Merging upstream version 0.6.

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

1 files changed, 72 insertions, 46 deletions

diff --git a/main.cc b/main.cc
index dc21a9a..17ec3ee 100644
--- a/main.cc
+++ b/main.cc
@@ -34,20 +34,20 @@
 #include <string>
 #include <vector>
 #include <fcntl.h>
+#include <inttypes.h>
 #include <pthread.h>
-#include <stdint.h>
 #include <unistd.h>
 #include <utime.h>
 #include <sys/stat.h>
 #include <lzlib.h>
 
-#if CHAR_BIT != 8
-#  error "Environments where CHAR_BIT != 8 are not supported."
-#endif
-
 #include "arg_parser.h"
 #include "plzip.h"
 
+#if CHAR_BIT != 8
+#error "Environments where CHAR_BIT != 8 are not supported."
+#endif
+
 #ifndef LLONG_MAX
 #define LLONG_MAX  0x7FFFFFFFFFFFFFFFLL
 #endif
@@ -77,7 +77,7 @@ struct { const char * from; const char * to; } const known_extensions[] = {
   { ".tlz", ".tar" },
   { 0,      0      } };
 
-struct lzma_options
+struct Lzma_options
   {
   int dictionary_size;		// 4KiB..512MiB
   int match_len_limit;		// 5..273
@@ -87,6 +87,7 @@ enum Mode { m_compress = 0, m_decompress, m_test };
 
 std::string output_filename;
 int outfd = -1;
+mode_t outfd_mode = S_IRUSR | S_IWUSR;
 bool delete_output_on_interrupt = false;
 pthread_t main_thread;
 pid_t main_thread_pid;
@@ -99,7 +100,6 @@ void show_help() throw()
   std::printf( "\nOptions:\n" );
   std::printf( "  -h, --help                 display this help and exit\n" );
   std::printf( "  -V, --version              output version information and exit\n" );
-//  std::printf( "  -b, --member-size=<n>      set member size limit in bytes\n" );
   std::printf( "  -B, --data-size=<n>        set input data block size in bytes\n" );
   std::printf( "  -c, --stdout               send output to standard output\n" );
   std::printf( "  -d, --decompress           decompress\n" );
@@ -110,7 +110,6 @@ void show_help() throw()
   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" );
@@ -141,7 +140,31 @@ void show_version() throw()
   }
 
 
-long long getnum( const char * ptr, const int bs = 0,
+const char * format_num( long long num, long long limit = 9999,
+                         const int set_prefix = 0 ) throw()
+  {
+  const char * const si_prefix[8] =
+    { "k", "M", "G", "T", "P", "E", "Z", "Y" };
+  const char * const binary_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;
+  const char *p = "";
+  limit = std::max( 999LL, std::min( 999999LL, limit ) );
+
+  for( int i = 0; i < 8 && ( llabs( num ) > limit ||
+       ( llabs( num ) >= factor && num % factor == 0 ) ); ++i )
+    { num /= factor; p = prefix[i]; }
+  snprintf( buf, sizeof buf, "%lld %s", num, p );
+  return buf;
+  }
+
+
+long long getnum( const char * const ptr, const int bs = 0,
                   const long long llimit = LLONG_MIN + 1,
                   const long long ulimit = LLONG_MAX ) throw()
   {
@@ -199,7 +222,7 @@ long long getnum( const char * ptr, const int bs = 0,
   }
 
 
-int get_dict_size( const char * arg ) throw()
+int get_dict_size( const char * const arg ) throw()
   {
   char *tail;
   int bits = std::strtol( arg, &tail, 0 );
@@ -223,7 +246,7 @@ int extension_index( const std::string & name ) throw()
   }
 
 
-int open_instream( const std::string & name, struct stat * in_statsp,
+int open_instream( const std::string & name, struct stat * const in_statsp,
                    const Mode program_mode, const int eindex,
                    const bool force, const bool to_stdout ) throw()
   {
@@ -293,13 +316,10 @@ void set_d_outname( const std::string & name, const int i ) throw()
 
 bool open_outstream( const bool force ) throw()
   {
-  if( force )
-    outfd = open( output_filename.c_str(),
-                  O_CREAT | O_TRUNC | O_WRONLY | o_binary,
-                  S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH );
-  else outfd = open( output_filename.c_str(),
-                     O_CREAT | O_EXCL | O_WRONLY | o_binary,
-                     S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH );
+  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 )
     {
     if( errno == EEXIST ) outfd = -2; else outfd = -1;
@@ -393,11 +413,11 @@ void set_signals( const bool to_file ) throw()
   {
   if( to_file )
     {
-    signal( SIGHUP, signal_handler );
-    signal( SIGINT, signal_handler );
-    signal( SIGTERM, signal_handler );
+    std::signal( SIGHUP, signal_handler );
+    std::signal( SIGINT, signal_handler );
+    std::signal( SIGTERM, signal_handler );
     }
-  signal( SIGUSR1, signal_handler );
+  std::signal( SIGUSR1, signal_handler );
   }
 
 } // end namespace
@@ -406,6 +426,12 @@ void set_signals( const bool to_file ) throw()
 int verbosity = 0;
 
 
+// This can be called from any thread, main thread or sub-threads alike, since
+// they all call common helper functions that call fatal() in case of an error.
+//
+void fatal() { signal_handler( SIGUSR1 ); }
+
+
 void Pretty_print::operator()( const char * const msg ) const throw()
   {
   if( verbosity >= 0 )
@@ -423,7 +449,7 @@ void Pretty_print::operator()( const char * const msg ) const throw()
   }
 
 
-void show_error( const char * msg, const int errcode, const bool help ) throw()
+void show_error( const char * const msg, const int errcode, const bool help ) throw()
   {
   if( verbosity >= 0 )
     {
@@ -439,7 +465,7 @@ void show_error( const char * msg, const int errcode, const bool help ) throw()
   }
 
 
-void internal_error( const char * msg )
+void internal_error( const char * const msg )
   {
   std::string s( "internal error: " ); s += msg;
   show_error( s.c_str() );
@@ -447,16 +473,10 @@ void internal_error( const char * msg )
   }
 
 
-// This can be called from any thread, main thread or sub-threads alike, since
-// they all call common helper functions that call fatal() in case of an error.
-//
-void fatal() { signal_handler( SIGUSR1 ); }
-
-
 // Returns the number of bytes really read.
 // If (returned value < size) and (errno == 0), means EOF was reached.
 //
-int readblock( const int fd, uint8_t * buf, const int size ) throw()
+int readblock( const int fd, uint8_t * const buf, const int size ) throw()
   {
   int rest = size;
   errno = 0;
@@ -475,7 +495,7 @@ int readblock( const int fd, uint8_t * buf, const int size ) throw()
 // Returns the number of bytes really written.
 // If (returned value < size), it is always an error.
 //
-int writeblock( const int fd, const uint8_t * buf, const int size ) throw()
+int writeblock( const int fd, const uint8_t * const buf, const int size ) throw()
   {
   int rest = size;
   errno = 0;
@@ -490,22 +510,23 @@ int writeblock( const int fd, const uint8_t * buf, const int size ) throw()
   }
 
 
-int main( const int argc, const char * argv[] )
+int main( const int argc, const char * const argv[] )
   {
   // Mapping from gzip/bzip2 style 1..9 compression modes
   // to the corresponding LZMA compression modes.
-  const lzma_options option_mapping[] =
+  const Lzma_options option_mapping[] =
     {
+    { 1 << 16,   5 },		// -0
     { 1 << 20,  10 },		// -1
-    { 1 << 20,  12 },		// -2
-    { 1 << 20,  17 },		// -3
-    { 1 << 21,  26 },		// -4
+    { 3 << 19,  12 },		// -2
+    { 1 << 21,  17 },		// -3
+    { 3 << 20,  26 },		// -4
     { 1 << 22,  44 },		// -5
     { 1 << 23,  80 },		// -6
     { 1 << 24, 108 },		// -7
-    { 1 << 24, 163 },		// -8
+    { 3 << 23, 163 },		// -8
     { 1 << 25, 273 } };		// -9
-  lzma_options encoder_options = option_mapping[5];	// default = "-6"
+  Lzma_options encoder_options = option_mapping[6];	// default = "-6"
   int data_size = 0;
   int debug_level = 0;
   int infd = -1;
@@ -533,6 +554,7 @@ int main( const int argc, const char * argv[] )
 
   const Arg_parser::Option options[] =
     {
+    { '0',  0,                Arg_parser::no  },
     { '1', "fast",            Arg_parser::no  },
     { '2',  0,                Arg_parser::no  },
     { '3',  0,                Arg_parser::no  },
@@ -546,6 +568,7 @@ int main( const int argc, const char * argv[] )
     { 'B', "data-size",       Arg_parser::yes },
     { 'c', "stdout",          Arg_parser::no  },
     { 'd', "decompress",      Arg_parser::no  },
+    { 'e', "extreme",         Arg_parser::no  },
     { 'D', "debug",           Arg_parser::yes },
     { 'f', "force",           Arg_parser::no  },
     { 'h', "help",            Arg_parser::no  },
@@ -570,20 +593,19 @@ int main( const int argc, const char * argv[] )
     {
     const int code = parser.code( argind );
     if( !code ) break;					// no more options
-    const char * arg = parser.argument( argind ).c_str();
+    const char * const arg = parser.argument( argind ).c_str();
     switch( code )
       {
-      case '1': case '2': case '3':
-      case '4': case '5': case '6':
-      case '7': case '8': case '9':
-                encoder_options = option_mapping[code-'1']; break;
+      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 'b': break;
       case 'B': data_size = getnum( arg, 0, 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, 0, 0, 3 );
-                break;
+      case 'D': debug_level = getnum( arg, 0, 0, 3 ); break;
+      case 'e': break;
       case 'f': force = true; break;
       case 'h': show_help(); return 0;
       case 'k': keep_input_files = true; break;
@@ -605,6 +627,8 @@ int main( const int argc, const char * argv[] )
 
   if( data_size <= 0 )
     data_size = 2 * std::max( 65536, encoder_options.dictionary_size );
+  else if( data_size < encoder_options.dictionary_size )
+    encoder_options.dictionary_size = std::max( data_size, LZ_min_dictionary_size() );
 
   if( num_workers <= 0 )
     {
@@ -648,6 +672,7 @@ int main( const int argc, const char * argv[] )
           if( program_mode == m_compress )
             set_c_outname( default_output_filename );
           else output_filename = default_output_filename;
+          outfd_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
           if( !open_outstream( force ) )
             {
             if( outfd == -1 && retval < 1 ) retval = 1;
@@ -672,6 +697,7 @@ int main( const int argc, const char * argv[] )
           if( program_mode == m_compress )
             set_c_outname( input_filename );
           else set_d_outname( input_filename, eindex );
+          outfd_mode = S_IRUSR | S_IWUSR;
           if( !open_outstream( force ) )
             {
             if( outfd == -1 && retval < 1 ) retval = 1;