my @regexes;
if ($param eq 'mod') {
@regexes = ...
} else {
@regexes = ...
}
####
&[^;]+;\s&[^;]+;
##
##
#!/usr/bin/perl
use warnings;
use strict;
my ($infile, $param) = @ARGV;
my @regexes = $param ? (qr/&[^;]+;\s&[^;]+;/)
: (qr/–§/,
qr/–Ü/,
qr/ߧ/);
open my $in, '<', $infile or die "Cannot open $infile for reading: $!";
my $xml;
{
local $/;
$xml = <$in>;
}
open my $out, '>', 'pairs.txt' or die $!;
print {$out} "Find pair of entities without/with separating space\n\ninput file: ";
print {$out} "$infile";
print {$out} "\n========================================================================\n\n";
for my $i (0 .. $#regexes) {
my $regex = $regexes[$i];
$regex =~ s/^\(\?\^://;
$regex =~ s/\)$//;
print {$out} "$regex: $1\n" while $xml =~ /($regex)/g;
}
close $in;
close $out;