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
|
/* Lzip - LZMA lossless data compressor
Copyright (C) 2008-2016 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 2 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/>.
*/
#define _FILE_OFFSET_BITS 64
#include <algorithm>
#include <cerrno>
#include <cstdlib>
#include <cstring>
#include <string>
#include <vector>
#include <stdint.h>
#include "lzip.h"
#include "encoder_base.h"
Dis_slots dis_slots;
Prob_prices prob_prices;
bool Matchfinder_base::read_block()
{
if( !at_stream_end && stream_pos < buffer_size )
{
const int size = buffer_size - stream_pos;
const int rd = readblock( infd, buffer + stream_pos, size );
stream_pos += rd;
if( rd != size && errno ) throw Error( "Read error" );
if( rd < size ) { at_stream_end = true; pos_limit = buffer_size; }
}
return pos < stream_pos;
}
void Matchfinder_base::normalize_pos()
{
if( pos > stream_pos )
internal_error( "pos > stream_pos in Matchfinder_base::normalize_pos." );
if( !at_stream_end )
{
const int offset = pos - dictionary_size - before_size;
const int size = stream_pos - offset;
std::memmove( buffer, buffer + offset, size );
partial_data_pos += offset;
pos -= offset;
stream_pos -= offset;
for( int i = 0; i < num_prev_positions; ++i )
prev_positions[i] -= std::min( prev_positions[i], offset );
for( int i = 0; i < pos_array_size; ++i )
pos_array[i] -= std::min( pos_array[i], offset );
read_block();
}
}
Matchfinder_base::Matchfinder_base( const int before, const int dict_size,
const int after_size, const int dict_factor,
const int num_prev_positions23,
const int pos_array_factor, const int ifd )
:
partial_data_pos( 0 ),
before_size( before ),
pos( 0 ),
cyclic_pos( 0 ),
stream_pos( 0 ),
infd( ifd ),
at_stream_end( false )
{
const int buffer_size_limit =
( dict_factor * dict_size ) + before_size + after_size;
buffer_size = std::max( 65536, dict_size );
buffer = (uint8_t *)std::malloc( buffer_size );
if( !buffer ) throw std::bad_alloc();
if( read_block() && !at_stream_end && buffer_size < buffer_size_limit )
{
buffer_size = buffer_size_limit;
uint8_t * const tmp = (uint8_t *)std::realloc( buffer, buffer_size );
if( !tmp ) { std::free( buffer ); throw std::bad_alloc(); }
buffer = tmp;
read_block();
}
if( at_stream_end && stream_pos < dict_size )
dictionary_size = std::max( (int)min_dictionary_size, stream_pos );
else
dictionary_size = dict_size;
pos_limit = buffer_size;
if( !at_stream_end ) pos_limit -= after_size;
unsigned size = 1 << std::max( 16, real_bits( dictionary_size - 1 ) - 2 );
if( dictionary_size > 1 << 26 ) // 64 MiB
size >>= 1;
key4_mask = size - 1;
size += num_prev_positions23;
num_prev_positions = size;
pos_array_size = pos_array_factor * ( dictionary_size + 1 );
size += pos_array_size;
prev_positions = new( std::nothrow ) int32_t[size];
if( !prev_positions ) { std::free( buffer ); throw std::bad_alloc(); }
pos_array = prev_positions + num_prev_positions;
for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = 0;
}
void Matchfinder_base::reset()
{
if( stream_pos > pos )
std::memmove( buffer, buffer + pos, stream_pos - pos );
partial_data_pos = 0;
stream_pos -= pos;
pos = 0;
cyclic_pos = 0;
for( int i = 0; i < num_prev_positions; ++i ) prev_positions[i] = 0;
read_block();
}
void Range_encoder::flush_data()
{
if( pos > 0 )
{
if( outfd >= 0 && writeblock( outfd, buffer, pos ) != pos )
throw Error( "Write error" );
partial_member_pos += pos;
pos = 0;
show_progress();
}
}
// End Of Stream mark => (dis == 0xFFFFFFFFU, len == min_match_len)
void LZ_encoder_base::full_flush( const State state )
{
const int pos_state = data_position() & pos_state_mask;
renc.encode_bit( bm_match[state()][pos_state], 1 );
renc.encode_bit( bm_rep[state()], 0 );
encode_pair( 0xFFFFFFFFU, min_match_len, pos_state );
renc.flush();
File_trailer trailer;
trailer.data_crc( crc() );
trailer.data_size( data_position() );
trailer.member_size( renc.member_position() + File_trailer::size );
for( int i = 0; i < File_trailer::size; ++i )
renc.put_byte( trailer.data[i] );
renc.flush_data();
}
void LZ_encoder_base::reset()
{
Matchfinder_base::reset();
crc_ = 0xFFFFFFFFU;
bm_literal[0][0].reset( ( 1 << literal_context_bits ) * 0x300 );
bm_match[0][0].reset( State::states * pos_states );
bm_rep[0].reset( State::states );
bm_rep0[0].reset( State::states );
bm_rep1[0].reset( State::states );
bm_rep2[0].reset( State::states );
bm_len[0][0].reset( State::states * pos_states );
bm_dis_slot[0][0].reset( len_states * (1 << dis_slot_bits ) );
bm_dis[0].reset( modeled_distances - end_dis_model );
bm_align[0].reset( dis_align_size );
match_len_model.reset();
rep_len_model.reset();
renc.reset();
}
|