Merging upstream version 1.4.

Signed-off-by: Daniel Baumann <daniel@debian.org>

ChangeLog

@@ -1,3 +1,8 @@
+2024-01-02  Antonio Diaz Diaz  <antonio@gnu.org>
+
+	* Version 1.4 released.
+	* lzd.cc: Use header_size and trailer_size instead of 6 and 20.
+
 2022-10-24  Antonio Diaz Diaz  <antonio@gnu.org>
 
 	* Version 1.3 released.
@@ -6,7 +11,7 @@
 2021-01-04  Antonio Diaz Diaz  <antonio@gnu.org>
 
 	* Version 1.2 released.
-	* lzd.cc (main): Verify also mismatches in member size.
+	* lzd.cc (main): Check also mismatches in member size.
 	  Accept and ignore the option '-d' for compatibility with zutils.
 	  Remove warning about "lzd not safe for real work".
 	  Print license notice.
@@ -70,7 +75,7 @@
 	* Version 0.1 released.
 
 
-Copyright (C) 2013-2022 Antonio Diaz Diaz.
+Copyright (C) 2013-2024 Antonio Diaz Diaz.
 
 This file is a collection of facts, and thus it is not copyrightable,
 but just in case, you have unlimited permission to copy, distribute, and

INSTALL

@@ -31,7 +31,8 @@ extracted from the archive.
 4. Optionally, type 'make check' to run the tests that come with lzd.
 
 5. Type 'make install' to install the program and any data files and
-   documentation.
+   documentation. You need root privileges to install into a prefix owned
+   by root.
 
 
 Another way
@@ -51,7 +52,7 @@ After running 'configure', you can run 'make' and 'make install' as
 explained above.
 
 
-Copyright (C) 2013-2022 Antonio Diaz Diaz.
+Copyright (C) 2013-2024 Antonio Diaz Diaz.
 
 This file is free documentation: you have unlimited permission to copy,
 distribute, and modify it.

Makefile.in

@@ -24,15 +24,18 @@ $(progname) : $(objs)
 %.o : %.cc
 	$(CXX) $(CPPFLAGS) $(CXXFLAGS) -DPROGVERSION=\"$(pkgversion)\" -c -o $@ $<
 
-$(objs) : Makefile
+# prevent 'make' from trying to remake source files
+$(VPATH)/configure $(VPATH)/Makefile.in $(VPATH)/doc/$(pkgname).texi : ;
+%.h %.cc : ;
 
+$(objs) : Makefile
 
 doc :
 
 info : $(VPATH)/doc/$(pkgname).info
 
 $(VPATH)/doc/$(pkgname).info : $(VPATH)/doc/$(pkgname).texi
-	cd $(VPATH)/doc && makeinfo $(pkgname).texi
+	cd $(VPATH)/doc && $(MAKEINFO) $(pkgname).texi
 
 man : $(VPATH)/doc/$(progname).1
 

NEWS

@@ -1,5 +1,4 @@
-Changes in version 1.3:
+Changes in version 1.4:
 
-Lzd now discards the first byte of the LZMA stream explicity (instead of
+Define constants 'header_size' and 'trailer_size' instead of using 6 and 20.
-shifting 1 extra byte in the initialization of 'code') to make the intent
+(Lzd is supposed to be educational, and using numbers is bad practice).
-clearer.

README

@@ -7,7 +7,7 @@ lzip works. Lzd is written in C++.
 The source code of lzd is used in the lzip manual as a reference
 decompressor in the description of the lzip file format. Reading the lzip
 manual will help you understand the source code. Lzd is compliant with the
-lzip specification; it verifies the 3 integrity factors.
+lzip specification; it checks the 3 integrity factors.
 
 The source code of lzd is also used as a reference in the description of the
 media type 'application/lzip'.
@@ -18,33 +18,9 @@ ignores) the option '-d' for compatibility with other lzip tools. In
 particular, accepting the option '-d' allows lzd to be used as argument to
 the option '--lz' of the tools from the zutils package.
 
-Lzd will correctly decompress the concatenation of two or more compressed
+Lzd correctly decompresses the concatenation of two or more compressed
 files. The result is the concatenation of the corresponding decompressed
-data. Integrity of such concatenated compressed input is also verified.
+data. Integrity of such concatenated compressed input is also checked.
-
-The lzip file format is designed for data sharing and long-term archiving,
-taking into account both data integrity and decoder availability:
-
-   * The lzip format provides very safe integrity checking and some data
-     recovery means. The program lziprecover can repair bit flip errors
-     (one of the most common forms of data corruption) in lzip files, and
-     provides data recovery capabilities, including error-checked merging
-     of damaged copies of a file.
-
-   * The lzip format is as simple as possible (but not simpler). The lzip
-     manual provides the source code of a simple decompressor along with a
-     detailed explanation of how it works, so that with the only help of the
-     lzip manual it would be possible for a digital archaeologist to extract
-     the data from a lzip file long after quantum computers eventually
-     render LZMA obsolete.
-
-   * Additionally the lzip reference implementation is copylefted, which
-     guarantees that it will remain free forever.
-
-A nice feature of the lzip format is that a corrupt byte is easier to repair
-the nearer it is from the beginning of the file. Therefore, with the help of
-lziprecover, losing an entire archive just because of a corrupt byte near
-the beginning is a thing of the past.
 
 The ideas embodied in lzd are due to (at least) the following people:
 Abraham Lempel and Jacob Ziv (for the LZ algorithm), Andrei Markov (for the
@@ -52,11 +28,10 @@ definition of Markov chains), G.N.N. Martin (for the definition of range
 encoding), and Igor Pavlov (for putting all the above together in LZMA).
 
 
-Copyright (C) 2013-2022 Antonio Diaz Diaz.
+Copyright (C) 2013-2024 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
+The file Makefile.in is a data file used by configure to produce the Makefile.
-Makefile. It has the same copyright owner and permissions that configure
+It has the same copyright owner and permissions that configure itself.
-itself.

configure

@@ -1,12 +1,12 @@
 #! /bin/sh
 # configure script for Lzd - Educational decompressor for the lzip format
-# Copyright (C) 2013-2022 Antonio Diaz Diaz.
+# Copyright (C) 2013-2024 Antonio Diaz Diaz.
 #
 # This configure script is free software: you have unlimited permission
 # to copy, distribute, and modify it.
 
 pkgname=lzd
-pkgversion=1.3
+pkgversion=1.4
 progname=lzd
 srctrigger=lzd.cc
 
@@ -24,6 +24,7 @@ CXX=g++
 CPPFLAGS=
 CXXFLAGS='-Wall -W -O2'
 LDFLAGS=
+MAKEINFO=makeinfo
 
 # checking whether we are using GNU C++.
 /bin/sh -c "${CXX} --version" > /dev/null 2>&1 || { CXX=c++ ; CXXFLAGS=-O2 ; }
@@ -65,10 +66,11 @@ while [ $# != 0 ] ; do
 		echo "  --infodir=DIR         info files directory [${infodir}]"
 		echo "  --mandir=DIR          man pages directory [${mandir}]"
 		echo "  CXX=COMPILER          C++ compiler to use [${CXX}]"
-		echo "  CPPFLAGS=OPTIONS      command line options for the preprocessor [${CPPFLAGS}]"
+		echo "  CPPFLAGS=OPTIONS      command-line options for the preprocessor [${CPPFLAGS}]"
-		echo "  CXXFLAGS=OPTIONS      command line options for the C++ compiler [${CXXFLAGS}]"
+		echo "  CXXFLAGS=OPTIONS      command-line options for the C++ compiler [${CXXFLAGS}]"
 		echo "  CXXFLAGS+=OPTIONS     append options to the current value of CXXFLAGS"
-		echo "  LDFLAGS=OPTIONS       command line options for the linker [${LDFLAGS}]"
+		echo "  LDFLAGS=OPTIONS       command-line options for the linker [${LDFLAGS}]"
+		echo "  MAKEINFO=NAME         makeinfo program to use [${MAKEINFO}]"
 		echo
 		exit 0 ;;
 	--version | -V)
@@ -96,6 +98,7 @@ while [ $# != 0 ] ; do
 	CXXFLAGS=*)  CXXFLAGS=${optarg} ;;
 	CXXFLAGS+=*) CXXFLAGS="${CXXFLAGS} ${optarg}" ;;
 	LDFLAGS=*)    LDFLAGS=${optarg} ;;
+	MAKEINFO=*)  MAKEINFO=${optarg} ;;
 
 	--*)
 		echo "configure: WARNING: unrecognized option: '${option}'" 1>&2 ;;
@@ -147,7 +150,7 @@ if [ -z "${no_create}" ] ; then
 # This script is free software: you have unlimited permission
 # to copy, distribute, and modify it.
 
-exec /bin/sh $0 ${args} --no-create
+exec /bin/sh "$0" ${args} --no-create
 EOF
 	chmod +x config.status
 fi
@@ -164,10 +167,11 @@ echo "CXX = ${CXX}"
 echo "CPPFLAGS = ${CPPFLAGS}"
 echo "CXXFLAGS = ${CXXFLAGS}"
 echo "LDFLAGS = ${LDFLAGS}"
+echo "MAKEINFO = ${MAKEINFO}"
 rm -f Makefile
 cat > Makefile << EOF
 # Makefile for Lzd - Educational decompressor for the lzip format
-# Copyright (C) 2013-2022 Antonio Diaz Diaz.
+# Copyright (C) 2013-2024 Antonio Diaz Diaz.
 # This file was generated automatically by configure. Don't edit.
 #
 # This Makefile is free software: you have unlimited permission
@@ -187,6 +191,7 @@ CXX = ${CXX}
 CPPFLAGS = ${CPPFLAGS}
 CXXFLAGS = ${CXXFLAGS}
 LDFLAGS = ${LDFLAGS}
+MAKEINFO = ${MAKEINFO}
 EOF
 cat "${srcdir}/Makefile.in" >> Makefile
 

lzd.cc

@@ -1,5 +1,5 @@
 /* Lzd - Educational decompressor for the lzip format
-   Copyright (C) 2013-2022 Antonio Diaz Diaz.
+   Copyright (C) 2013-2024 Antonio Diaz Diaz.
 
    This program is free software. Redistribution and use in source and
    binary forms, with or without modification, are permitted provided
@@ -18,7 +18,7 @@
 */
 /*
    Exit status: 0 for a normal exit, 1 for environmental problems
-   (file not found, invalid command line options, I/O errors, etc), 2 to
+   (file not found, invalid command-line options, I/O errors, etc), 2 to
    indicate a corrupt or invalid input file.
 */
 
@@ -130,10 +130,11 @@ public:
 const CRC32 crc32;
 
 
-typedef uint8_t Lzip_header[6];		// 0-3 magic bytes
+enum { header_size = 6, trailer_size = 20 };
-					//   4 version
+typedef uint8_t Lzip_header[header_size]; // 0-3 magic bytes
-					//   5 coded dictionary size
+					  //   4 version
-typedef uint8_t Lzip_trailer[20];
+					  //   5 coded dictionary size
+typedef uint8_t Lzip_trailer[trailer_size];
 			//  0-3  CRC32 of the uncompressed data
 			//  4-11 size of the uncompressed data
 			// 12-19 member size including header and trailer
@@ -145,7 +146,8 @@ class Range_decoder
   uint32_t range;
 
 public:
-  Range_decoder() : member_pos( 6 ), code( 0 ), range( 0xFFFFFFFFU )
+  Range_decoder()
+    : member_pos( header_size ), code( 0 ), range( 0xFFFFFFFFU )
     {
     get_byte();			// discard first byte of the LZMA stream
     for( int i = 0; i < 4; ++i ) code = ( code << 8 ) | get_byte();
@@ -168,9 +170,9 @@ public:
     return symbol;
     }
 
-  unsigned decode_bit( Bit_model & bm )
+  bool decode_bit( Bit_model & bm )
     {
-    unsigned symbol;
+    bool symbol;
     const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability;
     if( code < bound )
       {
@@ -216,8 +218,8 @@ public:
     unsigned symbol = 1;
     for( int i = 7; i >= 0; --i )
       {
-      const unsigned match_bit = ( match_byte >> i ) & 1;
+      const bool match_bit = ( match_byte >> i ) & 1;
-      const unsigned bit = decode_bit( bm[symbol+(match_bit<<8)+0x100] );
+      const bool bit = decode_bit( bm[symbol+(match_bit<<8)+0x100] );
       symbol = ( symbol << 1 ) | bit;
       if( match_bit != bit )
         {
@@ -232,11 +234,12 @@ public:
   unsigned decode_len( Len_model & lm, const int pos_state )
     {
     if( decode_bit( lm.choice1 ) == 0 )
-      return decode_tree( lm.bm_low[pos_state], len_low_bits );
+      return min_match_len +
+             decode_tree( lm.bm_low[pos_state], len_low_bits );
     if( decode_bit( lm.choice2 ) == 0 )
-      return len_low_symbols +
+      return min_match_len + len_low_symbols +
              decode_tree( lm.bm_mid[pos_state], len_mid_bits );
-    return len_low_symbols + len_mid_symbols +
+    return min_match_len + len_low_symbols + len_mid_symbols +
            decode_tree( lm.bm_high, len_high_bits );
     }
   };
@@ -371,12 +374,12 @@ bool LZ_decoder::decode_member()	// Return false if error
         rep0 = distance;
         }
       state.set_rep();
-      len = min_match_len + rdec.decode_len( rep_len_model, pos_state );
+      len = rdec.decode_len( rep_len_model, pos_state );
       }
     else					// match
       {
       rep3 = rep2; rep2 = rep1; rep1 = rep0;
-      len = min_match_len + rdec.decode_len( match_len_model, pos_state );
+      len = rdec.decode_len( match_len_model, pos_state );
       const int len_state = std::min( len - min_match_len, len_states - 1 );
       rep0 = rdec.decode_tree( bm_dis_slot[len_state], dis_slot_bits );
       if( rep0 >= start_dis_model )
@@ -395,7 +398,7 @@ bool LZ_decoder::decode_member()	// Return false if error
           if( rep0 == 0xFFFFFFFFU )		// marker found
             {
             flush_data();
-            return ( len == min_match_len );	// End Of Stream marker
+            return len == min_match_len;	// End Of Stream marker
             }
           }
         }
@@ -420,10 +423,10 @@ int main( const int argc, const char * const argv[] )
       "See the lzip manual for an explanation of the code.\n"
       "\nUsage: %s [-d] < file.lz > file\n"
       "Lzd decompresses from standard input to standard output.\n"
-      "\nCopyright (C) 2022 Antonio Diaz Diaz.\n"
+      "\nCopyright (C) 2024 Antonio Diaz Diaz.\n"
       "License 2-clause BSD.\n"
-      "This is free software: you are free to change and redistribute it.\n"
+      "This is free software: you are free to change and redistribute "
-      "There is NO WARRANTY, to the extent permitted by law.\n"
+      "it.\nThere is NO WARRANTY, to the extent permitted by law.\n"
       "Report bugs to lzip-bug@nongnu.org\n"
       "Lzd home page: http://www.nongnu.org/lzip/lzd.html\n",
       PROGVERSION, argv[0] );
@@ -437,8 +440,8 @@ int main( const int argc, const char * const argv[] )
 
   for( bool first_member = true; ; first_member = false )
     {
-    Lzip_header header;				// verify header
+    Lzip_header header;				// check header
-    for( int i = 0; i < 6; ++i ) header[i] = std::getc( stdin );
+    for( int i = 0; i < header_size; ++i ) header[i] = std::getc( stdin );
     if( std::feof( stdin ) || std::memcmp( header, "LZIP\x01", 5 ) != 0 )
       {
       if( first_member )
@@ -449,15 +452,15 @@ int main( const int argc, const char * const argv[] )
     unsigned dict_size = 1 << ( header[5] & 0x1F );
     dict_size -= ( dict_size / 16 ) * ( ( header[5] >> 5 ) & 7 );
     if( dict_size < min_dictionary_size || dict_size > max_dictionary_size )
-      { std::fputs( "Invalid dictionary size in member header.\n", stderr );
+      { std::fputs( "Invalid dictionary size in member header.\n",
-        return 2; }
+                    stderr ); return 2; }
 
     LZ_decoder decoder( dict_size );		// decode LZMA stream
     if( !decoder.decode_member() )
       { std::fputs( "Data error\n", stderr ); return 2; }
 
-    Lzip_trailer trailer;			// verify trailer
+    Lzip_trailer trailer;			// check trailer
-    for( int i = 0; i < 20; ++i ) trailer[i] = decoder.get_byte();
+    for( int i = 0; i < trailer_size; ++i ) trailer[i] = decoder.get_byte();
     int retval = 0;
     unsigned crc = 0;
     for( int i = 3; i >= 0; --i ) crc = ( crc << 8 ) + trailer[i];

testsuite/check.sh

@@ -1,6 +1,6 @@
 #! /bin/sh
 # check script for Lzd - Educational decompressor for the lzip format
-# Copyright (C) 2013-2022 Antonio Diaz Diaz.
+# Copyright (C) 2013-2024 Antonio Diaz Diaz.
 #
 # This script is free software: you have unlimited permission
 # to copy, distribute, and modify it.
@@ -41,20 +41,20 @@ printf "testing lzd-%s..." "$2"
 [ $? = 2 ] || test_failed $LINENO
 
 for i in "${in_lz}" "${in_em}" ; do
-	"${LZIP}" < "$i" > copy || test_failed $LINENO "$i"
+	"${LZIP}" < "$i" > out || test_failed $LINENO "$i"
-	cmp "${in}" copy || test_failed $LINENO "$i"
+	cmp "${in}" out || test_failed $LINENO "$i"
 done
 
 cat "${in}" "${in}" > in2 || framework_failure
-cat "${in_lz}" "${in_lz}" | "${LZIP}" > copy2 || test_failed $LINENO
+cat "${in_lz}" "${in_lz}" | "${LZIP}" > out2 || test_failed $LINENO
-cmp in2 copy2 || test_failed $LINENO
+cmp in2 out2 || test_failed $LINENO
-rm -f copy2 || framework_failure
+rm -f out2 || framework_failure
 
-cat "${in_lz}" "${in_lz}" > copy2.lz || framework_failure
+cat "${in_lz}" "${in_lz}" > out2.lz || framework_failure
-printf "\ngarbage" >> copy2.lz || framework_failure
+printf "\ngarbage" >> out2.lz || framework_failure
-"${LZIP}" -d < copy2.lz > copy2 || test_failed $LINENO
+"${LZIP}" -d < out2.lz > out2 || test_failed $LINENO
-cmp in2 copy2 || test_failed $LINENO
+cmp in2 out2 || test_failed $LINENO
-rm -f in2 copy2 copy2.lz || framework_failure
+rm -f in2 out2 out2.lz || framework_failure
 
 printf "\ntesting bad input..."
 
@@ -90,9 +90,9 @@ rm -f in2.lz in3.lz trunc.lz || framework_failure
 cat "${in_lz}" > ingin.lz || framework_failure
 printf "g" >> ingin.lz || framework_failure
 cat "${in_lz}" >> ingin.lz || framework_failure
-"${LZIP}" -d < ingin.lz > copy || test_failed $LINENO
+"${LZIP}" -d < ingin.lz > out || test_failed $LINENO
-cmp "${in}" copy || test_failed $LINENO
+cmp "${in}" out || test_failed $LINENO
-rm -f copy ingin.lz || framework_failure
+rm -f out ingin.lz || framework_failure
 
 echo
 if [ ${fail} = 0 ] ; then