WAIT/Parse/Ora.pm

#!/usr/bin/perl
#                              -*- Mode: Perl -*- 
# $Basename: HTML.pm $
# $Revision: 1.3 $
# Author          : Ulrich Pfeifer with Andreas König
# Created On      : Sat Nov 1 1997
# Last Modified By: Ulrich Pfeifer
# Last Modified On: Fri Jan  4 16:06:14 2002
# Language        : CPerl
# Update Count    : 14
# Status          : Unknown, Use with caution!
# 
# (C) Copyright 1997, Ulrich Pfeifer, all rights reserved.
# 
# 

package WAIT::Parse::Ora;
use HTML::Parser;
use strict;
use vars qw(@ISA);
@ISA = qw(WAIT::Parse::Base);

my $debug = 0;
my %text = (
            p     => 'text',
#            h1    => 'text',
#            h2    => 'text',
#            h3    => 'text',
            title => 'title',
           );

my $p = HTML::Parser->new(
                          api_version => 3,
                          start_h => [\&handle_start, "tagname, attr"],
                          end_h   => [\&handle_end,   "tagname"],
                          text_h  => [\&handle_text,  "dtext"],
                          marked_sections => 1,
                         );
my %result;
my $text;
my $open;

sub handle_start {
  my $tag = shift;

  return unless $text{$tag};
  $open++;
  print ">" x $open, $tag,  "\n" if $debug;
}

sub handle_end {
  my $tag = shift;

  return unless $text{$tag};
  print "<" x $open, $tag,  "\n" if $debug;
  $open--;
  $text =~ s/^\s+//;
  $text =~ s/\s+$//;
  $text =~ s/\s+/ /g;
  $result{$text{$tag}} .= $text . ' ';
  $text = '';
}


sub handle_text {
  $text .= $_[0] if $open;
}

sub split {
  my ($self, $doc) = @_;
  my %doc = ( isbn => '', author => '', about => '' );
  my $desc = $doc->{desc};
  my $auth = $doc->{author};

  if ($doc->{author}) {
    %result = ();
    $text = '';
    $open = 0;
    $p->parse($doc->{author});
    $p->eof;
    $doc{author} = $result{title};
    $doc{about}  = $result{text};
  }
  if ($doc->{index}) {
    $doc->{index} =~ /ISBN\s*([-\d]+)/ and $doc{isbn} = $1;
  }
  %result = ();
  $text = '';
  $open = 0;

  $p->parse($doc->{desc});
  $p->eof;

  $doc{text}  = $result{text};
  $doc{title} = $result{title};

  return \%doc;
}

1;
1	ulpfr	54	#!/usr/bin/perl
2			# -- Mode: Perl --
3			# $Basename: HTML.pm $
4	ulpfr	61	# $Revision: 1.3 $
5	ulpfr	54	# Author : Ulrich Pfeifer with Andreas König
6			# Created On : Sat Nov 1 1997
7			# Last Modified By: Ulrich Pfeifer
8	ulpfr	61	# Last Modified On: Fri Jan 4 16:06:14 2002
9	ulpfr	54	# Language : CPerl
10	ulpfr	61	# Update Count : 14
11	ulpfr	54	# Status : Unknown, Use with caution!
12			#
13			# (C) Copyright 1997, Ulrich Pfeifer, all rights reserved.
14			#
15			#
16
17			package WAIT::Parse::Ora;
18	ulpfr	58	use HTML::Parser;
19			use strict;
20	ulpfr	54	use vars qw(@ISA);
21			@ISA = qw(WAIT::Parse::Base);
22
23	ulpfr	58	my $debug = 0;
24			my %text = (
25			p => 'text',
26			# h1 => 'text',
27			# h2 => 'text',
28			# h3 => 'text',
29			title => 'title',
30			);
31	ulpfr	54
32	ulpfr	58	my $p = HTML::Parser->new(
33			api_version => 3,
34			start_h => [\&handle_start, "tagname, attr"],
35			end_h => [\&handle_end, "tagname"],
36			text_h => [\&handle_text, "dtext"],
37			marked_sections => 1,
38			);
39			my %result;
40			my $text;
41			my $open;
42
43			sub handle_start {
44			my $tag = shift;
45
46			return unless $text{$tag};
47			$open++;
48			print ">" x $open, $tag, "\n" if $debug;
49			}
50
51			sub handle_end {
52			my $tag = shift;
53
54			return unless $text{$tag};
55			print "<" x $open, $tag, "\n" if $debug;
56			$open--;
57			$text =~ s/^\s+//;
58			$text =~ s/\s+$//;
59			$text =~ s/\s+/ /g;
60			$result{$text{$tag}} .= $text . ' ';
61			$text = '';
62			}
63
64
65			sub handle_text {
66			$text .= $_[0] if $open;
67			}
68
69	ulpfr	54	sub split {
70			my ($self, $doc) = @_;
71	ulpfr	61	my %doc = ( isbn => '', author => '', about => '' );
72	ulpfr	54	my $desc = $doc->{desc};
73			my $auth = $doc->{author};
74
75	ulpfr	61	if ($doc->{author}) {
76			%result = ();
77			$text = '';
78			$open = 0;
79			$p->parse($doc->{author});
80			$p->eof;
81			$doc{author} = $result{title};
82			$doc{about} = $result{text};
83			}
84			if ($doc->{index}) {
85			$doc->{index} =~ /ISBN\s*([-\d]+)/ and $doc{isbn} = $1;
86			}
87	ulpfr	58	%result = ();
88			$text = '';
89			$open = 0;
90	ulpfr	54
91	ulpfr	58	$p->parse($doc->{desc});
92			$p->eof;
93	ulpfr	54
94	ulpfr	58	$doc{text} = $result{text};
95			$doc{title} = $result{title};
96
97			return \%doc;
98	ulpfr	54	}
99	ulpfr	58
100			1;