[537] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # mgbuildproc.pm --
|
---|
| 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 |
|
---|
[17] | 26 | # This document processor outputs a document
|
---|
| 27 | # for mg to process
|
---|
[4] | 28 |
|
---|
| 29 |
|
---|
| 30 | package mgbuildproc;
|
---|
| 31 |
|
---|
[9919] | 32 | use basebuildproc;
|
---|
[3767] | 33 |
|
---|
[4] | 34 | BEGIN {
|
---|
[9919] | 35 | @mgbuildproc::ISA = ('basebuildproc');
|
---|
[4] | 36 | }
|
---|
| 37 |
|
---|
| 38 | sub new {
|
---|
[9919] | 39 | my $class = shift @_;
|
---|
| 40 | my $self = new basebuildproc (@_);
|
---|
[4] | 41 | return bless $self, $class;
|
---|
| 42 | }
|
---|
| 43 |
|
---|
| 44 |
|
---|
[289] | 45 | sub find_paragraphs {
|
---|
| 46 | $_[1] =~ s/(<p\b)/\cC$1/gi;
|
---|
| 47 | }
|
---|
| 48 |
|
---|
[292] | 49 | sub filter_text {
|
---|
| 50 | # $self->filter_text ($field, $new_text);
|
---|
| 51 | # don't want to do anything for this version, however,
|
---|
| 52 | # in a particular collection you might want to override
|
---|
| 53 | # this method to post-process certain fields depending on
|
---|
| 54 | # the field, or whether we are outputting it for indexing
|
---|
| 55 | }
|
---|
| 56 |
|
---|
[4] | 57 | sub text {
|
---|
| 58 | my $self = shift (@_);
|
---|
| 59 | my ($doc_obj) = @_;
|
---|
| 60 | my $handle = $self->{'output_handle'};
|
---|
[9919] | 61 |
|
---|
[4] | 62 | # only output this document if it is one to be indexed
|
---|
| 63 | return if ($doc_obj->get_doc_type() ne "indexed_doc");
|
---|
[9919] | 64 |
|
---|
[69] | 65 | # see if this document belongs to this subcollection
|
---|
[9919] | 66 | my $indexed_doc = $self->is_subcollection_doc($doc_obj);
|
---|
[69] | 67 |
|
---|
[4] | 68 | # this is another document
|
---|
| 69 | $self->{'num_docs'} += 1;
|
---|
| 70 |
|
---|
| 71 | # get the parameters for the output
|
---|
| 72 | my ($level, $fields) = split (/:/, $self->{'index'});
|
---|
| 73 | $fields =~ s/\ball\b/Title,Creator,text/;
|
---|
| 74 | $fields =~ s/\btopall\b/topTitle,topCreator,toptext/;
|
---|
| 75 |
|
---|
| 76 | my $doc_section = 0; # just for this document
|
---|
| 77 | my $text = "";
|
---|
| 78 | my $text_extra = "";
|
---|
| 79 |
|
---|
| 80 | # get the text for this document
|
---|
| 81 | my $section = $doc_obj->get_top_section();
|
---|
| 82 | while (defined $section) {
|
---|
| 83 | # update a few statistics
|
---|
| 84 | $doc_section++;
|
---|
| 85 | $self->{'num_sections'} += 1;
|
---|
[69] | 86 |
|
---|
[12274] | 87 | my $indexed_section = $doc_obj->get_metadata_element($section, "gsdldoctype") || "indexed_section";
|
---|
[12356] | 88 | if (($indexed_doc) && ($indexed_section eq "indexed_section" || $indexed_section eq "indexed_doc")) {
|
---|
[69] | 89 | $self->{'num_bytes'} += $doc_obj->get_text_length ($section);
|
---|
[900] | 90 | foreach my $field (split (/,/, $fields)) {
|
---|
[69] | 91 | # only deal with this field if it doesn't start with top or
|
---|
| 92 | # this is the first section
|
---|
| 93 | my $real_field = $field;
|
---|
| 94 | if (!($real_field =~ s/^top//) || ($doc_section == 1)) {
|
---|
| 95 | my $new_text = "";
|
---|
[4743] | 96 | if ($level eq "dummy") {
|
---|
| 97 | # a dummy index is a special case used when no
|
---|
| 98 | # indexes are specified (since there must always be
|
---|
| 99 | # at least one index or we can't retrieve the
|
---|
| 100 | # compressed text) - we add a small amount of text
|
---|
| 101 | # to these dummy indexes which will never be seen
|
---|
| 102 | # but will overcome mg's problems with building
|
---|
| 103 | # empty indexes
|
---|
| 104 | $new_text = "this is dummy text to stop mg barfing";
|
---|
| 105 | $self->{'num_processed_bytes'} += length ($new_text);
|
---|
| 106 |
|
---|
| 107 | } elsif ($real_field eq "text") {
|
---|
[2336] | 108 | $new_text = $doc_obj->get_text ($section) if $self->{'store_text'};
|
---|
[1251] | 109 | $self->{'num_processed_bytes'} += length ($new_text);
|
---|
[69] | 110 | $new_text =~ s/[\cB\cC]//g;
|
---|
[289] | 111 | $self->find_paragraphs($new_text);
|
---|
[69] | 112 |
|
---|
| 113 | } else {
|
---|
[1072] | 114 | my $first = 1;
|
---|
[10474] | 115 | my @section_metadata = @{$doc_obj->get_metadata ($section, $real_field)};
|
---|
[12371] | 116 | if ($level eq "section" && $section ne $doc_obj->get_top_section() && $self->{'indexing_text'} && defined ($self->{'sections_index_document_metadata'})) {
|
---|
[10474] | 117 | if ($self->{'sections_index_document_metadata'} eq "always" || ( scalar(@section_metadata) == 0 && $self->{'sections_index_document_metadata'} eq "unless_section_metadata_exists")) {
|
---|
| 118 | push (@section_metadata, @{$doc_obj->get_metadata ($doc_obj->get_top_section(), $real_field)});
|
---|
| 119 | }
|
---|
| 120 | }
|
---|
| 121 | foreach my $meta (@section_metadata) {
|
---|
[1072] | 122 | $meta =~ s/[\cB\cC]//g;
|
---|
[1251] | 123 | $self->{'num_processed_bytes'} += length ($meta);
|
---|
[1072] | 124 | $new_text .= "\cC" unless $first;
|
---|
[2336] | 125 | $new_text .= $meta if $self->{'store_text'};
|
---|
[1072] | 126 | $first = 0;
|
---|
| 127 | }
|
---|
[69] | 128 | }
|
---|
[4] | 129 |
|
---|
[292] | 130 | # filter the text
|
---|
| 131 | $self->filter_text ($field, $new_text);
|
---|
| 132 |
|
---|
[69] | 133 | $text .= "$new_text\cC";
|
---|
[4] | 134 | }
|
---|
| 135 | }
|
---|
| 136 | }
|
---|
| 137 |
|
---|
| 138 | if ($level eq "document") { $text_extra .= "\cB"; }
|
---|
| 139 | else { $text .= "\cB"; }
|
---|
| 140 |
|
---|
| 141 | $section = $doc_obj->get_next_section($section);
|
---|
| 142 | }
|
---|
| 143 |
|
---|
| 144 | print $handle "$text$text_extra";
|
---|
| 145 | }
|
---|
| 146 |
|
---|
| 147 | 1;
|
---|
| 148 |
|
---|