Anonymous Monk has asked for the wisdom of the Perl Monks concerning the following question: Hello All, I have two excel files containing 58000 and 30000 entries respectively. I want to find out how many entries of file_1 are present in file_2. I have written below program but it is taking days to execute, Can anyone have better solution? 

 
#Modules to use
use Cwd 'abs_path';
use Win32::OLE;
use Win32::OLE qw(in with);
use Win32::OLE::Const "Microsoft Excel";
$Win32::OLE::Warn = 3;

my $start_run = time();

print"[USAGE]: <demoscript.pl> <.map file path> <Ouput excel path>\n";

print"[INFO]: Executing demoscript.pl V1.0.1.\n";


#Global Variables
my @longNames;

my $SystemPortTracingReport = $ARGV[0];    
my $CLEA_Family = $ARGV[1];    
my $GlobalB_HighFeature = $ARGV[2];    


my $Excel =Win32::OLE->new('Excel.Application');

# Open Excel file
my $Book = $Excel->Workbooks->Open($SystemPortTracingReport);
my $Book2 = $Excel->Workbooks->Open($CLEA_Family);

#Make Excel visible
$Excel->{Visible} = 1;

my $Sheet = $Book->Worksheets("GlobalB_HighFeature");
my $Sheet2 = $Book2->Worksheets("GlobalB_HighFeature_SerialDataR");
my $longNamecol;
my $Signalcolumn;
for($i=1; $i<30;$i++)
{
        if($Sheet->Cells($startingrow, $i)->{'Value'} eq "Long Name")
        {
            $longNamecol = $i;
        }
}
for($i=1; $i<30;$i++)
{
        if($Sheet2->Cells($startingrow, $i)->{'Value'} eq "Long Name")
        {
            $Signalcolumn = $i;
        }
}
print"\n$longNamecol\n";
print"\n$Signalcolumn\n";


my $emptyline=0;
for(my $k=2; $k<521754; $k++)
{
        if($Sheet->Cells($k,$longNamecol)->{'Value'} eq "")
        {
            $emptyline++;
        
        }
        else
        {
            push(@longNames, $Sheet->Cells($k,$longNamecol)->{'Value'}
+);
            # my $temp = $Sheet->Cells($k,$longNamecol)->{'Value'};
            # print"\n $temp";
            $count++;
        
        }

}

my $data;
my $length;
$length = scalar(@longNames);
print"Length $length";
print"Searching...........\n";
$Book->Save; #Or $Book->SaveAs("C:\\file_name.xls");
$Book->Close; #or $Excel->Quit;
for(my $m=0; $m<$length; $m++)
{

    for(my $l=2; $l<2990; $l++)
    {
        if($Sheet2->Cells($l,$Signalcolumn)->{'Value'} eq "")
        {
            next;
        
        }
        else
        {
            if($Sheet2->Cells($l,$Signalcolumn)->{'Value'} eq $longNam
+es[$m])
            {
                    $Sheet2->Cells($l,100)->{'Value'} = "matched"; 
                    print"\n***********Matched*************\n";
            
            }    
        }

    }


}
print"\n**********finished!**************\n";
#Save Excel file

$Book2->Save; #Or $Book->SaveAs("C:\\file_name.xls");
$Book2->Close; #or $Excel->Quit;

my $end_run = time();
my $run_time = $end_run - $start_run;
print"\n[INFO]Timetaken: $run_time [Secs]";

[download]

In reply to Xls reader by sainky

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.