1 // Copyright 2011 The Snappy-Go Authors. All rights reserved.
2 // Use of this source code is governed by a BSD-style
3 // license that can be found in the LICENSE file.
4 5 // Package snapref implements the Snappy compression format. It aims for very
6 // high speeds and reasonable compression.
7 //
8 // There are actually two Snappy formats: block and stream. They are related,
9 // but different: trying to decompress block-compressed data as a Snappy stream
10 // will fail, and vice versa. The block format is the Decode and Encode
11 // functions and the stream format is the Reader and Writer types.
12 //
13 // The block format, the more common case, is used when the complete size (the
14 // number of bytes) of the original data is known upfront, at the time
15 // compression starts. The stream format, also known as the framing format, is
16 // for when that isn't always true.
17 //
18 // The canonical, C++ implementation is at https://github.com/google/snappy and
19 // it only implements the block format.
20 package snapref
21 22 import (
23 "hash/crc32"
24 )
25 26 /*
27 Each encoded block begins with the varint-encoded length of the decoded data,
28 followed by a sequence of chunks. Chunks begin and end on byte boundaries. The
29 first byte of each chunk is broken into its 2 least and 6 most significant bits
30 called l and m: l ranges in [0, 4) and m ranges in [0, 64). l is the chunk tag.
31 Zero means a literal tag. All other values mean a copy tag.
32 33 For literal tags:
34 - If m < 60, the next 1 + m bytes are literal bytes.
35 - Otherwise, let n be the little-endian unsigned integer denoted by the next
36 m - 59 bytes. The next 1 + n bytes after that are literal bytes.
37 38 For copy tags, length bytes are copied from offset bytes ago, in the style of
39 Lempel-Ziv compression algorithms. In particular:
40 - For l == 1, the offset ranges in [0, 1<<11) and the length in [4, 12).
41 The length is 4 + the low 3 bits of m. The high 3 bits of m form bits 8-10
42 of the offset. The next byte is bits 0-7 of the offset.
43 - For l == 2, the offset ranges in [0, 1<<16) and the length in [1, 65).
44 The length is 1 + m. The offset is the little-endian unsigned integer
45 denoted by the next 2 bytes.
46 - For l == 3, this tag is a legacy format that is no longer issued by most
47 encoders. Nonetheless, the offset ranges in [0, 1<<32) and the length in
48 [1, 65). The length is 1 + m. The offset is the little-endian unsigned
49 integer denoted by the next 4 bytes.
50 */
51 const (
52 tagLiteral = 0x00
53 tagCopy1 = 0x01
54 tagCopy2 = 0x02
55 tagCopy4 = 0x03
56 )
57 58 const (
59 checksumSize = 4
60 chunkHeaderSize = 4
61 magicChunk = "\xff\x06\x00\x00" + magicBody
62 magicBody = "sNaPpY"
63 64 // maxBlockSize is the maximum size of the input to encodeBlock. It is not
65 // part of the wire format per se, but some parts of the encoder assume
66 // that an offset fits into a uint16.
67 //
68 // Also, for the framing format (Writer type instead of Encode function),
69 // https://github.com/google/snappy/blob/master/framing_format.txt says
70 // that "the uncompressed data in a chunk must be no longer than 65536
71 // bytes".
72 maxBlockSize = 65536
73 74 // maxEncodedLenOfMaxBlockSize equals MaxEncodedLen(maxBlockSize), but is
75 // hard coded to be a const instead of a variable, so that obufLen can also
76 // be a const. Their equivalence is confirmed by
77 // TestMaxEncodedLenOfMaxBlockSize.
78 maxEncodedLenOfMaxBlockSize = 76490
79 80 obufHeaderLen = len(magicChunk) + checksumSize + chunkHeaderSize
81 obufLen = obufHeaderLen + maxEncodedLenOfMaxBlockSize
82 )
83 84 const (
85 chunkTypeCompressedData = 0x00
86 chunkTypeUncompressedData = 0x01
87 chunkTypePadding = 0xfe
88 chunkTypeStreamIdentifier = 0xff
89 )
90 91 var crcTable = crc32.MakeTable(crc32.Castagnoli)
92 93 // crc implements the checksum specified in section 3 of
94 // https://github.com/google/snappy/blob/master/framing_format.txt
95 func crc(b []byte) uint32 {
96 c := crc32.Update(0, crcTable, b)
97 return uint32(c>>15|c<<17) + 0xa282ead8
98 }
99