HTML::FormatText::Zen - format HTML as plain text using zen

HTML-FormatExternal documentation Contained in the HTML-FormatExternal distribution.

Index

Code Index:

NAME

Top

HTML::FormatText::Zen - format HTML as plain text using zen

SYNOPSIS

Top

 use HTML::FormatText::Zen;
 $text = HTML::FormatText::Zen->format_file ($filename);
 $text = HTML::FormatText::Zen->format_string ($html_string);

 $formatter = HTML::FormatText::Zen->new;
 $tree = HTML::TreeBuilder->new_from_file ($filename);
 $text = $formatter->format ($tree);

DESCRIPTION

Top

HTML::FormatText::Zen turns HTML into plain text using the zen program.

http://www.nocrew.org/software/zen/

The module interface is compatible with formatters like HTML::FormatText, but all parsing etc is done by zen.

See HTML::FormatExternal for the formatting functions. But as of zen version 0.2.3 the options have no effect. Input charset is always latin-1, output is latin-1, and dump width is 80 columns with no left margin.

SEE ALSO

Top

HTML::FormatExternal

HOME PAGE

Top

http://user42.tuxfamily.org/html-formatexternal/index.html

LICENSE

Top

Copyright 2008, 2009, 2010 Kevin Ryde

HTML-FormatExternal is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3, or (at your option) any later version.

HTML-FormatExternal is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with HTML-FormatExternal. If not, see <http://www.gnu.org/licenses/>.

HTML-FormatExternal documentation Contained in the HTML-FormatExternal distribution. 
# Copyright 2008, 2009, 2010 Kevin Ryde

# HTML-FormatExternal is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License as published
# by the Free Software Foundation; either version 3, or (at your option) any
# later version.
#
# HTML-FormatExternal is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
# or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
# for more details.
#
# You should have received a copy of the GNU General Public License along
# with HTML-FormatExternal.  If not, see <http://www.gnu.org/licenses/>.

package HTML::FormatText::Zen;
use 5.006;
use strict;
use warnings;
use HTML::FormatExternal;
our @ISA = ('HTML::FormatExternal');

our $VERSION = 19;

use constant DEFAULT_LEFTMARGIN => 3;
use constant DEFAULT_RIGHTMARGIN => 77;

sub program_full_version {
  my ($self_or_class) = @_;
  return $self_or_class->_run_version ('zen', '--version');
}
sub program_version {
  my ($self_or_class) = @_;
  my $version = $self_or_class->program_full_version;
  if (! defined $version) { return undef; }

  # eg. "zen version 0.2.3"
  $version =~ /^zen version (.*)/i
    or $version =~ /^(.*)/;  # whole first line if format not recognised
  return $1;
}

sub _crunch_command {
  my ($class, $options) = @_;

  # is it worth enforcing/checking this ?
  #
  #   if (my $input_charset = $options->{'input_charset'}) {
  #     $input_charset =~ /^latin-?1$|^iso-?8859-1$/i
  #       or croak "Zen only accepts latin-1 input";
  #   }
  #   if (my $output_charset = $options->{'output_charset'}) {
  #     $output_charset =~ /^latin-?1$|^iso-?8859-1$/i
  #       or croak "Zen only produces latin-1 output";
  #   }

  # 'zen_options' not documented ...
  return ('zen', '-i', 'dump',
          @{$options->{'zen_options'} || []});
}

1;
__END__