tools/bwt/dcs-bwt/src/stream_compressor.cc

   1 // Copyright 2007 Google Inc.
   2 //
   3 // This program is free software; you can redistribute it and/or
   4 // modify it under the terms of the GNU General Public License
   5 // as published by the Free Software Foundation; either version 2
   6 // of the License, or (at your option) any later version.
   7 //
   8 // This program is distributed in the hope that it will be useful,
   9 // but WITHOUT ANY WARRANTY; without even the implied warranty of
  10 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  11 // GNU General Public License for more details.
  12 //
  13 // You should have received a copy of the GNU General Public License
  14 // along with this program; if not, write to the Free Software
  15 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  16
  17 #include "bbb_compress.h"
  18 #include "rl_compress.h"
  19 #include "stream_compressor.h"
  20
  21 #include <string>
  22
  23 namespace dcsbwt {
  24
  25 // Trivial implementations of StreamCompressor and StreamDecompressor
  26 // They serve as an example, and can be useful as a replacement of a real
  27 // (de)compressor in testing, debugging and development.
  28 class TrivialCompressor : public StreamCompressor {
  29  public:
  30   class Options : public StreamCompressor::OptionsBase {
  31    public:
  32     bool Set(const std::string& options) { return 0 == options.length(); }
  33     std::string Get() const { return std::string(); }
  34     int64 SizeInBytes() const { return 1; }
  35     StreamCompressor* GetCompressor() { return new TrivialCompressor; }
  36  };
  37
  38   TrivialCompressor() {}
  39   virtual ~TrivialCompressor() {}
  40
  41   virtual void WriteBegin() {}
  42   virtual void WriteEndPrivate() {}
  43   virtual void Write(const char* bytes, size_t n) { Emit(bytes, n); }
  44  private:
  45   TrivialCompressor(const TrivialCompressor&);
  46   TrivialCompressor& operator=(const TrivialCompressor&);
  47 };
  48
  49 class TrivialDecompressor : public StreamDecompressor {
  50  public:
  51   static StreamDecompressor* Create(const std::string&) {
  52     return new TrivialDecompressor;
  53   }
  54   TrivialDecompressor() {}
  55   virtual ~TrivialDecompressor() {}
  56   virtual void ReadBegin() {}
  57   virtual void ReadEnd() {}
  58   virtual void Read(char* bytes, size_t n) { GetCompressed(bytes, n); }
  59   virtual int64 SizeInBytes() const { return 1; }
  60  private:
  61   TrivialDecompressor(const TrivialDecompressor&);
  62   TrivialDecompressor& operator=(const TrivialDecompressor&);
  63 };
  64
  65
  66 /////////////////////// StreamCompressor ///////////////////////
  67
  68 const int StreamCompressor::kBufferSize = 1 << 16;
  69
  70 // Select the compression algorithm based on the first character
  71 // of the options_string and let the algorithm specific options
  72 // processor handle the rest of options_string.
  73 bool StreamCompressor::Options::Set(const std::string& options_string) {
  74   if (options_string.length() < 1) return false;
  75   char compression_algorithm = options_string[0];
  76   OptionsBase* options;
  77   switch (compression_algorithm) {
  78     case 't':  // TrivialCompressor (see above)
  79       options = new TrivialCompressor::Options;
  80       break;
  81     case 'b':  // BbbCompressor (see bbb_compressor.h)
  82       options = new BbbCompressor::Options;
  83       break;
  84     case 'c':
  85       options = new ByteCompressor::Options;
  86       break;
  87     case 'r':
  88       options = new RunLengthCompressor::Options;
  89       break;
  90     default:
  91       return false;
  92   }
  93   std::string algorithm_specific_options_string(options_string, 1);
  94   bool success = options->Set(algorithm_specific_options_string);
  95   if (success) {
  96     compression_algorithm_ = compression_algorithm;
  97     if (algorithm_specific_options_) delete algorithm_specific_options_;
  98     algorithm_specific_options_ = options;
  99   } else {
 100     delete options;
 101   }
 102   return success;
 103 }
 104
 105 StreamCompressor* StreamCompressor::Options::GetCompressor() {
 106   return algorithm_specific_options_->GetCompressor();
 107 }
 108
 109 StreamCompressor* StreamCompressor::Connect(OutStream* output,
 110                                             Options options) {
 111   StreamCompressor* compressor = options.GetCompressor();
 112   if (compressor) {
 113     // '\n' is used as the terminator of the compression format string.
 114     std::string compression_format = options.Get() + '\n';
 115     output->Write(compression_format.data(), compression_format.length());
 116     compressor->output_.Connect(output);
 117     compressor->ConnectPrivate(&compressor->output_);
 118   }
 119   return compressor;
 120 }
 121
 122 OutStream* StreamCompressor::Disconnect() {
 123   DisconnectPrivate();
 124   OutStream* oldoutput = output_.Disconnect();
 125   delete this;
 126   return oldoutput;
 127 }
 128
 129 /////////////////////// StreamDecompressor ///////////////////////
 130
 131 StreamDecompressor* StreamDecompressor::Connect(InStreamBuffer* input) {
 132   // The compression format is identified by the input prefix ending
 133   // with the first '\n'.
 134   std::string format;
 135   char ch = input->ReadByte();
 136   while (ch != '\n') {
 137     if (format.length() > 1000) return NULL; // guard against infinite loop
 138     format += ch;
 139     ch = input->ReadByte();
 140   }
 141   if (0 == format.length()) return NULL;
 142   char compression_type = format[0];
 143   std::string options(format, 1);
 144   StreamDecompressor* decompressor;
 145   switch (compression_type) {
 146     case 't':
 147       decompressor = TrivialDecompressor::Create(options);
 148       break;
 149     case 'b':
 150       decompressor = BbbDecompressor::Create(options);
 151       break;
 152     case 'c':
 153       decompressor = ByteDecompressor::Create(options);
 154       break;
 155     case 'r':
 156       decompressor = RunLengthDecompressor::Create(options);
 157       break;
 158     default:
 159       decompressor = NULL;
 160   }
 161   if (decompressor) {
 162     decompressor->format_ = format;
 163     decompressor->input_.Connect(input);
 164     decompressor->ConnectPrivate(decompressor->input_.GetServant());
 165   }
 166   return decompressor;
 167 }
 168
 169 InStreamBuffer* StreamDecompressor::Disconnect() {
 170   DisconnectPrivate();
 171   InStreamBuffer* oldinput = input_.Disconnect();
 172   delete this;
 173   return oldinput;
 174 }
 175
 176 }  // namespace dcsbwt