1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # TEXTPlug.pm -- simple text plugin
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program is free software; you can redistribute it and/or modify
|
---|
11 | # it under the terms of the GNU General Public License as published by
|
---|
12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
13 | # (at your option) any later version.
|
---|
14 | #
|
---|
15 | # This program is distributed in the hope that it will be useful,
|
---|
16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | # GNU General Public License for more details.
|
---|
19 | #
|
---|
20 | # You should have received a copy of the GNU General Public License
|
---|
21 | # along with this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 | # creates simple single-level document from .txt or .text files
|
---|
27 | # (case-insensitive match on filenames). Adds Title metadata
|
---|
28 | # of first 100 characters found.
|
---|
29 |
|
---|
30 | package TEXTPlug;
|
---|
31 |
|
---|
32 | use BasPlug;
|
---|
33 | use sorttools;
|
---|
34 |
|
---|
35 | sub BEGIN {
|
---|
36 | @ISA = ('BasPlug');
|
---|
37 | }
|
---|
38 |
|
---|
39 | sub new {
|
---|
40 | my ($class) = @_;
|
---|
41 | $self = new BasPlug ();
|
---|
42 |
|
---|
43 | return bless $self, $class;
|
---|
44 | }
|
---|
45 |
|
---|
46 | sub is_recursive {
|
---|
47 | my $self = shift (@_);
|
---|
48 |
|
---|
49 | return 0; # this is not a recursive plugin
|
---|
50 | }
|
---|
51 |
|
---|
52 |
|
---|
53 | # return number of files processed, undef if can't process
|
---|
54 | # Note that $base_dir might be "" and that $file might
|
---|
55 | # include directories
|
---|
56 | sub read {
|
---|
57 | my $self = shift (@_);
|
---|
58 | my ($pluginfo, $base_dir, $file, $metadata, $processor) = @_;
|
---|
59 |
|
---|
60 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
61 |
|
---|
62 | return undef unless ($filename =~ /\.(te?xt(\.gz)?)$/i && (-e $filename));
|
---|
63 |
|
---|
64 | my $gz = 0;
|
---|
65 | if (defined $2) {
|
---|
66 | $gz = $2;
|
---|
67 | $gz = 1 if ($gz =~ /\.gz/i);
|
---|
68 | }
|
---|
69 |
|
---|
70 | print STDERR "TEXTPlug: processing $filename\n" if $processor->{'verbosity'};
|
---|
71 |
|
---|
72 | # create a new document
|
---|
73 | my $doc_obj = new doc ($file, "indexed_doc");
|
---|
74 |
|
---|
75 | if ($gz) {
|
---|
76 | open (FILE, "zcat $filename |") || die "TEXTPlug::read - zcat can't open $filename\n";
|
---|
77 | } else {
|
---|
78 | open (FILE, $filename) || die "TEXTPlug::read - can't open $filename\n";
|
---|
79 | }
|
---|
80 | my $cursection = $doc_obj->get_top_section();
|
---|
81 |
|
---|
82 | my $text = "";
|
---|
83 | my $line = "";
|
---|
84 | my $foundtitle = 0;
|
---|
85 | # don't need to get title if it has been passed
|
---|
86 | # in from another plugin
|
---|
87 | if (defined $metadata->{'Title'}) {
|
---|
88 | $foundtitle = 1;
|
---|
89 | }
|
---|
90 | while (defined ($line = <FILE>)) {
|
---|
91 | # use first line as title (or first 100 characters if it's long)
|
---|
92 | if (!$foundtitle && length($line) > 5) {
|
---|
93 | my $title = "";
|
---|
94 | if (length($line) > 100) {
|
---|
95 | $title = substr ($line, 0, 100);
|
---|
96 | } else {
|
---|
97 | $title = $line;
|
---|
98 | }
|
---|
99 | $doc_obj->add_metadata ($cursection, "Title", $title);
|
---|
100 | $foundtitle = 1;
|
---|
101 | }
|
---|
102 | $text .= $line;
|
---|
103 | }
|
---|
104 |
|
---|
105 | $doc_obj->add_text ($cursection, "<pre>\n$text\n</pre>");
|
---|
106 |
|
---|
107 |
|
---|
108 | foreach $field (keys(%$metadata)) {
|
---|
109 | # $metadata->{$field} may be an array reference
|
---|
110 | if (ref ($metadata->{$field}) eq "ARRAY") {
|
---|
111 | map {
|
---|
112 | $doc_obj->add_metadata ($cursection, $field, $_);
|
---|
113 | } @{$metadata->{$field}};
|
---|
114 | } else {
|
---|
115 | $doc_obj->add_metadata ($cursection, $field, $metadata->{$field});
|
---|
116 | }
|
---|
117 | }
|
---|
118 |
|
---|
119 | # add OID
|
---|
120 | $doc_obj->set_OID ();
|
---|
121 |
|
---|
122 | # process the document
|
---|
123 | $processor->process($doc_obj);
|
---|
124 |
|
---|
125 | return 1; # processed the file
|
---|
126 | }
|
---|
127 |
|
---|
128 | 1;
|
---|
129 |
|
---|
130 |
|
---|
131 |
|
---|
132 |
|
---|
133 |
|
---|
134 |
|
---|
135 |
|
---|
136 |
|
---|
137 |
|
---|
138 |
|
---|
139 |
|
---|