1
0
Fork 0

Merging upstream version 1.1~rc2.

Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-17 19:14:54 +01:00
parent a8d17e4a46
commit 950a431716
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
22 changed files with 1309 additions and 1071 deletions

292
encoder.h
View file

@ -1,4 +1,4 @@
/* Clzip - A data compressor based on the LZMA algorithm
/* Clzip - Data compressor based on the LZMA algorithm
Copyright (C) 2010 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
@ -24,8 +24,9 @@ extern Dis_slots dis_slots;
static inline void Dis_slots_init()
{
for( int slot = 0; slot < 4; ++slot ) dis_slots[slot] = slot;
for( int i = 4, size = 2, slot = 4; slot < 24; slot += 2 )
int i, size, slot;
for( slot = 0; slot < 4; ++slot ) dis_slots[slot] = slot;
for( i = 4, size = 2, slot = 4; slot < 24; slot += 2 )
{
memset( &dis_slots[i], slot, size );
memset( &dis_slots[i+size], slot + 1, size );
@ -49,13 +50,13 @@ extern Prob_prices prob_prices;
static inline void Prob_prices_init()
{
const int num_bits = ( bit_model_total_bits - 2 );
for( int i = num_bits - 1; i >= 0; --i )
int i, j = 1, end = 2;
prob_prices[0] = bit_model_total_bits << price_shift;
for( i = num_bits - 1; i >= 0; --i, end <<= 1 )
{
int start = 1 << ( num_bits - i - 1 );
int end = 1 << ( num_bits - i);
for( int j = start; j < end; ++j )
prob_prices[j] = (i << price_shift) +
( ((end - j) << price_shift) >> (num_bits - i - 1) );
for( ; j < end; ++j )
prob_prices[j] = ( i << price_shift ) +
( ((end - j) << price_shift) >> (num_bits - i - 1) );
}
}
@ -73,10 +74,11 @@ static inline int price_bit( const Bit_model bm, const int bit )
{ if( bit ) return price1( bm ); else return price0( bm ); }
static inline int price_symbol( const Bit_model bm[], int symbol, const int num_bits )
static inline int price_symbol( const Bit_model bm[], int symbol,
const int num_bits )
{
symbol |= ( 1 << num_bits );
int price = 0;
symbol |= ( 1 << num_bits );
while( symbol > 1 )
{
const int bit = symbol & 1;
@ -92,7 +94,8 @@ static inline int price_symbol_reversed( const Bit_model bm[], int symbol,
{
int price = 0;
int model = 1;
for( int i = num_bits; i > 0; --i )
int i;
for( i = num_bits; i > 0; --i )
{
const int bit = symbol & 1;
symbol >>= 1;
@ -108,8 +111,9 @@ static inline int price_matched( const Bit_model bm[], const int symbol,
{
int price = 0;
int model = 1;
int i;
for( int i = 7; i >= 0; --i )
for( i = 7; i >= 0; --i )
{
const int match_bit = ( match_byte >> i ) & 1;
int bit = ( symbol >> i ) & 1;
@ -130,86 +134,87 @@ static inline int price_matched( const Bit_model bm[], const int symbol,
}
enum { // bytes to keep in buffer before dictionary
mf_before_size = max_num_trials + 1,
// bytes to keep in buffer after pos
mf_after_size = max_match_len,
mf_num_prev_positions4 = 1 << 20,
mf_num_prev_positions3 = 1 << 18,
mf_num_prev_positions2 = 1 << 16,
mf_num_prev_positions = mf_num_prev_positions4 + mf_num_prev_positions3 +
mf_num_prev_positions2 };
enum { /* bytes to keep in buffer before dictionary */
before_size = max_num_trials + 1,
/* bytes to keep in buffer after pos */
after_size = max_match_len,
num_prev_positions4 = 1 << 20,
num_prev_positions3 = 1 << 18,
num_prev_positions2 = 1 << 16,
num_prev_positions = num_prev_positions4 + num_prev_positions3 +
num_prev_positions2 };
struct Matchfinder
{
long long partial_data_pos;
int dictionary_size_; // bytes to keep in buffer before pos
int buffer_size;
uint8_t * buffer;
int pos;
int cyclic_pos;
int stream_pos; // first byte not yet read from file
int pos_limit; // when reached, a new block must be read
int infd_; // input file descriptor
int match_len_limit_;
int32_t * prev_positions; // last seen position of key
uint8_t * buffer; /* input buffer */
int32_t * prev_positions; /* last seen position of key */
int32_t * prev_pos_tree;
bool at_stream_end; // stream_pos shows real end of file
int dictionary_size_; /* bytes to keep in buffer before pos */
int buffer_size;
int pos; /* current pos in buffer */
int cyclic_pos; /* current pos in dictionary */
int stream_pos; /* first byte not yet read from file */
int pos_limit; /* when reached, a new block must be read */
int match_len_limit_;
int cycles;
int infd; /* input file descriptor */
bool at_stream_end; /* stream_pos shows real end of file */
};
bool Mf_read_block( struct Matchfinder * const matchfinder );
bool Mf_read_block( struct Matchfinder * const mf );
void Mf_init( struct Matchfinder * const matchfinder,
const int dict_size, const int len_limit, const int infd );
void Mf_init( struct Matchfinder * const mf,
const int dict_size, const int len_limit, const int ifd );
static inline void Mf_free( struct Matchfinder * const matchfinder )
static inline void Mf_free( struct Matchfinder * const mf )
{
free( matchfinder->prev_pos_tree ); matchfinder->prev_pos_tree = 0;
free( matchfinder->prev_positions ); matchfinder->prev_positions = 0;
free( matchfinder->buffer ); matchfinder->buffer = 0;
free( mf->prev_pos_tree ); mf->prev_pos_tree = 0;
free( mf->prev_positions ); mf->prev_positions = 0;
free( mf->buffer ); mf->buffer = 0;
}
static inline uint8_t Mf_peek( struct Matchfinder * const matchfinder, const int i )
{ return matchfinder->buffer[matchfinder->pos+i]; }
static inline int Mf_available_bytes( struct Matchfinder * const matchfinder )
{ return matchfinder->stream_pos - matchfinder->pos; }
static inline long long Mf_data_position( struct Matchfinder * const matchfinder )
{ return matchfinder->partial_data_pos + matchfinder->pos; }
static inline int Mf_dictionary_size( struct Matchfinder * const matchfinder )
{ return matchfinder->dictionary_size_; }
static inline bool Mf_finished( struct Matchfinder * const matchfinder )
{ return matchfinder->at_stream_end && matchfinder->pos >= matchfinder->stream_pos; }
static inline int Mf_match_len_limit( struct Matchfinder * const matchfinder )
{ return matchfinder->match_len_limit_; }
static inline const uint8_t * Mf_ptr_to_current_pos( struct Matchfinder * const matchfinder )
{ return matchfinder->buffer + matchfinder->pos; }
static inline uint8_t Mf_peek( struct Matchfinder * const mf, const int i )
{ return mf->buffer[mf->pos+i]; }
static inline int Mf_available_bytes( struct Matchfinder * const mf )
{ return mf->stream_pos - mf->pos; }
static inline long long Mf_data_position( struct Matchfinder * const mf )
{ return mf->partial_data_pos + mf->pos; }
static inline int Mf_dictionary_size( struct Matchfinder * const mf )
{ return mf->dictionary_size_; }
static inline bool Mf_finished( struct Matchfinder * const mf )
{ return mf->at_stream_end && mf->pos >= mf->stream_pos; }
static inline int Mf_match_len_limit( struct Matchfinder * const mf )
{ return mf->match_len_limit_; }
static inline const uint8_t * Mf_ptr_to_current_pos( struct Matchfinder * const mf )
{ return mf->buffer + mf->pos; }
static inline bool Mf_dec_pos( struct Matchfinder * const matchfinder,
static inline bool Mf_dec_pos( struct Matchfinder * const mf,
const int ahead )
{
if( ahead < 0 || matchfinder->pos < ahead ) return false;
matchfinder->pos -= ahead;
matchfinder->cyclic_pos -= ahead;
if( matchfinder->cyclic_pos < 0 )
matchfinder->cyclic_pos += matchfinder->dictionary_size_;
if( ahead < 0 || mf->pos < ahead ) return false;
mf->pos -= ahead;
mf->cyclic_pos -= ahead;
if( mf->cyclic_pos < 0 ) mf->cyclic_pos += mf->dictionary_size_;
return true;
}
static inline int Mf_true_match_len( struct Matchfinder * const matchfinder,
const int index, const int distance, int len_limit )
static inline int Mf_true_match_len( struct Matchfinder * const mf,
const int index, const int distance,
int len_limit )
{
if( index + len_limit > Mf_available_bytes( matchfinder ) )
len_limit = Mf_available_bytes( matchfinder ) - index;
const uint8_t * const data = matchfinder->buffer + matchfinder->pos + index - distance;
const uint8_t * const data = mf->buffer + mf->pos + index - distance;
int i = 0;
if( index + len_limit > Mf_available_bytes( mf ) )
len_limit = Mf_available_bytes( mf ) - index;
while( i < len_limit && data[i] == data[i+distance] ) ++i;
return i;
}
bool Mf_reset( struct Matchfinder * const matchfinder );
bool Mf_move_pos( struct Matchfinder * const matchfinder );
int Mf_longest_match_len( struct Matchfinder * const matchfinder,
int * const distances );
void Mf_reset( struct Matchfinder * const mf );
void Mf_move_pos( struct Matchfinder * const mf );
int Mf_longest_match_len( struct Matchfinder * const mf, int * const distances );
enum { re_buffer_size = 65536 };
@ -218,28 +223,15 @@ struct Range_encoder
{
uint64_t low;
long long partial_member_pos;
uint8_t * buffer;
int pos;
uint8_t * buffer; /* output buffer */
int pos; /* current pos in buffer */
uint32_t range;
int ff_count;
int outfd_; // output file descriptor
int outfd; /* output file descriptor */
uint8_t cache;
};
static inline void Re_flush_data( struct Range_encoder * const range_encoder )
{
if( range_encoder->pos > 0 )
{
if( range_encoder->outfd_ >= 0 )
{
const int wr = writeblock( range_encoder->outfd_, range_encoder->buffer, range_encoder->pos );
if( wr != range_encoder->pos )
{ show_error( "write error", errno, false ); cleanup_and_fail( 1 ); }
}
range_encoder->partial_member_pos += range_encoder->pos;
range_encoder->pos = 0;
}
}
void Re_flush_data( struct Range_encoder * const range_encoder );
static inline void Re_put_byte( struct Range_encoder * const range_encoder,
const uint8_t b )
@ -263,36 +255,37 @@ static inline void Re_shift_low( struct Range_encoder * const range_encoder )
}
static inline void Re_init( struct Range_encoder * const range_encoder,
const int outfd )
const int ofd )
{
range_encoder->low = 0;
range_encoder->partial_member_pos = 0;
range_encoder->buffer = (uint8_t *)malloc( re_buffer_size );
if( !range_encoder->buffer )
{
show_error( "not enough memory. Try a smaller dictionary size", 0, false );
show_error( "Not enough memory. Try a smaller dictionary size.", 0, false );
cleanup_and_fail( 1 );
}
range_encoder->pos = 0;
range_encoder->range = 0xFFFFFFFFU;
range_encoder->ff_count = 0;
range_encoder->outfd_ = outfd;
range_encoder->outfd = ofd;
range_encoder->cache = 0;
}
static inline void Re_free( struct Range_encoder * const range_encoder )
{ free( range_encoder->buffer ); range_encoder->buffer = 0; }
static inline void Re_flush( struct Range_encoder * const range_encoder )
{ for( int i = 0; i < 5; ++i ) Re_shift_low( range_encoder ); }
static inline long long Re_member_position( struct Range_encoder * const range_encoder )
{ return range_encoder->partial_member_pos + range_encoder->pos + range_encoder->ff_count; }
static inline void Re_flush( struct Range_encoder * const range_encoder )
{ int i; for( i = 0; i < 5; ++i ) Re_shift_low( range_encoder ); }
static inline void Re_encode( struct Range_encoder * const range_encoder,
const int symbol, const int num_bits )
{
for( int i = num_bits - 1; i >= 0; --i )
int i;
for( i = num_bits - 1; i >= 0; --i )
{
range_encoder->range >>= 1;
if( (symbol >> i) & 1 ) range_encoder->low += range_encoder->range;
@ -325,7 +318,8 @@ static inline void Re_encode_tree( struct Range_encoder * const range_encoder,
{
int mask = ( 1 << ( num_bits - 1 ) );
int model = 1;
for( int i = num_bits; i > 0; --i, mask >>= 1 )
int i;
for( i = num_bits; i > 0; --i, mask >>= 1 )
{
const int bit = ( symbol & mask );
Re_encode_bit( range_encoder, &bm[model], bit );
@ -338,7 +332,8 @@ static inline void Re_encode_tree_reversed( struct Range_encoder * const range_e
Bit_model bm[], int symbol, const int num_bits )
{
int model = 1;
for( int i = num_bits; i > 0; --i )
int i;
for( i = num_bits; i > 0; --i )
{
const int bit = symbol & 1;
Re_encode_bit( range_encoder, &bm[model], bit );
@ -351,7 +346,8 @@ static inline void Re_encode_matched( struct Range_encoder * const range_encoder
Bit_model bm[], int symbol, int match_byte )
{
int model = 1;
for( int i = 7; i >= 0; --i )
int i;
for( i = 7; i >= 0; --i )
{
const int match_bit = ( match_byte >> i ) & 1;
int bit = ( symbol >> i ) & 1;
@ -405,18 +401,19 @@ static inline void Lee_update_prices( struct Len_encoder * const len_encoder,
static inline void Lee_init( struct Len_encoder * const len_encoder,
const int len_limit )
{
int i, j;
Bm_init( &len_encoder->choice1 );
Bm_init( &len_encoder->choice2 );
for( int i = 0; i < pos_states; ++i )
for( int j = 0; j < len_low_symbols; ++j )
for( i = 0; i < pos_states; ++i )
for( j = 0; j < len_low_symbols; ++j )
Bm_init( &len_encoder->bm_low[i][j] );
for( int i = 0; i < pos_states; ++i )
for( int j = 0; j < len_mid_symbols; ++j )
for( i = 0; i < pos_states; ++i )
for( j = 0; j < len_mid_symbols; ++j )
Bm_init( &len_encoder->bm_mid[i][j] );
for( int i = 0; i < len_high_symbols; ++i )
for( i = 0; i < len_high_symbols; ++i )
Bm_init( &len_encoder->bm_high[i] );
len_encoder->len_symbols = len_limit + 1 - min_match_len;
for( int i = 0; i < pos_states; ++i ) Lee_update_prices( len_encoder, i );
for( i = 0; i < pos_states; ++i ) Lee_update_prices( len_encoder, i );
}
void Lee_encode( struct Len_encoder * const len_encoder,
@ -433,16 +430,17 @@ struct Literal_encoder
Bit_model bm_literal[1<<literal_context_bits][0x300];
};
static inline void Lie_init( struct Literal_encoder * const literal_encoder )
{
for( int i = 0; i < 1<<literal_context_bits; ++i )
for( int j = 0; j < 0x300; ++j )
Bm_init( &literal_encoder->bm_literal[i][j] );
}
static inline int Lie_state( const int prev_byte )
{ return ( prev_byte >> ( 8 - literal_context_bits ) ); }
static inline void Lie_init( struct Literal_encoder * const literal_encoder )
{
int i, j;
for( i = 0; i < 1<<literal_context_bits; ++i )
for( j = 0; j < 0x300; ++j )
Bm_init( &literal_encoder->bm_literal[i][j] );
}
static inline void Lie_encode( struct Literal_encoder * const literal_encoder,
struct Range_encoder * const range_encoder,
uint8_t prev_byte, uint8_t symbol )
@ -450,29 +448,28 @@ static inline void Lie_encode( struct Literal_encoder * const literal_encoder,
static inline void Lie_encode_matched( struct Literal_encoder * const literal_encoder,
struct Range_encoder * const range_encoder,
uint8_t prev_byte, uint8_t match_byte, uint8_t symbol )
uint8_t prev_byte, uint8_t symbol, uint8_t match_byte )
{ Re_encode_matched( range_encoder, literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, match_byte ); }
static inline int Lie_price_matched( struct Literal_encoder * const literal_encoder,
uint8_t prev_byte, uint8_t symbol, uint8_t match_byte )
{ return price_matched( literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, match_byte ); }
static inline int Lie_price_symbol( struct Literal_encoder * const literal_encoder,
uint8_t prev_byte, uint8_t symbol )
{ return price_symbol( literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, 8 ); }
static inline int Lie_price_matched( struct Literal_encoder * const literal_encoder,
uint8_t prev_byte, uint8_t symbol, uint8_t match_byte )
{ return price_matched( literal_encoder->bm_literal[Lie_state(prev_byte)], symbol, match_byte ); }
enum { lze_dis_align_mask = dis_align_size - 1,
lze_infinite_price = 0x0FFFFFFF,
lze_max_marker_size = 16,
num_rep_distances = 4 }; // must be 4
enum { infinite_price = 0x0FFFFFFF,
max_marker_size = 16,
num_rep_distances = 4 }; /* must be 4 */
struct Trial
{
State state;
int dis;
int prev_index; // index of prev trial in trials[]
int price; // dual use var; cumulative price, match length
int prev_index; /* index of prev trial in trials[] */
int price; /* dual use var; cumulative price, match length */
int reps[num_rep_distances];
};
@ -489,14 +486,14 @@ struct LZ_encoder
int longest_match_found;
uint32_t crc_;
Bit_model bm_match[St_states][pos_states];
Bit_model bm_rep[St_states];
Bit_model bm_rep0[St_states];
Bit_model bm_rep1[St_states];
Bit_model bm_rep2[St_states];
Bit_model bm_len[St_states][pos_states];
Bit_model bm_match[states][pos_states];
Bit_model bm_rep[states];
Bit_model bm_rep0[states];
Bit_model bm_rep1[states];
Bit_model bm_rep2[states];
Bit_model bm_len[states][pos_states];
Bit_model bm_dis_slot[max_dis_states][1<<dis_slot_bits];
Bit_model bm_dis[modeled_distances-end_dis_model];
Bit_model bm_dis[modeled_distances-end_dis_model+1];
Bit_model bm_align[dis_align_size];
struct Matchfinder * matchfinder;
@ -521,18 +518,19 @@ void LZe_fill_distance_prices( struct LZ_encoder * const encoder );
static inline uint32_t LZe_crc( struct LZ_encoder * const encoder )
{ return encoder->crc_ ^ 0xFFFFFFFFU; }
// move-to-front dis in/into reps
/* move-to-front dis in/into reps */
static inline void LZe_mtf_reps( const int dis, int reps[num_rep_distances] )
{
int i;
if( dis >= num_rep_distances )
{
for( int i = num_rep_distances - 1; i > 0; --i ) reps[i] = reps[i-1];
for( i = num_rep_distances - 1; i > 0; --i ) reps[i] = reps[i-1];
reps[0] = dis - num_rep_distances;
}
else if( dis > 0 )
{
const int distance = reps[dis];
for( int i = dis; i > 0; --i ) reps[i] = reps[i-1];
for( i = dis; i > 0; --i ) reps[i] = reps[i-1];
reps[0] = distance;
}
}
@ -546,9 +544,10 @@ static inline int LZe_price_rep_len1( struct LZ_encoder * const encoder,
static inline int LZe_price_rep( struct LZ_encoder * const encoder, const int rep,
const State state, const int pos_state )
{
int price;
if( rep == 0 ) return price0( encoder->bm_rep0[state] ) +
price1( encoder->bm_len[state][pos_state] );
int price = price1( encoder->bm_rep0[state] );
price = price1( encoder->bm_rep0[state] );
if( rep == 1 )
price += price0( encoder->bm_rep1[state] );
else
@ -559,27 +558,33 @@ static inline int LZe_price_rep( struct LZ_encoder * const encoder, const int re
return price;
}
static inline int LZe_price_pair( struct LZ_encoder * const encoder, const int dis,
const int len, const int pos_state )
static inline int LZe_price_pair( struct LZ_encoder * const encoder,
const int dis, const int len,
const int pos_state )
{
if( len <= min_match_len && dis >= modeled_distances )
return lze_infinite_price;
int price = Lee_price( &encoder->len_encoder, len, pos_state );
const int dis_state = get_dis_state( len );
int price;
if( len <= min_match_len && dis >= modeled_distances )
return infinite_price;
price = Lee_price( &encoder->len_encoder, len, pos_state );
if( dis < modeled_distances )
price += encoder->dis_prices[dis_state][dis];
else
price += encoder->dis_slot_prices[dis_state][get_slot( dis )] +
encoder->align_prices[dis & lze_dis_align_mask];
encoder->align_prices[dis & (dis_align_size - 1)];
return price;
}
static inline void LZe_encode_pair( struct LZ_encoder * const encoder,
const uint32_t dis, const int len, const int pos_state )
const uint32_t dis, const int len,
const int pos_state )
{
Lee_encode( &encoder->len_encoder, &encoder->range_encoder, len, pos_state );
const int dis_slot = get_slot( dis );
Re_encode_tree( &encoder->range_encoder, encoder->bm_dis_slot[get_dis_state(len)], dis_slot, dis_slot_bits );
Lee_encode( &encoder->len_encoder, &encoder->range_encoder, len, pos_state );
Re_encode_tree( &encoder->range_encoder,
encoder->bm_dis_slot[get_dis_state(len)],
dis_slot, dis_slot_bits );
if( dis_slot >= start_dis_model )
{
@ -607,16 +612,15 @@ static inline int LZe_read_match_distances( struct LZ_encoder * const encoder )
return len;
}
static inline bool LZe_move_pos( struct LZ_encoder * const encoder,
static inline void LZe_move_pos( struct LZ_encoder * const encoder,
int n, bool skip )
{
while( --n >= 0 )
{
if( skip ) skip = false;
else Mf_longest_match_len( encoder->matchfinder, 0 );
if( !Mf_move_pos( encoder->matchfinder ) ) return false;
Mf_move_pos( encoder->matchfinder );
}
return true;
}
static inline void LZe_backward( struct LZ_encoder * const encoder, int cur )
@ -626,7 +630,7 @@ static inline void LZe_backward( struct LZ_encoder * const encoder, int cur )
{
const int prev_index = encoder->trials[cur].prev_index;
struct Trial * const prev_trial = &encoder->trials[prev_index];
prev_trial->price = cur - prev_index; // len
prev_trial->price = cur - prev_index; /* len */
cur = *dis; *dis = prev_trial->dis; prev_trial->dis = cur;
cur = prev_index;
}