Merging upstream version 1.5.

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

1 files changed, 74 insertions, 70 deletions

diff --git a/main.cc b/main.cc
index a2c1287..676f7d8 100644
--- a/main.cc
+++ b/main.cc
@@ -1,6 +1,6 @@
 /*  Plzip - Parallel compressor compatible with lzip
     Copyright (C) 2009 Laszlo Ersek.
-    Copyright (C) 2009-2015 Antonio Diaz Diaz.
+    Copyright (C) 2009-2016 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
@@ -67,12 +67,13 @@
 #error "Environments where CHAR_BIT != 8 are not supported."
 #endif
 
+int verbosity = 0;
 
 namespace {
 
 const char * const Program_name = "Plzip";
 const char * const program_name = "plzip";
-const char * const program_year = "2015";
+const char * const program_year = "2016";
 const char * invocation_name = 0;
 
 struct { const char * from; const char * to; } const known_extensions[] = {
@@ -90,9 +91,6 @@ enum Mode { m_compress, m_decompress, m_test };
 
 std::string output_filename;
 int outfd = -1;
-const mode_t usr_rw = S_IRUSR | S_IWUSR;
-const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
-mode_t outfd_mode = usr_rw;
 bool delete_output_on_interrupt = false;
 
 
@@ -103,15 +101,16 @@ void show_help( const long num_online )
   std::printf( "\nOptions:\n"
                "  -h, --help                     display this help and exit\n"
                "  -V, --version                  output version information and exit\n"
+               "  -a, --trailing-error           exit with error status if trailing data\n"
                "  -B, --data-size=<bytes>        set size of input data blocks [2x8=16 MiB]\n"
-               "  -c, --stdout                   send output to standard output\n"
+               "  -c, --stdout                   write to standard output, keep input files\n"
                "  -d, --decompress               decompress\n"
                "  -f, --force                    overwrite existing output files\n"
                "  -F, --recompress               force re-compression of compressed files\n"
                "  -k, --keep                     keep (don't delete) input files\n"
                "  -m, --match-length=<bytes>     set match length limit in bytes [36]\n"
                "  -n, --threads=<n>              set number of (de)compression threads [%ld]\n"
-               "  -o, --output=<file>            if reading stdin, place the output into <file>\n"
+               "  -o, --output=<file>            if reading standard input, write to <file>\n"
                "  -q, --quiet                    suppress all messages\n"
                "  -s, --dictionary-size=<bytes>  set dictionary size limit in bytes [8 MiB]\n"
                "  -t, --test                     test compressed file integrity\n"
@@ -123,13 +122,15 @@ void show_help( const long num_online )
     {
     std::printf( "  -D, --debug=<level>        (0-1) print debug statistics to stderr\n" );
     }
-  std::printf( "If no file names are given, plzip compresses or decompresses\n"
-               "from standard input to standard output.\n"
+  std::printf( "If no file names are given, or if a file is '-', plzip compresses or\n"
+               "decompresses from standard input to standard output.\n"
                "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n"
                "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n"
-               "The bidimensional parameter space of LZMA can't be mapped to a linear\n"
+               "Dictionary sizes 12 to 29 are interpreted as powers of two, meaning 2^12\n"
+               "to 2^29 bytes.\n"
+               "\nThe bidimensional parameter space of LZMA can't be mapped to a linear\n"
                "scale optimal for all files. If your files are large, very repetitive,\n"
-               "etc, you may need to use the --match-length and --dictionary-size\n"
+               "etc, you may need to use the --dictionary-size and --match-length\n"
                "options directly to achieve optimal performance.\n"
                "\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
                "not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or\n"
@@ -190,11 +191,9 @@ unsigned long long getnum( const char * const ptr,
   if( !errno && tail[0] )
     {
     const int factor = ( tail[1] == 'i' ) ? 1024 : 1000;
-    int exponent = 0;
-    bool bad_multiplier = false;
+    int exponent = 0;				// 0 = bad multiplier
     switch( tail[0] )
       {
-      case ' ': break;
       case 'Y': exponent = 8; break;
       case 'Z': exponent = 7; break;
       case 'E': exponent = 6; break;
@@ -202,13 +201,10 @@ unsigned long long getnum( const char * const ptr,
       case 'T': exponent = 4; break;
       case 'G': exponent = 3; break;
       case 'M': exponent = 2; break;
-      case 'K': if( factor == 1024 ) exponent = 1; else bad_multiplier = true;
-                break;
-      case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true;
-                break;
-      default : bad_multiplier = true;
+      case 'K': if( factor == 1024 ) exponent = 1; break;
+      case 'k': if( factor == 1000 ) exponent = 1; break;
       }
-    if( bad_multiplier )
+    if( exponent <= 0 )
       {
       show_error( "Bad multiplier in numerical argument.", 0, true );
       std::exit( 1 );
@@ -238,7 +234,7 @@ int get_dict_size( const char * const arg )
     return ( 1 << bits );
   int dictionary_size = getnum( arg, LZ_min_dictionary_size(),
                                      LZ_max_dictionary_size() );
-  if( dictionary_size == 65535 ) ++dictionary_size;
+  if( dictionary_size == 65535 ) ++dictionary_size;	// no fast encoder
   return dictionary_size;
   }
 
@@ -283,7 +279,7 @@ int open_instream( const char * const name, struct stat * const in_statsp,
       const bool can_read = ( i == 0 &&
                               ( S_ISBLK( mode ) || S_ISCHR( mode ) ||
                                 S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
-      const bool no_ofile = to_stdout || program_mode == m_test;
+      const bool no_ofile = ( to_stdout || program_mode == m_test );
       if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || !no_ofile ) ) )
         {
         if( verbosity >= 0 )
@@ -326,13 +322,17 @@ void set_d_outname( const std::string & name, const int i )
   }
 
 
-bool open_outstream( const bool force )
+bool open_outstream( const bool force, const bool from_stdin )
   {
+  const mode_t usr_rw = S_IRUSR | S_IWUSR;
+  const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
+  const mode_t outfd_mode = from_stdin ? all_rw : usr_rw;
   int flags = O_CREAT | O_WRONLY | O_BINARY;
   if( force ) flags |= O_TRUNC; else flags |= O_EXCL;
 
   outfd = open( output_filename.c_str(), flags, outfd_mode );
-  if( outfd < 0 && verbosity >= 0 )
+  if( outfd >= 0 ) delete_output_on_interrupt = true;
+  else if( verbosity >= 0 )
     {
     if( errno == EEXIST )
       std::fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n",
@@ -403,7 +403,11 @@ void close_and_set_permissions( const struct stat * const in_statsp )
           fchmod( outfd, mode & ~( S_ISUID | S_ISGID | S_ISVTX ) ) != 0 )
         warning = true;
     }
-  if( close( outfd ) != 0 ) cleanup_and_fail( 1 );
+  if( close( outfd ) != 0 )
+    {
+    show_error( "Error closing output file", errno );
+    cleanup_and_fail( 1 );
+    }
   outfd = -1;
   delete_output_on_interrupt = false;
   if( in_statsp )
@@ -435,24 +439,18 @@ void set_signals()
 } // end namespace
 
 
-int verbosity = 0;
-
-
 void show_error( const char * const msg, const int errcode, const bool help )
   {
-  if( verbosity >= 0 )
+  if( verbosity < 0 ) return;
+  if( msg && msg[0] )
     {
-    if( msg && msg[0] )
-      {
-      std::fprintf( stderr, "%s: %s", program_name, msg );
-      if( errcode > 0 )
-        std::fprintf( stderr, ": %s", std::strerror( errcode ) );
-      std::fputc( '\n', stderr );
-      }
-    if( help )
-      std::fprintf( stderr, "Try '%s --help' for more information.\n",
-                    invocation_name );
+    std::fprintf( stderr, "%s: %s", program_name, msg );
+    if( errcode > 0 ) std::fprintf( stderr, ": %s", std::strerror( errcode ) );
+    std::fputc( '\n', stderr );
     }
+  if( help )
+    std::fprintf( stderr, "Try '%s --help' for more information.\n",
+                  invocation_name );
   }
 
 
@@ -473,20 +471,18 @@ void show_progress( const int packet_size,
   static const Pretty_print * pp = 0;
   static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER;
 
-  if( verbosity >= 2 )
+  if( verbosity < 2 ) return;
+  if( p )					// initialize static vars
+    { csize = cfile_size; pos = 0; pp = p; }
+  if( pp )
     {
-    if( p )					// initialize static vars
-      { csize = cfile_size; pos = 0; pp = p; }
-    if( pp )
-      {
-      xlock( &mutex );
-      pos += packet_size;
-      if( csize > 0 )
-        std::fprintf( stderr, "%4llu%%", pos / csize );
-      std::fprintf( stderr, "  %.1f MB\r", pos / 1000000.0 );
-      pp->reset(); (*pp)();			// restore cursor position
-      xunlock( &mutex );
-      }
+    xlock( &mutex );
+    pos += packet_size;
+    if( csize > 0 )
+      std::fprintf( stderr, "%4llu%%", pos / csize );
+    std::fprintf( stderr, "  %.1f MB\r", pos / 1000000.0 );
+    pp->reset(); (*pp)();			// restore cursor position
+    xunlock( &mutex );
     }
   }
 
@@ -497,7 +493,7 @@ int main( const int argc, const char * const argv[] )
      to the corresponding LZMA compression modes. */
   const Lzma_options option_mapping[] =
     {
-    {   65535,  16 },		// -0
+    {   65535,  16 },		// -0 (65535,16 chooses fast encoder)
     { 1 << 20,   5 },		// -1
     { 3 << 19,   6 },		// -2
     { 1 << 21,   8 },		// -3
@@ -517,13 +513,15 @@ int main( const int argc, const char * const argv[] )
   int num_workers = 0;		// start this many worker threads
   Mode program_mode = m_compress;
   bool force = false;
+  bool ignore_trailing = true;
   bool keep_input_files = false;
   bool recompress = false;
   bool to_stdout = false;
   invocation_name = argv[0];
 
-  if( LZ_version()[0] != LZ_version_string[0] )
-    internal_error( "bad library version." );
+  if( LZ_version()[0] < '1' )
+    { show_error( "Bad library version. At least lzlib 1.0 is required." );
+      return 1; }
 
   const long num_online = std::max( 1L, sysconf( _SC_NPROCESSORS_ONLN ) );
   long max_workers = sysconf( _SC_THREAD_THREADS_MAX );
@@ -542,6 +540,7 @@ int main( const int argc, const char * const argv[] )
     { '7',  0,                Arg_parser::no  },
     { '8',  0,                Arg_parser::no  },
     { '9', "best",            Arg_parser::no  },
+    { 'a', "trailing-error",  Arg_parser::no  },
     { 'b', "member-size",     Arg_parser::yes },
     { 'B', "data-size",       Arg_parser::yes },
     { 'c', "stdout",          Arg_parser::no  },
@@ -572,28 +571,30 @@ int main( const int argc, const char * const argv[] )
     const int code = parser.code( argind );
     if( !code ) break;					// no more options
     const std::string & arg = parser.argument( argind );
+    const char * const ptr = arg.c_str();
     switch( code )
       {
       case '0': 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;
+      case 'a': ignore_trailing = false; break;
       case 'b': break;
-      case 'B': data_size = getnum( arg.c_str(), 2 * LZ_min_dictionary_size(),
+      case 'B': data_size = getnum( ptr, 2 * LZ_min_dictionary_size(),
                                     2 * LZ_max_dictionary_size() ); break;
       case 'c': to_stdout = true; break;
       case 'd': program_mode = m_decompress; break;
-      case 'D': debug_level = getnum( arg.c_str(), 0, 3 ); break;
+      case 'D': debug_level = getnum( ptr, 0, 3 ); break;
       case 'f': force = true; break;
       case 'F': recompress = true; break;
       case 'h': show_help( num_online ); return 0;
       case 'k': keep_input_files = true; break;
       case 'm': encoder_options.match_len_limit =
-                  getnum( arg.c_str(), LZ_min_match_len_limit(),
-                                       LZ_max_match_len_limit() ); break;
-      case 'n': num_workers = getnum( arg.c_str(), 1, max_workers ); break;
+                  getnum( ptr, LZ_min_match_len_limit(),
+                               LZ_max_match_len_limit() ); break;
+      case 'n': num_workers = getnum( ptr, 1, max_workers ); break;
       case 'o': default_output_filename = arg; break;
       case 'q': verbosity = -1; break;
-      case 's': encoder_options.dictionary_size = get_dict_size( arg.c_str() );
+      case 's': encoder_options.dictionary_size = get_dict_size( ptr );
                 break;
       case 'S': break;
       case 't': program_mode = m_test; break;
@@ -637,9 +638,10 @@ 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 );
 
   int retval = 0;
+  bool stdin_used = false;
   for( unsigned i = 0; i < filenames.size(); ++i )
     {
     struct stat in_stats;
@@ -647,6 +649,7 @@ int main( const int argc, const char * const argv[] )
 
     if( filenames[i].empty() || filenames[i] == "-" )
       {
+      if( stdin_used ) continue; else stdin_used = true;
       input_filename.clear();
       infd = STDIN_FILENO;
       if( program_mode != m_test )
@@ -658,8 +661,7 @@ int main( const int argc, const char * const argv[] )
           if( program_mode == m_compress )
             set_c_outname( default_output_filename );
           else output_filename = default_output_filename;
-          outfd_mode = all_rw;
-          if( !open_outstream( force ) )
+          if( !open_outstream( force, true ) )
             {
             if( retval < 1 ) retval = 1;
             close( infd ); infd = -1;
@@ -683,8 +685,7 @@ int main( const int argc, const char * const argv[] )
           if( program_mode == m_compress )
             set_c_outname( input_filename );
           else set_d_outname( input_filename, eindex );
-          outfd_mode = usr_rw;
-          if( !open_outstream( force ) )
+          if( !open_outstream( force, false ) )
             {
             if( retval < 1 ) retval = 1;
             close( infd ); infd = -1;
@@ -694,10 +695,12 @@ int main( const int argc, const char * const argv[] )
         }
       }
 
-    if( !check_tty( infd, program_mode ) ) return 1;
+    if( !check_tty( infd, program_mode ) )
+      {
+      if( retval < 1 ) retval = 1;
+      cleanup_and_fail( retval );
+      }
 
-    if( output_filename.size() && !to_stdout && program_mode != m_test )
-      delete_output_on_interrupt = true;
     const struct stat * const in_statsp = input_filename.size() ? &in_stats : 0;
     const bool infd_isreg = in_statsp && S_ISREG( in_statsp->st_mode );
     pp.set_name( input_filename );
@@ -711,7 +714,8 @@ int main( const int argc, const char * const argv[] )
                       num_workers, infd, outfd, pp, debug_level );
       }
     else
-      tmp = decompress( num_workers, infd, outfd, pp, debug_level, infd_isreg );
+      tmp = decompress( num_workers, infd, outfd, pp, debug_level,
+                        ignore_trailing, infd_isreg );
     if( tmp > retval ) retval = tmp;
     if( tmp && program_mode != m_test ) cleanup_and_fail( retval );