1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # BasPlug.pm -- base class for all the import plugins
|
---|
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 | package BasPlug;
|
---|
27 |
|
---|
28 | use parsargv;
|
---|
29 | use multiread;
|
---|
30 | use cnseg;
|
---|
31 | use strict;
|
---|
32 |
|
---|
33 | sub print_usage {
|
---|
34 | print STDERR "\nOne of your plugins uses an incorrect general option (general options are those\n";
|
---|
35 | print STDERR "available to all plugins). Check your collect.cfg configuration file.\n";
|
---|
36 |
|
---|
37 | print STDERR "\n usage: plugin plugin-name [options]\n\n";
|
---|
38 | print STDERR " currently supported general options are:\n";
|
---|
39 | print STDERR " -input_encoding The encoding of the source documents. Documents will be\n";
|
---|
40 | print STDERR " converted from these encodings and stored internally as\n";
|
---|
41 | print STDERR " utf8. The default input_encoding is Latin1. Accepted values\n";
|
---|
42 | print STDERR " are:\n";
|
---|
43 | print STDERR " iso_8859_1 (extended ascii)\n";
|
---|
44 | print STDERR " Latin1 (the same as iso-8859-1)\n";
|
---|
45 | print STDERR " ascii (7 bit ascii -- may be faster than Latin1 as no\n";
|
---|
46 | print STDERR " conversion is neccessary)\n";
|
---|
47 | print STDERR " gb (GB or GBK simplified Chinese)\n";
|
---|
48 | print STDERR " iso_8859_6 (8 bit Arabic)\n";
|
---|
49 | print STDERR " windows_1256 (Windows codepage 1256 (Arabic))\n";
|
---|
50 | print STDERR " Arabic (the same as windows_1256)\n";
|
---|
51 | print STDERR " utf8 (either utf8 or unicode -- automatically detected)\n";
|
---|
52 | print STDERR " unicode (just unicode -- doesn't currently do endian\n";
|
---|
53 | print STDERR " detection)\n\n";
|
---|
54 | }
|
---|
55 |
|
---|
56 | sub new {
|
---|
57 | my $class = shift (@_);
|
---|
58 |
|
---|
59 | my $self = {};
|
---|
60 | my $encodings = "^(iso_8859_1|Latin1|ascii|gb|iso_8859_6|windows_1256|Arabic|utf8|unicode)\$";
|
---|
61 |
|
---|
62 | # general options available to all plugins
|
---|
63 | if (!parsargv::parse(\@_, "input_encoding/$encodings/Latin1", \$self->{'input_encoding'},
|
---|
64 | "allow_extra_options")) {
|
---|
65 | &print_usage();
|
---|
66 | die "\n";
|
---|
67 | }
|
---|
68 |
|
---|
69 | return bless $self, $class;
|
---|
70 | }
|
---|
71 |
|
---|
72 | sub begin {
|
---|
73 | my $self = shift (@_);
|
---|
74 | my ($pluginfo, $base_dir, $processor, $maxdocs) = @_;
|
---|
75 | }
|
---|
76 |
|
---|
77 | sub end {
|
---|
78 | my ($self) = @_;
|
---|
79 | }
|
---|
80 |
|
---|
81 | # return 1 if this class might recurse using $pluginfo
|
---|
82 | sub is_recursive {
|
---|
83 | my $self = shift (@_);
|
---|
84 |
|
---|
85 | die "BasPlug::is_recursive function must be implemented in sub classes\n";
|
---|
86 | }
|
---|
87 |
|
---|
88 | # return number of files processed, undef if can't process
|
---|
89 | # Note that $base_dir might be "" and that $file might
|
---|
90 | # include directories
|
---|
91 | sub read {
|
---|
92 | my $self = shift (@_);
|
---|
93 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
94 |
|
---|
95 | die "BasPlug::read function must be implemented in sub classes\n";
|
---|
96 |
|
---|
97 | return undef; # will never get here
|
---|
98 | }
|
---|
99 |
|
---|
100 | # uses the multiread package to read in the entire file pointed to
|
---|
101 | # by filename and loads the resulting text into $$textref. Input text
|
---|
102 | # may be in any of the encodings handled by multiread, output text
|
---|
103 | # will be in utf8
|
---|
104 | sub read_file {
|
---|
105 | my $self = shift (@_);
|
---|
106 | my ($filename, $textref) = @_;
|
---|
107 |
|
---|
108 | $$textref = "";
|
---|
109 | my $encoding = "";
|
---|
110 | if ($self->{'input_encoding'} =~ /^(Latin1|iso_8859_1)$/) {
|
---|
111 | $encoding = "iso_8859_1";
|
---|
112 | } elsif ($self->{'input_encoding'} =~ /^(Arabic|windows_1256)$/) {
|
---|
113 | $encoding = "windows_1256";
|
---|
114 | } else {
|
---|
115 | $encoding = $self->{'input_encoding'};
|
---|
116 | }
|
---|
117 |
|
---|
118 | open (FILE, $filename) || die "BasPlug::read_file could not open $filename for reading ($!)\n";
|
---|
119 |
|
---|
120 | if ($encoding eq "ascii") {
|
---|
121 | undef $/;
|
---|
122 | $$textref = <FILE>;
|
---|
123 | $/ = "\n";
|
---|
124 | } else {
|
---|
125 | my $reader = new multiread();
|
---|
126 | $reader->set_handle ('BasPlug::FILE');
|
---|
127 | $reader->set_encoding ($encoding);
|
---|
128 | $reader->read_file ($textref);
|
---|
129 |
|
---|
130 | if ($encoding eq "gb") {
|
---|
131 | # segment the Chinese words
|
---|
132 | $$textref = &cnseg::segment($$textref);
|
---|
133 | }
|
---|
134 | }
|
---|
135 |
|
---|
136 | close FILE;
|
---|
137 | }
|
---|
138 |
|
---|
139 | # add any extra metadata that's been passed around from one
|
---|
140 | # plugin to another.
|
---|
141 | # extra_metadata uses add_utf8_metadata so it expects metadata values
|
---|
142 | # to already be in utf8
|
---|
143 | sub extra_metadata {
|
---|
144 | my $self = shift (@_);
|
---|
145 | my ($doc_obj, $cursection, $metadata) = @_;
|
---|
146 |
|
---|
147 | foreach my $field (keys(%$metadata)) {
|
---|
148 | # $metadata->{$field} may be an array reference
|
---|
149 | if (ref ($metadata->{$field}) eq "ARRAY") {
|
---|
150 | map {
|
---|
151 | $doc_obj->add_utf8_metadata ($cursection, $field, $_);
|
---|
152 | } @{$metadata->{$field}};
|
---|
153 | } else {
|
---|
154 | $doc_obj->add_utf8_metadata ($cursection, $field, $metadata->{$field});
|
---|
155 | }
|
---|
156 | }
|
---|
157 | }
|
---|
158 |
|
---|
159 | 1;
|
---|