View Javadoc

1   /**
2    *
3    * Licensed to the Apache Software Foundation (ASF) under one
4    * or more contributor license agreements.  See the NOTICE file
5    * distributed with this work for additional information
6    * regarding copyright ownership.  The ASF licenses this file
7    * to you under the Apache License, Version 2.0 (the
8    * "License"); you may not use this file except in compliance
9    * with the License.  You may obtain a copy of the License at
10   *
11   *     http://www.apache.org/licenses/LICENSE-2.0
12   *
13   * Unless required by applicable law or agreed to in writing, software
14   * distributed under the License is distributed on an "AS IS" BASIS,
15   * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16   * See the License for the specific language governing permissions and
17   * limitations under the License.
18   */
19  package org.apache.hadoop.hbase.io.hfile;
20  
21  import java.io.IOException;
22  import java.nio.ByteBuffer;
23  
24  import org.apache.hadoop.classification.InterfaceAudience;
25  import org.apache.hadoop.hbase.KeyValue;
26  
27  /**
28   * A scanner allows you to position yourself within a HFile and
29   * scan through it.  It allows you to reposition yourself as well.
30   *
31   * <p>A scanner doesn't always have a key/value that it is pointing to
32   * when it is first created and before
33   * {@link #seekTo()}/{@link #seekTo(byte[])} are called.
34   * In this case, {@link #getKey()}/{@link #getValue()} returns null.  At most
35   * other times, a key and value will be available.  The general pattern is that
36   * you position the Scanner using the seekTo variants and then getKey and
37   * getValue.
38   */
39  @InterfaceAudience.Private
40  public interface HFileScanner {
41    /**
42     * SeekTo or just before the passed <code>key</code>.  Examine the return
43     * code to figure whether we found the key or not.
44     * Consider the key stream of all the keys in the file,
45     * <code>k[0] .. k[n]</code>, where there are n keys in the file.
46     * @param key Key to find.
47     * @return -1, if key < k[0], no position;
48     * 0, such that k[i] = key and scanner is left in position i; and
49     * 1, such that k[i] < key, and scanner is left in position i.
50     * The scanner will position itself between k[i] and k[i+1] where
51     * k[i] < key <= k[i+1].
52     * If there is no key k[i+1] greater than or equal to the input key, then the
53     * scanner will position itself at the end of the file and next() will return
54     * false when it is called.
55     * @throws IOException
56     */
57    int seekTo(byte[] key) throws IOException;
58    int seekTo(byte[] key, int offset, int length) throws IOException;
59    /**
60     * Reseek to or just before the passed <code>key</code>. Similar to seekTo
61     * except that this can be called even if the scanner is not at the beginning
62     * of a file.
63     * This can be used to seek only to keys which come after the current position
64     * of the scanner.
65     * Consider the key stream of all the keys in the file,
66     * <code>k[0] .. k[n]</code>, where there are n keys in the file after
67     * current position of HFileScanner.
68     * The scanner will position itself between k[i] and k[i+1] where
69     * k[i] < key <= k[i+1].
70     * If there is no key k[i+1] greater than or equal to the input key, then the
71     * scanner will position itself at the end of the file and next() will return
72     * false when it is called.
73     * @param key Key to find (should be non-null)
74     * @return -1, if key < k[0], no position;
75     * 0, such that k[i] = key and scanner is left in position i; and
76     * 1, such that k[i] < key, and scanner is left in position i.
77     * @throws IOException
78     */
79    int reseekTo(byte[] key) throws IOException;
80    int reseekTo(byte[] key, int offset, int length) throws IOException;
81    /**
82     * Consider the key stream of all the keys in the file,
83     * <code>k[0] .. k[n]</code>, where there are n keys in the file.
84     * @param key Key to find
85     * @return false if key <= k[0] or true with scanner in position 'i' such
86     * that: k[i] < key.  Furthermore: there may be a k[i+1], such that
87     * k[i] < key <= k[i+1] but there may also NOT be a k[i+1], and next() will
88     * return false (EOF).
89     * @throws IOException
90     */
91    boolean seekBefore(byte[] key) throws IOException;
92    boolean seekBefore(byte[] key, int offset, int length) throws IOException;
93    /**
94     * Positions this scanner at the start of the file.
95     * @return False if empty file; i.e. a call to next would return false and
96     * the current key and value are undefined.
97     * @throws IOException
98     */
99    boolean seekTo() throws IOException;
100   /**
101    * Scans to the next entry in the file.
102    * @return Returns false if you are at the end otherwise true if more in file.
103    * @throws IOException
104    */
105   boolean next() throws IOException;
106   /**
107    * Gets a buffer view to the current key. You must call
108    * {@link #seekTo(byte[])} before this method.
109    * @return byte buffer for the key. The limit is set to the key size, and the
110    * position is 0, the start of the buffer view.
111    */
112   ByteBuffer getKey();
113   /**
114    * Gets a buffer view to the current value.  You must call
115    * {@link #seekTo(byte[])} before this method.
116    *
117    * @return byte buffer for the value. The limit is set to the value size, and
118    * the position is 0, the start of the buffer view.
119    */
120   ByteBuffer getValue();
121   /**
122    * @return Instance of {@link KeyValue}.
123    */
124   KeyValue getKeyValue();
125   /**
126    * Convenience method to get a copy of the key as a string - interpreting the
127    * bytes as UTF8. You must call {@link #seekTo(byte[])} before this method.
128    * @return key as a string
129    */
130   String getKeyString();
131   /**
132    * Convenience method to get a copy of the value as a string - interpreting
133    * the bytes as UTF8. You must call {@link #seekTo(byte[])} before this method.
134    * @return value as a string
135    */
136   String getValueString();
137   /**
138    * @return Reader that underlies this Scanner instance.
139    */
140   HFile.Reader getReader();
141   /**
142    * @return True is scanner has had one of the seek calls invoked; i.e.
143    * {@link #seekBefore(byte[])} or {@link #seekTo()} or {@link #seekTo(byte[])}.
144    * Otherwise returns false.
145    */
146   boolean isSeeked();
147 }