1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # SplitPlug.pm - a plugin for splitting input files into segments that
|
---|
4 | # will then be individually processed.
|
---|
5 | #
|
---|
6 | #
|
---|
7 | # Copyright 2000 Gordon W. Paynter ([email protected])
|
---|
8 | # Copyright 2000 The New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # A component of the Greenstone digital library software
|
---|
11 | # from the New Zealand Digital Library Project at the
|
---|
12 | # University of Waikato, New Zealand.
|
---|
13 | #
|
---|
14 | # This program is free software; you can redistribute it and/or modify
|
---|
15 | # it under the terms of the GNU General Public License as published by
|
---|
16 | # the Free Software Foundation; either version 2 of the License, or
|
---|
17 | # (at your option) any later version.
|
---|
18 | #
|
---|
19 | # This program is distributed in the hope that it will be useful,
|
---|
20 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
21 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
22 | # GNU General Public License for more details.
|
---|
23 | #
|
---|
24 | # You should have received a copy of the GNU General Public License
|
---|
25 | # along with this program; if not, write to the Free Software
|
---|
26 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
27 | #
|
---|
28 | ###########################################################################
|
---|
29 |
|
---|
30 |
|
---|
31 | # SplitPlug is a plugin for splitting input files into segments that will
|
---|
32 | # then be individually processed.
|
---|
33 |
|
---|
34 | # This plugin should not be called directly. Instead, if you need to
|
---|
35 | # process input files that contain several documents, you should write a
|
---|
36 | # plugin with a process function that will handle one of those documents
|
---|
37 | # and have it inherit from SplitPlug. See ReferPlug for an example.
|
---|
38 |
|
---|
39 |
|
---|
40 | package SplitPlug;
|
---|
41 |
|
---|
42 | use BasPlug;
|
---|
43 | use util;
|
---|
44 |
|
---|
45 |
|
---|
46 | # SplitPlug is a sub-class of BasPlug.
|
---|
47 | sub BEGIN {
|
---|
48 | @ISA = ('BasPlug');
|
---|
49 | }
|
---|
50 |
|
---|
51 | sub new {
|
---|
52 | my ($class) = @_;
|
---|
53 | $self = new BasPlug($class, @_);
|
---|
54 |
|
---|
55 | if (!parsargv::parse(\@_,
|
---|
56 | q^split_exp/.*/^, \$self->{'split_exp'},
|
---|
57 | "allow_extra_options")) {
|
---|
58 | print STDERR "\nIncorrect options passed to $class.";
|
---|
59 | print STDERR "\nCheck your collect.cfg configuration file\n";
|
---|
60 | die "\n";
|
---|
61 | }
|
---|
62 |
|
---|
63 | return bless $self, $class;
|
---|
64 | }
|
---|
65 |
|
---|
66 | sub init {
|
---|
67 | my $self = shift (@_);
|
---|
68 | my ($verbosity, $outhandle) = @_;
|
---|
69 |
|
---|
70 | $self->BasPlug::init($verbosity, $outhandle);
|
---|
71 |
|
---|
72 | # set split_exp to default unless explicitly set
|
---|
73 | if (!$self->{'split_exp'}) {
|
---|
74 | $self->{'split_exp'} = $self->get_default_split_exp ();
|
---|
75 | }
|
---|
76 |
|
---|
77 | }
|
---|
78 |
|
---|
79 | # This plugin recurs over the segments it finds
|
---|
80 | sub is_recursive {
|
---|
81 | return 1;
|
---|
82 | }
|
---|
83 |
|
---|
84 | # By default, we split the input text at blank lines
|
---|
85 | sub get_default_split_exp {
|
---|
86 | return q^\n\s*\n^;
|
---|
87 | }
|
---|
88 |
|
---|
89 |
|
---|
90 | # The read function opens a file and splits it into parts.
|
---|
91 | # Each part is sent to the process function
|
---|
92 | #
|
---|
93 | # Returns: Number of document objects created (or undef if it fails)
|
---|
94 |
|
---|
95 | sub read {
|
---|
96 | my $self = shift (@_);
|
---|
97 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
98 | my $outhandle = $self->{'outhandle'};
|
---|
99 | my $verbosity = $self->{'verbosity'};
|
---|
100 |
|
---|
101 | # Figure out the exact filename of this file (and maybe block it)
|
---|
102 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
103 | my $block_exp = $self->{'block_exp'};
|
---|
104 | return 0 if $self->{'block_exp'} ne "" && $filename =~ /$self->{'block_exp'}/;
|
---|
105 | if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
|
---|
106 | return undef;
|
---|
107 | }
|
---|
108 | my $plugin_name = ref ($self);
|
---|
109 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
110 |
|
---|
111 | my ($language, $encoding);
|
---|
112 | if ($self->{'input_encoding'} eq "auto") {
|
---|
113 | # use textcat to automatically work out the input encoding and language
|
---|
114 | ($language, $encoding) = $self->get_language_encoding ($filename);
|
---|
115 |
|
---|
116 | } elsif ($self->{'extract_language'}) {
|
---|
117 | # use textcat to get language metadata
|
---|
118 | ($language, $extracted_encoding) = $self->get_language_encoding ($filename);
|
---|
119 | $encoding = $self->{'input_encoding'};
|
---|
120 |
|
---|
121 | if ($extracted_encoding ne $encoding && $self->{'verbosity'}) {
|
---|
122 | print $outhandle "$plugin_name: WARNING: $file was read using $encoding encoding but ";
|
---|
123 | print $outhandle "appears to be encoded as $extracted_encoding.\n";
|
---|
124 | }
|
---|
125 |
|
---|
126 | } else {
|
---|
127 | $language = $self->{'default_language'};
|
---|
128 | $encoding = $self->{'input_encoding'};
|
---|
129 | }
|
---|
130 |
|
---|
131 | # Read in file ($text will be in utf8)
|
---|
132 | my $text = "";
|
---|
133 | $self->read_file ($filename, $encoding, \$text);
|
---|
134 |
|
---|
135 | if ($text !~ /\w/) {
|
---|
136 | my $outhandle = $self->{'outhandle'};
|
---|
137 | print $outhandle "$plugin_name: ERROR: $file contains no text\n"
|
---|
138 | if $self->{'verbosity'};
|
---|
139 | return 0;
|
---|
140 | }
|
---|
141 |
|
---|
142 |
|
---|
143 | # Split the text into several smaller segments
|
---|
144 | my $split_exp = $self->{'split_exp'};
|
---|
145 | my @segments = split(/$split_exp/, $text);
|
---|
146 | print $outhandle "SplitPlug found " . (scalar @segments) . " documents in $filename\n"
|
---|
147 | if $self->{'verbosity'};
|
---|
148 |
|
---|
149 | # Process each segment in turn
|
---|
150 | my ($count, $segment, $segtext, $status, $id);
|
---|
151 | $segment = 0;
|
---|
152 | $count = 0;
|
---|
153 | foreach $segtext (@segments) {
|
---|
154 | $segment++;
|
---|
155 |
|
---|
156 | # create a new document
|
---|
157 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
158 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Language", $language);
|
---|
159 | $doc_obj->add_utf8_metadata($doc_obj->get_top_section(), "Encoding", $encoding);
|
---|
160 |
|
---|
161 | # Calculate a "base" document ID.
|
---|
162 | if (!defined $id) {
|
---|
163 | $doc_obj->set_OID();
|
---|
164 | $id = $doc_obj->get_OID();
|
---|
165 | }
|
---|
166 |
|
---|
167 | # include any metadata passed in from previous plugins
|
---|
168 | # note that this metadata is associated with the top level section
|
---|
169 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
170 |
|
---|
171 | # do plugin specific processing of doc_obj
|
---|
172 | print $outhandle "segment $segment - ";
|
---|
173 | $status = $self->process (\$segtext, $pluginfo, $base_dir, $file, $metadata, $doc_obj);
|
---|
174 | if (!defined $status) {
|
---|
175 | print $outhandle "WARNING - no plugin could process segment $segment of $file\n"
|
---|
176 | if ($verbosity >= 2);
|
---|
177 | next;
|
---|
178 | }
|
---|
179 | $count += $status;
|
---|
180 |
|
---|
181 | # do any automatic metadata extraction
|
---|
182 | $self->auto_extract_metadata ($doc_obj);
|
---|
183 |
|
---|
184 | # add an OID
|
---|
185 | $doc_obj->set_OID($id . "s" . $segment);
|
---|
186 |
|
---|
187 | # process the document
|
---|
188 | $processor->process($doc_obj);
|
---|
189 | }
|
---|
190 |
|
---|
191 | # Return number of document objects produced
|
---|
192 | return $count;
|
---|
193 | }
|
---|
194 |
|
---|
195 |
|
---|
196 | 1;
|
---|