view release on metacpan or  search on metacpan

lib/CAM/PDF.pm  view on Meta::CPAN

            for my $line (split /\n/xms, $text)  # trailing null strings omitted
            {
               $lines++;
               my $w = $self->getStringWidth($fontmetrics, $line);
               if ($w && $w > $stringwidth)
               {
                  $stringwidth = $w;
               }
            }
            $lines ||= 1;
            # Initial guess
            $fontsize = ($dy - 2 * $border) / ($lines * 1.5);
            my $fontwidth = $fontsize * $stringwidth;
            my $maxwidth = $dx - 2 * $border;
            if ($fontwidth > $maxwidth)
            {
               $fontsize *= $maxwidth / $fontwidth;
            }

            # allow for user override
            if (exists $opts->{max_autoscale_fontsize} && $fontsize > $opts->{max_autoscale_fontsize}) {

lib/CAM/PDF.pm  view on Meta::CPAN

         # escape characters
         $text = $self->writeString($text);

         if ($flags{Multiline})
         {
            # TODO: wrap the field with wrapString()??
            # Shawn Dawson of Silent Solutions pointed out that this does not auto-wrap the input text

            my $linebreaks = $text =~ s/ \\n /\) Tj T* \(/gxms;

            # Total guess work:
            # line height is either 150% of fontsize or thrice
            # the corner offset
            $tl = $fontsize ? $fontsize * 1.5 : $ty * 3;

            # Bottom aligned
            #$ty += $linebreaks * $tl;
            # Top aligned
            $ty = $dy - $border - $tl;

            if ($flags{Justify} ne 'left')

lib/CAM/PDF/PageText.pm  view on Meta::CPAN

=head1 SYNOPSIS

   my $pdf = CAM::PDF->new($filename);
   my $pageone_tree = $pdf->getPageContentTree(1);
   print CAM::PDF::PageText->render($pageone_tree);

=head1 DESCRIPTION

This module attempts to extract sequential text from a PDF page.  This
is not a robust process, as PDF text is graphically laid out in
arbitrary order.  This module uses a few heuristics to try to guess
what text goes next to what other text, but may be fooled easily by,
say, subscripts, non-horizontal text, changes in font, form fields
etc.

All those disclaimers aside, it is useful for a quick dump of text
from a simple PDF file.

=head1 LICENSE

Same as L<CAM::PDF>