
050     */
051    @Deprecated
052    public StringKeyAnalyzer() {
053        // empty
054    }
055
056    @Override
057    public int bitIndex(final String key, final int offsetInBits, final int lengthInBits,
058                        final String other, final int otherOffsetInBits, final int otherLengthInBits) {
059
060        boolean allNull = true;
061
062        if (offsetInBits % LENGTH != 0 || otherOffsetInBits % LENGTH != 0
063                || lengthInBits % LENGTH != 0 || otherLengthInBits % LENGTH != 0) {
064            throw new IllegalArgumentException("The offsets and lengths must be at Character boundaries");
065        }
066
067        final int beginIndex1 = offsetInBits / LENGTH;
068        final int beginIndex2 = otherOffsetInBits / LENGTH;
069
070        final int endIndex1 = beginIndex1 + lengthInBits / LENGTH;
071        final int endIndex2 = beginIndex2 + otherLengthInBits / LENGTH;
072
073        final int length = Math.max(endIndex1, endIndex2);
074
075        // Look at each character, and if they're different
076        // then figure out which bit makes the difference
077        // and return it.
078        char k = 0, f = 0;
079        for (int i = 0; i < length; i++) {
080            final int index1 = beginIndex1 + i;
081            final int index2 = beginIndex2 + i;
082
083            if (index1 >= endIndex1) {
084                k = 0;
085            } else {
086                k = key.charAt(index1);
087            }
088
089            if (other == null || index2 >= endIndex2) {
090                f = 0;
091            } else {
092                f = other.charAt(index2);
093            }
094
095            if (k != f) {
096                final int x = k ^ f;
097                return i * LENGTH + Integer.numberOfLeadingZeros(x) - LENGTH;
098            }
099
100            if (k != 0) {
101                allNull = false;
102            }
103        }
104
105        // All bits are 0
106        if (allNull) {
107            return NULL_BIT_KEY;
108        }
109
110        // Both keys are equal
111        return EQUAL_BIT_KEY;
112    }
113
114    @Override
115    public int bitsPerElement() {
116        return LENGTH;
117    }
118
119    @Override
120    public boolean isBitSet(final String key, final int bitIndex, final int lengthInBits) {
121        if (key == null || bitIndex >= lengthInBits) {
122            return false;
123        }
124
125        final int index = bitIndex / LENGTH;
126        final int bit = bitIndex % LENGTH;
127
128        return (key.charAt(index) & mask(bit)) != 0;
129    }
130
131    @Override
132    public boolean isPrefix(final String prefix, final int offsetInBits,
133                            final int lengthInBits, final String key) {
134        if (offsetInBits % LENGTH != 0 || lengthInBits % LENGTH != 0) {
135            throw new IllegalArgumentException(
136                    "Cannot determine prefix outside of Character boundaries");
137        }
138
139        final String s1 = prefix.substring(offsetInBits / LENGTH, lengthInBits / LENGTH);
140        return key.startsWith(s1);
141    }
142
143    @Override
144    public int lengthInBits(final String key) {
145        return key != null ? key.length() * LENGTH : 0;
146    }
147}