[2810] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # XMLPlug.pm -- base class for XML 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) 2001 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 XMLPlug;
|
---|
| 27 |
|
---|
| 28 | use BasPlug;
|
---|
| 29 | use doc;
|
---|
| 30 |
|
---|
| 31 | sub BEGIN {
|
---|
| 32 | @ISA = ('BasPlug');
|
---|
| 33 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/cpan");
|
---|
| 34 | }
|
---|
| 35 |
|
---|
| 36 | use XML::Parser;
|
---|
| 37 |
|
---|
| 38 | my ($self);
|
---|
| 39 | sub new {
|
---|
| 40 | my $class = shift (@_);
|
---|
| 41 |
|
---|
| 42 | # $self is global for use within subroutines called by XML::Parser
|
---|
| 43 | $self = new BasPlug ($class, @_);
|
---|
| 44 |
|
---|
| 45 | my $parser = new XML::Parser('Style' => 'Stream',
|
---|
| 46 | 'Handlers' => {'Char' => \&Char,
|
---|
| 47 | 'XMLDecl' => \&XMLDecl,
|
---|
| 48 | 'Doctype' => \&Doctype,
|
---|
| 49 | 'Default' => \&Default
|
---|
| 50 | }
|
---|
| 51 | );
|
---|
| 52 | $self->{'parser'} = $parser;
|
---|
| 53 |
|
---|
| 54 | return bless $self, $class;
|
---|
| 55 | }
|
---|
| 56 |
|
---|
| 57 |
|
---|
| 58 | sub read {
|
---|
| 59 | my $self = shift (@_);
|
---|
| 60 |
|
---|
| 61 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
| 62 |
|
---|
| 63 | my $filename = $file;
|
---|
| 64 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
---|
| 65 |
|
---|
| 66 | if ($self->{'block_exp'} ne "" && $filename =~ /$self->{'block_exp'}/) {
|
---|
| 67 | $self->{'num_blocked'} ++;
|
---|
| 68 | return 0;
|
---|
| 69 | }
|
---|
| 70 | if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
|
---|
| 71 | return undef;
|
---|
| 72 | }
|
---|
| 73 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
---|
| 74 | $self->{'file'} = $file;
|
---|
| 75 | $self->{'filename'} = $filename;
|
---|
| 76 | $self->{'processor'} = $processor;
|
---|
| 77 | $self->{'metadata'} = $metadata;
|
---|
| 78 |
|
---|
| 79 | eval {
|
---|
| 80 | $self->{'parser'}->parsefile($filename);
|
---|
| 81 | };
|
---|
| 82 | if ($@) {
|
---|
| 83 |
|
---|
| 84 | # parsefile may either croak somewhere in XML::Parser (e.g. because
|
---|
| 85 | # the document is not well formed) or die somewhere in XMLPlug or a
|
---|
| 86 | # derived plugin (e.g. because we're attempting to process a
|
---|
| 87 | # document whose DOCTYPE is not meant for this plugin). For the
|
---|
| 88 | # first case we'll print a warning and continue, for the second
|
---|
| 89 | # we'll just continue quietly
|
---|
| 90 |
|
---|
| 91 | my ($msg) = $@ =~ /Carp::croak\(\'(.*?)\'\)/;
|
---|
| 92 | if (defined $msg) {
|
---|
| 93 | my $outhandle = $self->{'outhandle'};
|
---|
| 94 | my $plugin_name = ref ($self);
|
---|
| 95 | print $outhandle "$plugin_name failed to process $file ($msg)\n";
|
---|
| 96 | }
|
---|
| 97 | return undef;
|
---|
| 98 | }
|
---|
| 99 |
|
---|
| 100 | return 1; # processed the file
|
---|
| 101 | }
|
---|
| 102 |
|
---|
| 103 | sub get_default_process_exp {
|
---|
| 104 | my $self = shift (@_);
|
---|
| 105 |
|
---|
| 106 | return q^(?i)\.xml$^;
|
---|
| 107 | }
|
---|
| 108 |
|
---|
| 109 | sub StartDocument {$self->xml_start_document(@_);}
|
---|
| 110 | sub XMLDecl {$self->xml_xmldecl(@_);}
|
---|
| 111 | sub Doctype {$self->xml_doctype(@_);}
|
---|
| 112 | sub StartTag {$self->xml_start_tag(@_);}
|
---|
| 113 | sub EndTag {$self->xml_end_tag(@_);}
|
---|
| 114 | sub Text {$self->xml_text(@_);}
|
---|
| 115 | sub PI {$self->xml_pi(@_);}
|
---|
| 116 | sub EndDocument {$self->xml_end_document(@_);}
|
---|
| 117 | sub Default {$self->xml_default(@_);}
|
---|
| 118 |
|
---|
| 119 | # This Char function overrides the one in XML::Parser::Stream to overcome a
|
---|
| 120 | # problem where $expat->{Text} is treated as the return value, slowing
|
---|
| 121 | # things down significantly in some cases.
|
---|
| 122 | sub Char {
|
---|
| 123 | $_[0]->{'Text'} .= $_[1];
|
---|
| 124 | return undef;
|
---|
| 125 | }
|
---|
| 126 |
|
---|
| 127 | # Called at the beginning of the XML document.
|
---|
| 128 | sub xml_start_document {
|
---|
| 129 | my $self = shift(@_);
|
---|
| 130 | my ($expat) = @_;
|
---|
| 131 |
|
---|
| 132 | $self->open_document();
|
---|
| 133 | }
|
---|
| 134 |
|
---|
| 135 | # Called for XML declarations
|
---|
| 136 | sub xml_xmldecl {
|
---|
| 137 | my $self = shift(@_);
|
---|
| 138 | my ($expat, $version, $encoding, $standalone) = @_;
|
---|
| 139 | }
|
---|
| 140 |
|
---|
| 141 | # Called for DOCTYPE declarations - use die to bail out if this doctype
|
---|
| 142 | # is not meant for this plugin
|
---|
| 143 | sub xml_doctype {
|
---|
| 144 | my $self = shift(@_);
|
---|
| 145 | my ($expat, $name, $sysid, $pubid, $internal) = @_;
|
---|
| 146 | die "XMLPlug Cannot process XML document with DOCTYPE of $name";
|
---|
| 147 | }
|
---|
| 148 |
|
---|
| 149 | # Called for every start tag. The $_ variable will contain a copy of the
|
---|
| 150 | # tag and the %_ variable will contain the element's attributes.
|
---|
| 151 | sub xml_start_tag {
|
---|
| 152 | my $self = shift(@_);
|
---|
| 153 | my ($expat, $element) = @_;
|
---|
| 154 | }
|
---|
| 155 |
|
---|
| 156 | # Called for every end tag. The $_ variable will contain a copy of the tag.
|
---|
| 157 | sub xml_end_tag {
|
---|
| 158 | my $self = shift(@_);
|
---|
| 159 | my ($expat, $element) = @_;
|
---|
| 160 | }
|
---|
| 161 |
|
---|
| 162 | # Called just before start or end tags with accumulated non-markup text in
|
---|
| 163 | # the $_ variable.
|
---|
| 164 | sub xml_text {
|
---|
| 165 | my $self = shift(@_);
|
---|
| 166 | my ($expat) = @_;
|
---|
| 167 | }
|
---|
| 168 |
|
---|
| 169 | # Called for processing instructions. The $_ variable will contain a copy
|
---|
| 170 | # of the pi.
|
---|
| 171 | sub xml_pi {
|
---|
| 172 | my $self = shift(@_);
|
---|
| 173 | my ($expat, $target, $data) = @_;
|
---|
| 174 | }
|
---|
| 175 |
|
---|
| 176 | # Called at the end of the XML document.
|
---|
| 177 | sub xml_end_document {
|
---|
| 178 | my $self = shift(@_);
|
---|
| 179 | my ($expat) = @_;
|
---|
| 180 |
|
---|
| 181 | $self->close_document();
|
---|
| 182 | }
|
---|
| 183 |
|
---|
| 184 | # Called for any characters not handled by the above functions.
|
---|
| 185 | sub xml_default {
|
---|
| 186 | my $self = shift(@_);
|
---|
| 187 | my ($expat, $text) = @_;
|
---|
| 188 | }
|
---|
| 189 |
|
---|
| 190 | sub open_document {
|
---|
| 191 | my $self = shift(@_);
|
---|
| 192 |
|
---|
| 193 | # create a new document
|
---|
| 194 | $self->{'doc_obj'} = new doc ($self->{'filename'}, "indexed_doc");
|
---|
| 195 | $self->{'doc_obj'}->set_OIDtype ($self->{'processor'}->{'OIDtype'});
|
---|
| 196 | }
|
---|
| 197 |
|
---|
| 198 | sub close_document {
|
---|
| 199 | my $self = shift(@_);
|
---|
| 200 |
|
---|
| 201 | # include any metadata passed in from previous plugins
|
---|
| 202 | # note that this metadata is associated with the top level section
|
---|
| 203 | $self->extra_metadata ($self->{'doc_obj'},
|
---|
| 204 | $self->{'doc_obj'}->get_top_section(),
|
---|
| 205 | $self->{'metadata'});
|
---|
| 206 |
|
---|
| 207 | # do any automatic metadata extraction
|
---|
| 208 | $self->auto_extract_metadata ($self->{'doc_obj'});
|
---|
| 209 |
|
---|
| 210 | # add an OID
|
---|
| 211 | $self->{'doc_obj'}->set_OID();
|
---|
| 212 |
|
---|
| 213 | # process the document
|
---|
| 214 | $self->{'processor'}->process($self->{'doc_obj'});
|
---|
| 215 |
|
---|
| 216 | $self->{'num_processed'} ++;
|
---|
| 217 | }
|
---|
| 218 |
|
---|
| 219 | 1;
|
---|
| 220 |
|
---|