summaryrefslogtreecommitdiffstats
path: root/lzip.h
blob: 1c67344e234433ddf609bf575b805d4b34d45b1a (plain)
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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
/*  Lziprecover - Data recovery tool for lzipped files
    Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.

    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with this program.  If not, see <http://www.gnu.org/licenses/>.
*/

class State
  {
  unsigned char st;

public:
  enum { states = 12 };
  State() throw() : st( 0 ) {}
  unsigned char operator()() const throw() { return st; }
  bool is_char() const throw() { return st < 7; }

  void set_char() throw()
    {
    static const unsigned char next[states] =
      { 0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5 };
    st = next[st];
    }

  void set_match() throw()
    {
    static const unsigned char next[states] =
      { 7, 7, 7, 7, 7, 7, 7, 10, 10, 10, 10, 10 };
    st = next[st];
    }

  void set_rep() throw()
    {
    static const unsigned char next[states] =
      { 8, 8, 8, 8, 8, 8, 8, 11, 11, 11, 11, 11 };
    st = next[st];
    }

  void set_short_rep() throw()
    {
    static const unsigned char next[states] =
      { 9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11 };
    st = next[st];
    }
  };


enum {
  min_dictionary_bits = 12,
  min_dictionary_size = 1 << min_dictionary_bits,
  max_dictionary_bits = 29,
  max_dictionary_size = 1 << max_dictionary_bits,
  min_member_size = 36,
  literal_context_bits = 3,
  pos_state_bits = 2,
  pos_states = 1 << pos_state_bits,
  pos_state_mask = pos_states - 1,

  dis_slot_bits = 6,
  start_dis_model = 4,
  end_dis_model = 14,
  modeled_distances = 1 << (end_dis_model / 2),
  dis_align_bits = 4,
  dis_align_size = 1 << dis_align_bits,

  len_low_bits = 3,
  len_mid_bits = 3,
  len_high_bits = 8,
  len_low_symbols = 1 << len_low_bits,
  len_mid_symbols = 1 << len_mid_bits,
  len_high_symbols = 1 << len_high_bits,
  max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols,

  min_match_len = 2,					// must be 2
  max_match_len = min_match_len + max_len_symbols - 1,	// 273
  min_match_len_limit = 5,

  max_dis_states = 4 };

inline int get_dis_state( int len ) throw()
  {
  len -= min_match_len;
  if( len >= max_dis_states ) len = max_dis_states - 1;
  return len;
  }


enum { bit_model_move_bits = 5,
       bit_model_total_bits = 11,
       bit_model_total = 1 << bit_model_total_bits };

struct Bit_model
  {
  unsigned int probability;
  Bit_model() throw() : probability( bit_model_total / 2 ) {}
  };


class Pretty_print
  {
  const char * const stdin_name;
  unsigned int longest_name;
  const int verbosity_;
  std::string name_;
  mutable bool first_post;

public:
  Pretty_print( const std::vector< std::string > & filenames, const int v )
    : stdin_name( "(stdin)" ), longest_name( 0 ), verbosity_( v ),
      first_post( false )
    {
    const unsigned int stdin_name_len = std::strlen( stdin_name );
    for( unsigned int i = 0; i < filenames.size(); ++i )
      {
      const std::string & s = filenames[i];
      const unsigned int len = ( ( s == "-" ) ? stdin_name_len : s.size() );
      if( len > longest_name ) longest_name = len;
      }
    if( longest_name == 0 ) longest_name = stdin_name_len;
    }

  Pretty_print( const std::string & filename, const int v )
    : stdin_name( "(stdin)" ), verbosity_( v ), first_post( false )
    {
    const unsigned int stdin_name_len = std::strlen( stdin_name );
    longest_name = ( ( filename == "-" ) ? stdin_name_len : filename.size() );
    if( longest_name == 0 ) longest_name = stdin_name_len;
    set_name( filename );
    }

  void set_name( const std::string & filename )
    {
    if( filename.size() && filename != "-" ) name_ = filename;
    else name_ = stdin_name;
    first_post = true;
    }

  void reset() const throw() { if( name_.size() ) first_post = true; }
  const char * name() const throw() { return name_.c_str(); }
  int verbosity() const throw() { return verbosity_; }
  void operator()( const char * const msg = 0 ) const throw();
  };


class CRC32
  {
  uint32_t data[256];		// Table of CRCs of all 8-bit messages.

public:
  CRC32()
    {
    for( unsigned int n = 0; n < 256; ++n )
      {
      unsigned int c = n;
      for( int k = 0; k < 8; ++k )
        { if( c & 1 ) c = 0xEDB88320U ^ ( c >> 1 ); else c >>= 1; }
      data[n] = c;
      }
    }

  uint32_t operator[]( const uint8_t byte ) const throw() { return data[byte]; }
  void update( uint32_t & crc, const uint8_t byte ) const throw()
    { crc = data[(crc^byte)&0xFF] ^ ( crc >> 8 ); }
  void update( uint32_t & crc, const uint8_t * const buffer, const int size ) const throw()
    {
    for( int i = 0; i < size; ++i )
      crc = data[(crc^buffer[i])&0xFF] ^ ( crc >> 8 );
    }
  };

extern const CRC32 crc32;


inline int real_bits( const int value ) throw()
  {
  int bits = 0;
  for( int i = 1, mask = 1; mask > 0; ++i, mask <<= 1 )
    if( value & mask ) bits = i;
  return bits;
  }

const uint8_t magic_string[4] = { 'L', 'Z', 'I', 'P' };

struct File_header
  {
  uint8_t data[6];			// 0-3 magic bytes
					//   4 version
					//   5 coded_dict_size
  enum { size = 6 };

  void set_magic() throw()
    { std::memcpy( data, magic_string, 4 ); data[4] = 1; }

  bool verify_magic() const throw()
    { return ( std::memcmp( data, magic_string, 4 ) == 0 ); }

  uint8_t version() const throw() { return data[4]; }
  bool verify_version() const throw() { return ( data[4] <= 1 ); }

  int dictionary_size() const throw()
    {
    int sz = ( 1 << ( data[5] & 0x1F ) );
    if( sz > min_dictionary_size && sz <= max_dictionary_size )
      sz -= ( sz / 16 ) * ( ( data[5] >> 5 ) & 0x07 );
    return sz;
    }

  bool dictionary_size( const int sz ) throw()
    {
    if( sz >= min_dictionary_size && sz <= max_dictionary_size )
      {
      data[5] = real_bits( sz - 1 );
      if( sz > min_dictionary_size )
        {
        const int base_size = 1 << data[5];
        const int wedge = base_size / 16;
        for( int i = 7; i >= 1; --i )
          if( base_size - ( i * wedge ) >= sz )
            { data[5] |= ( i << 5 ); break; }
        }
      return true;
      }
    return false;
    }
  };


struct File_trailer
  {
  uint8_t data[20];	//  0-3  CRC32 of the uncompressed data
			//  4-11 size of the uncompressed data
			// 12-19 member size including header and trailer

  static int size( const int version = 1 )
    { return ( ( version >= 1 ) ? 20 : 12 ); }

  uint32_t data_crc() const throw()
    {
    uint32_t tmp = 0;
    for( int i = 3; i >= 0; --i ) { tmp <<= 8; tmp += data[i]; }
    return tmp;
    }

  void data_crc( uint32_t crc ) throw()
    { for( int i = 0; i <= 3; ++i ) { data[i] = (uint8_t)crc; crc >>= 8; } }

  long long data_size() const throw()
    {
    long long tmp = 0;
    for( int i = 11; i >= 4; --i ) { tmp <<= 8; tmp += data[i]; }
    return tmp;
    }

  void data_size( long long sz ) throw()
    {
    for( int i = 4; i <= 11; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; }
    }

  long long member_size() const throw()
    {
    long long tmp = 0;
    for( int i = 19; i >= 12; --i ) { tmp <<= 8; tmp += data[i]; }
    return tmp;
    }

  void member_size( long long sz ) throw()
    {
    for( int i = 12; i <= 19; ++i ) { data[i] = (uint8_t)sz; sz >>= 8; }
    }
  };


struct Error
  {
  const char * const msg;
  Error( const char * const s ) throw() : msg( s ) {}
  };


#ifndef LLONG_MAX
#define LLONG_MAX  0x7FFFFFFFFFFFFFFFLL
#endif
#ifndef LLONG_MIN
#define LLONG_MIN  (-LLONG_MAX - 1LL)
#endif
#ifndef ULLONG_MAX
#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL
#endif


class Block
  {
  long long pos_, size_;		// pos + size <= LLONG_MAX

public:
  Block( const long long p, const long long s ) throw()
    : pos_( p ), size_( s ) {}

  long long pos() const throw() { return pos_; }
  long long size() const throw() { return size_; }
  long long end() const throw() { return pos_ + size_; }

  void pos( const long long p ) throw() { pos_ = p; }
  void size( const long long s ) throw() { size_ = s; }

  bool overlaps( const Block & b ) const throw()
    { return ( pos_ < b.end() && b.pos_ < end() ); }
  void shift( Block & b ) throw() { ++size_; ++b.pos_; --b.size_; }
  };


// defined in decoder.cc
int readblock( const int fd, uint8_t * const buf, const int size ) throw();
int writeblock( const int fd, const uint8_t * const buf, const int size ) throw();

// defined in main.cc
extern int verbosity;
const char * format_num( long long num, long long limit = LLONG_MAX,
                         const int set_prefix = 0 ) throw();
int open_instream( const std::string & name, struct stat * const in_statsp,
                   const bool to_stdout, const bool reg_only = false ) throw();
int open_outstream_rw( const std::string & output_filename,
                       const bool force ) throw();
void show_error( const char * const msg, const int errcode = 0,
                 const bool help = false ) throw();
void internal_error( const char * const msg );

// defined in merge.cc
void cleanup_and_fail( const std::string & output_filename,
                       const int outfd, const int retval ) throw();
bool copy_file( const int infd, const int outfd,
                const long long size = LLONG_MAX );
bool try_decompress( const int fd, const long long file_size,
                     long long * failure_posp = 0 );
bool verify_header( const File_header & header );
bool verify_single_member( const int fd, const long long file_size );
int merge_files( const std::vector< std::string > & filenames,
                 const std::string & output_filename, const bool force );

// defined in range_dec.cc
int list_file( const std::string & input_filename );
int range_decompress( const std::string & input_filename,
                      const std::string & default_output_filename,
                      const std::string & range_string,
                      const bool to_stdout, const bool force );

// defined in repair.cc
int repair_file( const std::string & input_filename,
                 const std::string & output_filename, const bool force );

// defined in split.cc
int split_file( const std::string & input_filename,
                const std::string & default_output_filename, const bool force );