[1676] | 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/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
| 110 |
|
---|
| 111 | # Read in file ($text will be in utf8)
|
---|
| 112 | my $text = "";
|
---|
| 113 | $self->read_file ($filename, \$text);
|
---|
| 114 |
|
---|
| 115 | if ($text !~ /\w/) {
|
---|
| 116 | my $outhandle = $self->{'outhandle'};
|
---|
| 117 | print $outhandle "$plugin_name: ERROR: $file contains no text\n"
|
---|
| 118 | if $self->{'verbosity'};
|
---|
| 119 | return 0;
|
---|
| 120 | }
|
---|
| 121 |
|
---|
| 122 | # Split the text into several smaller segments
|
---|
| 123 | my $split_exp = $self->{'split_exp'};
|
---|
| 124 | my @segments = split(/$split_exp/, $text);
|
---|
| 125 | print $outhandle "SplitPlug found " . (scalar @segments) . " documents in $filename\n"
|
---|
| 126 | if $self->{'verbosity'};
|
---|
| 127 |
|
---|
| 128 | # Process each segment in turn
|
---|
| 129 | my ($count, $segment, $segtext, $status, $id);
|
---|
| 130 | $segment = 0;
|
---|
| 131 | $count = 0;
|
---|
| 132 | foreach $segtext (@segments) {
|
---|
| 133 | $segment++;
|
---|
| 134 |
|
---|
| 135 | # create a new document
|
---|
| 136 | my $doc_obj = new doc ($filename, "indexed_doc");
|
---|
| 137 |
|
---|
| 138 | # Calculate a "base" document ID.
|
---|
| 139 | if (!defined $id) {
|
---|
| 140 | $doc_obj->set_OID();
|
---|
| 141 | $id = $doc_obj->get_OID();
|
---|
| 142 | }
|
---|
| 143 |
|
---|
| 144 | # include any metadata passed in from previous plugins
|
---|
| 145 | # note that this metadata is associated with the top level section
|
---|
| 146 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
---|
| 147 |
|
---|
| 148 | # do plugin specific processing of doc_obj
|
---|
| 149 | print $outhandle "segment $segment - ";
|
---|
| 150 | $status = $self->process (\$segtext, $pluginfo, $base_dir, $file, $metadata, $doc_obj);
|
---|
| 151 | if (!defined $status) {
|
---|
| 152 | print $outhandle "WARNING - no plugin could process segment $segment of $file\n"
|
---|
| 153 | if ($verbosity >= 2);
|
---|
| 154 | next;
|
---|
| 155 | }
|
---|
| 156 | $count += $status;
|
---|
| 157 |
|
---|
| 158 | # do any automatic metadata extraction
|
---|
| 159 | $self->auto_extract_metadata ($doc_obj);
|
---|
| 160 |
|
---|
| 161 | # add an OID
|
---|
| 162 | $doc_obj->set_OID($id . "s" . $segment);
|
---|
| 163 |
|
---|
| 164 | # process the document
|
---|
| 165 | $processor->process($doc_obj);
|
---|
| 166 | }
|
---|
| 167 |
|
---|
| 168 | # Return number of document objects produced
|
---|
| 169 | return $count;
|
---|
| 170 | }
|
---|
| 171 |
|
---|
| 172 |
|
---|
| 173 | 1;
|
---|