1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
package pdf2xml;
use strict;
=pod
=head1 NAME
pdf2xml - swish-e sample module to convert pdf2xml
=head1 SYNOPSIS
use pdf2xml;
my $xml_record_ref = pdf2xml( $pdf_file_name );
# or by passing content in a scalar reference
my $xml_text_ref = pdf2xml( \$pdf_content );
=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 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: pdf2xml.pm 1279 2003-06-12 04:00:45Z whmoseley $
$VERSION = sprintf '%d.%02d', q$Revision: 1279 $ =~ /: (\d+)\.(\d+)/;
require Exporter;
@ISA = qw(Exporter);
@EXPORT = qw(pdf2xml);
my @InfoTags = qw/Title Subject Author CreationDate Creator Producer ModDate Keywords/;
sub pdf2xml {
my $file_or_content = shift;
my $file = ref $file_or_content
? create_temp_file( $file_or_content )
: $file_or_content;
my $headers = get_pdf_headers( $file ) || '';
my $content_ref = get_pdf_content_ref( $file );
my $txt = <<EOF;
<all>
<headers>
$headers
</headers>
<content>
$$content_ref
</content>
</all>
EOF
return \$txt if ref $file_or_content;
my $mtime = (stat $file )[9];
my $size = length $txt;
my $ret = <<EOF;
Content-Length: $size
Last-Mtime: $mtime
Path-Name: $file
EOF
$ret .= $txt;
return \$ret;
}
sub get_pdf_headers {
my $file = shift;
my $sym = gensym;
# This doesn't work
my $path = $file;
for ( $path ) {
s/"/\\"/g;
$path = qq["$path"];
}
open $sym, "pdfinfo $path |" || die "$0: Failed to open $file $!";
my %metadata;
while (<$sym>) {
if ( /^\s*([^:]+):\s+(.+)$/ ) {
my ( $metaname, $value ) = ( lc( $1 ), escapeXML( $2 ) );
$metaname =~ tr/ /_/;
$metadata{$metaname} = $value;
}
}
close $sym or die "$0: Failed close on pipe to pdfinfo for $file: $?";
return join "\n", map { "<$_>$metadata{$_}</$_>" } sort keys %metadata;
}
sub get_pdf_content_ref {
my $file = shift;
# This doesn't work
my $path = $file;
for ( $path ) {
s/"/\\"/g;
$path = qq["$path"];
}
my $sym = gensym;
open $sym, "pdftotext $path - |" or die "$0: failed to run pdftotext: $!";
local $/ = undef;
my $content = escapeXML(<$sym>);
close $sym or die "$0: Failed close on pipe to pdftotext for $file: $?";
return \$content;
}
# How are URLs printed with pdftotext?
sub escapeXML {
my $str = shift;
for ( $str ) {
s/&/&/go;
s/"/"/go;
s/</</go;
s/>/>/go;
}
return $str;
}
# This is the portable way to do this, I suppose.
# Otherwise, just create a file in the local directory.
sub create_temp_file {
my $scalar_ref = shift;
require "File/Temp.pm";
my ( $fh, $file_name ) = File::Temp::tempfile( UNLINK => 1 );
print $fh $$scalar_ref or die $!;
close $fh or die "Failed to close '$file_name' $!";
return $file_name;
}
|
