View Javadoc
1   /*
2    * Copyright (C) 2011 The Guava Authors
3    *
4    * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
5    * in compliance with the License. You may obtain a copy of the License at
6    *
7    * http://www.apache.org/licenses/LICENSE-2.0
8    *
9    * Unless required by applicable law or agreed to in writing, software distributed under the License
10   * is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
11   * or implied. See the License for the specific language governing permissions and limitations under
12   * the License.
13   */
14  
15  package com.google.common.hash;
16  
17  import com.google.common.annotations.Beta;
18  import com.google.errorprone.annotations.CanIgnoreReturnValue;
19  import java.nio.ByteBuffer;
20  import java.nio.charset.Charset;
21  
22  /**
23   * A {@link PrimitiveSink} that can compute a hash code after reading the input. Each hasher should
24   * translate all multibyte values ({@link #putInt(int)}, {@link #putLong(long)}, etc) to bytes in
25   * little-endian order.
26   *
27   * <p><b>Warning:</b> The result of calling any methods after calling {@link #hash} is undefined.
28   *
29   * <p><b>Warning:</b> Using a specific character encoding when hashing a {@link CharSequence} with
30   * {@link #putString(CharSequence, Charset)} is generally only useful for cross-language
31   * compatibility (otherwise prefer {@link #putUnencodedChars}). However, the character encodings
32   * must be identical across languages. Also beware that {@link Charset} definitions may occasionally
33   * change between Java releases.
34   *
35   * <p><b>Warning:</b> Chunks of data that are put into the {@link Hasher} are not delimited. The
36   * resulting {@link HashCode} is dependent only on the bytes inserted, and the order in which they
37   * were inserted, not how those bytes were chunked into discrete put() operations. For example, the
38   * following three expressions all generate colliding hash codes: <pre>   {@code
39   *
40   *   newHasher().putByte(b1).putByte(b2).putByte(b3).hash()
41   *   newHasher().putByte(b1).putBytes(new byte[] { b2, b3 }).hash()
42   *   newHasher().putBytes(new byte[] { b1, b2, b3 }).hash()}</pre>
43   *
44   * <p>If you wish to avoid this, you should either prepend or append the size of each chunk. Keep in
45   * mind that when dealing with char sequences, the encoded form of two concatenated char sequences
46   * is not equivalent to the concatenation of their encoded form. Therefore,
47   * {@link #putString(CharSequence, Charset)} should only be used consistently with <i>complete</i>
48   * sequences and not broken into chunks.
49   *
50   * @author Kevin Bourrillion
51   * @since 11.0
52   */
53  @Beta
54  @CanIgnoreReturnValue
55  public interface Hasher extends PrimitiveSink {
56    @Override
57    Hasher putByte(byte b);
58  
59    @Override
60    Hasher putBytes(byte[] bytes);
61  
62    @Override
63    Hasher putBytes(byte[] bytes, int off, int len);
64  
65    @Override
66    Hasher putBytes(ByteBuffer bytes);
67  
68    @Override
69    Hasher putShort(short s);
70  
71    @Override
72    Hasher putInt(int i);
73  
74    @Override
75    Hasher putLong(long l);
76  
77    /**
78     * Equivalent to {@code putInt(Float.floatToRawIntBits(f))}.
79     */
80    @Override
81    Hasher putFloat(float f);
82  
83    /**
84     * Equivalent to {@code putLong(Double.doubleToRawLongBits(d))}.
85     */
86    @Override
87    Hasher putDouble(double d);
88  
89    /**
90     * Equivalent to {@code putByte(b ? (byte) 1 : (byte) 0)}.
91     */
92    @Override
93    Hasher putBoolean(boolean b);
94  
95    @Override
96    Hasher putChar(char c);
97  
98    /**
99     * Equivalent to processing each {@code char} value in the {@code CharSequence}, in order. In
100    * other words, no character encoding is performed; the low byte and high byte of each {@code
101    * char} are hashed directly (in that order). The input must not be updated while this method is
102    * in progress.
103    *
104    * <p><b>Warning:</b> This method will produce different output than most other languages do when
105    * running the same hash function on the equivalent input. For cross-language compatibility, use
106    * {@link #putString}, usually with a charset of UTF-8. For other use cases, use {@code
107    * putUnencodedChars}.
108    *
109    * @since 15.0 (since 11.0 as putString(CharSequence)).
110    */
111   @Override
112   Hasher putUnencodedChars(CharSequence charSequence);
113 
114   /**
115    * Equivalent to {@code putBytes(charSequence.toString().getBytes(charset))}.
116    *
117    * <p><b>Warning:</b> This method, which reencodes the input before hashing it, is useful only for
118    * cross-language compatibility. For other use cases, prefer {@link #putUnencodedChars}, which is
119    * faster, produces the same output across Java releases, and hashes every {@code char} in the
120    * input, even if some are invalid.
121    */
122   @Override
123   Hasher putString(CharSequence charSequence, Charset charset);
124 
125   /**
126    * A simple convenience for {@code funnel.funnel(object, this)}.
127    */
128   <T> Hasher putObject(T instance, Funnel<? super T> funnel);
129 
130   /**
131    * Computes a hash code based on the data that have been provided to this hasher. The result is
132    * unspecified if this method is called more than once on the same instance.
133    */
134   HashCode hash();
135 
136   /**
137    * {@inheritDoc}
138    *
139    * @deprecated This returns {@link Object#hashCode()}; you almost certainly mean to call
140    *     {@code hash().asInt()}.
141    */
142   @Override
143   @Deprecated
144   int hashCode();
145 }