View Javadoc
1   /*
2    * Copyright (C) 2010, Google Inc.
3    * and other copyright owners as documented in the project's IP log.
4    *
5    * This program and the accompanying materials are made available
6    * under the terms of the Eclipse Distribution License v1.0 which
7    * accompanies this distribution, is reproduced below, and is
8    * available at http://www.eclipse.org/org/documents/edl-v10.php
9    *
10   * All rights reserved.
11   *
12   * Redistribution and use in source and binary forms, with or
13   * without modification, are permitted provided that the following
14   * conditions are met:
15   *
16   * - Redistributions of source code must retain the above copyright
17   *   notice, this list of conditions and the following disclaimer.
18   *
19   * - Redistributions in binary form must reproduce the above
20   *   copyright notice, this list of conditions and the following
21   *   disclaimer in the documentation and/or other materials provided
22   *   with the distribution.
23   *
24   * - Neither the name of the Eclipse Foundation, Inc. nor the
25   *   names of its contributors may be used to endorse or promote
26   *   products derived from this software without specific prior
27   *   written permission.
28   *
29   * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
30   * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
31   * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
32   * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
33   * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
34   * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
35   * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
36   * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
37   * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
38   * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
39   * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
40   * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
41   * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
42   */
43  
44  package org.eclipse.jgit.internal.storage.pack;
45  
46  /**
47   * Supports {@link DeltaIndex} by performing a partial scan of the content.
48   */
49  class DeltaIndexScanner {
50  	final int[] table;
51  
52  	// To save memory the buckets for hash chains are stored in correlated
53  	// arrays. This permits us to get 3 values per entry, without paying
54  	// the penalty for an object header on each entry.
55  
56  	final long[] entries;
57  
58  	final int[] next;
59  
60  	final int tableMask;
61  
62  	private int entryCnt;
63  
64  	DeltaIndexScanner(byte[] raw, int len) {
65  		// Clip the length so it falls on a block boundary. We won't
66  		// bother to scan the final partial block.
67  		//
68  		len -= (len % DeltaIndex.BLKSZ);
69  
70  		final int worstCaseBlockCnt = len / DeltaIndex.BLKSZ;
71  		if (worstCaseBlockCnt < 1) {
72  			table = new int[] {};
73  			tableMask = 0;
74  
75  			entries = new long[] {};
76  			next = new int[] {};
77  
78  		} else {
79  			table = new int[tableSize(worstCaseBlockCnt)];
80  			tableMask = table.length - 1;
81  
82  			// As we insert blocks we preincrement so that 0 is never a
83  			// valid entry. Therefore we have to allocate one extra space.
84  			//
85  			entries = new long[1 + worstCaseBlockCnt];
86  			next = new int[entries.length];
87  
88  			scan(raw, len);
89  		}
90  	}
91  
92  	private void scan(byte[] raw, int end) {
93  		// We scan the input backwards, and always insert onto the
94  		// front of the chain. This ensures that chains will have lower
95  		// offsets at the front of the chain, allowing us to prefer the
96  		// earlier match rather than the later match.
97  		//
98  		int lastHash = 0;
99  		int ptr = end - DeltaIndex.BLKSZ;
100 		do {
101 			final int key = DeltaIndex.hashBlock(raw, ptr);
102 			final int tIdx = key & tableMask;
103 
104 			final int head = table[tIdx];
105 			if (head != 0 && lastHash == key) {
106 				// Two consecutive blocks have the same content hash,
107 				// prefer the earlier block because we want to use the
108 				// longest sequence we can during encoding.
109 				//
110 				entries[head] = (((long) key) << 32) | ptr;
111 			} else {
112 				final int eIdx = ++entryCnt;
113 				entries[eIdx] = (((long) key) << 32) | ptr;
114 				next[eIdx] = head;
115 				table[tIdx] = eIdx;
116 			}
117 
118 			lastHash = key;
119 			ptr -= DeltaIndex.BLKSZ;
120 		} while (0 <= ptr);
121 	}
122 
123 	private static int tableSize(int worstCaseBlockCnt) {
124 		int shift = 32 - Integer.numberOfLeadingZeros(worstCaseBlockCnt);
125 		int sz = 1 << (shift - 1);
126 		if (sz < worstCaseBlockCnt)
127 			sz <<= 1;
128 		return sz;
129 	}
130 }