summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--ChangeLog35
-rw-r--r--INSTALL4
-rw-r--r--Makefile.in41
-rw-r--r--NEWS22
-rw-r--r--README17
-rw-r--r--bbexample.cc210
-rwxr-xr-xconfigure8
-rw-r--r--decoder.cc36
-rw-r--r--decoder.h33
-rw-r--r--doc/lzlib.info69
-rw-r--r--doc/lzlib.texinfo49
-rw-r--r--encoder.cc87
-rw-r--r--encoder.h77
-rw-r--r--lzcheck.cc36
-rw-r--r--lzip.h105
-rw-r--r--lzlib.cc32
-rw-r--r--lzlib.h4
-rw-r--r--main.cc186
-rwxr-xr-xtestsuite/check.sh47
-rw-r--r--testsuite/test.txt (renamed from testsuite/test1)0
-rw-r--r--testsuite/test_sync.lzbin0 -> 11658 bytes
-rw-r--r--testsuite/test_v0.lz (renamed from testsuite/test1.lz)bin11540 -> 11540 bytes
-rw-r--r--testsuite/test_v1.lzbin0 -> 11548 bytes
23 files changed, 714 insertions, 384 deletions
diff --git a/ChangeLog b/ChangeLog
index d1281f9..8fc5df8 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,16 @@
+2011-01-03 Antonio Diaz Diaz <ant_diaz@teleline.es>
+
+ * Version 1.1 released.
+ * Compression time has been reduced by 2%.
+ * All declarations not belonging to the API have been
+ encapsulated in the namespace `Lzlib'.
+ * testsuite: `test1' renamed to `test.txt'. Added new tests.
+ * Match length limits set by options -1 to -9 of minilzip have
+ been changed to match those of lzip 1.11.
+ * main.cc: Set stdin/stdout in binary mode on OS2.
+ * bbexample.cc: New file containing example functions for
+ buffer-to-buffer compression/decompression.
+
2010-05-08 Antonio Diaz Diaz <ant_diaz@teleline.es>
* Version 1.0 released.
@@ -5,7 +18,7 @@
* Added new function LZ_decompress_member_version.
* Added new function LZ_decompress_dictionary_size.
* Added new function LZ_decompress_data_crc.
- * Variables declared "extern" have been encapsulated in a
+ * Variables declared `extern' have been encapsulated in a
namespace.
* main.cc: Fixed warning about fchown's return value being ignored.
* decoder.h: Input_buffer integrated in Range_decoder.
@@ -14,7 +27,7 @@
* Version 0.9 released.
* Compression time has been reduced by 8%.
- * main.cc: New constant "o_binary".
+ * main.cc: New constant `o_binary'.
2010-01-17 Antonio Diaz Diaz <ant_diaz@teleline.es>
@@ -23,18 +36,18 @@
* Added new function LZ_decompress_sync_to_member.
* Added new function LZ_decompress_write_size.
* Added new function LZ_strerror.
- * lzlib.h: API change. Replaced "enum" with functions for values
+ * lzlib.h: API change. Replaced `enum' with functions for values
of dictionary size limits to make interface names consistent.
- * lzlib.h: API change. "LZ_errno" replaced with "LZ_Errno".
- * lzlib.h: API change. Replaced "void *" with "struct LZ_Encoder *"
- and "struct LZ_Decoder *" to make interface type safe.
+ * lzlib.h: API change. `LZ_errno' replaced with `LZ_Errno'.
+ * lzlib.h: API change. Replaced `void *' with `struct LZ_Encoder *'
+ and `struct LZ_Decoder *' to make interface type safe.
* decoder.cc: Truncated member trailer is now correctly detected.
* encoder.cc: Matchfinder::reset now also clears at_stream_end_,
allowing LZ_compress_restart_member to restart a finished stream.
* lzlib.cc: Accept only query or close operations after a fatal
error has occurred.
* Shared version of lzlib is no more built by default.
- * testsuite/check.sh: Use "test1" instead of "COPYING" for testing.
+ * testsuite/check.sh: Use `test1' instead of `COPYING' for testing.
2009-10-20 Antonio Diaz Diaz <ant_diaz@teleline.es>
@@ -60,7 +73,7 @@
* Added new function LZ_compress_sync_flush.
* Added new function LZ_compress_write_size.
* Decompression speed has been improved.
- * Added chapter "Buffering" to the manual.
+ * Added chapter `Buffering' to the manual.
2009-05-03 Antonio Diaz Diaz <ant_diaz@teleline.es>
@@ -78,8 +91,8 @@
* Version 0.1 released.
-Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This file is a collection of facts, and thus it is not copyrightable,
-but just in case, I give you unlimited permission to copy, distribute
-and modify it.
+but just in case, you have unlimited permission to copy, distribute and
+modify it.
diff --git a/INSTALL b/INSTALL
index 2649f53..5f00801 100644
--- a/INSTALL
+++ b/INSTALL
@@ -1,7 +1,7 @@
Requirements
------------
You will need a C++ compiler.
-I use gcc 4.3.4 and 3.3.6, but the code should compile with any
+I use gcc 4.3.5 and 3.3.6, but the code should compile with any
standards compliant compiler.
Gcc is available at http://gcc.gnu.org.
@@ -50,7 +50,7 @@ After running `configure', you can run `make' and `make install' as
explained above.
-Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.
diff --git a/Makefile.in b/Makefile.in
index a68698a..94e0114 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -20,22 +20,25 @@ objs = arg_parser.o main.o
all : $(progname) $(progname_shared)
lib$(libname).a: $(lib_objs)
- $(AR) -rcs lib$(libname).a $(lib_objs)
+ $(AR) -rcs $@ $^
lib$(libname).so.$(pkgversion) : $(sh_lib_objs)
- $(CXX) -shared -Wl,--soname=lib$(libname).so.$(soversion) -o lib$(libname).so.$(pkgversion) $(sh_lib_objs)
+ $(CXX) -shared -Wl,--soname=lib$(libname).so.$(soversion) -o $@ $^
$(progname) : $(objs) lib$(libname).a
- $(CXX) $(LDFLAGS) -o $(progname) $(objs) lib$(libname).a
+ $(CXX) $(LDFLAGS) -o $@ $^
$(progname)_shared : $(objs) lib$(libname).so.$(pkgversion)
- $(CXX) $(LDFLAGS) -o $(progname)_shared $(objs) lib$(libname).so.$(pkgversion)
+ $(CXX) $(LDFLAGS) -o $@ $^
$(progname)_profiled : $(objs) lib$(libname).a
- $(CXX) $(LDFLAGS) -pg -o $(progname)_profiled $(objs) lib$(libname).a
+ $(CXX) $(LDFLAGS) -pg -o $@ $^
+
+bbexample : bbexample.o lib$(libname).a
+ $(CXX) $(LDFLAGS) -o $@ $^
lzcheck : lzcheck.o lib$(libname).a
- $(CXX) $(LDFLAGS) -o lzcheck lzcheck.o lib$(libname).a
+ $(CXX) $(LDFLAGS) -o $@ $^
main.o : main.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $<
@@ -44,13 +47,13 @@ main.o : main.cc
$(CXX) $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
sh_decoder.o : decoder.cc
- $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_decoder.o $<
+ $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
sh_encoder.o : encoder.cc
- $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_encoder.o $<
+ $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
sh_lzlib.o : lzlib.cc
- $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o sh_lzlib.o $<
+ $(CXX) -fpic -fPIC $(CPPFLAGS) $(CXXFLAGS) -c -o $@ $<
$(lib_objs) : Makefile lzlib.h lzip.h
$(sh_lib_objs) : Makefile lzlib.h lzip.h
@@ -63,6 +66,7 @@ sh_decoder.o : decoder.h
sh_encoder.o : encoder.h
sh_lzlib.o : decoder.h encoder.h
main.o : arg_parser.h lzlib.h
+bbexample.o : Makefile lzlib.h
lzcheck.o : Makefile lzlib.h
@@ -76,14 +80,14 @@ $(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texinfo
man : $(VPATH)/doc/$(progname).1
$(VPATH)/doc/$(progname).1 : $(progname)
- help2man -n 'test program for the lzlib library' \
- -o $(VPATH)/doc/$(progname).1 --no-info ./$(progname)
+ help2man -n 'reduces the size of files' \
+ -o $@ --no-info ./$(progname)
Makefile : $(VPATH)/configure $(VPATH)/Makefile.in
./config.status
-check : all lzcheck
- @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite
+check : all bbexample lzcheck
+ @$(VPATH)/testsuite/check.sh $(VPATH)/testsuite $(pkgversion)
install : all install-info
if [ ! -d "$(DESTDIR)$(includedir)" ] ; then $(INSTALL_DIR) "$(DESTDIR)$(includedir)" ; fi
@@ -112,7 +116,7 @@ install-man :
install-strip : all
$(MAKE) INSTALL_PROGRAM='$(INSTALL_PROGRAM) -s' install
-uninstall : uninstall-info
+uninstall : uninstall-info uninstall-man
-rm -f "$(DESTDIR)$(includedir)/$(libname)lib.h"
-rm -f "$(DESTDIR)$(libdir)/lib$(libname).a"
-rm -f "$(DESTDIR)$(libdir)/lib$(libname).so.$(soversion)"
@@ -139,17 +143,18 @@ dist : doc
$(DISTNAME)/doc/$(pkgname).info \
$(DISTNAME)/doc/$(pkgname).texinfo \
$(DISTNAME)/testsuite/check.sh \
- $(DISTNAME)/testsuite/test1 \
- $(DISTNAME)/testsuite/test1.lz \
+ $(DISTNAME)/testsuite/test.txt \
+ $(DISTNAME)/testsuite/test_sync.lz \
+ $(DISTNAME)/testsuite/test_v[01].lz \
$(DISTNAME)/*.h \
$(DISTNAME)/*.cc
rm -f $(DISTNAME)
lzip -v -9 $(DISTNAME).tar
clean :
- -rm -f $(progname) $(progname)_profiled $(objs) $(lib_objs) *.a
+ -rm -f $(progname) $(progname)_profiled $(objs)
-rm -f $(progname)_shared $(sh_lib_objs) *.so.$(pkgversion)
- -rm -f lzcheck.o
+ -rm -f bbexample bbexample.o lzcheck lzcheck.o $(lib_objs) *.a
distclean : clean
-rm -f Makefile config.status *.tar *.tar.lz
diff --git a/NEWS b/NEWS
index 502457a..dade660 100644
--- a/NEWS
+++ b/NEWS
@@ -1,14 +1,16 @@
-Changes in version 1.0:
+Changes in version 1.1:
-New functions:
- LZ_decompress_member_finished.
- LZ_decompress_member_version.
- LZ_decompress_dictionary_size.
- LZ_decompress_data_crc.
+Compression time has been reduced by 2%.
-Variables declared "extern" have been encapsulated in a namespace.
+All declarations not belonging to the API have been encapsulated in the
+namespace "Lzlib".
-A warning about fchown's return value being ignored has been fixed.
+New tests have been added to the testsuite.
-Input_buffer has been integrated in Range_decoder, simplifying the code
-and making decompression slightly faster.
+Match length limits set by options -1 to -9 of minilzip have been
+changed to match those of lzip 1.11.
+
+Minilzip now sets stdin and stdout in binary mode on OS2.
+
+The file bbexample.cc, containing example functions for buffer-to-buffer
+compression/decompression, has been added.
diff --git a/README b/README
index ea8f363..2ef6461 100644
--- a/README
+++ b/README
@@ -2,21 +2,22 @@ Description
Lzlib is a data compression library providing in-memory LZMA compression
and decompression functions, including integrity checking of the
-uncompressed data. The compressed data format used by the library is the
+decompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
-library are declared in the file lzlib.h. An usage example of the
-library is given in the file main.cc.
+library are declared in the file lzlib.h. Usage examples of the library
+are given in the files main.cc and bbexample.cc from the source
+distribution.
-Compression/decompression is done by repeteadly calling a couple of
+Compression/decompression is done by repeatedly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
Lzlib will correctly decompress a data stream which is the concatenation
of two or more compressed data streams. The result is the concatenation
-of the corresponding uncompressed data streams. Integrity testing of
+of the corresponding decompressed data streams. Integrity testing of
concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not install
@@ -29,11 +30,11 @@ Igor Pavlov. For a description of the LZMA algorithm, see the Lzip
manual.
-Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This file is free documentation: you have unlimited permission to copy,
distribute and modify it.
The file Makefile.in is a data file used by configure to produce the
-Makefile. It has the same copyright owner and permissions that this
-file.
+Makefile. It has the same copyright owner and permissions that configure
+itself.
diff --git a/bbexample.cc b/bbexample.cc
new file mode 100644
index 0000000..df91300
--- /dev/null
+++ b/bbexample.cc
@@ -0,0 +1,210 @@
+/* Buff to buff example - A test program for the lzlib library
+ Copyright (C) 2010, 2011 Antonio Diaz Diaz.
+
+ This program is free software: you have unlimited permission
+ to copy, distribute and modify it.
+
+ Usage is:
+ bbexample filename
+
+ This program is an example of how buffer-to-buffer
+ compression/decompression can be implemented using lzlib.
+*/
+
+#ifndef __cplusplus
+#include <stdbool.h>
+#endif
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+#include <unistd.h>
+
+#include "lzlib.h"
+
+#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
+
+
+// Compresses `size' bytes from `data'. Returns the address of a
+// malloc'd buffer containing the compressed data and its size in
+// `*out_sizep'.
+// In case of error, returns 0 and does not modify `*out_sizep'.
+
+uint8_t * bbcompress( const uint8_t * const data, const int size,
+ int * const out_sizep )
+ {
+ int dict_size = 8 << 20; // 8 MiB
+ const int match_len_limit = 36;
+ const long long member_size = LLONG_MAX;
+ if( dict_size > size ) dict_size = size;
+ if( dict_size < LZ_min_dictionary_size() )
+ dict_size = LZ_min_dictionary_size();
+ struct LZ_Encoder * encoder =
+ LZ_compress_open( dict_size, match_len_limit, member_size );
+ if( !encoder || LZ_compress_errno( encoder ) != LZ_ok )
+ { LZ_compress_close( encoder ); return 0; }
+
+ const int delta_size = (size < 256) ? 64 : size / 4; // size may be zero
+ int new_data_size = delta_size; // initial size
+ uint8_t * new_data = (uint8_t *)malloc( new_data_size );
+ if( !new_data )
+ { LZ_compress_close( encoder ); return 0; }
+
+ int new_pos = 0;
+ int written = 0;
+ bool error = false;
+ while( true )
+ {
+ if( LZ_compress_write_size( encoder ) > 0 )
+ {
+ if( written < size )
+ {
+ const int wr = LZ_compress_write( encoder, data + written,
+ size - written );
+ if( wr < 0 ) { error = true; break; }
+ written += wr;
+ }
+ if( written >= size ) LZ_compress_finish( encoder );
+ }
+ const int rd = LZ_compress_read( encoder, new_data + new_pos,
+ new_data_size - new_pos );
+ if( rd < 0 ) { error = true; break; }
+ new_pos += rd;
+ if( LZ_compress_finished( encoder ) == 1 ) break;
+ if( new_pos >= new_data_size )
+ {
+ void * const tmp = realloc( new_data, new_data_size + delta_size );
+ if( !tmp ) { error = true; break; }
+ new_data = (uint8_t *)tmp;
+ new_data_size += delta_size;
+ }
+ }
+
+ if( LZ_compress_close( encoder ) < 0 ) error = true;
+ if( error ) { free( new_data ); return 0; }
+ *out_sizep = new_pos;
+ return new_data;
+ }
+
+
+// Decompresses `size' bytes from `data'. Returns the address of a
+// malloc'd buffer containing the decompressed data and its size in
+// `*out_sizep'.
+// In case of error, returns 0 and does not modify `*out_sizep'.
+
+uint8_t * bbdecompress( const uint8_t * const data, const int size,
+ int * const out_sizep )
+ {
+ struct LZ_Decoder * decoder = LZ_decompress_open();
+ if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok )
+ { LZ_decompress_close( decoder ); return 0; }
+
+ const int delta_size = size;
+ int new_data_size = delta_size; // initial size
+ uint8_t * new_data = (uint8_t *)malloc( new_data_size );
+ if( !new_data )
+ { LZ_decompress_close( decoder ); return 0; }
+
+ int new_pos = 0;
+ int written = 0;
+ bool error = false;
+ while( true )
+ {
+ if( LZ_decompress_write_size( decoder ) > 0 )
+ {
+ if( written < size )
+ {
+ const int wr = LZ_decompress_write( decoder, data + written,
+ size - written );
+ if( wr < 0 ) { error = true; break; }
+ written += wr;
+ }
+ if( written >= size ) LZ_decompress_finish( decoder );
+ }
+ const int rd = LZ_decompress_read( decoder, new_data + new_pos,
+ new_data_size - new_pos );
+ if( rd < 0 ) { error = true; break; }
+ new_pos += rd;
+ if( LZ_decompress_finished( decoder ) == 1 ) break;
+ if( new_pos >= new_data_size )
+ {
+ void * const tmp = realloc( new_data, new_data_size + delta_size );
+ if( !tmp ) { error = true; break; }
+ new_data = (uint8_t *)tmp;
+ new_data_size += delta_size;
+ }
+ }
+
+ if( LZ_decompress_close( decoder ) < 0 ) error = true;
+ if( error ) { free( new_data ); return 0; }
+ *out_sizep = new_pos;
+ return new_data;
+ }
+
+
+int main( const int argc, const char * const argv[] )
+ {
+ if( argc < 2 )
+ {
+ fprintf( stderr, "Usage: bbexample filename\n" );
+ return 1;
+ }
+
+ FILE *file = fopen( argv[1], "rb" );
+ if( !file )
+ {
+ fprintf( stderr, "bbexample: Can't open file `%s' for reading\n", argv[1] );
+ return 1;
+ }
+
+ const int in_buffer_size = 1 << 20;
+ uint8_t * const in_buffer = (uint8_t *)malloc( in_buffer_size );
+ if( !in_buffer )
+ {
+ fprintf( stderr, "bbexample: Not enough memory.\n" );
+ return 1;
+ }
+ const int in_size = fread( in_buffer, 1, in_buffer_size, file );
+ if( in_size >= in_buffer_size )
+ {
+ fprintf( stderr, "bbexample: Input file `%s' is too big.\n", argv[1] );
+ return 1;
+ }
+ fclose( file );
+
+ int mid_size = 0;
+ uint8_t * const mid_buffer = bbcompress( in_buffer, in_size, &mid_size );
+ if( !mid_buffer )
+ {
+ fprintf( stderr, "bbexample: Not enough memory or compress error.\n" );
+ return 1;
+ }
+
+ int out_size = 0;
+ uint8_t * const out_buffer = bbdecompress( mid_buffer, mid_size, &out_size );
+ if( !out_buffer )
+ {
+ fprintf( stderr, "bbexample: Not enough memory or decompress error.\n" );
+ return 1;
+ }
+
+ if( in_size != out_size ||
+ ( out_size > 0 && memcmp( in_buffer, out_buffer, out_size ) ) )
+ {
+ fprintf( stderr, "bbexample: Decompressed data differs from original.\n" );
+ return 1;
+ }
+
+ free( out_buffer );
+ free( mid_buffer );
+ free( in_buffer );
+ return 0;
+ }
diff --git a/configure b/configure
index 73e800b..ca758e4 100755
--- a/configure
+++ b/configure
@@ -1,16 +1,16 @@
#! /bin/sh
# configure script for Lzlib - A compression library for lzip files
-# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
#
# This configure script is free software: you have unlimited permission
# to copy, distribute and modify it.
#
-# Date of this version: 2010-05-08
+# Date of this version: 2011-01-03
args=
no_create=
pkgname=lzlib
-pkgversion=1.0
+pkgversion=1.1
soversion=1
progname=minilzip
progname_shared=
@@ -183,7 +183,7 @@ echo "LDFLAGS = ${LDFLAGS}"
rm -f Makefile
cat > Makefile << EOF
# Makefile for Lzlib - A compression library for lzip files
-# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
# This file was generated automatically by configure. Do not edit.
#
# This Makefile is free software: you have unlimited permission
diff --git a/decoder.cc b/decoder.cc
index a260571..0d8d4d5 100644
--- a/decoder.cc
+++ b/decoder.cc
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -38,7 +38,9 @@
#include "decoder.h"
-const CRC32 Lzlib_namespace::crc32;
+namespace Lzlib {
+
+const CRC32 crc32;
// Seeks a member header and updates `get'.
// Returns true if it finds a valid header.
@@ -98,7 +100,11 @@ bool LZ_decoder::verify_trailer()
{
if( !range_decoder.finished() )
trailer.data[i] = range_decoder.get_byte();
- else { error = true; for( ; i < trailer_size; ++i ) trailer.data[i] = 0; }
+ else
+ {
+ error = true;
+ for( ; i < trailer_size; ++i ) trailer.data[i] = 0;
+ }
}
if( member_version == 0 ) trailer.member_size( member_size );
if( !range_decoder.code_is_zero() ) error = true;
@@ -132,7 +138,7 @@ int LZ_decoder::decode_member()
const int pos_state = data_position() & pos_state_mask;
if( range_decoder.decode_bit( bm_match[state()][pos_state] ) == 0 )
{
- const uint8_t prev_byte = get_byte( 0 );
+ const uint8_t prev_byte = get_prev_byte();
if( state.is_char() )
put_byte( literal_decoder.decode( range_decoder, prev_byte ) );
else
@@ -146,12 +152,7 @@ int LZ_decoder::decode_member()
if( range_decoder.decode_bit( bm_rep[state()] ) == 1 )
{
len = 0;
- if( range_decoder.decode_bit( bm_rep0[state()] ) == 0 )
- {
- if( range_decoder.decode_bit( bm_len[state()][pos_state] ) == 0 )
- { len = 1; state.set_short_rep(); }
- }
- else
+ if( range_decoder.decode_bit( bm_rep0[state()] ) == 1 )
{
unsigned int distance;
if( range_decoder.decode_bit( bm_rep1[state()] ) == 0 )
@@ -166,15 +167,20 @@ int LZ_decoder::decode_member()
rep1 = rep0;
rep0 = distance;
}
+ else
+ {
+ if( range_decoder.decode_bit( bm_len[state()][pos_state] ) == 0 )
+ { state.set_short_rep(); len = 1; }
+ }
if( len == 0 )
{
- len = min_match_len + rep_match_len_decoder.decode( range_decoder, pos_state );
state.set_rep();
+ len = min_match_len + rep_match_len_decoder.decode( range_decoder, pos_state );
}
}
else
{
- unsigned int rep0_saved = rep0;
+ const unsigned int rep0_saved = rep0;
len = min_match_len + len_decoder.decode( range_decoder, pos_state );
const int dis_slot = range_decoder.decode_tree( bm_dis_slot[get_dis_state(len)], dis_slot_bits );
if( dis_slot < start_dis_model ) rep0 = dis_slot;
@@ -207,11 +213,13 @@ int LZ_decoder::decode_member()
}
return 4;
}
- if( rep0 >= (unsigned int)dictionary_size ) return 1;
}
}
rep3 = rep2; rep2 = rep1; rep1 = rep0_saved;
state.set_match();
+ if( rep0 >= (unsigned int)dictionary_size ||
+ ( rep0 >= (unsigned int)put && !partial_data_pos ) )
+ return 1;
}
copy_block( rep0, len );
}
@@ -277,3 +285,5 @@ int Circular_buffer::write_data( const uint8_t * const in_buffer, const int in_s
}
return size;
}
+
+} // end namespace Lzlib
diff --git a/decoder.h b/decoder.h
index 3842ed5..1b89bd8 100644
--- a/decoder.h
+++ b/decoder.h
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -25,6 +25,8 @@
Public License.
*/
+namespace Lzlib {
+
class Range_decoder : public Circular_buffer
{
enum { min_available_bytes = 8 };
@@ -51,7 +53,8 @@ public:
bool finished() const throw() { return at_stream_end_ && !used_bytes(); }
int free_bytes() const throw()
{ if( at_stream_end_ ) return 0; return Circular_buffer::free_bytes(); }
- long long member_position() const throw() { return member_pos; }
+ long long member_position() const throw()
+ { return member_pos; }
void purge() throw() { at_stream_end_ = true; Circular_buffer::reset(); }
void reset() throw() { at_stream_end_ = false; Circular_buffer::reset(); }
@@ -211,7 +214,8 @@ public:
uint8_t decode_matched( Range_decoder & range_decoder,
const uint8_t prev_byte, const uint8_t match_byte )
- { return range_decoder.decode_matched( bm_literal[lstate(prev_byte)], match_byte ); }
+ { return range_decoder.decode_matched( bm_literal[lstate(prev_byte)],
+ match_byte ); }
};
@@ -219,9 +223,9 @@ class LZ_decoder : public Circular_buffer
{
enum { min_free_bytes = max_match_len };
long long partial_data_pos;
- const int member_version;
const int dictionary_size;
uint32_t crc_;
+ const int member_version;
bool member_finished_;
bool verify_trailer_pending;
unsigned int rep0; // rep[0-3] latest four distances
@@ -237,7 +241,7 @@ class LZ_decoder : public Circular_buffer
Bit_model bm_rep2[State::states];
Bit_model bm_len[State::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];
Range_decoder & range_decoder;
@@ -245,6 +249,14 @@ class LZ_decoder : public Circular_buffer
Len_decoder rep_match_len_decoder;
Literal_decoder literal_decoder;
+ bool verify_trailer();
+
+ uint8_t get_prev_byte() const throw()
+ {
+ const int i = ( ( put > 0 ) ? put : buffer_size ) - 1;
+ return buffer[i];
+ }
+
uint8_t get_byte( const int distance ) const throw()
{
int i = put - distance - 1;
@@ -278,16 +290,14 @@ class LZ_decoder : public Circular_buffer
}
}
- bool verify_trailer();
-
public:
LZ_decoder( const File_header & header, Range_decoder & rdec )
:
Circular_buffer( std::max( 65536, header.dictionary_size() ) + min_free_bytes ),
partial_data_pos( 0 ),
- member_version( header.version() ),
dictionary_size( header.dictionary_size() ),
crc_( 0xFFFFFFFFU ),
+ member_version( header.version() ),
member_finished_( false ),
verify_trailer_pending( false ),
rep0( 0 ),
@@ -301,12 +311,13 @@ public:
{ return free_bytes() >= min_free_bytes; }
uint32_t crc() const throw() { return crc_ ^ 0xFFFFFFFFU; }
- int decode_member();
bool member_finished() const throw()
{ return ( member_finished_ && !used_bytes() ); }
- long long member_position() const throw()
- { return range_decoder.member_position(); }
long long data_position() const throw()
{ return partial_data_pos + put; }
+
+ int decode_member();
};
+
+} // end namespace Lzlib
diff --git a/doc/lzlib.info b/doc/lzlib.info
index af9f67b..4fddce8 100644
--- a/doc/lzlib.info
+++ b/doc/lzlib.info
@@ -12,25 +12,25 @@ File: lzlib.info, Node: Top, Next: Introduction, Up: (dir)
Lzlib Manual
************
-This manual is for Lzlib (version 1.0, 8 May 2010).
+This manual is for Lzlib (version 1.1, 3 January 2011).
* Menu:
-* Introduction:: Purpose and features of Lzlib
-* Library Version:: Checking library version
-* Buffering:: Sizes of Lzlib's buffers
-* Parameter Limits:: Min / max values for some parameters
-* Compression Functions:: Descriptions of the compression functions
-* Decompression Functions:: Descriptions of the decompression functions
-* Error Codes:: Meaning of codes returned by functions
-* Error Messages:: Error messages corresponding to error codes
-* Data Format:: Detailed format of the compressed data
-* Examples:: A small tutorial with examples
-* Problems:: Reporting bugs
-* Concept Index:: Index of concepts
+* Introduction:: Purpose and features of Lzlib
+* Library Version:: Checking library version
+* Buffering:: Sizes of Lzlib's buffers
+* Parameter Limits:: Min / max values for some parameters
+* Compression Functions:: Descriptions of the compression functions
+* Decompression Functions:: Descriptions of the decompression functions
+* Error Codes:: Meaning of codes returned by functions
+* Error Messages:: Error messages corresponding to error codes
+* Data Format:: Detailed format of the compressed data
+* Examples:: A small tutorial with examples
+* Problems:: Reporting bugs
+* Concept Index:: Index of concepts
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This manual is free documentation: you have unlimited permission to
copy, distribute and modify it.
@@ -43,14 +43,15 @@ File: lzlib.info, Node: Introduction, Next: Library Version, Prev: Top, Up:
Lzlib is a data compression library providing in-memory LZMA compression
and decompression functions, including integrity checking of the
-uncompressed data. The compressed data format used by the library is the
+decompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
-library are declared in the file `lzlib.h'. An usage example of the
-library is given in the file main.cc.
+library are declared in the file `lzlib.h'. Usage examples of the
+library are given in the files `main.cc' and `bbexample.cc' from the
+source distribution.
- Compression/decompression is done by repeteadly calling a couple of
+ Compression/decompression is done by repeatedly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
@@ -63,7 +64,7 @@ function with a SIZE equal to 0.
Lzlib will correctly decompress a data stream which is the
concatenation of two or more compressed data streams. The result is the
-concatenation of the corresponding uncompressed data streams. Integrity
+concatenation of the corresponding decompressed data streams. Integrity
testing of concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not
@@ -550,9 +551,11 @@ File: lzlib.info, Node: Examples, Next: Problems, Prev: Data Format, Up: Top
10 A small tutorial with examples
*********************************
-This chaper shows the order in which the library functions should be
+This chapter shows the order in which the library functions should be
called depending on what kind of data stream you want to compress or
-decompress.
+decompress. See the file `bbexample.cc' in the source distribution for
+an example of how buffer-to-buffer compression/decompression can be
+implemented using lzlib.
Example 1: Normal compression (MEMBER_SIZE > total output).
@@ -700,17 +703,17 @@ Concept Index

Tag Table:
Node: Top219
-Node: Introduction1152
-Node: Library Version2927
-Node: Buffering3572
-Node: Parameter Limits4692
-Node: Compression Functions5649
-Node: Decompression Functions11695
-Node: Error Codes17766
-Node: Error Messages19705
-Node: Data Format20284
-Node: Examples22254
-Node: Problems25967
-Node: Concept Index26539
+Node: Introduction1310
+Node: Library Version3135
+Node: Buffering3780
+Node: Parameter Limits4900
+Node: Compression Functions5857
+Node: Decompression Functions11903
+Node: Error Codes17974
+Node: Error Messages19913
+Node: Data Format20492
+Node: Examples22462
+Node: Problems26328
+Node: Concept Index26900

End Tag Table
diff --git a/doc/lzlib.texinfo b/doc/lzlib.texinfo
index ef46af9..d03d817 100644
--- a/doc/lzlib.texinfo
+++ b/doc/lzlib.texinfo
@@ -5,8 +5,8 @@
@finalout
@c %**end of header
-@set UPDATED 8 May 2010
-@set VERSION 1.0
+@set UPDATED 3 January 2011
+@set VERSION 1.1
@dircategory Data Compression
@direntry
@@ -14,6 +14,7 @@
@end direntry
+@ifnothtml
@titlepage
@title Lzlib
@subtitle A compression library for lzip files
@@ -25,6 +26,7 @@
@end titlepage
@contents
+@end ifnothtml
@node Top
@top
@@ -32,22 +34,22 @@
This manual is for Lzlib (version @value{VERSION}, @value{UPDATED}).
@menu
-* Introduction:: Purpose and features of Lzlib
-* Library Version:: Checking library version
-* Buffering:: Sizes of Lzlib's buffers
-* Parameter Limits:: Min / max values for some parameters
-* Compression Functions:: Descriptions of the compression functions
-* Decompression Functions:: Descriptions of the decompression functions
-* Error Codes:: Meaning of codes returned by functions
-* Error Messages:: Error messages corresponding to error codes
-* Data Format:: Detailed format of the compressed data
-* Examples:: A small tutorial with examples
-* Problems:: Reporting bugs
-* Concept Index:: Index of concepts
+* Introduction:: Purpose and features of Lzlib
+* Library Version:: Checking library version
+* Buffering:: Sizes of Lzlib's buffers
+* Parameter Limits:: Min / max values for some parameters
+* Compression Functions:: Descriptions of the compression functions
+* Decompression Functions:: Descriptions of the decompression functions
+* Error Codes:: Meaning of codes returned by functions
+* Error Messages:: Error messages corresponding to error codes
+* Data Format:: Detailed format of the compressed data
+* Examples:: A small tutorial with examples
+* Problems:: Reporting bugs
+* Concept Index:: Index of concepts
@end menu
@sp 1
-Copyright @copyright{} 2009, 2010 Antonio Diaz Diaz.
+Copyright @copyright{} 2009, 2010, 2011 Antonio Diaz Diaz.
This manual is free documentation: you have unlimited permission
to copy, distribute and modify it.
@@ -59,14 +61,15 @@ to copy, distribute and modify it.
Lzlib is a data compression library providing in-memory LZMA compression
and decompression functions, including integrity checking of the
-uncompressed data. The compressed data format used by the library is the
+decompressed data. The compressed data format used by the library is the
lzip format.
The functions and variables forming the interface of the compression
-library are declared in the file @samp{lzlib.h}. An usage example of the
-library is given in the file main.cc.
+library are declared in the file @samp{lzlib.h}. Usage examples of the
+library are given in the files @samp{main.cc} and @samp{bbexample.cc}
+from the source distribution.
-Compression/decompression is done by repeteadly calling a couple of
+Compression/decompression is done by repeatedly calling a couple of
read/write functions until all the data has been processed by the
library. This interface is safer and less error prone than the
traditional zlib interface.
@@ -79,7 +82,7 @@ the data to be compressed in advance, just call the read function with a
Lzlib will correctly decompress a data stream which is the concatenation
of two or more compressed data streams. The result is the concatenation
-of the corresponding uncompressed data streams. Integrity testing of
+of the corresponding decompressed data streams. Integrity testing of
concatenated compressed data streams is also supported.
All the library functions are thread safe. The library does not install
@@ -617,9 +620,11 @@ safe recovery of undamaged members from multimember files.
@chapter A small tutorial with examples
@cindex examples
-This chaper shows the order in which the library functions should be
+This chapter shows the order in which the library functions should be
called depending on what kind of data stream you want to compress or
-decompress.
+decompress. See the file @samp{bbexample.cc} in the source distribution
+for an example of how buffer-to-buffer compression/decompression can be
+implemented using lzlib.
@sp 1
@noindent
diff --git a/encoder.cc b/encoder.cc
index 032b07c..a0001c1 100644
--- a/encoder.cc
+++ b/encoder.cc
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -38,8 +38,10 @@
#include "encoder.h"
-const Dis_slots Lzlib_namespace::dis_slots;
-const Prob_prices Lzlib_namespace::prob_prices;
+namespace Lzlib {
+
+const Dis_slots dis_slots;
+const Prob_prices prob_prices;
int Matchfinder::write_data( const uint8_t * const in_buffer, const int in_size ) throw()
@@ -62,16 +64,17 @@ Matchfinder::Matchfinder( const int dict_size, const int len_limit )
buffer_size( ( 2 * std::max( 65536, dictionary_size_ ) ) +
before_size + after_size ),
buffer( new( std::nothrow ) uint8_t[buffer_size] ),
+ prev_positions( new( std::nothrow ) int32_t[num_prev_positions] ),
+ prev_pos_tree( new( std::nothrow ) int32_t[2*dictionary_size_] ),
pos( 0 ),
cyclic_pos( 0 ),
stream_pos( 0 ),
pos_limit( buffer_size - after_size ),
match_len_limit_( len_limit ),
- prev_positions( new( std::nothrow ) int32_t[num_prev_positions] ),
+ cycles( ( len_limit < max_match_len ) ? 16 + ( len_limit / 2 ) : 256 ),
at_stream_end_( false ),
been_flushed( false )
{
- prev_pos_tree = new( std::nothrow ) int32_t[2*dictionary_size_];
if( !buffer || !prev_positions || !prev_pos_tree )
{
if( prev_pos_tree ) delete[] prev_pos_tree;
@@ -102,7 +105,8 @@ bool Matchfinder::move_pos() throw()
if( ++cyclic_pos >= dictionary_size_ ) cyclic_pos = 0;
if( ++pos >= pos_limit )
{
- if( pos > stream_pos ) { pos = stream_pos; return false; }
+ if( pos > stream_pos )
+ { pos = stream_pos; return false; }
else
{
const int offset = pos - dictionary_size_ - before_size;
@@ -123,15 +127,14 @@ bool Matchfinder::move_pos() throw()
int Matchfinder::longest_match_len( int * const distances ) throw()
{
- int idx0 = cyclic_pos << 1;
- int idx1 = idx0 + 1;
+ int32_t * ptr0 = prev_pos_tree + ( cyclic_pos << 1 );
+ int32_t * ptr1 = ptr0 + 1;
int len_limit = match_len_limit_;
if( len_limit > available_bytes() )
{
been_flushed = true;
len_limit = available_bytes();
- if( len_limit < 4 )
- { prev_pos_tree[idx0] = prev_pos_tree[idx1] = -1; return 0; }
+ if( len_limit < 4 ) { *ptr0 = *ptr1 = -1; return 0; }
}
int maxlen = min_match_len - 1;
@@ -166,10 +169,9 @@ int Matchfinder::longest_match_len( int * const distances ) throw()
int len = 0, len0 = 0, len1 = 0;
- for( int count = 16 + ( match_len_limit_ / 2 ); ; )
+ for( int count = cycles; ; )
{
- if( newpos < min_pos || --count < 0 )
- { prev_pos_tree[idx0] = prev_pos_tree[idx1] = -1; break; }
+ if( newpos < min_pos || --count < 0 ) { *ptr0 = *ptr1 = -1; break; }
const uint8_t * const newdata = buffer + newpos;
if( been_flushed ) len = 0;
while( len < len_limit && newdata[len] == data[len] ) ++len;
@@ -177,30 +179,31 @@ int Matchfinder::longest_match_len( int * const distances ) throw()
const int delta = pos - newpos;
if( distances ) while( maxlen < len ) distances[++maxlen] = delta - 1;
- const int newidx = ( cyclic_pos - delta +
- ( ( cyclic_pos >= delta ) ? 0 : dictionary_size_ ) ) << 1;
+ int32_t * const newptr = prev_pos_tree +
+ ( ( cyclic_pos - delta +
+ ( ( cyclic_pos >= delta ) ? 0 : dictionary_size_ ) ) << 1 );
if( len < len_limit )
{
if( newdata[len] < data[len] )
{
- prev_pos_tree[idx0] = newpos;
- idx0 = newidx + 1;
- newpos = prev_pos_tree[idx0];
+ *ptr0 = newpos;
+ ptr0 = newptr + 1;
+ newpos = *ptr0;
len0 = len; if( len1 < len ) len = len1;
}
else
{
- prev_pos_tree[idx1] = newpos;
- idx1 = newidx;
- newpos = prev_pos_tree[idx1];
+ *ptr1 = newpos;
+ ptr1 = newptr;
+ newpos = *ptr1;
len1 = len; if( len0 < len ) len = len0;
}
}
else
{
- prev_pos_tree[idx0] = prev_pos_tree[newidx];
- prev_pos_tree[idx1] = prev_pos_tree[newidx+1];
+ *ptr0 = newptr[0];
+ *ptr1 = newptr[1];
break;
}
}
@@ -250,6 +253,17 @@ void LZ_encoder::fill_align_prices() throw()
void LZ_encoder::fill_distance_prices() throw()
{
+ for( int dis = start_dis_model; dis < modeled_distances; ++dis )
+ {
+ const int dis_slot = dis_slots.table( dis );
+ const int direct_bits = ( dis_slot >> 1 ) - 1;
+ const int base = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
+ const int price =
+ price_symbol_reversed( bm_dis + base - dis_slot, dis - base, direct_bits );
+ for( int dis_state = 0; dis_state < max_dis_states; ++dis_state )
+ dis_prices[dis_state][dis] = price;
+ }
+
for( int dis_state = 0; dis_state < max_dis_states; ++dis_state )
{
int * const dsp = dis_slot_prices[dis_state];
@@ -266,13 +280,7 @@ void LZ_encoder::fill_distance_prices() throw()
for( ; dis < start_dis_model; ++dis )
dp[dis] = dsp[dis];
for( ; dis < modeled_distances; ++dis )
- {
- const int dis_slot = dis_slots[dis];
- const int direct_bits = ( dis_slot >> 1 ) - 1;
- const int base = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
- dp[dis] = dsp[dis_slot] +
- price_symbol_reversed( bm_dis + base - dis_slot, dis - base, direct_bits );
- }
+ dp[dis] += dsp[dis_slots.table( dis )];
}
}
@@ -415,7 +423,8 @@ int LZ_encoder::sequence_optimizer( const int reps[num_rep_distances],
const uint8_t cur_byte = matchfinder[0];
const uint8_t match_byte = matchfinder[-cur_trial.reps[0]-1];
- int next_price = cur_trial.price + price0( bm_match[cur_trial.state()][pos_state] );
+ int next_price = cur_trial.price +
+ price0( bm_match[cur_trial.state()][pos_state] );
if( cur_trial.state.is_char() )
next_price += literal_encoder.price_symbol( prev_byte, cur_byte );
else
@@ -519,7 +528,7 @@ LZ_encoder::LZ_encoder( Matchfinder & mf, const File_header & header,
matchfinder( mf ),
len_encoder( matchfinder.match_len_limit() ),
rep_match_len_encoder( matchfinder.match_len_limit() ),
- num_dis_slots( 2 * File_header::real_bits( matchfinder.dictionary_size() - 1 ) ),
+ num_dis_slots( 2 * real_bits( matchfinder.dictionary_size() - 1 ) ),
fill_counter( 0 ),
member_finished_( false )
{
@@ -533,6 +542,7 @@ LZ_encoder::LZ_encoder( Matchfinder & mf, const File_header & header,
bool LZ_encoder::encode_member( const bool finish )
{
+ const int fill_count = ( matchfinder.match_len_limit() > 12 ) ? 512 : 2048;
State & state = main_state;
if( member_finished_ ) return true;
if( range_encoder.member_position() >= member_size_limit )
@@ -543,9 +553,9 @@ bool LZ_encoder::encode_member( const bool finish )
{
if( matchfinder.available_bytes() < 4 && !matchfinder.at_stream_end() )
return true;
- range_encoder.encode_bit( bm_match[state()][0], 0 );
const uint8_t prev_byte = 0;
const uint8_t cur_byte = matchfinder[0];
+ range_encoder.encode_bit( bm_match[state()][0], 0 );
literal_encoder.encode( range_encoder, prev_byte, cur_byte );
crc32.update( crc_, cur_byte );
if( !move_pos( 1 ) ) return false;
@@ -560,7 +570,8 @@ bool LZ_encoder::encode_member( const bool finish )
}
if( !matchfinder.enough_available_bytes() ||
!range_encoder.enough_free_bytes() ) return true;
- if( fill_counter <= 0 ) { fill_distance_prices(); fill_counter = 512; }
+ if( fill_counter <= 0 )
+ { fill_distance_prices(); fill_counter = fill_count; }
int ahead = sequence_optimizer( rep_distances, state );
if( ahead <= 0 ) return false;
@@ -568,7 +579,8 @@ bool LZ_encoder::encode_member( const bool finish )
for( int i = 0; ; )
{
- const int pos_state = ( matchfinder.data_position() - ahead ) & pos_state_mask;
+ const int pos_state =
+ ( matchfinder.data_position() - ahead ) & pos_state_mask;
const int dis = trials[i].dis;
const int len = trials[i].price;
@@ -584,7 +596,8 @@ bool LZ_encoder::encode_member( const bool finish )
else
{
const uint8_t match_byte = matchfinder[-ahead-rep_distances[0]-1];
- literal_encoder.encode_matched( range_encoder, prev_byte, match_byte, cur_byte );
+ literal_encoder.encode_matched( range_encoder,
+ prev_byte, cur_byte, match_byte );
}
state.set_char();
}
@@ -630,3 +643,5 @@ bool LZ_encoder::encode_member( const bool finish )
}
}
}
+
+} // end namespace Lzlib
diff --git a/encoder.h b/encoder.h
index 5f65743..eecdae4 100644
--- a/encoder.h
+++ b/encoder.h
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -25,8 +25,10 @@
Public License.
*/
-const int max_num_trials = 1 << 12;
-const int price_shift = 6;
+namespace Lzlib {
+
+enum { max_num_trials = 1 << 12,
+ price_shift = 6 };
class Dis_slots
{
@@ -45,6 +47,8 @@ public:
}
}
+ unsigned char table( const int dis ) const throw() { return data[dis]; }
+
int operator[]( const uint32_t dis ) const throw()
{
if( dis < (1 << 12) ) return data[dis];
@@ -53,8 +57,7 @@ public:
}
};
-namespace Lzlib_namespace { extern const Dis_slots dis_slots; }
-using Lzlib_namespace::dis_slots;
+extern const Dis_slots dis_slots;
class Prob_prices
@@ -65,13 +68,13 @@ public:
Prob_prices()
{
const int num_bits = ( bit_model_total_bits - 2 );
- for( int i = num_bits - 1; i >= 0; --i )
+ int j = 1, end = 2;
+ data[0] = bit_model_total_bits << price_shift;
+ for( int 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 )
- data[j] = (i << price_shift) +
- ( ((end - j) << price_shift) >> (num_bits - i - 1) );
+ for( ; j < end; ++j )
+ data[j] = ( i << price_shift ) +
+ ( ( (end - j) << price_shift ) >> ( num_bits - i - 1 ) );
}
}
@@ -79,8 +82,7 @@ public:
{ return data[probability >> 2]; }
};
-namespace Lzlib_namespace { extern const Prob_prices prob_prices; }
-using Lzlib_namespace::prob_prices;
+extern const Prob_prices prob_prices;
inline int price0( const Bit_model & bm ) throw()
@@ -95,8 +97,8 @@ inline int price_bit( const Bit_model & bm, const int bit ) throw()
inline int price_symbol( const Bit_model bm[], int symbol, const int num_bits ) throw()
{
- symbol |= ( 1 << num_bits );
int price = 0;
+ symbol |= ( 1 << num_bits );
while( symbol > 1 )
{
const int bit = symbol & 1;
@@ -165,14 +167,15 @@ class Matchfinder
long long partial_data_pos;
const int dictionary_size_; // bytes to keep in buffer before pos
const int buffer_size;
- uint8_t * const buffer;
- int pos;
- int cyclic_pos;
+ uint8_t * const buffer; // input buffer
+ int32_t * const prev_positions; // last seen position of key
+ int32_t * const prev_pos_tree;
+ int pos; // current pos in buffer
+ int cyclic_pos; // current pos in dictionary
int stream_pos; // first byte not yet read from file
const int pos_limit; // when reached, a new block must be read
const int match_len_limit_;
- int32_t * const prev_positions; // last seen position of key
- int32_t * prev_pos_tree;
+ const int cycles;
bool at_stream_end_; // stream_pos shows real end of file
bool been_flushed;
@@ -187,8 +190,8 @@ public:
int available_bytes() const throw() { return stream_pos - pos; }
long long data_position() const throw() { return partial_data_pos + pos; }
int dictionary_size() const throw() { return dictionary_size_; }
- void flushing( const bool b ) throw() { at_stream_end_ = b; }
bool finished() const throw() { return at_stream_end_ && pos >= stream_pos; }
+ void flushing( const bool b ) throw() { at_stream_end_ = b; }
int free_bytes() const throw()
{ if( at_stream_end_ ) return 0; return buffer_size - stream_pos; }
int match_len_limit() const throw() { return match_len_limit_; }
@@ -258,6 +261,9 @@ public:
ff_count( 0 ),
cache( 0 ) {}
+ long long member_position() const throw()
+ { return partial_member_pos + used_bytes() + ff_count; }
+
bool enough_free_bytes() const throw()
{ return free_bytes() >= min_free_bytes; }
@@ -277,9 +283,6 @@ public:
cache = 0;
}
- long long member_position() const throw()
- { return partial_member_pos + used_bytes() + ff_count; }
-
void encode( const int symbol, const int num_bits )
{
for( int i = num_bits - 1; i >= 0; --i )
@@ -408,24 +411,28 @@ class Literal_encoder
{ return ( prev_byte >> ( 8 - literal_context_bits ) ); }
public:
- void encode( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t symbol )
+ void encode( Range_encoder & range_encoder,
+ uint8_t prev_byte, uint8_t symbol )
{ range_encoder.encode_tree( bm_literal[lstate(prev_byte)], symbol, 8 ); }
- void encode_matched( Range_encoder & range_encoder, uint8_t prev_byte, uint8_t match_byte, uint8_t symbol )
- { range_encoder.encode_matched( bm_literal[lstate(prev_byte)], symbol, match_byte ); }
-
- int price_matched( uint8_t prev_byte, uint8_t symbol, uint8_t match_byte ) const throw()
- { return ::price_matched( bm_literal[lstate(prev_byte)], symbol, match_byte ); }
+ void encode_matched( Range_encoder & range_encoder,
+ uint8_t prev_byte, uint8_t symbol, uint8_t match_byte )
+ { range_encoder.encode_matched( bm_literal[lstate(prev_byte)],
+ symbol, match_byte ); }
int price_symbol( uint8_t prev_byte, uint8_t symbol ) const throw()
- { return ::price_symbol( bm_literal[lstate(prev_byte)], symbol, 8 ); }
+ { return Lzlib::price_symbol( bm_literal[lstate(prev_byte)], symbol, 8 ); }
+
+ int price_matched( uint8_t prev_byte, uint8_t symbol,
+ uint8_t match_byte ) const throw()
+ { return Lzlib::price_matched( bm_literal[lstate(prev_byte)],
+ symbol, match_byte ); }
};
class LZ_encoder
{
- enum { dis_align_mask = dis_align_size - 1,
- infinite_price = 0x0FFFFFFF,
+ enum { infinite_price = 0x0FFFFFFF,
max_marker_size = 16,
num_rep_distances = 4 }; // must be 4
@@ -451,7 +458,7 @@ class LZ_encoder
Bit_model bm_rep2[State::states];
Bit_model bm_len[State::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];
Matchfinder & matchfinder;
@@ -525,7 +532,7 @@ class LZ_encoder
price += dis_prices[dis_state][dis];
else
price += dis_slot_prices[dis_state][dis_slots[dis]] +
- align_prices[dis & dis_align_mask];
+ align_prices[dis & (dis_align_size - 1)];
return price;
}
@@ -604,3 +611,5 @@ public:
long long member_position() const throw()
{ return range_encoder.member_position(); }
};
+
+} // end namespace Lzlib
diff --git a/lzcheck.cc b/lzcheck.cc
index b54f525..ce53a41 100644
--- a/lzcheck.cc
+++ b/lzcheck.cc
@@ -1,5 +1,5 @@
/* Lzcheck - A test program for the lzlib library
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This program is free software: you have unlimited permission
to copy, distribute and modify it.
@@ -39,7 +39,7 @@ uint8_t mid_buffer[buffer_size];
uint8_t out_buffer[buffer_size];
-int main( const int argc, const char * argv[] )
+int main( const int argc, const char * const argv[] )
{
if( argc < 2 )
{
@@ -50,13 +50,14 @@ int main( const int argc, const char * argv[] )
FILE *file = std::fopen( argv[1], "rb" );
if( !file )
{
- std::fprintf( stderr, "Can't open file `%s' for reading\n", argv[1] );
+ std::fprintf( stderr,
+ "lzcheck: Can't open file `%s' for reading\n", argv[1] );
return 1;
}
-// std::fprintf( stderr, "lzcheck: testing file `%s'\n", argv[1] );
+// std::fprintf( stderr, "lzcheck: Testing file `%s'\n", argv[1] );
const int dictionary_size = 1 << 20;
- const int match_len_limit = 80;
+ const int match_len_limit = 36;
const long long member_size = LLONG_MAX;
LZ_Encoder * encoder = LZ_compress_open( dictionary_size, match_len_limit,
member_size );
@@ -66,10 +67,11 @@ int main( const int argc, const char * argv[] )
LZ_compress_close( encoder );
if( mem_error )
{
- std::fprintf( stderr, "not enough memory.\n" );
+ std::fprintf( stderr, "lzcheck: Not enough memory.\n" );
return 1;
}
- std::fprintf( stderr, "internal error: invalid argument to encoder.\n" );
+ std::fprintf( stderr,
+ "lzcheck: internal error: Invalid argument to encoder.\n" );
return 3;
}
@@ -77,7 +79,7 @@ int main( const int argc, const char * argv[] )
if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok )
{
LZ_decompress_close( decoder );
- std::fprintf( stderr, "not enough memory.\n" );
+ std::fprintf( stderr, "lzcheck: Not enough memory.\n" );
return 1;
}
@@ -96,7 +98,7 @@ int main( const int argc, const char * argv[] )
const int mid_size = LZ_compress_read( encoder, mid_buffer, buffer_size );
if( mid_size < 0 )
{
- std::fprintf( stderr, "LZ_compress_read error: %s.\n",
+ std::fprintf( stderr, "lzcheck: LZ_compress_read error: %s.\n",
LZ_strerror( LZ_compress_errno( encoder ) ) );
retval = 3; break;
}
@@ -104,14 +106,14 @@ int main( const int argc, const char * argv[] )
const int out_size = LZ_decompress_read( decoder, out_buffer, buffer_size );
if( out_size < 0 )
{
- std::fprintf( stderr, "LZ_decompress_read error: %s.\n",
+ std::fprintf( stderr, "lzcheck: LZ_decompress_read error: %s.\n",
LZ_strerror( LZ_decompress_errno( decoder ) ) );
retval = 3; break;
}
if( out_size != in_size || std::memcmp( in_buffer + l, out_buffer, out_size ) )
{
- std::fprintf( stderr, "sync error at pos %d. in_size = %d, out_size = %d\n",
+ std::fprintf( stderr, "lzcheck: Sync error at pos %d. in_size = %d, out_size = %d\n",
l, in_size, out_size );
for( int i = 0; i < in_size; ++i )
std::fputc( in_buffer[l+i], stderr );
@@ -133,7 +135,7 @@ int main( const int argc, const char * argv[] )
LZ_decompress_read( decoder, out_buffer, buffer_size ) != 0 ||
LZ_compress_restart_member( encoder, member_size ) < 0 )
{
- std::fprintf( stderr, "can't finish member: %s.\n",
+ std::fprintf( stderr, "lzcheck: Can't finish member: %s.\n",
LZ_strerror( LZ_decompress_errno( decoder ) ) );
retval = 3;
}
@@ -158,7 +160,7 @@ int main( const int argc, const char * argv[] )
buffer_size - leading_garbage );
if( mid_size < 0 )
{
- std::fprintf( stderr, "LZ_compress_read error: %s.\n",
+ std::fprintf( stderr, "lzcheck: LZ_compress_read error: %s.\n",
LZ_strerror( LZ_compress_errno( encoder ) ) );
retval = 3; break;
}
@@ -174,7 +176,7 @@ int main( const int argc, const char * argv[] )
}
if( out_size < 0 )
{
- std::fprintf( stderr, "LZ_decompress_read error: %s.\n",
+ std::fprintf( stderr, "lzcheck: LZ_decompress_read error: %s.\n",
LZ_strerror( LZ_decompress_errno( decoder ) ) );
retval = 3; break;
}
@@ -182,7 +184,7 @@ int main( const int argc, const char * argv[] )
if( out_size != in_size || std::memcmp( in_buffer + l, out_buffer, out_size ) )
{
- std::fprintf( stderr, "sync error at pos %d. in_size = %d, out_size = %d\n",
+ std::fprintf( stderr, "lzcheck: Sync error at pos %d. in_size = %d, out_size = %d\n",
l, in_size, out_size );
for( int i = 0; i < in_size; ++i )
std::fputc( in_buffer[l+i], stderr );
@@ -202,7 +204,7 @@ int main( const int argc, const char * argv[] )
LZ_decompress_reset( decoder ) < 0 ||
LZ_compress_restart_member( encoder, member_size ) < 0 )
{
- std::fprintf( stderr, "can't restart member: %s.\n",
+ std::fprintf( stderr, "lzcheck: Can't restart member: %s.\n",
LZ_strerror( LZ_decompress_errno( decoder ) ) );
retval = 3; break;
}
@@ -215,7 +217,7 @@ int main( const int argc, const char * argv[] )
LZ_decompress_sync_to_member( decoder ) < 0 ||
LZ_compress_restart_member( encoder, member_size ) < 0 )
{
- std::fprintf( stderr, "can't seek to next member: %s.\n",
+ std::fprintf( stderr, "lzcheck: Can't seek to next member: %s.\n",
LZ_strerror( LZ_decompress_errno( decoder ) ) );
retval = 3; break;
}
diff --git a/lzip.h b/lzip.h
index 2138056..0d77aa7 100644
--- a/lzip.h
+++ b/lzip.h
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -25,6 +25,8 @@
Public License.
*/
+namespace Lzlib {
+
class State
{
unsigned char st;
@@ -37,56 +39,64 @@ public:
void set_char() throw()
{
- static const unsigned char next[states] = {0, 0, 0, 0, 1, 2, 3, 4, 5, 6, 4, 5};
+ 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};
+ 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};
+ 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};
+ static const unsigned char next[states] =
+ {9, 9, 9, 9, 9, 9, 9, 11, 11, 11, 11, 11};
st = next[st];
}
};
-const int min_dictionary_bits = 12;
-const int min_dictionary_size = 1 << min_dictionary_bits;
-const int max_dictionary_bits = 29;
-const int max_dictionary_size = 1 << max_dictionary_bits;
-const int literal_context_bits = 3;
-const int pos_state_bits = 2;
-const int pos_states = 1 << pos_state_bits;
-const int pos_state_mask = pos_states - 1;
-
-const int dis_slot_bits = 6;
-const int start_dis_model = 4;
-const int end_dis_model = 14;
-const int modeled_distances = 1 << (end_dis_model / 2);
-const int dis_align_bits = 4;
-const int dis_align_size = 1 << dis_align_bits;
-
-const int len_low_bits = 3;
-const int len_mid_bits = 3;
-const int len_high_bits = 8;
-const int len_low_symbols = 1 << len_low_bits;
-const int len_mid_symbols = 1 << len_mid_bits;
-const int len_high_symbols = 1 << len_high_bits;
-const int max_len_symbols = len_low_symbols + len_mid_symbols + len_high_symbols;
-
-const int min_match_len = 2; // must be 2
-const int max_match_len = min_match_len + max_len_symbols - 1; // 273
-const int min_match_len_limit = 5;
-
-const int max_dis_states = 4;
+enum {
+ min_dictionary_bits = 12,
+ min_dictionary_size = 1 << min_dictionary_bits,
+ max_dictionary_bits = 29,
+ max_dictionary_size = 1 << max_dictionary_bits,
+ 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()
{
@@ -96,9 +106,9 @@ inline int get_dis_state( int len ) throw()
}
-const int bit_model_move_bits = 5;
-const int bit_model_total_bits = 11;
-const int bit_model_total = 1 << bit_model_total_bits;
+enum { bit_model_move_bits = 5,
+ bit_model_total_bits = 11,
+ bit_model_total = 1 << bit_model_total_bits };
struct Bit_model
{
@@ -133,10 +143,17 @@ public:
}
};
-namespace Lzlib_namespace { extern const CRC32 crc32; }
-using Lzlib_namespace::crc32;
+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
@@ -162,14 +179,6 @@ struct File_header
dictionary_size() <= max_dictionary_size );
}
- static 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;
- }
-
int dictionary_size() const throw()
{
int sz = ( 1 << ( data[5] & 0x1F ) );
@@ -284,3 +293,5 @@ public:
int read_data( uint8_t * const out_buffer, const int out_size ) throw();
int write_data( const uint8_t * const in_buffer, const int in_size ) throw();
};
+
+} // end namespace Lzlib
diff --git a/lzlib.cc b/lzlib.cc
index 740e067..4a4b77b 100644
--- a/lzlib.cc
+++ b/lzlib.cc
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -35,6 +35,8 @@
#include "encoder.h"
+using namespace Lzlib;
+
struct LZ_Encoder
{
long long partial_in_size;
@@ -60,15 +62,6 @@ struct LZ_Encoder
};
-bool verify_encoder( LZ_Encoder * const encoder )
- {
- if( !encoder ) return false;
- if( !encoder->matchfinder || !encoder->lz_encoder )
- { encoder->lz_errno = LZ_bad_argument; return false; }
- return true;
- }
-
-
struct LZ_Decoder
{
long long partial_in_size;
@@ -95,6 +88,17 @@ struct LZ_Decoder
};
+namespace Lzlib {
+
+bool verify_encoder( LZ_Encoder * const encoder )
+ {
+ if( !encoder ) return false;
+ if( !encoder->matchfinder || !encoder->lz_encoder )
+ { encoder->lz_errno = LZ_bad_argument; return false; }
+ return true;
+ }
+
+
bool verify_decoder( struct LZ_Decoder * const decoder )
{
if( !decoder ) return false;
@@ -103,6 +107,8 @@ bool verify_decoder( struct LZ_Decoder * const decoder )
return true;
}
+} // end namespace Lzlib
+
const char * LZ_version() { return LZ_version_string; }
@@ -387,7 +393,7 @@ int LZ_decompress_read( struct LZ_Decoder * const decoder,
if( d.seeking ) return 0;
if( d.lz_decoder && d.lz_decoder->member_finished() )
{
- d.partial_in_size += d.lz_decoder->member_position();
+ d.partial_in_size += d.rdec->member_position();
d.partial_out_size += d.lz_decoder->data_position();
delete d.lz_decoder;
d.lz_decoder = 0;
@@ -511,7 +517,7 @@ long long LZ_decompress_member_position( struct LZ_Decoder * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
if( decoder->lz_decoder )
- return decoder->lz_decoder->member_position();
+ return decoder->rdec->member_position();
else return 0;
}
@@ -520,7 +526,7 @@ long long LZ_decompress_total_in_size( struct LZ_Decoder * const decoder )
{
if( !verify_decoder( decoder ) ) return -1;
if( decoder->lz_decoder )
- return decoder->partial_in_size + decoder->lz_decoder->member_position();
+ return decoder->partial_in_size + decoder->rdec->member_position();
return decoder->partial_in_size;
}
diff --git a/lzlib.h b/lzlib.h
index 8eb6d75..8833d4d 100644
--- a/lzlib.h
+++ b/lzlib.h
@@ -1,5 +1,5 @@
/* Lzlib - A compression library for lzip files
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
This library is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
@@ -29,7 +29,7 @@
extern "C" {
#endif
-const char * const LZ_version_string = "1.0";
+const char * const LZ_version_string = "1.1";
enum LZ_Errno { LZ_ok = 0, LZ_bad_argument, LZ_mem_error,
LZ_sequence_error, LZ_header_error, LZ_unexpected_eof,
diff --git a/main.cc b/main.cc
index ce21764..afcabfe 100644
--- a/main.cc
+++ b/main.cc
@@ -1,5 +1,5 @@
/* Minilzip - A test program for the lzlib library
- Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+ 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
@@ -63,10 +63,10 @@ int writeblock( const int fd, const uint8_t * const buf, const int size ) throw(
namespace {
+const char * const Program_name = "Minilzip";
+const char * const program_name = "minilzip";
+const char * const program_year = "2011";
const char * invocation_name = 0;
-const char * const Program_name = "Minilzip";
-const char * const program_name = "minilzip";
-const char * const program_year = "2010";
#ifdef O_BINARY
const int o_binary = O_BINARY;
@@ -85,27 +85,26 @@ struct Lzma_options
int match_len_limit; // 5..273
};
-enum Mode { m_compress = 0, m_decompress, m_test };
+enum Mode { m_compress, m_decompress, m_test };
std::string output_filename;
int outfd = -1;
-mode_t outfd_mode = S_IRUSR | S_IWUSR;
int verbosity = 0;
+mode_t outfd_mode = S_IRUSR | S_IWUSR;
bool delete_output_on_interrupt = false;
class Pretty_print
{
const char * const stdin_name;
- const unsigned int stdin_name_len;
unsigned int longest_name;
std::string name_;
mutable bool first_post;
public:
Pretty_print( const std::vector< std::string > & filenames )
- : stdin_name( "(stdin)" ), stdin_name_len( std::strlen( stdin_name ) ),
- longest_name( 0 ), first_post( false )
+ : stdin_name( "(stdin)" ), longest_name( 0 ), 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];
@@ -140,7 +139,7 @@ void show_help() throw()
std::printf( " -d, --decompress decompress\n" );
std::printf( " -f, --force overwrite existing output files\n" );
std::printf( " -k, --keep keep (don't delete) input files\n" );
- std::printf( " -m, --match-length=<n> set match length limit in bytes [80]\n" );
+ std::printf( " -m, --match-length=<n> set match length limit in bytes [36]\n" );
std::printf( " -o, --output=<file> if reading stdin, place the output into <file>\n" );
std::printf( " -q, --quiet suppress all messages\n" );
std::printf( " -s, --dictionary-size=<n> set dictionary size limit in bytes [8MiB]\n" );
@@ -169,26 +168,18 @@ void show_version() throw()
}
-const char * format_num( long long num, long long limit = 9999,
- const int set_prefix = 0 ) throw()
+const char * format_num( long long num ) throw()
{
- const char * const si_prefix[8] =
- { "k", "M", "G", "T", "P", "E", "Z", "Y" };
- const char * const binary_prefix[8] =
+ const char * const prefix[8] =
{ "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" };
- static bool si = false;
- static char buf[16];
-
- if( set_prefix ) si = ( set_prefix > 0 );
- const int factor = ( si ) ? 1000 : 1024;
- const char * const *prefix = ( si ) ? si_prefix : binary_prefix;
+ enum { buf_size = 16, factor = 1024 };
+ static char buf[buf_size];
const char *p = "";
- limit = std::max( 999LL, std::min( 999999LL, limit ) );
- for( int i = 0; i < 8 && ( llabs( num ) > limit ||
+ for( int i = 0; i < 8 && ( llabs( num ) > 9999 ||
( llabs( num ) >= factor && num % factor == 0 ) ); ++i )
{ num /= factor; p = prefix[i]; }
- snprintf( buf, sizeof buf, "%lld %s", num, p );
+ snprintf( buf, buf_size, "%lld %s", num, p );
return buf;
}
@@ -202,7 +193,7 @@ long long getnum( const char * const ptr, const int bs = 0,
long long result = strtoll( ptr, &tail, 0 );
if( tail == ptr )
{
- show_error( "bad or missing numerical argument", 0, true );
+ show_error( "Bad or missing numerical argument.", 0, true );
std::exit( 1 );
}
@@ -232,7 +223,7 @@ long long getnum( const char * const ptr, const int bs = 0,
}
if( bad_multiplier )
{
- show_error( "bad multiplier in numerical argument", 0, true );
+ show_error( "Bad multiplier in numerical argument.", 0, true );
std::exit( 1 );
}
for( int i = 0; i < exponent; ++i )
@@ -244,7 +235,7 @@ long long getnum( const char * const ptr, const int bs = 0,
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
if( errno )
{
- show_error( "numerical argument out of limits" );
+ show_error( "Numerical argument out of limits." );
std::exit( 1 );
}
return result;
@@ -283,7 +274,7 @@ int open_instream( const std::string & name, struct stat * const in_statsp,
if( program_mode == m_compress && !force && eindex >= 0 )
{
if( verbosity >= 0 )
- std::fprintf( stderr, "%s: input file `%s' already has `%s' suffix.\n",
+ std::fprintf( stderr, "%s: Input file `%s' already has `%s' suffix.\n",
program_name, name.c_str(),
known_extensions[eindex].from );
}
@@ -300,14 +291,16 @@ int open_instream( const std::string & name, struct stat * const in_statsp,
{
const int i = fstat( infd, in_statsp );
const mode_t & mode = in_statsp->st_mode;
- if( i < 0 || !( S_ISREG( mode ) || ( to_stdout &&
- ( S_ISFIFO( mode ) || S_ISSOCK( mode ) ||
- S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) )
+ const bool can_read = ( i == 0 &&
+ ( S_ISBLK( mode ) || S_ISCHR( mode ) ||
+ S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
+ if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) )
{
if( verbosity >= 0 )
- std::fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n",
+ std::fprintf( stderr, "%s: Input file `%s' is not a regular file%s.\n",
program_name, name.c_str(),
- to_stdout ? "" : " and `--stdout' was not specified" );
+ ( can_read && !to_stdout ) ?
+ " and `--stdout' was not specified" : "" );
close( infd );
infd = -1;
}
@@ -339,7 +332,7 @@ void set_d_outname( const std::string & name, const int i ) throw()
}
output_filename = name; output_filename += ".out";
if( verbosity >= 0 )
- std::fprintf( stderr, "%s: can't guess original name for `%s' -- using `%s'.\n",
+ std::fprintf( stderr, "%s: Can't guess original name for `%s' -- using `%s'.\n",
program_name, name.c_str(), output_filename.c_str() );
}
@@ -350,18 +343,14 @@ bool open_outstream( const bool force ) throw()
if( force ) flags |= O_TRUNC; else flags |= O_EXCL;
outfd = open( output_filename.c_str(), flags, outfd_mode );
- if( outfd < 0 )
+ if( outfd < 0 && verbosity >= 0 )
{
- if( errno == EEXIST ) outfd = -2; else outfd = -1;
- if( verbosity >= 0 )
- {
- if( outfd == -2 )
- std::fprintf( stderr, "%s: Output file %s already exists, skipping.\n",
- program_name, output_filename.c_str() );
- else
- std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n",
- program_name, output_filename.c_str(), std::strerror( errno ) );
- }
+ if( errno == EEXIST )
+ std::fprintf( stderr, "%s: Output file `%s' already exists, skipping.\n",
+ program_name, output_filename.c_str() );
+ else
+ std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n",
+ program_name, output_filename.c_str(), std::strerror( errno ) );
}
return ( outfd >= 0 );
}
@@ -369,7 +358,7 @@ bool open_outstream( const bool force ) throw()
bool check_tty( const int infd, const Mode program_mode ) throw()
{
- if( program_mode == m_compress && isatty( outfd ) )
+ if( program_mode == m_compress && outfd >= 0 && isatty( outfd ) )
{
show_error( "I won't write compressed data to a terminal.", 0, true );
return false;
@@ -391,7 +380,7 @@ void cleanup_and_fail( const int retval ) throw()
delete_output_on_interrupt = false;
if( verbosity >= 0 )
std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n",
- program_name, output_filename.c_str() );
+ program_name, output_filename.c_str() );
if( outfd >= 0 ) { close( outfd ); outfd = -1; }
if( std::remove( output_filename.c_str() ) != 0 )
show_error( "WARNING: deletion of output file (apparently) failed." );
@@ -406,9 +395,10 @@ void close_and_set_permissions( const struct stat * const in_statsp )
bool error = false;
if( in_statsp )
{
- if( fchmod( outfd, in_statsp->st_mode ) != 0 ||
- ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 &&
- errno != EPERM ) ) error = true;
+ if( ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 &&
+ errno != EPERM ) ||
+ fchmod( outfd, in_statsp->st_mode ) != 0 )
+ error = true;
// fchown will in many cases return with EPERM, which can be safely ignored.
}
if( close( outfd ) == 0 ) outfd = -1;
@@ -424,7 +414,7 @@ void close_and_set_permissions( const struct stat * const in_statsp )
}
if( error )
{
- show_error( "I can't change output file attributes." );
+ show_error( "Can't change output file attributes." );
cleanup_and_fail( 1 );
}
}
@@ -461,10 +451,11 @@ int do_compress( LZ_Encoder * const encoder, const long long member_size,
buffer_size );
const int rd = readblock( infd, buffer, size );
if( rd != size && errno )
- { pp(); show_error( "read error", errno ); return 1; }
+ { pp(); show_error( "Read error", errno ); return 1; }
if( rd > 0 && rd != LZ_compress_write( encoder, buffer, rd ) )
internal_error( "library error (LZ_compress_write)" );
if( rd < size ) LZ_compress_finish( encoder );
+// else LZ_compress_sync_flush( encoder );
in_size += rd;
}
const int out_size = LZ_compress_read( encoder, buffer, buffer_size );
@@ -472,15 +463,15 @@ int do_compress( LZ_Encoder * const encoder, const long long member_size,
{
pp();
if( verbosity >= 0 )
- std::fprintf( stderr, "LZ_compress_read error: %s.\n",
- LZ_strerror( LZ_compress_errno( encoder ) ) );
+ std::fprintf( stderr, "%s: LZ_compress_read error: %s.\n",
+ program_name, LZ_strerror( LZ_compress_errno( encoder ) ) );
return 1;
}
else if( out_size > 0 )
{
const int wr = writeblock( outfd, buffer, out_size );
if( wr != out_size )
- { pp(); show_error( "write error", errno ); return 1; }
+ { pp(); show_error( "Write error", errno ); return 1; }
}
else if( in_size == 0 ) internal_error( "library error (LZ_compress_read)" );
if( LZ_compress_member_finished( encoder ) )
@@ -494,7 +485,7 @@ int do_compress( LZ_Encoder * const encoder, const long long member_size,
{
close_and_set_permissions( in_statsp );
if( !next_filename() )
- { pp(); show_error( "too many volume files" ); return 1; }
+ { pp( "Too many volume files." ); return 1; }
if( !open_outstream( true ) ) return 1;
delete_output_on_interrupt = true;
}
@@ -505,8 +496,8 @@ int do_compress( LZ_Encoder * const encoder, const long long member_size,
{
pp();
if( verbosity >= 0 )
- std::fprintf( stderr, "LZ_compress_restart_member error: %s.\n",
- LZ_strerror( LZ_compress_errno( encoder ) ) );
+ std::fprintf( stderr, "%s: LZ_compress_restart_member error: %s.\n",
+ program_name, LZ_strerror( LZ_compress_errno( encoder ) ) );
return 1;
}
}
@@ -517,7 +508,7 @@ int do_compress( LZ_Encoder * const encoder, const long long member_size,
const long long in_size = LZ_compress_total_in_size( encoder );
const long long out_size = LZ_compress_total_out_size( encoder );
if( in_size <= 0 || out_size <= 0 )
- std::fprintf( stderr, "no data compressed.\n" );
+ std::fprintf( stderr, "No data compressed.\n" );
else
std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, "
"%5.2f%% saved, %lld in, %lld out.\n",
@@ -543,7 +534,7 @@ int compress( const long long member_size, const long long volume_size,
if( !encoder || LZ_compress_errno( encoder ) != LZ_ok )
{
if( !encoder || LZ_compress_errno( encoder ) == LZ_mem_error )
- pp( "not enough memory. Try a smaller dictionary size" );
+ pp( "Not enough memory. Try a smaller dictionary size" );
else
internal_error( "invalid argument to encoder" );
retval = 1;
@@ -569,7 +560,7 @@ int do_decompress( LZ_Decoder * const decoder, const int infd,
const int max_in_size = in_size;
in_size = readblock( infd, buffer, max_in_size );
if( in_size != max_in_size && errno )
- { pp(); show_error( "read error", errno ); return 1; }
+ { pp(); show_error( "Read error", errno ); return 1; }
if( in_size > 0 && in_size != LZ_decompress_write( decoder, buffer, in_size ) )
internal_error( "library error (LZ_decompress_write)" );
if( in_size < max_in_size ) LZ_decompress_finish( decoder );
@@ -585,22 +576,28 @@ int do_decompress( LZ_Decoder * const decoder, const int infd,
{
const int wr = writeblock( outfd, buffer, rd );
if( wr != rd )
- { pp(); show_error( "write error", errno ); return 1; }
+ { pp(); show_error( "Write error", errno ); return 1; }
}
}
else if( rd < 0 ) { out_size = rd; break; }
if( verbosity >= 1 && LZ_decompress_member_finished( decoder ) == 1 )
{
+ const long long data_position = LZ_decompress_data_position( decoder );
+ const long long member_size = LZ_decompress_member_position( decoder );
pp();
if( verbosity >= 2 )
std::fprintf( stderr, "version %d, dictionary size %7sB. ",
LZ_decompress_member_version( decoder ),
format_num( LZ_decompress_dictionary_size( decoder ) ) );
+ if( verbosity >= 4 && data_position > 0 && member_size > 0 )
+ std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, %5.2f%% saved. ",
+ (double)data_position / member_size,
+ ( 8.0 * member_size ) / data_position,
+ 100.0 * ( 1.0 - ( (double)member_size / data_position ) ) );
if( verbosity >= 3 )
- std::fprintf( stderr, "data crc %08X, data size %9lld, member size %8lld. ",
+ std::fprintf( stderr, "data CRC %08X, data size %9lld, member size %8lld. ",
LZ_decompress_data_crc( decoder ),
- LZ_decompress_data_position( decoder ),
- LZ_decompress_member_position( decoder ) );
+ data_position, member_size );
if( testing ) std::fprintf( stderr, "ok\n" );
else std::fprintf( stderr, "done\n" );
pp.reset();
@@ -614,19 +611,19 @@ int do_decompress( LZ_Decoder * const decoder, const int infd,
{
if( LZ_decompress_total_out_size( decoder ) > 0 )
break; // trailing garbage
- pp( "error reading member header" );
+ pp( "Error reading member header" );
return 1;
}
if( lz_errno == LZ_mem_error )
{
- pp( "not enough memory. Find a machine with more memory" );
+ pp( "Not enough memory. Find a machine with more memory" );
return 1;
}
pp();
if( lz_errno == LZ_unexpected_eof )
{
if( verbosity >= 0 )
- std::fprintf( stderr, "file ends unexpectedly at pos %lld\n",
+ std::fprintf( stderr, "File ends unexpectedly at pos %lld\n",
LZ_decompress_total_in_size( decoder ) );
return 2;
}
@@ -651,7 +648,7 @@ int decompress( const int infd, const Pretty_print & pp,
if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok )
{
- pp( "not enough memory. Find a machine with more memory" );
+ pp( "Not enough memory. Find a machine with more memory" );
retval = 1;
}
else retval = do_decompress( decoder, infd, pp, testing );
@@ -699,22 +696,24 @@ void show_error( const char * const msg, const int errcode, const bool help ) th
{
if( verbosity >= 0 )
{
- if( msg && msg[0] != 0 )
+ if( msg && msg[0] )
{
std::fprintf( stderr, "%s: %s", program_name, msg );
- if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) );
+ if( errcode > 0 )
+ std::fprintf( stderr, ": %s", std::strerror( errcode ) );
std::fprintf( stderr, "\n" );
}
- if( help && invocation_name && invocation_name[0] != 0 )
- std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name );
+ if( help && invocation_name && invocation_name[0] )
+ std::fprintf( stderr, "Try `%s --help' for more information.\n",
+ invocation_name );
}
}
void internal_error( const char * const msg )
{
- std::string s( "internal error: " ); s += msg;
- show_error( s.c_str() );
+ if( verbosity >= 0 )
+ std::fprintf( stderr, "%s: internal error: %s.\n", program_name, msg );
std::exit( 3 );
}
@@ -762,15 +761,15 @@ int main( const int argc, const char * const argv[] )
// to the corresponding LZMA compression modes.
const Lzma_options option_mapping[] =
{
- { 1 << 16, 5 }, // -0
- { 1 << 20, 10 }, // -1
- { 3 << 19, 12 }, // -2
- { 1 << 21, 17 }, // -3
- { 3 << 20, 26 }, // -4
- { 1 << 22, 44 }, // -5
- { 1 << 23, 80 }, // -6
- { 1 << 24, 108 }, // -7
- { 3 << 23, 163 }, // -8
+ { 1 << 20, 5 }, // -0
+ { 1 << 20, 5 }, // -1
+ { 3 << 19, 6 }, // -2
+ { 1 << 21, 8 }, // -3
+ { 3 << 20, 12 }, // -4
+ { 1 << 22, 20 }, // -5
+ { 1 << 23, 36 }, // -6
+ { 1 << 24, 68 }, // -7
+ { 3 << 23, 132 }, // -8
{ 1 << 25, 273 } }; // -9
Lzma_options encoder_options = option_mapping[6]; // default = "-6"
long long member_size = LLONG_MAX;
@@ -793,8 +792,8 @@ int main( const int argc, const char * const argv[] )
const Arg_parser::Option options[] =
{
- { '0', 0, Arg_parser::no },
- { '1', "fast", Arg_parser::no },
+ { '0', "fast", Arg_parser::no },
+ { '1', 0, Arg_parser::no },
{ '2', 0, Arg_parser::no },
{ '3', 0, Arg_parser::no },
{ '4', 0, Arg_parser::no },
@@ -820,7 +819,7 @@ int main( const int argc, const char * const argv[] )
{ 'V', "version", Arg_parser::no },
{ 0 , 0, Arg_parser::no } };
- Arg_parser parser( argc, argv, options );
+ const Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 1; }
@@ -838,7 +837,7 @@ int main( const int argc, const char * const argv[] )
case 'b': member_size = getnum( arg, 0, 100000, LLONG_MAX / 2 ); break;
case 'c': to_stdout = true; break;
case 'd': program_mode = m_decompress; break;
- case 'e': break;
+ case 'e': break; // ignored by now
case 'f': force = true; break;
case 'h': show_help(); return 0;
case 'k': keep_input_files = true; break;
@@ -855,7 +854,12 @@ int main( const int argc, const char * const argv[] )
case 'V': show_version(); return 0;
default : internal_error( "uncaught option" );
}
- }
+ } // end process options
+
+#if defined(__OS2__)
+ _fsetmode( stdin, "b" );
+ _fsetmode( stdout, "b" );
+#endif
bool filenames_given = false;
for( ; argind < parser.arguments(); ++argind )
@@ -954,9 +958,7 @@ int main( const int argc, const char * const argv[] )
}
if( outfd >= 0 && close( outfd ) != 0 )
{
- if( verbosity >= 0 )
- std::fprintf( stderr, "%s: Can't close stdout: %s.\n",
- program_name, std::strerror( errno ) );
+ show_error( "Can't close stdout", errno );
if( retval < 1 ) retval = 1;
}
return retval;
diff --git a/testsuite/check.sh b/testsuite/check.sh
index 69060bd..be6204b 100755
--- a/testsuite/check.sh
+++ b/testsuite/check.sh
@@ -1,6 +1,6 @@
#! /bin/sh
# check script for Lzlib - A compression library for lzip files
-# Copyright (C) 2009, 2010 Antonio Diaz Diaz.
+# Copyright (C) 2009, 2010, 2011 Antonio Diaz Diaz.
#
# This script is free software: you have unlimited permission
# to copy, distribute and modify it.
@@ -10,6 +10,7 @@ export LC_ALL
objdir=`pwd`
testdir=`cd "$1" ; pwd`
LZIP="${objdir}"/minilzip
+BBEXAMPLE="${objdir}"/bbexample
LZCHECK="${objdir}"/lzcheck
framework_failure() { echo "failure in testing framework" ; exit 1 ; }
@@ -20,17 +21,31 @@ fi
if [ -d tmp ] ; then rm -rf tmp ; fi
mkdir tmp
-printf "testing lzlib..."
+printf "testing lzlib-%s..." "$2"
cd "${objdir}"/tmp
-cat "${testdir}"/test1 > in || framework_failure
+cat "${testdir}"/test.txt > in || framework_failure
fail=0
-"${LZIP}" -t "${testdir}"/test1.lz || fail=1
-"${LZIP}" -cd "${testdir}"/test1.lz > copy || fail=1
+"${LZIP}" -t "${testdir}"/test_v0.lz || fail=1
+printf .
+"${LZIP}" -cd "${testdir}"/test_v0.lz > copy || fail=1
+cmp in copy || fail=1
+printf .
+
+"${LZIP}" -t "${testdir}"/test_v1.lz || fail=1
+printf .
+"${LZIP}" -cd "${testdir}"/test_v1.lz > copy || fail=1
cmp in copy || fail=1
+printf .
-for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
+"${LZIP}" -t "${testdir}"/test_sync.lz || fail=1
+printf .
+"${LZIP}" -cd "${testdir}"/test_sync.lz > copy || fail=1
+cmp in copy || fail=1
+printf .
+
+for i in s4Ki 0 1 2 3 4 5 6 7 8s16 9s16 ; do
"${LZIP}" -k -$i in || fail=1
mv -f in.lz copy.lz || fail=1
printf "garbage" >> copy.lz || fail=1
@@ -39,7 +54,7 @@ for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
printf .
done
-for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
+for i in s4Ki 0 1 2 3 4 5 6 7 8s16 9s16 ; do
"${LZIP}" -c -$i in > out || fail=1
printf "g" >> out || fail=1
"${LZIP}" -cd out > copy || fail=1
@@ -47,21 +62,31 @@ for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
printf .
done
-for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
+for i in s4Ki 0 1 2 3 4 5 6 7 8s16 9s16 ; do
"${LZIP}" -$i < in > out || fail=1
"${LZIP}" -d < out > copy || fail=1
cmp in copy || fail=1
printf .
done
-for i in s4Ki 0 1 2 3 4 5 6 7 8 9s16 ; do
- "${LZIP}" -fe -$i -o out < in || fail=1
+for i in s4Ki 0 1 2 3 4 5 6 7 8s16 9s16 ; do
+ "${LZIP}" -f -$i -o out < in || fail=1
"${LZIP}" -df -o copy < out.lz || fail=1
cmp in copy || fail=1
printf .
done
-"${LZCHECK}" in 2>/dev/null || fail=1
+"${LZIP}" -$i < in > anyothername || fail=1
+"${LZIP}" -dq anyothername || fail=1
+cmp in anyothername.out || fail=1
+printf .
+
+"${BBEXAMPLE}" in || fail=1
+printf .
+"${BBEXAMPLE}" out || fail=1
+printf .
+
+"${LZCHECK}" in || fail=1
printf .
echo
diff --git a/testsuite/test1 b/testsuite/test.txt
index 5b244d5..5b244d5 100644
--- a/testsuite/test1
+++ b/testsuite/test.txt
diff --git a/testsuite/test_sync.lz b/testsuite/test_sync.lz
new file mode 100644
index 0000000..419fa97
--- /dev/null
+++ b/testsuite/test_sync.lz
Binary files differ
diff --git a/testsuite/test1.lz b/testsuite/test_v0.lz
index a09b1e8..a09b1e8 100644
--- a/testsuite/test1.lz
+++ b/testsuite/test_v0.lz
Binary files differ
diff --git a/testsuite/test_v1.lz b/testsuite/test_v1.lz
new file mode 100644
index 0000000..f1c79eb
--- /dev/null
+++ b/testsuite/test_v1.lz
Binary files differ
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-05 02:39:24 +0000