#!/usr/bin/perl use strict; use warnings; my $kTestLines = 2000000; my $kMinSame = 2; my $testA = 'testA.txt'; my $testB = 'testB.txt'; srand (1); buildTestFile($_) for $testA, $testB; open my $inA, '<', $testA or die "Can't open $testA: $!\n"; open my $inB, '<', $testB or die "Can't open $testB: $!\n"; my %aKeys; print scalar localtime, "\n"; while (my $aLine = <$inA>) { chomp $aLine; my @keys = map {lc} split /\s+/, $aLine; push @{$aKeys{$_}}, $. for @keys; } while (my $bLine = <$inB>) { chomp $bLine; my @bWords = map {lc} split (/\s/, $bLine); my %lineAHits; ++$lineAHits{$_} for map {@{$aKeys{$_}}} grep {exists $aKeys{$_}} @bWords; my @matchALines = grep {+$lineAHits{$_} >= $kMinSame} keys %lineAHits; next if !@matchALines; printf "%s:\n %s\n", join (', ', @matchALines), $bLine; } print scalar localtime, "\n"; sub buildTestFile { my ($fName) = @_; open my $fOut, '>', $fName or die "Can't create '$fName': $!\n"; for (1 .. $kTestLines) { my %words = map {$_ => undef} map { join '', map {randLetter()} 1 .. 4 } 1 .. 4; print $fOut join (' ', keys %words), "\n"; } } sub randLetter { return chr 65 + rand 26; } #### Sat Feb 27 11:43:38 2016 704856: CYXG GWVB OYLX YNWJ 849378: ECML DIYS APPF OYLR ... 1090468: VSIR CKVJ GWIV IOXN 1327692: YJOQ YOJT NCZL VCSA 740815: ZZJN WYVG EETN QADD Sat Feb 27 11:47:08 2016