WAIT/Parse/Ora.pm

#!/usr/bin/perl
#                              -*- Mode: Perl -*- 
# $Basename: HTML.pm $
# $Revision: 1.4 $
# 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 => '', colophon => '' );
  my $desc = $doc->{desc};
  my $auth = $doc->{author};
  my $colophon = $doc->{colophon};

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

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

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

  return \%doc;
}

1;
1	#!/usr/bin/perl
2	# -- Mode: Perl --
3	# $Basename: HTML.pm $
4	# $Revision: 1.4 $
5	# Author : Ulrich Pfeifer with Andreas König
6	# Created On : Sat Nov 1 1997
7	# Last Modified By: Ulrich Pfeifer
8	# Last Modified On: Fri Jan 4 16:06:14 2002
9	# Language : CPerl
10	# Update Count : 14
11	# Status : Unknown, Use with caution!
12	#
13	# (C) Copyright 1997, Ulrich Pfeifer, all rights reserved.
14	#
15	#
16
17	package WAIT::Parse::Ora;
18	use HTML::Parser;
19	use strict;
20	use vars qw(@ISA);
21	@ISA = qw(WAIT::Parse::Base);
22
23	my $debug = 0;
24	my %text = (
25	p => 'text',
26	# h1 => 'text',
27	# h2 => 'text',
28	# h3 => 'text',
29	title => 'title',
30	);
31
32	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 $open;
67	}
68
69	sub split {
70	my ($self, $doc) = @_;
71	my %doc = ( isbn => '', author => '', about => '', colophon => '' );
72	my $desc = $doc->{desc};
73	my $auth = $doc->{author};
74	my $colophon = $doc->{colophon};
75
76	if ($doc->{author}) {
77	%result = ();
78	$text = '';
79	$open = 0;
80	$p->parse($doc->{author});
81	$p->eof;
82	$doc{author} = $result{title};
83	$doc{author} =~ s/^By\s+//;
84	$doc{about} = $result{text};
85	}
86	if ($doc->{index}) {
87	$doc->{index} =~ /ISBN\s*([^<]+)/ and $doc{isbn} = $1;
88	}
89	if ($doc->{colophon}) {
90	%result = ();
91	$text = '';
92	$open = 0;
93	$p->parse($doc->{colophon});
94	$p->eof;
95	$doc{colophon} = $result{text};
96	}
97	%result = ();
98	$text = '';
99	$open = 0;
100
101	$p->parse($doc->{desc});
102	$p->eof;
103
104	$doc{text} = $result{text};
105	$doc{title} = $result{title};
106
107	return \%doc;
108	}
109
110	1;