Merging upstream version 1.11.

Signed-off-by: Daniel Baumann <mail@daniel-baumann.ch>

1 files changed, 166 insertions, 90 deletions

diff --git a/main.cc b/main.cc
index 4191d6b..193f4ac 100644
--- a/main.cc
+++ b/main.cc
@@ -1,4 +1,4 @@
-/*  Lzip - A data compressor based on the LZMA algorithm
+/*  Lzip - Data compressor based on the LZMA algorithm
     Copyright (C) 2008, 2009, 2010 Antonio Diaz Diaz.
 
     This program is free software: you can redistribute it and/or modify
@@ -37,11 +37,26 @@
 #include <unistd.h>
 #include <utime.h>
 #include <sys/stat.h>
+#if defined(__MSVCRT__)
+#include <io.h>
+#define fchmod(x,y) 0
+#define fchown(x,y,z) 0
+#define SIGHUP SIGTERM
+#define S_ISSOCK(x) 0
+#define S_IRGRP 0
+#define S_IWGRP 0
+#define S_IROTH 0
+#define S_IWOTH 0
+#endif
+#if defined(__OS2__)
+#include <io.h>
+#endif
 
 #include "arg_parser.h"
 #include "lzip.h"
 #include "decoder.h"
 #include "encoder.h"
+#include "fast_encoder.h"
 
 #if CHAR_BIT != 8
 #error "Environments where CHAR_BIT != 8 are not supported."
@@ -82,17 +97,18 @@ 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;
+int verbosity = 0;
 mode_t outfd_mode = S_IRUSR | S_IWUSR;
 bool delete_output_on_interrupt = false;
 
 
 void show_help() throw()
   {
-  std::printf( "%s - A data compressor based on the LZMA algorithm.\n", Program_name );
+  std::printf( "%s - Data compressor based on the LZMA algorithm.\n", Program_name );
   std::printf( "\nUsage: %s [options] [files]\n", invocation_name );
   std::printf( "\nOptions:\n" );
   std::printf( "  -h, --help                 display this help and exit\n" );
@@ -102,15 +118,15 @@ 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" );
   std::printf( "  -S, --volume-size=<n>      set volume size limit in bytes\n" );
   std::printf( "  -t, --test                 test compressed file integrity\n" );
   std::printf( "  -v, --verbose              be verbose (a 2nd -v gives more)\n" );
-  std::printf( "  -1 .. -9                   set compression level [default 6]\n" );
-  std::printf( "      --fast                 alias for -1\n" );
+  std::printf( "  -0 .. -9                   set compression level [default 6]\n" );
+  std::printf( "      --fast                 alias for -0\n" );
   std::printf( "      --best                 alias for -9\n" );
   std::printf( "If no file names are given, %s compresses or decompresses\n", program_name );
   std::printf( "from standard input to standard output.\n" );
@@ -131,26 +147,19 @@ 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 };
+  static char buf[buf_size];
   const char *p = "";
-  limit = std::max( 999LL, std::min( 999999LL, limit ) );
+  const int factor = 1024;
 
-  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;
   }
 
@@ -164,7 +173,7 @@ 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 );
     }
 
@@ -194,7 +203,7 @@ 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 )
@@ -206,7 +215,7 @@ 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;
@@ -245,7 +254,7 @@ 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 );
     }
@@ -267,7 +276,7 @@ int open_instream( const std::string & name, struct stat * const in_statsp,
                         S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) )
         {
         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" );
         close( infd );
@@ -301,7 +310,7 @@ 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() );
   }
 
@@ -312,18 +321,14 @@ 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 );
   }
@@ -331,7 +336,7 @@ 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;
@@ -368,8 +373,9 @@ 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 ) error = true;
-    else (void)fchown( outfd, in_statsp->st_uid, in_statsp->st_gid );
+    if( fchmod( outfd, in_statsp->st_mode ) != 0 ||
+        ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 &&
+          errno != EPERM ) ) error = true;
     // fchown will in many cases return with EPERM, which can be safely ignored.
     }
   if( close( outfd ) == 0 ) outfd = -1;
@@ -385,7 +391,7 @@ 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 );
     }
   }
@@ -429,7 +435,7 @@ int compress( const long long member_size, const long long volume_size,
       const long long size =
         std::min( member_size, volume_size - partial_volume_size );
       if( !encoder.encode_member( size ) )
-        { pp(); show_error( "read error", errno ); retval = 1; break; }
+        { pp( "Encoder error" ); retval = 1; break; }
       in_size += matchfinder.data_position();
       out_size += encoder.member_position();
       if( matchfinder.finished() ) break;
@@ -441,20 +447,18 @@ int compress( const long long member_size, const long long volume_size,
           {
           close_and_set_permissions( in_statsp );
           if( !next_filename() )
-            { pp(); show_error( "too many volume files" ); retval = 1; break; }
+            { pp( "Too many volume files" ); retval = 1; break; }
           if( !open_outstream( true ) ) { retval = 1; break; }
           delete_output_on_interrupt = true;
           }
         }
-      if( !matchfinder.reset() )
-        { pp(); show_error( "can't reset matchfinder", errno );
-          retval = 1; break; }
+      matchfinder.reset();
       }
 
     if( retval == 0 && verbosity >= 1 )
       {
       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",
@@ -466,10 +470,73 @@ int compress( const long long member_size, const long long volume_size,
     }
   catch( std::bad_alloc )
     {
-    pp( "not enough memory. Try a smaller dictionary size" );
+    pp( "Not enough memory. Try a smaller dictionary size" );
     retval = 1;
     }
-  catch( Error e ) { pp(); show_error( e.s, errno ); retval = 1; }
+  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
+  return retval;
+  }
+
+
+int fcompress( const long long member_size, const long long volume_size,
+               const int infd,
+               const Pretty_print & pp, const struct stat * const in_statsp )
+  {
+  if( verbosity >= 1 ) pp();
+  File_header header;
+  header.set_magic();
+  int retval = 0;
+
+  try {
+    Fmatchfinder fmatchfinder( infd );
+    header.dictionary_size( fmatchfinder.dictionary_size() );
+
+    long long in_size = 0, out_size = 0, partial_volume_size = 0;
+    while( true )		// encode one member per iteration
+      {
+      FLZ_encoder encoder( fmatchfinder, header, outfd );
+      const long long size =
+        std::min( member_size, volume_size - partial_volume_size );
+      if( !encoder.encode_member( size ) )
+        { pp( "Encoder error" ); retval = 1; break; }
+      in_size += fmatchfinder.data_position();
+      out_size += encoder.member_position();
+      if( fmatchfinder.finished() ) break;
+      partial_volume_size += encoder.member_position();
+      if( partial_volume_size >= volume_size - min_dictionary_size )
+        {
+        partial_volume_size = 0;
+        if( delete_output_on_interrupt )
+          {
+          close_and_set_permissions( in_statsp );
+          if( !next_filename() )
+            { pp( "Too many volume files" ); retval = 1; break; }
+          if( !open_outstream( true ) ) { retval = 1; break; }
+          delete_output_on_interrupt = true;
+          }
+        }
+      fmatchfinder.reset();
+      }
+
+    if( retval == 0 && verbosity >= 1 )
+      {
+      if( in_size <= 0 || out_size <= 0 )
+        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",
+                      (double)in_size / out_size,
+                      ( 8.0 * out_size ) / in_size,
+                      100.0 * ( 1.0 - ( (double)out_size / in_size ) ),
+                      in_size, out_size );
+      }
+    }
+  catch( std::bad_alloc )
+    {
+    pp( "Not enough memory. Try a smaller dictionary size" );
+    retval = 1;
+    }
+  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
   return retval;
   }
 
@@ -489,26 +556,26 @@ int decompress( const int infd, const Pretty_print & pp, const bool testing )
         header.data[i] = rdec.get_byte();
       if( rdec.finished() )			// End Of File
         {
-        if( first_member ) { pp( "error reading member header" ); retval = 1; }
+        if( first_member ) { pp( "Error reading member header" ); retval = 1; }
         break;
         }
       if( !header.verify_magic() )
         {
         if( !first_member ) break;		// trailing garbage
-        pp( "bad magic number (file not in lzip format)" );
+        pp( "Bad magic number (file not in lzip format)" );
         retval = 2; break;
         }
       if( !header.verify_version() )
         {
         if( verbosity >= 0 )
           { pp();
-            std::fprintf( stderr, "version %d member format not supported, newer %s needed.\n",
-                          header.version(), program_name ); }
+            std::fprintf( stderr, "Version %d member format not supported.\n",
+                          header.version() ); }
         retval = 2; break;
         }
       if( header.dictionary_size() < min_dictionary_size ||
           header.dictionary_size() > max_dictionary_size )
-        { pp( "invalid dictionary size in member header" ); retval = 2; break; }
+        { pp( "Invalid dictionary size in member header" ); retval = 2; break; }
 
       if( verbosity >= 1 )
         {
@@ -528,10 +595,10 @@ int decompress( const int infd, const Pretty_print & pp, const bool testing )
           {
           pp();
           if( result == 2 )
-            std::fprintf( stderr, "file ends unexpectedly at pos %lld\n",
+            std::fprintf( stderr, "File ends unexpectedly at pos %lld\n",
                           partial_file_pos );
           else
-            std::fprintf( stderr, "decoder error at pos %lld\n",
+            std::fprintf( stderr, "Decoder error at pos %lld\n",
                           partial_file_pos );
           }
         retval = 2; break;
@@ -543,10 +610,10 @@ int decompress( const int infd, const Pretty_print & pp, const bool testing )
     }
   catch( std::bad_alloc )
     {
-    pp( "not enough memory. Find a machine with more memory" );
+    pp( "Not enough memory. Find a machine with more memory" );
     retval = 1;
     }
-  catch( Error e ) { pp(); show_error( e.s, errno ); retval = 1; }
+  catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; }
   return retval;
   }
 
@@ -568,12 +635,9 @@ void set_signals() throw()
 } // end namespace
 
 
-int verbosity = 0;
-
-
 void Pretty_print::operator()( const char * const msg ) const throw()
   {
-  if( verbosity >= 0 )
+  if( verbosity_ >= 0 )
     {
     if( first_post )
       {
@@ -592,22 +656,23 @@ 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() );
+  std::fprintf( stderr, "%s: internal error: %s.\n", program_name, msg );
   std::exit( 3 );
   }
 
@@ -655,15 +720,15 @@ 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 << 16,  16 },		// -0 entry values not used
+    { 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;
@@ -673,16 +738,16 @@ int main( const int argc, const char * const argv[] )
   bool force = false;
   bool keep_input_files = false;
   bool to_stdout = false;
+  bool zero = false;
   std::string input_filename;
   std::string default_output_filename;
   std::vector< std::string > filenames;
   invocation_name = argv[0];
-//  std::setvbuf( stderr, 0, _IONBF, 0 );
 
   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  },
@@ -720,9 +785,11 @@ int main( const int argc, const char * const argv[] )
     const char * const arg = parser.argument( argind ).c_str();
     switch( code )
       {
-      case '0': case '1': case '2': case '3': case '4':
+      case '0': zero = true; break;
+      case '1': case '2': case '3': case '4':
       case '5': case '6': case '7': case '8': case '9':
-                encoder_options = option_mapping[code-'0']; break;
+                encoder_options = option_mapping[code-'0'];
+                zero = false; break;
       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;
@@ -731,11 +798,12 @@ int main( const int argc, const char * const argv[] )
       case 'h': show_help(); return 0;
       case 'k': keep_input_files = true; break;
       case 'm': encoder_options.match_len_limit =
-                  getnum( arg, 0, min_match_len_limit, max_match_len ); break;
+                  getnum( arg, 0, min_match_len_limit, max_match_len );
+                zero = false; break;
       case 'o': default_output_filename = arg; break;
       case 'q': verbosity = -1; break;
       case 's': encoder_options.dictionary_size = get_dict_size( arg );
-                break;
+                zero = false; break;
       case 'S': volume_size = getnum( arg, 0, 100000, LLONG_MAX / 2 ); break;
       case 't': program_mode = m_test; break;
       case 'v': if( verbosity < 4 ) ++verbosity; break;
@@ -744,6 +812,11 @@ int main( const int argc, const char * const argv[] )
       }
     }
 
+#if defined(__MSVCRT__) || defined(__OS2__)
+  _setmode( STDIN_FILENO, O_BINARY );
+  _setmode( STDOUT_FILENO, O_BINARY );
+#endif
+
   bool filenames_given = false;
   for( ; argind < parser.arguments(); ++argind )
     {
@@ -756,7 +829,7 @@ int main( const int argc, const char * const argv[] )
       ( filenames_given || default_output_filename.size() ) )
     set_signals();
 
-  Pretty_print pp( filenames );
+  Pretty_print pp( filenames, verbosity );
   if( program_mode == m_test )
     outfd = -1;
   else if( program_mode == m_compress )
@@ -828,8 +901,13 @@ int main( const int argc, const char * const argv[] )
     pp.set_name( input_filename );
     int tmp = 0;
     if( program_mode == m_compress )
-      tmp = compress( member_size, volume_size, encoder_options, infd,
-                      pp, in_statsp );
+      {
+      if( zero )
+        tmp = fcompress( member_size, volume_size, infd, pp, in_statsp );
+      else
+        tmp = compress( member_size, volume_size, encoder_options, infd,
+                        pp, in_statsp );
+      }
     else
       tmp = decompress( infd, pp, program_mode == m_test );
     if( tmp > retval ) retval = tmp;
@@ -846,9 +924,7 @@ 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;