Dr. Dobb's is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.


Channels ▼
RSS

Database

Removing Duplicate Files Across Disk Drives


February 1991/Removing Duplicate Files Across Disk Drives/Listing 2

Listing 2 (no_dup.c)

/*
   Find multiple copies of the same file on a single disk
   drive. Compiled under Microsoft C 6.0 using:
      cl /Fs /W4 /Ox /AC no_dup.c
   Compiles without modifications undder TURBO C integrated
   environment.
   In both cases requires compact memory model libraries.
*/

#include "no_dup.h"

Flag first_call = True;

GlobalOpt globalopt = { False, False, 0, 0L };

int main( int argc, char **argv )
   {
   DirEntry *current_file, *next_file;
   DirList *path, *root, *new_path;
   char current_path[MAX_PATH], file_spec[MAX_FLEN];
   PtrList *ptrbase, *ptrlist;
   Flag duplicate = False;

   for( ; argc > 1; argc-- )
      {
      if(argv[argc-1][1] == 'f' || argv[argc-1][1] == 'F')
         globalopt.file = True;
      else if( argv[argc-1][1] == 'd'
             || argv[argc-1] [1] == 'D' )
         globalopt.dir = True;
      else
         fprintf( stderr,
                "Invalid command line switch: %s\n",
                argv[argc-l] );
      }

   strcpy( file_spec, "*.*" );
   current_file = NULL;
   (void) getcwd( current_path, MAX_PATH );
   fprintf( stderr, "%s\n", VERSION );
   printf( "Processing %s\n", current_path );
   path = make_path( current_path, "", NULL );
   new_path = root = path;
   if( (ptrbase = malloc( sizeof( PtrList ) * MAX_FILES ))
          == NULL )
      {
      fprintf( stderr, "Insufficient near memory.\n" );
      exit( EXIT_FAILURE );
      }
   ptrlist = ptrbase;

   while( (path = get_path( root ) ) != NULL )
      {
      strcpy( current_path, path->pathname );
      strcat( current_path, file_spec );
      first_call = True;

      while( (current_file = get_direntry(current_path))
             ! = NULL )
         {
         current_file->path = path->pathname;
         if( current_file->attrib & FA_DIREC )
            {
            new_path = make_path( path->pathname,
                   current_file->name, new_path );
            }
         else
            {
            ++globalopt.file_count;
            globalopt.total_file_size
                   += current_file->size;
            if( globalopt.file_count == MAX_FILES )
                {
                fprintf( stderr,
                    "Too many files\n"
                    "Program is limited to %u files.\n",
                    MAX_FILES );
                exit( EXIT_FAILURE );
                }
            *ptrlist = ( char * ) current_file;
            ++ptrlist;
            }
         }
         path->dir_processed = True;
      }
      *ptrlist = NULL;
      printf( "Processed %d files occupying %lu bytes.\n",
             globalopt.file_count,
             globalopt.total_file_size );

      qsort( (void *) ptrbase,
             (size_t) globalopt.file_count,
             (size_t) sizeof( PtrList ), name_comp );

      if( globalopt.file )    /* optionally list files */
         {
         printf( SEPARATOR );
         printf( "Listing of all files below %s\n",root);
         for( ptrlist = ptrbase; *ptrlist; ptrlist++ )
            fprint_direntry( stdout,
                  (DirEntry *) *ptrlist );
         }

      printf( SEPARATOR );
      printf( "Duplicate files below %s\n", root );
      for( ptrlist = ptrbase, duplicate = False;
            *ptrlist; ptrlist++ )
         {
         current_file = ( DirEntry * ) *ptrlist;
         next_file    = ( DirEntry * ) *(ptrlist+1);
         if( !strcmp(current_file->name,next_file->name))
            {
            duplicate = True;
            fprint_direntry( stdout, current_file );
            {
         else if( duplicate == True )
            {
            /* print the last file in a group */
            /* otherwise we'll miss it */
            current_file = ( DirEntry * ) *ptrlist;
            fprint_direntry( stdout, current_file );
            printf( SEPARATOR );
            duplicate = False;
            }
         }

      return EXIT_SUCCESS;
   }

/*
   get file info from DOS directory and allocate memory
*/
DirEntry *get_direntry( char *path )
   {
   static struct ffblk file_info;
   DirEntry *new_entry;

   if( first_call == True )
      {
      if( findfirst( path, &file_info, FA_DIREC ) )
         return NULL;
      first_call = False;
      }
   else
      {
      if( findnext( &file_info ) )
         {
         return NULL;
         }
      }
   if( (new_entry = malloc(sizeof(DirEntry))) == NULL )
      {
      fprintf( stderr, "Insufficient far memory.\n" );
      exit( EXIT_FAILURE );
      }

   strcpy( new_entry->name, file_info.ff_name );
   new_entry->attrib = file_info.ff_attrib;
   if( new_entry->attrib & FA_DIREC )
      new_entry->dir_processed = False;
   new_entry->time   = file_info.ff_ftime;
   new_entry->date   = file_info.ff_fdate;
   new_entry->size   = file_info.ff_fsize;

   return new_entry;
   }

/*
   build a directory path by appending subdir to basedir
*/
DirList *make_path( char *basedir, char *subdir,
      DirList *prev )
   {
   DirList *new_dir;

   if( (new_dir = malloc( sizeof( DirList ) ) ) == NULL )
      {
      fprintf( stderr, "Insufficient near memory.\n" );
      exit( EXIT_FAILURE );
      }
   strcpy( new_dir->pathname, basedir );
   strcat( new_dir->pathname, subdir );
   if( *(new_dir->pathname + strlen(new_dir->pathname) - 1)
         != '\\' )
      strcat( new_dir->pathname, "\\" );
   if( strcmp( subdir, "." ) && strcmp( subdir, ".." ) )
      {
      /* only "real" directories meet the condition */
      new_dir->dir_processed = False;
      if( globalopt.dir )
         printf( "Directory:%s\n", new_dir->pathname );
      }
   else
      new_dir->dir_processed = True;
   if( prev )
      {
      new_dir->prev = prev;
      new_dir->next = NULL;
      prev->next = new_dir;
      }
   else
      {
      new_dir->prev = NULL;
      new_dir->next = NULL;
      }
   return new_dir;
   }

/*
   find an unprocessed directory
*/
DirList *get_path( DirList *root )
   {
   DirList *path;

   path = root;
   while( path->next && (path->dir_processed == True) )
      {
      path = path->next;
      }
   if( path->dir_processed == True)
      return NULL;
   else
      return path;

   }

/*
   DirEntry comparison function
*/
int name_comp( const void *p1, const void *p2 )
   {
   PtrList *ptr1, *ptr2;
   DirEntry *f1, *f2;
   int status;

   ptr1 = (PtrList *) p1;
   ptr2 = (PtrList *) p2;
   f1   = (DirEntry *) *ptr1;
   f2   = (DirEntry *) *ptr2;

   if( status = strcmp( f1->name, f2->name ))
      return( status );
   else if( status = f1->date - f2->date )
      return( status );
   else if( status = f1->time - f2->time )
      return( status );
   else
      return( strcmp( f1->path, f2->path ) );
   }

/*
   print file information to the ouptut stream
*/
void fprint_direntry( FILE *fout, DirEntry *current_file )
   {
   char date_buf[10], time_buf[10];

   fprintf( fout, "%-14s %6ld %c%c %s %s %s\n",
          current_file->name,
          current_file->size,
          (current_file->attrib & FA_RDONLY ) ? 'R' : '.',
          (current_file->attrib & FA_ARCH   ) ? 'A' : '.',
          datestr( current_file->date, date_buf ),
          timestr( current_file->time, time_buf ),
          current_file->path );

   }

/*
   The following functions are copied from QC 2.0 online
   help. These functions convert wr_time and wr_date into
   strings.
*/
char *timestr( unsigned t, char *buf )
{
   int h = (t >> 11) & 0x1f, m = (t >> 5) & 0x3f;
   sprintf( buf, "%2.2d:%02.2d", h, m );
   return buf;
}

char *datestr( unsigned d, char *buf )
{
   sprintf( buf, "%2.2d/%02.2d/%02.2d",
         (d >> 5) & 0x0f, d & 0x1f, (d >> 9) + 80 );
   return buf;
}


Related Reading


More Insights






Currently we allow the following HTML tags in comments:

Single tags

These tags can be used alone and don't need an ending tag.

<br> Defines a single line break

<hr> Defines a horizontal line

Matching tags

These require an ending tag - e.g. <i>italic text</i>

<a> Defines an anchor

<b> Defines bold text

<big> Defines big text

<blockquote> Defines a long quotation

<caption> Defines a table caption

<cite> Defines a citation

<code> Defines computer code text

<em> Defines emphasized text

<fieldset> Defines a border around elements in a form

<h1> This is heading 1

<h2> This is heading 2

<h3> This is heading 3

<h4> This is heading 4

<h5> This is heading 5

<h6> This is heading 6

<i> Defines italic text

<p> Defines a paragraph

<pre> Defines preformatted text

<q> Defines a short quotation

<samp> Defines sample computer code text

<small> Defines small text

<span> Defines a section in a document

<s> Defines strikethrough text

<strike> Defines strikethrough text

<strong> Defines strong text

<sub> Defines subscripted text

<sup> Defines superscripted text

<u> Defines underlined text

Dr. Dobb's encourages readers to engage in spirited, healthy debate, including taking us to task. However, Dr. Dobb's moderates all comments posted to our site, and reserves the right to modify or remove any content that it determines to be derogatory, offensive, inflammatory, vulgar, irrelevant/off-topic, racist or obvious marketing or spam. Dr. Dobb's further reserves the right to disable the profile of any commenter participating in said activities.

 
Disqus Tips To upload an avatar photo, first complete your Disqus profile. | View the list of supported HTML tags you can use to style comments. | Please read our commenting policy.