swish-e/prog-bin/pdf2html.pm

package pdf2html;
use strict;

=pod

=head1 NAME

pdf2html - swish-e sample module to convert pdf to html

=head1 SYNOPSIS

    use pdf2html;
    my $html_record_ref = pdf2html( $pdf_file_name, 'title' );

    # or by passing content in a scalar reference
    my $html_text_ref = pdf2html( \$pdf_content, 'title' );


=head1 DESCRIPTION

Sample module for use with other swish-e 'prog' document source programs.

Pass either a file name, or a scalar reference.

The differece is when you pass a reference to a scalar
only the content is returned.  When you pass a file name
an entire record is returned ready to be fed to swish -- this
includes the headers required by swish for indexing.

The second optional parameter is the extracted PDF info tag to use as the HTML title.


The plan is to find a library that will do this to avoid forking an external
program.

=head1 REQUIREMENTS

Uses the xpdf package that includes the pdftotext conversion program.
This is available from http://www.foolabs.com/xpdf/xpdf.html.

You will also need the module File::Temp (and its dependencies)
available from CPAN if passing content to this module (instead of a file name).


=head1 AUTHOR

Bill Moseley

=cut

use Symbol;


use vars qw(
    @ISA
    @EXPORT
    $VERSION
);

# $Id: pdf2html.pm,v 1.3 2002/01/31 00:37:43 whmoseley Exp $
$VERSION = sprintf '%d.%02d', q$Revision: 1.3 $ =~ /: (\d+)\.(\d+)/;

require Exporter;
@ISA    = qw(Exporter);
@EXPORT = qw(pdf2html);

my @InfoTags = qw/Title Subject Author CreationDate Creator Producer ModDate Keywords/;


sub pdf2html {
    my $file_or_content = shift;
    my $title_tag = shift;


    my $file = ref $file_or_content
    ? create_temp_file( $file_or_content )
    : $file_or_content;

    my $headers = get_pdf_headers( $file, $title_tag ) || '';

    my $content_ref = get_pdf_content_ref( $file );

    my $txt = <<EOF;
<html>    
<head>
$headers
</head>
<body>
<pre>
$$content_ref
</pre>
</body>
</html>
EOF

    if ( ref $file_or_content ) {
        unlink $file;
        return \$txt;
    }

    my $mtime  = (stat $file )[9];

    my $size = length $txt;

    my $ret = <<EOF;
Content-Length: $size
Last-Mtime: $mtime
Path-Name: $file

EOF

$ret .= $txt;

    return \$ret;
    

}

sub get_pdf_headers {

    my $file = shift;
    my $title_tag = shift;

    
    my $sym = gensym;

    open $sym, "pdfinfo $file |" || die "$0: Failed to open $file $!";

    my %metadata;

    while (<$sym>) {
        if ( /^\s*([^:]+):\s+(.+)$/ ) {
            my ( $metaname, $value ) = ( lc( $1 ), escapeXML( $2 ) );
            $metaname =~ tr/ /_/;
            $metadata{$metaname} = $value;
        }
    }
    close $sym or warn "$0: Failed close on pipe to pdfinfo for $file: $?";

    my $metas = join "\n", map { qq[<meta name="$_" content="$metadata{$_}">] } sort keys %metadata;

    if ( $title_tag && exists $metadata{ $title_tag } ) {
        $metas = "<title>$metadata{ $title_tag }</title>\n$metas";
    }

    return $metas;

}

sub get_pdf_content_ref {
    my $file = shift;

    my $sym = gensym;
    open $sym, "pdftotext $file - |" or die "$0: failed to run pdftotext: $!";

    local $/ = undef;
    my $content = escapeXML(<$sym>);

    close $sym or warn "$0: Failed close on pipe to pdftotext for $file: $?";

    return \$content;
}


# How are URLs printed with pdftotext?
sub escapeXML {

   my $str = shift;

   for ( $str ) {
       s/</&lt;/go;
       s/>/&gt;/go;
       tr/\014/ /; # ^L
       # s/&/&amp;/go;
       # s/"/&quot;/go;
    }
   return $str;
}

# This is the portable way to do this, I suppose.
# Otherwise, just create a file in the local directory.

sub create_temp_file {
    my $scalar_ref = shift;

    require "File/Temp.pm";

    my ( $fh, $file_name ) = File::Temp::tempfile();

    print $fh $$scalar_ref or die $!;


    close $fh or die "Failed to close '$file_name' $!";

    return $file_name;
}
    

1	package pdf2html;
2	use strict;
3
4	=pod
5
6	=head1 NAME
7
8	pdf2html - swish-e sample module to convert pdf to html
9
10	=head1 SYNOPSIS
11
12	use pdf2html;
13	my $html_record_ref = pdf2html( $pdf_file_name, 'title' );
14
15	# or by passing content in a scalar reference
16	my $html_text_ref = pdf2html( \$pdf_content, 'title' );
17
18
19
20
21	=head1 DESCRIPTION
22
23	Sample module for use with other swish-e 'prog' document source programs.
24
25	Pass either a file name, or a scalar reference.
26
27	The differece is when you pass a reference to a scalar
28	only the content is returned. When you pass a file name
29	an entire record is returned ready to be fed to swish -- this
30	includes the headers required by swish for indexing.
31
32	The second optional parameter is the extracted PDF info tag to use as the HTML title.
33
34
35
36	The plan is to find a library that will do this to avoid forking an external
37	program.
38
39	=head1 REQUIREMENTS
40
41	Uses the xpdf package that includes the pdftotext conversion program.
42	This is available from http://www.foolabs.com/xpdf/xpdf.html.
43
44	You will also need the module File::Temp (and its dependencies)
45	available from CPAN if passing content to this module (instead of a file name).
46
47
48	=head1 AUTHOR
49
50	Bill Moseley
51
52	=cut
53
54	use Symbol;
55
56
57	use vars qw(
58	@ISA
59	@EXPORT
60	$VERSION
61	);
62
63	# $Id: pdf2html.pm,v 1.3 2002/01/31 00:37:43 whmoseley Exp $
64	$VERSION = sprintf '%d.%02d', q$Revision: 1.3 $ =~ /: (\d+)\.(\d+)/;
65
66	require Exporter;
67	@ISA = qw(Exporter);
68	@EXPORT = qw(pdf2html);
69
70	my @InfoTags = qw/Title Subject Author CreationDate Creator Producer ModDate Keywords/;
71
72
73	sub pdf2html {
74	my $file_or_content = shift;
75	my $title_tag = shift;
76
77
78	my $file = ref $file_or_content
79	? create_temp_file( $file_or_content )
80	: $file_or_content;
81
82	my $headers = get_pdf_headers( $file, $title_tag ) \|\| '';
83
84	my $content_ref = get_pdf_content_ref( $file );
85
86	my $txt = <<EOF;
87	<html>
88	<head>
89	$headers
90	</head>
91	<body>
92	<pre>
93	$$content_ref
94	</pre>
95	</body>
96	</html>
97	EOF
98
99	if ( ref $file_or_content ) {
100	unlink $file;
101	return \$txt;
102	}
103
104	my $mtime = (stat $file )[9];
105
106	my $size = length $txt;
107
108	my $ret = <<EOF;
109	Content-Length: $size
110	Last-Mtime: $mtime
111	Path-Name: $file
112
113	EOF
114
115	$ret .= $txt;
116
117	return \$ret;
118
119
120	}
121
122	sub get_pdf_headers {
123
124	my $file = shift;
125	my $title_tag = shift;
126
127
128	my $sym = gensym;
129
130	open $sym, "pdfinfo $file \|" \|\| die "$0: Failed to open $file $!";
131
132	my %metadata;
133
134	while (<$sym>) {
135	if ( /^\s*([^:]+):\s+(.+)$/ ) {
136	my ( $metaname, $value ) = ( lc( $1 ), escapeXML( $2 ) );
137	$metaname =~ tr/ /_/;
138	$metadata{$metaname} = $value;
139	}
140	}
141	close $sym or warn "$0: Failed close on pipe to pdfinfo for $file: $?";
142
143	my $metas = join "\n", map { qq[<meta name="$_" content="$metadata{$_}">] } sort keys %metadata;
144
145	if ( $title_tag && exists $metadata{ $title_tag } ) {
146	$metas = "<title>$metadata{ $title_tag }</title>\n$metas";
147	}
148
149	return $metas;
150
151	}
152
153	sub get_pdf_content_ref {
154	my $file = shift;
155
156	my $sym = gensym;
157	open $sym, "pdftotext $file - \|" or die "$0: failed to run pdftotext: $!";
158
159	local $/ = undef;
160	my $content = escapeXML(<$sym>);
161
162	close $sym or warn "$0: Failed close on pipe to pdftotext for $file: $?";
163
164	return \$content;
165	}
166
167
168
169	# How are URLs printed with pdftotext?
170	sub escapeXML {
171
172	my $str = shift;
173
174	for ( $str ) {
175	s/</</go;
176	s/>/>/go;
177	tr/\014/ /; # ^L
178	# s/&/&/go;
179	# s/"/"/go;
180	}
181	return $str;
182	}
183
184	# This is the portable way to do this, I suppose.
185	# Otherwise, just create a file in the local directory.
186
187	sub create_temp_file {
188	my $scalar_ref = shift;
189
190	require "File/Temp.pm";
191
192	my ( $fh, $file_name ) = File::Temp::tempfile();
193
194	print $fh $$scalar_ref or die $!;
195
196
197	close $fh or die "Failed to close '$file_name' $!";
198
199	return $file_name;
200	}
201
202