Ok, now try this with grep added
#!/usr/bin/perl use strict; my $t0 = time; my $file1 = $ARGV[0] || 'ficc.txt'; my $file2 = $ARGV[1] || 'fic.txt'; my %uniq1=(); my $count1=0; my $words1=0; open FICC,'<',$file1 or die "$file1 : $!"; while (<FICC>) { my @words = split /\s+/,lc $_; ++$uniq1{$_} for @words; $words1 += @words; ++$count1; } close FICC; my $uniq1 = scalar keys %uniq1; my %uniq2=(); my $count2=0; my $words2=0; open FIC,'<',$file2 or die "$file2 : $!"; while (my $line = <FIC>) { my @words = split /\s+/,lc $line; ++$uniq2{$_} for @words; $words2 += @words; ++$count2; my @match = grep $uniq1{$_}, @words; } close FICC; my $uniq2 = scalar keys %uniq2; my $dur = int time-$t0; print " File1 : $count1 lines $words1 words $uniq1 unique in $file1 File2 : $count2 lines $words2 words $uniq2 unique in $file2 Time : $dur seconds\n";
These are the results for my i5-2500K
File1 : 4000000 lines 7998273 words 6379952 unique in ficc1.txt File2 : 4000000 lines 11999843 words 9364684 unique in fic1.txt Time : 37 secondspoj
In reply to Re^7: compare two text file line by line, how to optimise
by poj
in thread compare two text file line by line, how to optimise
by thespirit
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |