Merging upstream version 1.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 124 insertions, 74 deletions

diff --git a/COPYING b/COPYING
new file mode 100644
index 0000000..5b9d8b9
--- /dev/null
+++ b/COPYING
@@ -0,0 +1,17 @@
+    Lzd - Educational decompressor for the lzip format
+    Copyright (C) Antonio Diaz Diaz.
+
+    This program is free software. Redistribution and use in source and
+    binary forms, with or without modification, are permitted provided
+    that the following conditions are met:
+
+    1. Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+
+    2. Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
diff --git a/ChangeLog b/ChangeLog
index c7c931f..380d736 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2017-05-02  Antonio Diaz Diaz  <antonio@gnu.org>
+
+	* Version 1.0 released.
+	* lzd.cc: Minor code improvements.
+	* testsuite/check.sh: A POSIX shell is required to run the tests.
+
 2016-05-10  Antonio Diaz Diaz  <antonio@gnu.org>
 
 	* Version 0.9 released.
@@ -43,7 +49,7 @@
 	* Version 0.1 released.
 
 
-Copyright (C) 2013-2016 Antonio Diaz Diaz.
+Copyright (C) 2013-2017 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
diff --git a/INSTALL b/INSTALL
index dc2e623..c245516 100644
--- a/INSTALL
+++ b/INSTALL
@@ -50,7 +50,7 @@ After running 'configure', you can run 'make' and 'make install' as
 explained above.
 
 
-Copyright (C) 2013-2016 Antonio Diaz Diaz.
+Copyright (C) 2013-2017 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 42cdcc0..471ff4b 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -95,16 +95,17 @@ dist : doc
 	ln -sf $(VPATH) $(DISTNAME)
 	tar -Hustar --owner=root --group=root -cvf $(DISTNAME).tar \
 	  $(DISTNAME)/AUTHORS \
+	  $(DISTNAME)/COPYING \
 	  $(DISTNAME)/ChangeLog \
 	  $(DISTNAME)/INSTALL \
 	  $(DISTNAME)/Makefile.in \
 	  $(DISTNAME)/NEWS \
 	  $(DISTNAME)/README \
 	  $(DISTNAME)/configure \
+	  $(DISTNAME)/*.cc \
 	  $(DISTNAME)/testsuite/check.sh \
 	  $(DISTNAME)/testsuite/test.txt \
-	  $(DISTNAME)/testsuite/test.txt.lz \
-	  $(DISTNAME)/*.cc
+	  $(DISTNAME)/testsuite/test.txt.lz
 	rm -f $(DISTNAME)
 	lzip -v -9 $(DISTNAME).tar
 
diff --git a/NEWS b/NEWS
index 085da72..2f713df 100644
--- a/NEWS
+++ b/NEWS
@@ -1,4 +1,5 @@
-Changes in version 0.9:
+Changes in version 1.0:
 
-A configure warning happening on some shells when testing for g++ has
-been fixed.
+Minor code improvements have been made.
+
+The tests have been improved.
diff --git a/README b/README
index ae73fc1..e16763e 100644
--- a/README
+++ b/README
@@ -24,11 +24,11 @@ availability:
      merging of damaged copies of a file.
 
    * The lzip format is as simple as possible (but not simpler). The
-     lzip manual provides the 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.
+     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.
@@ -45,7 +45,7 @@ range encoding), and Igor Pavlov (for putting all the above together in
 LZMA).
 
 
-Copyright (C) 2013-2016 Antonio Diaz Diaz.
+Copyright (C) 2013-2017 Antonio Diaz Diaz.
 
 This file is free documentation: you have unlimited permission to copy,
 distribute and modify it.
diff --git a/configure b/configure
index 226e838..7499b98 100755
--- a/configure
+++ b/configure
@@ -1,12 +1,12 @@
 #! /bin/sh
 # configure script for Lzd - Educational decompressor for the lzip format
-# Copyright (C) 2013-2016 Antonio Diaz Diaz.
+# Copyright (C) 2013-2017 Antonio Diaz Diaz.
 #
 # This configure script is free software: you have unlimited permission
 # to copy, distribute and modify it.
 
 pkgname=lzd
-pkgversion=0.9
+pkgversion=1.0
 progname=lzd
 srctrigger=lzd.cc
 
@@ -26,11 +26,11 @@ CXXFLAGS='-Wall -W -O2'
 LDFLAGS=
 
 # checking whether we are using GNU C++.
-if /bin/sh -c "${CXX} --version" > /dev/null 2>&1 ; then true
-else
+/bin/sh -c "${CXX} --version" > /dev/null 2>&1 ||
+	{
 	CXX=c++
-	CXXFLAGS='-W -O2'
-fi
+	CXXFLAGS=-O2
+	}
 
 # Loop over all args
 args=
@@ -52,9 +52,12 @@ while [ $# != 0 ] ; do
 	# Process the options
 	case ${option} in
 	--help | -h)
-		echo "Usage: configure [options]"
+		echo "Usage: $0 [OPTION]... [VAR=VALUE]..."
+		echo
+		echo "To assign makefile variables (e.g., CXX, CXXFLAGS...), specify them as"
+		echo "arguments to configure in the form VAR=VALUE."
 		echo
-		echo "Options: [defaults in brackets]"
+		echo "Options and variables: [defaults in brackets]"
 		echo "  -h, --help            display this help and exit"
 		echo "  -V, --version         output version information and exit"
 		echo "  --srcdir=DIR          find the sources in DIR [. or ..]"
@@ -165,7 +168,7 @@ echo "LDFLAGS = ${LDFLAGS}"
 rm -f Makefile
 cat > Makefile << EOF
 # Makefile for Lzd - Educational decompressor for the lzip format
-# Copyright (C) 2013-2016 Antonio Diaz Diaz.
+# Copyright (C) 2013-2017 Antonio Diaz Diaz.
 # This file was generated automatically by configure. Don't edit.
 #
 # This Makefile is free software: you have unlimited permission
diff --git a/lzd.cc b/lzd.cc
index 56dce37..6fd536a 100644
--- a/lzd.cc
+++ b/lzd.cc
@@ -1,5 +1,5 @@
 /*  Lzd - Educational decompressor for the lzip format
-    Copyright (C) 2013-2016 Antonio Diaz Diaz.
+    Copyright (C) 2013-2017 Antonio Diaz Diaz.
 
     This program is free software. Redistribution and use in source and
     binary forms, with or without modification, are permitted provided
@@ -150,10 +150,10 @@ public:
 
   uint8_t get_byte() { return std::getc( stdin ); }
 
-  int decode( const int num_bits )
+  unsigned decode( const int num_bits )
     {
-    int symbol = 0;
-    for( int i = 0; i < num_bits; ++i )
+    unsigned symbol = 0;
+    for( int i = num_bits; i > 0; --i )
       {
       range >>= 1;
       symbol <<= 1;
@@ -164,9 +164,9 @@ public:
     return symbol;
     }
 
-  int decode_bit( Bit_model & bm )
+  unsigned decode_bit( Bit_model & bm )
     {
-    int symbol;
+    unsigned symbol;
     const uint32_t bound = ( range >> bit_model_total_bits ) * bm.probability;
     if( code < bound )
       {
@@ -186,18 +186,18 @@ public:
     return symbol;
     }
 
-  int decode_tree( Bit_model bm[], const int num_bits )
+  unsigned decode_tree( Bit_model bm[], const int num_bits )
     {
-    int symbol = 1;
+    unsigned symbol = 1;
     for( int i = 0; i < num_bits; ++i )
       symbol = ( symbol << 1 ) | decode_bit( bm[symbol] );
     return symbol - (1 << num_bits);
     }
 
-  int decode_tree_reversed( Bit_model bm[], const int num_bits )
+  unsigned decode_tree_reversed( Bit_model bm[], const int num_bits )
     {
-    int symbol = decode_tree( bm, num_bits );
-    int reversed_symbol = 0;
+    unsigned symbol = decode_tree( bm, num_bits );
+    unsigned reversed_symbol = 0;
     for( int i = 0; i < num_bits; ++i )
       {
       reversed_symbol = ( reversed_symbol << 1 ) | ( symbol & 1 );
@@ -206,14 +206,13 @@ public:
     return reversed_symbol;
     }
 
-  int decode_matched( Bit_model bm[], const int match_byte )
+  unsigned decode_matched( Bit_model bm[], const unsigned match_byte )
     {
-    Bit_model * const bm1 = bm + 0x100;
-    int symbol = 1;
+    unsigned symbol = 1;
     for( int i = 7; i >= 0; --i )
       {
-      const int match_bit = ( match_byte >> i ) & 1;
-      const int bit = decode_bit( bm1[(match_bit<<8)+symbol] );
+      const unsigned match_bit = ( match_byte >> i ) & 1;
+      const unsigned bit = decode_bit( bm[symbol+(match_bit<<8)+0x100] );
       symbol = ( symbol << 1 ) | bit;
       if( match_bit != bit )
         {
@@ -225,7 +224,7 @@ public:
     return symbol & 0xFF;
     }
 
-  int decode_len( Len_model & lm, const int pos_state )
+  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 );
@@ -253,9 +252,9 @@ class LZ_decoder
 
   uint8_t peek( const unsigned distance ) const
     {
-    unsigned i = pos - distance - 1;
-    if( pos <= distance ) i += dictionary_size;
-    return buffer[i];
+    if( pos > distance ) return buffer[pos - distance - 1];
+    if( pos_wrapped ) return buffer[dictionary_size + pos - distance - 1];
+    return 0;			// prev_byte of first byte
     }
 
   void put_byte( const uint8_t b )
@@ -274,7 +273,7 @@ public:
     stream_pos( 0 ),
     crc_( 0xFFFFFFFFU ),
     pos_wrapped( false )
-    { buffer[dictionary_size-1] = 0; }		// prev_byte of first byte
+    {}
 
   ~LZ_decoder() { delete[] buffer; }
 
@@ -312,13 +311,13 @@ bool LZ_decoder::decode_member()		// Returns false if error
   Bit_model bm_rep2[State::states];
   Bit_model bm_len[State::states][pos_states];
   Bit_model bm_dis_slot[len_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];
   Len_model match_len_model;
   Len_model rep_len_model;
-  unsigned rep0 = 0;			// rep[0-3] latest four distances
-  unsigned rep1 = 0;			// used for efficient coding of
-  unsigned rep2 = 0;			// repeated distances
+  unsigned rep0 = 0;		// rep[0-3] latest four distances
+  unsigned rep1 = 0;		// used for efficient coding of
+  unsigned rep2 = 0;		// repeated distances
   unsigned rep3 = 0;
   State state;
 
@@ -341,7 +340,12 @@ bool LZ_decoder::decode_member()		// Returns false if error
       int len;
       if( rdec.decode_bit( bm_rep[state()] ) != 0 )		// 2nd bit
         {
-        if( rdec.decode_bit( bm_rep0[state()] ) != 0 )		// 3rd bit
+        if( rdec.decode_bit( bm_rep0[state()] ) == 0 )		// 3rd bit
+          {
+          if( rdec.decode_bit( bm_len[state()][pos_state] ) == 0 ) // 4th bit
+            { state.set_short_rep(); put_byte( peek( rep0 ) ); continue; }
+          }
+        else
           {
           unsigned distance;
           if( rdec.decode_bit( bm_rep1[state()] ) == 0 )	// 4th bit
@@ -357,11 +361,6 @@ bool LZ_decoder::decode_member()		// Returns false if error
           rep1 = rep0;
           rep0 = distance;
           }
-        else
-          {
-          if( rdec.decode_bit( bm_len[state()][pos_state] ) == 0 ) // 4th bit
-            { state.set_short_rep(); put_byte( peek( rep0 ) ); continue; }
-          }
         state.set_rep();
         len = min_match_len + rdec.decode_len( rep_len_model, pos_state );
         }
@@ -370,15 +369,14 @@ bool LZ_decoder::decode_member()		// Returns false if error
         rep3 = rep2; rep2 = rep1; rep1 = rep0;
         len = min_match_len + rdec.decode_len( match_len_model, pos_state );
         const int len_state = std::min( len - min_match_len, len_states - 1 );
-        const int dis_slot =
-          rdec.decode_tree( bm_dis_slot[len_state], dis_slot_bits );
-        if( dis_slot < start_dis_model ) rep0 = dis_slot;
-        else
+        rep0 = rdec.decode_tree( bm_dis_slot[len_state], dis_slot_bits );
+        if( rep0 >= start_dis_model )
           {
+          const unsigned dis_slot = rep0;
           const int direct_bits = ( dis_slot >> 1 ) - 1;
           rep0 = ( 2 | ( dis_slot & 1 ) ) << direct_bits;
           if( dis_slot < end_dis_model )
-            rep0 += rdec.decode_tree_reversed( bm_dis + rep0 - dis_slot - 1,
+            rep0 += rdec.decode_tree_reversed( bm_dis + ( rep0 - dis_slot ),
                                                direct_bits );
           else
             {
@@ -414,7 +412,7 @@ int main( const int argc, const char * const argv[] )
                  "It is not safe to use lzd for any real work.\n"
                  "\nUsage: %s < file.lz > file\n", argv[0] );
     std::printf( "Lzd decompresses from standard input to standard output.\n"
-                 "\nCopyright (C) 2016 Antonio Diaz Diaz.\n"
+                 "\nCopyright (C) 2017 Antonio Diaz Diaz.\n"
                  "This is free software: you are free to change and redistribute it.\n"
                  "There is NO WARRANTY, to the extent permitted by law.\n"
                  "Report bugs to lzip-bug@nongnu.org\n"
@@ -429,7 +427,7 @@ int main( const int argc, const char * const argv[] )
 
   for( bool first_member = true; ; first_member = false )
     {
-    File_header header;
+    File_header header;				// verify header
     for( int i = 0; i < 6; ++i ) header[i] = std::getc( stdin );
     if( std::feof( stdin ) || std::memcmp( header, "LZIP\x01", 5 ) != 0 )
       {
@@ -444,11 +442,11 @@ int main( const int argc, const char * const argv[] )
       { std::fputs( "Invalid dictionary size in member header.\n", stderr );
         return 2; }
 
-    LZ_decoder decoder( dict_size );
+    LZ_decoder decoder( dict_size );		// decode LZMA stream
     if( !decoder.decode_member() )
       { std::fputs( "Data error\n", stderr ); return 2; }
 
-    File_trailer trailer;
+    File_trailer trailer;			// verify trailer
     for( int i = 0; i < 20; ++i ) trailer[i] = std::getc( stdin );
     unsigned crc = 0;
     for( int i = 3; i >= 0; --i ) { crc <<= 8; crc += trailer[i]; }
diff --git a/testsuite/check.sh b/testsuite/check.sh
index f03377f..71cabc4 100755
--- a/testsuite/check.sh
+++ b/testsuite/check.sh
@@ -1,6 +1,6 @@
 #! /bin/sh
 # check script for Lzd - Educational decompressor for lzip files
-# Copyright (C) 2013-2016 Antonio Diaz Diaz.
+# Copyright (C) 2013-2017 Antonio Diaz Diaz.
 #
 # This script is free software: you have unlimited permission
 # to copy, distribute and modify it.
@@ -17,6 +17,13 @@ if [ ! -f "${LZIP}" ] || [ ! -x "${LZIP}" ] ; then
 	exit 1
 fi
 
+[ -e "${LZIP}" ] 2> /dev/null ||
+	{
+	echo "$0: a POSIX shell is required to run the tests"
+	echo "Try bash -c \"$0 $1 $2\""
+	exit 1
+	}
+
 if [ -d tmp ] ; then rm -rf tmp ; fi
 mkdir tmp
 cd "${objdir}"/tmp || framework_failure
@@ -24,24 +31,41 @@ cd "${objdir}"/tmp || framework_failure
 in="${testdir}"/test.txt
 in_lz="${testdir}"/test.txt.lz
 fail=0
+test_failed() { fail=1 ; printf " $1" ; [ -z "$2" ] || printf "($2)" ; }
 
 printf "testing lzd-%s..." "$2"
 
 "${LZIP}" < "${in}" 2> /dev/null
-if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
-dd if="${in_lz}" bs=1 count=6 2> /dev/null | "${LZIP}" 2> /dev/null
-if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
-dd if="${in_lz}" bs=1 count=20 2> /dev/null | "${LZIP}" > /dev/null 2>&1
-if [ $? = 2 ] ; then printf . ; else printf - ; fail=1 ; fi
+[ $? = 2 ] || test_failed $LINENO
 
-"${LZIP}" < "${in_lz}" > copy || fail=1
-cmp "${in}" copy || fail=1
-printf .
+"${LZIP}" < "${in_lz}" > copy || test_failed $LINENO
+cmp "${in}" copy || test_failed $LINENO
 
 cat "${in}" "${in}" > in2 || framework_failure
-cat "${in_lz}" "${in_lz}" | "${LZIP}" > copy2 || fail=1
-cmp in2 copy2 || fail=1
-printf .
+cat "${in_lz}" "${in_lz}" > in2.lz || framework_failure
+"${LZIP}" < in2.lz > copy2 || test_failed $LINENO
+cmp in2 copy2 || test_failed $LINENO
+
+printf "\ntesting bad input..."
+
+cat "${in_lz}" "${in_lz}" "${in_lz}" > in3.lz || framework_failure
+if dd if=in3.lz of=trunc.lz bs=14752 count=1 2> /dev/null &&
+   [ -e trunc.lz ] && cmp in2.lz trunc.lz > /dev/null 2>&1 ; then
+# can't detect truncated header of non-first member
+	for i in 6 20 14734 14758 ; do
+		dd if=in3.lz of=trunc.lz bs=$i count=1 2> /dev/null
+		"${LZIP}" < trunc.lz > out 2> /dev/null
+		[ $? = 2 ] || test_failed $LINENO $i
+	done
+else
+	printf "\nwarning: skipping truncation test: 'dd' does not work on your system."
+fi
+
+cat "${in_lz}" > ingin.lz || framework_failure
+printf "g" >> ingin.lz || framework_failure
+cat "${in_lz}" >> ingin.lz || framework_failure
+"${LZIP}" < ingin.lz > copy || test_failed $LINENO
+cmp "${in}" copy || test_failed $LINENO
 
 echo
 if [ ${fail} = 0 ] ; then
diff --git a/testsuite/test.txt.lz b/testsuite/test.txt.lz
index 41d2e39..22cea6e 100644
--- a/testsuite/test.txt.lz
+++ b/testsuite/test.txt.lz