diff options
Diffstat (limited to 'decoder.c')
| -rw-r--r-- | decoder.c | 103 |
1 files changed, 55 insertions, 48 deletions
@@ -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 @@ -28,18 +28,20 @@ #include "decoder.h" +CRC32 crc32; + bool Rd_read_block( struct Range_decoder * const rdec ) { if( !rdec->at_stream_end ) { - rdec->stream_pos = readblock( rdec->infd_, rdec->buffer, Rd_buffer_size ); - if( rdec->stream_pos != Rd_buffer_size && errno ) - { show_error( "read error", errno, false ); cleanup_and_fail( 1 ); } - rdec->at_stream_end = ( rdec->stream_pos < Rd_buffer_size ); + rdec->stream_pos = readblock( rdec->infd, rdec->buffer, rd_buffer_size ); + if( rdec->stream_pos != rd_buffer_size && errno ) + { show_error( "Read error", errno, false ); cleanup_and_fail( 1 ); } + rdec->at_stream_end = ( rdec->stream_pos < rd_buffer_size ); rdec->partial_member_pos += rdec->pos; rdec->pos = 0; } - return !Rd_finished( rdec ); + return rdec->pos < rdec->stream_pos; } @@ -49,8 +51,8 @@ void LZd_flush_data( struct LZ_decoder * const decoder ) if( size > 0 ) { CRC32_update_buf( &decoder->crc_, decoder->buffer + decoder->stream_pos, size ); - if( decoder->outfd_ >= 0 && - writeblock( decoder->outfd_, decoder->buffer + decoder->stream_pos, size ) != size ) + if( decoder->outfd >= 0 && + writeblock( decoder->outfd, decoder->buffer + decoder->stream_pos, size ) != size ) { show_error( "write error", errno, false ); cleanup_and_fail( 1 ); } if( decoder->pos >= decoder->buffer_size ) { decoder->partial_data_pos += decoder->pos; decoder->pos = 0; } @@ -62,22 +64,24 @@ void LZd_flush_data( struct LZ_decoder * const decoder ) bool LZd_verify_trailer( struct LZ_decoder * const decoder, struct Pretty_print * const pp ) { + int i; File_trailer trailer; const int trailer_size = Ft_versioned_size( decoder->member_version ); - const long long member_size = LZd_member_position( decoder ) + trailer_size; + const long long member_size = + Rd_member_position( decoder->range_decoder ) + trailer_size; bool error = false; - for( int i = 0; i < trailer_size && !error; ++i ) + for( i = 0; i < trailer_size && !error; ++i ) { if( !Rd_finished( decoder->range_decoder ) ) trailer[i] = Rd_get_byte( decoder->range_decoder ); else { error = true; - if( verbosity >= 0 ) + if( pp->verbosity >= 0 ) { Pp_show_msg( pp, 0 ); - fprintf( stderr, "trailer truncated at trailer position %d;" + fprintf( stderr, "Trailer truncated at trailer position %d;" " some checks may fail.\n", i ); } for( ; i < trailer_size; ++i ) trailer[i] = 0; @@ -87,19 +91,15 @@ bool LZd_verify_trailer( struct LZ_decoder * const decoder, if( !Rd_code_is_zero( decoder->range_decoder ) ) { error = true; - if( verbosity >= 0 ) - { - Pp_show_msg( pp, 0 ); - fprintf( stderr, "range_decoder final code is not zero.\n" ); - } + Pp_show_msg( pp, "Range decoder final code is not zero" ); } if( Ft_get_data_crc( trailer ) != LZd_crc( decoder ) ) { error = true; - if( verbosity >= 0 ) + if( pp->verbosity >= 0 ) { Pp_show_msg( pp, 0 ); - fprintf( stderr, "crc mismatch; trailer says %08X, data crc is %08X.\n", + fprintf( stderr, "CRC mismatch; trailer says %08X, data CRC is %08X.\n", (unsigned int)Ft_get_data_crc( trailer ), (unsigned int)LZd_crc( decoder ) ); } @@ -107,51 +107,56 @@ bool LZd_verify_trailer( struct LZ_decoder * const decoder, if( Ft_get_data_size( trailer ) != LZd_data_position( decoder ) ) { error = true; - if( verbosity >= 0 ) + if( pp->verbosity >= 0 ) { Pp_show_msg( pp, 0 ); - fprintf( stderr, "data size mismatch; trailer says %lld, data size is %lld (0x%llX).\n", + fprintf( stderr, "Data size mismatch; trailer says %lld, data size is %lld (0x%llX).\n", Ft_get_data_size( trailer ), LZd_data_position( decoder ), LZd_data_position( decoder ) ); } } if( Ft_get_member_size( trailer ) != member_size ) { error = true; - if( verbosity >= 0 ) + if( pp->verbosity >= 0 ) { Pp_show_msg( pp, 0 ); - fprintf( stderr, "member size mismatch; trailer says %lld, member size is %lld (0x%llX).\n", + fprintf( stderr, "Member size mismatch; trailer says %lld, member size is %lld (0x%llX).\n", Ft_get_member_size( trailer ), member_size, member_size ); } } - if( !error && verbosity >= 3 ) - fprintf( stderr, "data crc %08X, data size %9lld, member size %8lld. ", + if( !error && pp->verbosity >= 4 && LZd_data_position( decoder ) > 0 && member_size > 0 ) + fprintf( stderr, "%6.3f:1, %6.3f bits/byte, %5.2f%% saved. ", + (double)LZd_data_position( decoder ) / member_size, + ( 8.0 * member_size ) / LZd_data_position( decoder ), + 100.0 * ( 1.0 - ( (double)member_size / LZd_data_position( decoder ) ) ) ); + if( !error && pp->verbosity >= 3 ) + fprintf( stderr, "data CRC %08X, data size %9lld, member size %8lld. ", (unsigned int)Ft_get_data_crc( trailer ), Ft_get_data_size( trailer ), Ft_get_member_size( trailer ) ); return !error; } - // Return value: 0 = OK, 1 = decoder error, 2 = unexpected EOF, - // 3 = trailer error, 4 = unknown marker found. +/* Return value: 0 = OK, 1 = decoder error, 2 = unexpected EOF, + 3 = trailer error, 4 = unknown marker found. */ int LZd_decode_member( struct LZ_decoder * const decoder, struct Pretty_print * const pp ) { - unsigned int rep0 = 0; // rep[0-3] latest four distances - unsigned int rep1 = 0; // used for efficient coding of - unsigned int rep2 = 0; // repeated distances + unsigned int rep0 = 0; /* rep[0-3] latest four distances */ + unsigned int rep1 = 0; /* used for efficient coding of */ + unsigned int rep2 = 0; /* repeated distances */ unsigned int rep3 = 0; State state = 0; Rd_load( decoder->range_decoder ); while( true ) { + const int pos_state = LZd_data_position( decoder ) & pos_state_mask; if( Rd_finished( decoder->range_decoder ) ) { LZd_flush_data( decoder ); return 2; } - const int pos_state = LZd_data_position( decoder ) & pos_state_mask; if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_match[state][pos_state] ) == 0 ) { - const uint8_t prev_byte = LZd_get_byte( decoder, 0 ); + const uint8_t prev_byte = LZd_get_prev_byte( decoder ); if( St_is_char( state ) ) LZd_put_byte( decoder, Lid_decode( &decoder->literal_decoder, decoder->range_decoder, prev_byte ) ); @@ -166,12 +171,7 @@ int LZd_decode_member( struct LZ_decoder * const decoder, if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_rep[state] ) == 1 ) { len = 0; - if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_rep0[state] ) == 0 ) - { - if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_len[state][pos_state] ) == 0 ) - { len = 1; St_set_short_rep( &state ); } - } - else + if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_rep0[state] ) == 1 ) { unsigned int distance; if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_rep1[state] ) == 0 ) @@ -186,17 +186,23 @@ int LZd_decode_member( struct LZ_decoder * const decoder, rep1 = rep0; rep0 = distance; } + else + { + if( Rd_decode_bit( decoder->range_decoder, &decoder->bm_len[state][pos_state] ) == 0 ) + { St_set_short_rep( &state ); len = 1; } + } if( len == 0 ) { - len = min_match_len + Led_decode( &decoder->rep_match_len_decoder, decoder->range_decoder, pos_state ); St_set_rep( &state ); + len = min_match_len + Led_decode( &decoder->rep_match_len_decoder, decoder->range_decoder, pos_state ); } } else { - unsigned int rep0_saved = rep0; + int dis_slot; + const unsigned int rep0_saved = rep0; len = min_match_len + Led_decode( &decoder->len_decoder, decoder->range_decoder, pos_state ); - const int dis_slot = Rd_decode_tree( decoder->range_decoder, decoder->bm_dis_slot[get_dis_state(len)], dis_slot_bits ); + dis_slot = Rd_decode_tree( decoder->range_decoder, decoder->bm_dis_slot[get_dis_state(len)], dis_slot_bits ); if( dis_slot < start_dis_model ) rep0 = dis_slot; else { @@ -208,32 +214,33 @@ int LZd_decode_member( struct LZ_decoder * const decoder, { rep0 += Rd_decode( decoder->range_decoder, direct_bits - dis_align_bits ) << dis_align_bits; rep0 += Rd_decode_tree_reversed( decoder->range_decoder, decoder->bm_align, dis_align_bits ); - if( rep0 == 0xFFFFFFFFU ) // Marker found + if( rep0 == 0xFFFFFFFFU ) /* Marker found */ { rep0 = rep0_saved; Rd_normalize( decoder->range_decoder ); LZd_flush_data( decoder ); - if( len == min_match_len ) // End Of Stream marker + if( len == min_match_len ) /* End Of Stream marker */ { if( LZd_verify_trailer( decoder, pp ) ) return 0; else return 3; } - if( len == min_match_len + 1 ) // Sync Flush marker + if( len == min_match_len + 1 ) /* Sync Flush marker */ { Rd_load( decoder->range_decoder ); continue; } - if( verbosity >= 0 ) + if( pp->verbosity >= 0 ) { Pp_show_msg( pp, 0 ); - fprintf( stderr, "unsupported marker code `%d'.\n", len ); + fprintf( stderr, "Unsupported marker code `%d'.\n", len ); } return 4; } - if( rep0 >= (unsigned int)decoder->dictionary_size ) - { LZd_flush_data( decoder ); return 1; } } } rep3 = rep2; rep2 = rep1; rep1 = rep0_saved; St_set_match( &state ); + if( rep0 >= (unsigned int)decoder->dictionary_size || + ( rep0 >= (unsigned int)decoder->pos && !decoder->partial_data_pos ) ) + { LZd_flush_data( decoder ); return 1; } } LZd_copy_block( decoder, rep0, len ); } |