aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/snappy/snappy.h
blob: 9a3bc3fa64f8b234d7d98190c5dab914a1dea32d (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
// Copyright 2005 and onwards Google Inc.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//     * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// A light-weight compression algorithm.  It is designed for speed of
// compression and decompression, rather than for the utmost in space
// savings.
//
// For getting better compression ratios when you are compressing data
// with long repeated sequences or compressing data that is similar to
// other data, while still compressing fast, you might look at first
// using BMDiff and then compressing the output of BMDiff with
// Snappy.

#ifndef THIRD_PARTY_SNAPPY_SNAPPY_H__
#define THIRD_PARTY_SNAPPY_SNAPPY_H__

#include <cstddef>
#include <string>

#include <util/generic/fwd.h>

#include "snappy-stubs-public.h"

namespace snappy {
  class Source;
  class Sink;

  // ------------------------------------------------------------------------
  // Generic compression/decompression routines.
  // ------------------------------------------------------------------------

  // Compress the bytes read from "*source" and append to "*sink". Return the
  // number of bytes written.
  size_t Compress(Source* source, Sink* sink);

  // Find the uncompressed length of the given stream, as given by the header.
  // Note that the true length could deviate from this; the stream could e.g.
  // be truncated.
  //
  // Also note that this leaves "*source" in a state that is unsuitable for
  // further operations, such as RawUncompress(). You will need to rewind
  // or recreate the source yourself before attempting any further calls.
  bool GetUncompressedLength(Source* source, uint32* result);

  // ------------------------------------------------------------------------
  // Higher-level string based routines (should be sufficient for most users)
  // ------------------------------------------------------------------------

  // Sets "*compressed" to the compressed version of "input[0,input_length-1]".
  // Original contents of *compressed are lost.
  //
  // REQUIRES: "input[]" is not an alias of "*compressed".
  size_t Compress(const char* input, size_t input_length,
                  std::string* compressed);
  size_t Compress(const char* input, size_t input_length,
                  TString* compressed);

  // Decompresses "compressed[0,compressed_length-1]" to "*uncompressed".
  // Original contents of "*uncompressed" are lost.
  //
  // REQUIRES: "compressed[]" is not an alias of "*uncompressed".
  //
  // returns false if the message is corrupted and could not be decompressed
  bool Uncompress(const char* compressed, size_t compressed_length,
                  std::string* uncompressed);
  bool Uncompress(const char* compressed, size_t compressed_length,
                  TString* uncompressed);

  // Decompresses "compressed" to "*uncompressed".
  //
  // returns false if the message is corrupted and could not be decompressed
  bool Uncompress(Source* compressed, Sink* uncompressed);

  // This routine uncompresses as much of the "compressed" as possible
  // into sink.  It returns the number of valid bytes added to sink
  // (extra invalid bytes may have been added due to errors; the caller
  // should ignore those). The emitted data typically has length
  // GetUncompressedLength(), but may be shorter if an error is
  // encountered.
  size_t UncompressAsMuchAsPossible(Source* compressed, Sink* uncompressed);

  // ------------------------------------------------------------------------
  // Lower-level character array based routines.  May be useful for
  // efficiency reasons in certain circumstances.
  // ------------------------------------------------------------------------

  // REQUIRES: "compressed" must point to an area of memory that is at
  // least "MaxCompressedLength(input_length)" bytes in length.
  //
  // Takes the data stored in "input[0..input_length]" and stores
  // it in the array pointed to by "compressed".
  //
  // "*compressed_length" is set to the length of the compressed output.
  //
  // Example:
  //    char* output = new char[snappy::MaxCompressedLength(input_length)];
  //    size_t output_length;
  //    RawCompress(input, input_length, output, &output_length);
  //    ... Process(output, output_length) ...
  //    delete [] output;
  void RawCompress(const char* input,
                   size_t input_length,
                   char* compressed,
                   size_t* compressed_length);

  // Given data in "compressed[0..compressed_length-1]" generated by
  // calling the Snappy::Compress routine, this routine
  // stores the uncompressed data to
  //    uncompressed[0..GetUncompressedLength(compressed)-1]
  // returns false if the message is corrupted and could not be decrypted
  bool RawUncompress(const char* compressed, size_t compressed_length,
                     char* uncompressed);

  // Given data from the byte source 'compressed' generated by calling
  // the Snappy::Compress routine, this routine stores the uncompressed
  // data to
  //    uncompressed[0..GetUncompressedLength(compressed,compressed_length)-1]
  // returns false if the message is corrupted and could not be decrypted
  bool RawUncompress(Source* compressed, char* uncompressed);

  // Given data in "compressed[0..compressed_length-1]" generated by
  // calling the Snappy::Compress routine, this routine
  // stores the uncompressed data to the iovec "iov". The number of physical
  // buffers in "iov" is given by iov_cnt and their cumulative size
  // must be at least GetUncompressedLength(compressed). The individual buffers
  // in "iov" must not overlap with each other.
  //
  // returns false if the message is corrupted and could not be decrypted
  bool RawUncompressToIOVec(const char* compressed, size_t compressed_length,
                            const struct iovec* iov, size_t iov_cnt);

  // Given data from the byte source 'compressed' generated by calling
  // the Snappy::Compress routine, this routine stores the uncompressed
  // data to the iovec "iov". The number of physical
  // buffers in "iov" is given by iov_cnt and their cumulative size
  // must be at least GetUncompressedLength(compressed). The individual buffers
  // in "iov" must not overlap with each other.
  //
  // returns false if the message is corrupted and could not be decrypted
  bool RawUncompressToIOVec(Source* compressed, const struct iovec* iov,
                            size_t iov_cnt);

  // Returns the maximal size of the compressed representation of
  // input data that is "source_bytes" bytes in length;
  size_t MaxCompressedLength(size_t source_bytes);

  // REQUIRES: "compressed[]" was produced by RawCompress() or Compress()
  // Returns true and stores the length of the uncompressed data in
  // *result normally.  Returns false on parsing error.
  // This operation takes O(1) time.
  bool GetUncompressedLength(const char* compressed, size_t compressed_length,
                             size_t* result);

  // Returns true iff the contents of "compressed[]" can be uncompressed
  // successfully.  Does not return the uncompressed data.  Takes
  // time proportional to compressed_length, but is usually at least
  // a factor of four faster than actual decompression.
  bool IsValidCompressedBuffer(const char* compressed,
                               size_t compressed_length);

  // Returns true iff the contents of "compressed" can be uncompressed
  // successfully.  Does not return the uncompressed data.  Takes
  // time proportional to *compressed length, but is usually at least
  // a factor of four faster than actual decompression.
  // On success, consumes all of *compressed.  On failure, consumes an
  // unspecified prefix of *compressed.
  bool IsValidCompressed(Source* compressed);

  // The size of a compression block. Note that many parts of the compression
  // code assumes that kBlockSize <= 65536; in particular, the hash table
  // can only store 16-bit offsets, and EmitCopy() also assumes the offset
  // is 65535 bytes or less. Note also that if you change this, it will
  // affect the framing format (see framing_format.txt).
  //
  // Note that there might be older data around that is compressed with larger
  // block sizes, so the decompression code should not rely on the
  // non-existence of long backreferences.
  static constexpr int kBlockLog = 16;
  static constexpr size_t kBlockSize = 1 << kBlockLog;

  static constexpr int kMinHashTableBits = 8;
  static constexpr size_t kMinHashTableSize = 1 << kMinHashTableBits;

  static constexpr int kMaxHashTableBits = 14;
  static constexpr size_t kMaxHashTableSize = 1 << kMaxHashTableBits;
}  // end namespace snappy

#endif  // THIRD_PARTY_SNAPPY_SNAPPY_H__