on 07/18/2001 04:11 AM, Scott R. Godin at [EMAIL PROTECTED] wrote:
getting an error now, with HTML::Parser that doesn't happen on the unix box
I also run a similar script on (which I think is running 3.08 but I'll check
in a second ... no it's 3.23 there.)
# Modification of a read-only value attempted.
File 'Primus 8.5GB:Applications:MacPerl Ÿ:site_perl:HTML:Parser.pm'; Line 77
code that generates this error:
#!perl -w
use strict;
use HTML::Parser;
my $infile = 'test.html';
# now we make sure we declare these vars OUTside the loop, (*)
# but before the subs that use them
my @filedata = ();
my %inside = ();
sub tag {
my($tag, $num, $info) = @_;
$inside{$tag} += $num;
# not for all tags
push @filedata, "\n"
if (($tag eq 'tr') and ($num eq '-1'));
}
sub text {
return unless $inside{td} || $inside{th};
chomp(my $txt = $_[0]);
$txt =~ s/^\s+$//;
return if $txt eq "";
push @filedata, "$txt,";
}
# ok let's start by paring down all the unnecessary filesize
# and JUST leave ourselves with the important data
my $outfile = $infile;
chop($outfile);
print "Parsing: $infile into $outfile\n";
HTML::Parser->new(
'api_version' => '3',
'handlers' => [ 'start' => [ \&tag, "tagname, '+1', attr" ],
'end' => [ \&tag, "tagname, '-1'" ],
'text' => [ \&text, "text" ], ],
'marked_sections' => '1',
)->parse_file($infile) || die "Can't open input file: $!\n";
# delete the line
# 'marked_sections' => '1',
# and the problem goes away.
# many of the .t files fail for similar reasons.
print join("\t", @filedata);
open OUT, ">$outfile" or die "output file $outfile won't open! : $!" ;
print OUT @filedata;
close OUT;
--
Scott R. Godin | e-mail : [EMAIL PROTECTED]
Laughing Dragon Services | web : http://www.webdragon.net/
